jinqij commited on
Commit
e0500fc
·
verified ·
1 Parent(s): f4fad21

Upload folder using huggingface_hub

Browse files
00args.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3,
3
+ "train_bsz": 2,
4
+ "eval_bsz": 4,
5
+ "lr": 5e-06,
6
+ "deepspeed": "configs/ds_stage2.json",
7
+ "weight_decay": 0.01,
8
+ "save_eval_step_ratio": 0.333333,
9
+ "warmup_step_ratio": 0.1,
10
+ "grad_checkpointing": true,
11
+ "model": "llama3",
12
+ "common": {
13
+ "debug": false,
14
+ "device": "0,1,2,3",
15
+ "world_size": 4,
16
+ "rank": 0,
17
+ "master_address": "localhost",
18
+ "master_port": 48541,
19
+ "bf16": true,
20
+ "wandb_project_name": "CREAM",
21
+ "wandb_entity_name": "your_wandb_entity_name",
22
+ "run_name": "train_llama_w_qwen_binary_sft-lora_None-ckpt_None-25-04-27-20_56_47",
23
+ "output_dir": "outputs/sft/train_llama_w_qwen_binary_sft-lora_None-ckpt_None-25-04-27-20_56_47",
24
+ "load_args_path": null
25
+ },
26
+ "checkpoint": null,
27
+ "train_stage": "sft",
28
+ "dataset": {
29
+ "name": "train_llama_w_qwen_binary_sft",
30
+ "limit_size": null,
31
+ "max_length": 4096
32
+ },
33
+ "lora": {
34
+ "enable": false,
35
+ "alpha": 64,
36
+ "r": 32,
37
+ "dropout": 0.1
38
+ },
39
+ "dpo": {
40
+ "beta": 0.1,
41
+ "method": "original"
42
+ }
43
+ }
checkpoint-17229/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "hidden_act": "silu",
15
+ "hidden_size": 4096,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 14336,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 8,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": {
27
+ "factor": 8.0,
28
+ "high_freq_factor": 4.0,
29
+ "low_freq_factor": 1.0,
30
+ "original_max_position_embeddings": 8192,
31
+ "rope_type": "llama3"
32
+ },
33
+ "rope_theta": 500000.0,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.44.2",
37
+ "use_cache": true,
38
+ "vocab_size": 128259
39
+ }
checkpoint-17229/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.44.2"
12
+ }
checkpoint-17229/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db72da6c37fc1c7cc85d32adbc14db9b278d9066af62c5cbdf2f3877a57fed27
3
+ size 9976525976
checkpoint-17229/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fbffe57df7963fb81151bdb40219b434bf71cb1af43dc982e02b466adf53d83
3
+ size 6084079576
checkpoint-17229/model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060571648
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
296
+ "model.norm.weight": "model-00002-of-00002.safetensors"
297
+ }
298
+ }
checkpoint-17229/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-17229/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-17229/tokenizer_config.json ADDED
@@ -0,0 +1,2087 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<|pad|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ },
2059
+ "128257": {
2060
+ "content": "<think>",
2061
+ "lstrip": false,
2062
+ "normalized": true,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": false
2066
+ },
2067
+ "128258": {
2068
+ "content": "</think>",
2069
+ "lstrip": false,
2070
+ "normalized": true,
2071
+ "rstrip": false,
2072
+ "single_word": false,
2073
+ "special": false
2074
+ }
2075
+ },
2076
+ "bos_token": "<|begin_of_text|>",
2077
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2078
+ "clean_up_tokenization_spaces": true,
2079
+ "eos_token": "<|eot_id|>",
2080
+ "model_input_names": [
2081
+ "input_ids",
2082
+ "attention_mask"
2083
+ ],
2084
+ "model_max_length": 131072,
2085
+ "pad_token": "<|pad|>",
2086
+ "tokenizer_class": "PreTrainedTokenizerFast"
2087
+ }
checkpoint-17229/trainer_state.json ADDED
@@ -0,0 +1,3806 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 5743,
6
+ "global_step": 17229,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 90.67318725585938,
14
+ "learning_rate": 2.901915264074289e-09,
15
+ "loss": 4.6958,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "grad_norm": 104.22982025146484,
21
+ "learning_rate": 9.286128845037725e-08,
22
+ "loss": 5.0471,
23
+ "step": 32
24
+ },
25
+ {
26
+ "epoch": 0.01,
27
+ "grad_norm": 29.807086944580078,
28
+ "learning_rate": 1.857225769007545e-07,
29
+ "loss": 4.7906,
30
+ "step": 64
31
+ },
32
+ {
33
+ "epoch": 0.02,
34
+ "grad_norm": 25.591365814208984,
35
+ "learning_rate": 2.785838653511318e-07,
36
+ "loss": 4.3938,
37
+ "step": 96
38
+ },
39
+ {
40
+ "epoch": 0.02,
41
+ "grad_norm": 25.191415786743164,
42
+ "learning_rate": 3.71445153801509e-07,
43
+ "loss": 4.2526,
44
+ "step": 128
45
+ },
46
+ {
47
+ "epoch": 0.03,
48
+ "grad_norm": 34.85346984863281,
49
+ "learning_rate": 4.643064422518863e-07,
50
+ "loss": 4.1321,
51
+ "step": 160
52
+ },
53
+ {
54
+ "epoch": 0.03,
55
+ "grad_norm": 27.427072525024414,
56
+ "learning_rate": 5.571677307022636e-07,
57
+ "loss": 3.8133,
58
+ "step": 192
59
+ },
60
+ {
61
+ "epoch": 0.04,
62
+ "grad_norm": 21.698957443237305,
63
+ "learning_rate": 6.500290191526408e-07,
64
+ "loss": 3.8467,
65
+ "step": 224
66
+ },
67
+ {
68
+ "epoch": 0.04,
69
+ "grad_norm": 44.60033416748047,
70
+ "learning_rate": 7.42890307603018e-07,
71
+ "loss": 3.7419,
72
+ "step": 256
73
+ },
74
+ {
75
+ "epoch": 0.05,
76
+ "grad_norm": 49.22486877441406,
77
+ "learning_rate": 8.357515960533953e-07,
78
+ "loss": 3.6156,
79
+ "step": 288
80
+ },
81
+ {
82
+ "epoch": 0.06,
83
+ "grad_norm": 36.528568267822266,
84
+ "learning_rate": 9.286128845037726e-07,
85
+ "loss": 3.3479,
86
+ "step": 320
87
+ },
88
+ {
89
+ "epoch": 0.06,
90
+ "grad_norm": 48.99635696411133,
91
+ "learning_rate": 1.0214741729541498e-06,
92
+ "loss": 3.0823,
93
+ "step": 352
94
+ },
95
+ {
96
+ "epoch": 0.07,
97
+ "grad_norm": 44.24087142944336,
98
+ "learning_rate": 1.1143354614045271e-06,
99
+ "loss": 2.7423,
100
+ "step": 384
101
+ },
102
+ {
103
+ "epoch": 0.07,
104
+ "grad_norm": 50.86935806274414,
105
+ "learning_rate": 1.2071967498549044e-06,
106
+ "loss": 2.4941,
107
+ "step": 416
108
+ },
109
+ {
110
+ "epoch": 0.08,
111
+ "grad_norm": 31.083118438720703,
112
+ "learning_rate": 1.3000580383052816e-06,
113
+ "loss": 2.2775,
114
+ "step": 448
115
+ },
116
+ {
117
+ "epoch": 0.08,
118
+ "grad_norm": 35.24567413330078,
119
+ "learning_rate": 1.3929193267556587e-06,
120
+ "loss": 1.9606,
121
+ "step": 480
122
+ },
123
+ {
124
+ "epoch": 0.09,
125
+ "grad_norm": 53.384952545166016,
126
+ "learning_rate": 1.485780615206036e-06,
127
+ "loss": 1.6271,
128
+ "step": 512
129
+ },
130
+ {
131
+ "epoch": 0.09,
132
+ "grad_norm": 47.57023239135742,
133
+ "learning_rate": 1.5786419036564131e-06,
134
+ "loss": 1.3614,
135
+ "step": 544
136
+ },
137
+ {
138
+ "epoch": 0.1,
139
+ "grad_norm": 38.1913948059082,
140
+ "learning_rate": 1.6715031921067907e-06,
141
+ "loss": 1.007,
142
+ "step": 576
143
+ },
144
+ {
145
+ "epoch": 0.11,
146
+ "grad_norm": 24.733055114746094,
147
+ "learning_rate": 1.7643644805571678e-06,
148
+ "loss": 0.7387,
149
+ "step": 608
150
+ },
151
+ {
152
+ "epoch": 0.11,
153
+ "grad_norm": 20.36598777770996,
154
+ "learning_rate": 1.8572257690075451e-06,
155
+ "loss": 0.5821,
156
+ "step": 640
157
+ },
158
+ {
159
+ "epoch": 0.12,
160
+ "grad_norm": 9.40074634552002,
161
+ "learning_rate": 1.9500870574579222e-06,
162
+ "loss": 0.4921,
163
+ "step": 672
164
+ },
165
+ {
166
+ "epoch": 0.12,
167
+ "grad_norm": 9.734894752502441,
168
+ "learning_rate": 2.0429483459082996e-06,
169
+ "loss": 0.4433,
170
+ "step": 704
171
+ },
172
+ {
173
+ "epoch": 0.13,
174
+ "grad_norm": 8.26183032989502,
175
+ "learning_rate": 2.135809634358677e-06,
176
+ "loss": 0.4163,
177
+ "step": 736
178
+ },
179
+ {
180
+ "epoch": 0.13,
181
+ "grad_norm": 4.765627861022949,
182
+ "learning_rate": 2.2286709228090542e-06,
183
+ "loss": 0.403,
184
+ "step": 768
185
+ },
186
+ {
187
+ "epoch": 0.14,
188
+ "grad_norm": 3.9424140453338623,
189
+ "learning_rate": 2.321532211259431e-06,
190
+ "loss": 0.4155,
191
+ "step": 800
192
+ },
193
+ {
194
+ "epoch": 0.14,
195
+ "grad_norm": 3.6798696517944336,
196
+ "learning_rate": 2.414393499709809e-06,
197
+ "loss": 0.3943,
198
+ "step": 832
199
+ },
200
+ {
201
+ "epoch": 0.15,
202
+ "grad_norm": 3.714017868041992,
203
+ "learning_rate": 2.5072547881601862e-06,
204
+ "loss": 0.3845,
205
+ "step": 864
206
+ },
207
+ {
208
+ "epoch": 0.16,
209
+ "grad_norm": 3.57197642326355,
210
+ "learning_rate": 2.600116076610563e-06,
211
+ "loss": 0.3699,
212
+ "step": 896
213
+ },
214
+ {
215
+ "epoch": 0.16,
216
+ "grad_norm": 3.1965994834899902,
217
+ "learning_rate": 2.6929773650609405e-06,
218
+ "loss": 0.3559,
219
+ "step": 928
220
+ },
221
+ {
222
+ "epoch": 0.17,
223
+ "grad_norm": 2.980022668838501,
224
+ "learning_rate": 2.7858386535113174e-06,
225
+ "loss": 0.347,
226
+ "step": 960
227
+ },
228
+ {
229
+ "epoch": 0.17,
230
+ "grad_norm": 3.079709529876709,
231
+ "learning_rate": 2.878699941961695e-06,
232
+ "loss": 0.3415,
233
+ "step": 992
234
+ },
235
+ {
236
+ "epoch": 0.18,
237
+ "grad_norm": 2.8273375034332275,
238
+ "learning_rate": 2.971561230412072e-06,
239
+ "loss": 0.3531,
240
+ "step": 1024
241
+ },
242
+ {
243
+ "epoch": 0.18,
244
+ "grad_norm": 2.214918375015259,
245
+ "learning_rate": 3.0644225188624494e-06,
246
+ "loss": 0.3414,
247
+ "step": 1056
248
+ },
249
+ {
250
+ "epoch": 0.19,
251
+ "grad_norm": 2.4280753135681152,
252
+ "learning_rate": 3.1572838073128263e-06,
253
+ "loss": 0.3391,
254
+ "step": 1088
255
+ },
256
+ {
257
+ "epoch": 0.2,
258
+ "grad_norm": 1.955213189125061,
259
+ "learning_rate": 3.250145095763204e-06,
260
+ "loss": 0.3372,
261
+ "step": 1120
262
+ },
263
+ {
264
+ "epoch": 0.2,
265
+ "grad_norm": 2.2462759017944336,
266
+ "learning_rate": 3.3430063842135814e-06,
267
+ "loss": 0.3459,
268
+ "step": 1152
269
+ },
270
+ {
271
+ "epoch": 0.21,
272
+ "grad_norm": 2.0212900638580322,
273
+ "learning_rate": 3.4358676726639583e-06,
274
+ "loss": 0.3429,
275
+ "step": 1184
276
+ },
277
+ {
278
+ "epoch": 0.21,
279
+ "grad_norm": 1.7310266494750977,
280
+ "learning_rate": 3.5287289611143356e-06,
281
+ "loss": 0.3347,
282
+ "step": 1216
283
+ },
284
+ {
285
+ "epoch": 0.22,
286
+ "grad_norm": 2.134054183959961,
287
+ "learning_rate": 3.6215902495647133e-06,
288
+ "loss": 0.3187,
289
+ "step": 1248
290
+ },
291
+ {
292
+ "epoch": 0.22,
293
+ "grad_norm": 1.850546956062317,
294
+ "learning_rate": 3.7144515380150902e-06,
295
+ "loss": 0.3217,
296
+ "step": 1280
297
+ },
298
+ {
299
+ "epoch": 0.23,
300
+ "grad_norm": 2.3363544940948486,
301
+ "learning_rate": 3.8073128264654676e-06,
302
+ "loss": 0.3398,
303
+ "step": 1312
304
+ },
305
+ {
306
+ "epoch": 0.23,
307
+ "grad_norm": 1.707647681236267,
308
+ "learning_rate": 3.9001741149158445e-06,
309
+ "loss": 0.3132,
310
+ "step": 1344
311
+ },
312
+ {
313
+ "epoch": 0.24,
314
+ "grad_norm": 1.7750575542449951,
315
+ "learning_rate": 3.993035403366222e-06,
316
+ "loss": 0.315,
317
+ "step": 1376
318
+ },
319
+ {
320
+ "epoch": 0.25,
321
+ "grad_norm": 1.8037201166152954,
322
+ "learning_rate": 4.085896691816599e-06,
323
+ "loss": 0.3263,
324
+ "step": 1408
325
+ },
326
+ {
327
+ "epoch": 0.25,
328
+ "grad_norm": 2.307892084121704,
329
+ "learning_rate": 4.1787579802669765e-06,
330
+ "loss": 0.3119,
331
+ "step": 1440
332
+ },
333
+ {
334
+ "epoch": 0.26,
335
+ "grad_norm": 2.105405569076538,
336
+ "learning_rate": 4.271619268717354e-06,
337
+ "loss": 0.3253,
338
+ "step": 1472
339
+ },
340
+ {
341
+ "epoch": 0.26,
342
+ "grad_norm": 1.809043526649475,
343
+ "learning_rate": 4.364480557167731e-06,
344
+ "loss": 0.3293,
345
+ "step": 1504
346
+ },
347
+ {
348
+ "epoch": 0.27,
349
+ "grad_norm": 2.1056556701660156,
350
+ "learning_rate": 4.4573418456181085e-06,
351
+ "loss": 0.3091,
352
+ "step": 1536
353
+ },
354
+ {
355
+ "epoch": 0.27,
356
+ "grad_norm": 1.6170997619628906,
357
+ "learning_rate": 4.550203134068486e-06,
358
+ "loss": 0.3123,
359
+ "step": 1568
360
+ },
361
+ {
362
+ "epoch": 0.28,
363
+ "grad_norm": 1.9799582958221436,
364
+ "learning_rate": 4.643064422518862e-06,
365
+ "loss": 0.3225,
366
+ "step": 1600
367
+ },
368
+ {
369
+ "epoch": 0.28,
370
+ "grad_norm": 1.9572292566299438,
371
+ "learning_rate": 4.7359257109692405e-06,
372
+ "loss": 0.3257,
373
+ "step": 1632
374
+ },
375
+ {
376
+ "epoch": 0.29,
377
+ "grad_norm": 1.9340535402297974,
378
+ "learning_rate": 4.828786999419618e-06,
379
+ "loss": 0.3176,
380
+ "step": 1664
381
+ },
382
+ {
383
+ "epoch": 0.3,
384
+ "grad_norm": 1.9439414739608765,
385
+ "learning_rate": 4.921648287869994e-06,
386
+ "loss": 0.3114,
387
+ "step": 1696
388
+ },
389
+ {
390
+ "epoch": 0.3,
391
+ "grad_norm": 1.8130865097045898,
392
+ "learning_rate": 4.999998717225936e-06,
393
+ "loss": 0.3136,
394
+ "step": 1728
395
+ },
396
+ {
397
+ "epoch": 0.31,
398
+ "grad_norm": 1.8154480457305908,
399
+ "learning_rate": 4.999929755615174e-06,
400
+ "loss": 0.3215,
401
+ "step": 1760
402
+ },
403
+ {
404
+ "epoch": 0.31,
405
+ "grad_norm": 1.8465503454208374,
406
+ "learning_rate": 4.999755712464791e-06,
407
+ "loss": 0.3178,
408
+ "step": 1792
409
+ },
410
+ {
411
+ "epoch": 0.32,
412
+ "grad_norm": 1.7973068952560425,
413
+ "learning_rate": 4.999476595090482e-06,
414
+ "loss": 0.3196,
415
+ "step": 1824
416
+ },
417
+ {
418
+ "epoch": 0.32,
419
+ "grad_norm": 1.5011913776397705,
420
+ "learning_rate": 4.99909241522461e-06,
421
+ "loss": 0.3194,
422
+ "step": 1856
423
+ },
424
+ {
425
+ "epoch": 0.33,
426
+ "grad_norm": 1.8762191534042358,
427
+ "learning_rate": 4.998603189015714e-06,
428
+ "loss": 0.3238,
429
+ "step": 1888
430
+ },
431
+ {
432
+ "epoch": 0.33,
433
+ "grad_norm": 1.81588876247406,
434
+ "learning_rate": 4.9980089370278275e-06,
435
+ "loss": 0.328,
436
+ "step": 1920
437
+ },
438
+ {
439
+ "epoch": 0.34,
440
+ "grad_norm": 1.8873347043991089,
441
+ "learning_rate": 4.997309684239618e-06,
442
+ "loss": 0.3189,
443
+ "step": 1952
444
+ },
445
+ {
446
+ "epoch": 0.35,
447
+ "grad_norm": 1.7700365781784058,
448
+ "learning_rate": 4.996505460043337e-06,
449
+ "loss": 0.303,
450
+ "step": 1984
451
+ },
452
+ {
453
+ "epoch": 0.35,
454
+ "grad_norm": 1.6417065858840942,
455
+ "learning_rate": 4.99559629824358e-06,
456
+ "loss": 0.3155,
457
+ "step": 2016
458
+ },
459
+ {
460
+ "epoch": 0.36,
461
+ "grad_norm": 1.689789891242981,
462
+ "learning_rate": 4.99458223705587e-06,
463
+ "loss": 0.3254,
464
+ "step": 2048
465
+ },
466
+ {
467
+ "epoch": 0.36,
468
+ "grad_norm": 2.12276291847229,
469
+ "learning_rate": 4.993463319105047e-06,
470
+ "loss": 0.2986,
471
+ "step": 2080
472
+ },
473
+ {
474
+ "epoch": 0.37,
475
+ "grad_norm": 1.7065095901489258,
476
+ "learning_rate": 4.992239591423483e-06,
477
+ "loss": 0.3197,
478
+ "step": 2112
479
+ },
480
+ {
481
+ "epoch": 0.37,
482
+ "grad_norm": 2.3180906772613525,
483
+ "learning_rate": 4.990911105449098e-06,
484
+ "loss": 0.3153,
485
+ "step": 2144
486
+ },
487
+ {
488
+ "epoch": 0.38,
489
+ "grad_norm": 1.8196240663528442,
490
+ "learning_rate": 4.9894779170232024e-06,
491
+ "loss": 0.313,
492
+ "step": 2176
493
+ },
494
+ {
495
+ "epoch": 0.38,
496
+ "grad_norm": 2.0028891563415527,
497
+ "learning_rate": 4.987940086388146e-06,
498
+ "loss": 0.31,
499
+ "step": 2208
500
+ },
501
+ {
502
+ "epoch": 0.39,
503
+ "grad_norm": 1.862817645072937,
504
+ "learning_rate": 4.986297678184791e-06,
505
+ "loss": 0.3035,
506
+ "step": 2240
507
+ },
508
+ {
509
+ "epoch": 0.4,
510
+ "grad_norm": 1.7188054323196411,
511
+ "learning_rate": 4.984550761449788e-06,
512
+ "loss": 0.3504,
513
+ "step": 2272
514
+ },
515
+ {
516
+ "epoch": 0.4,
517
+ "grad_norm": 1.6241610050201416,
518
+ "learning_rate": 4.982699409612683e-06,
519
+ "loss": 0.2926,
520
+ "step": 2304
521
+ },
522
+ {
523
+ "epoch": 0.41,
524
+ "grad_norm": 1.9147684574127197,
525
+ "learning_rate": 4.980743700492822e-06,
526
+ "loss": 0.3212,
527
+ "step": 2336
528
+ },
529
+ {
530
+ "epoch": 0.41,
531
+ "grad_norm": 1.5901225805282593,
532
+ "learning_rate": 4.978683716296084e-06,
533
+ "loss": 0.3057,
534
+ "step": 2368
535
+ },
536
+ {
537
+ "epoch": 0.42,
538
+ "grad_norm": 1.670644760131836,
539
+ "learning_rate": 4.976519543611427e-06,
540
+ "loss": 0.3038,
541
+ "step": 2400
542
+ },
543
+ {
544
+ "epoch": 0.42,
545
+ "grad_norm": 1.3500678539276123,
546
+ "learning_rate": 4.974251273407246e-06,
547
+ "loss": 0.3019,
548
+ "step": 2432
549
+ },
550
+ {
551
+ "epoch": 0.43,
552
+ "grad_norm": 1.6647801399230957,
553
+ "learning_rate": 4.971879001027552e-06,
554
+ "loss": 0.3017,
555
+ "step": 2464
556
+ },
557
+ {
558
+ "epoch": 0.43,
559
+ "grad_norm": 1.793252944946289,
560
+ "learning_rate": 4.9694028261879576e-06,
561
+ "loss": 0.3068,
562
+ "step": 2496
563
+ },
564
+ {
565
+ "epoch": 0.44,
566
+ "grad_norm": 1.9570722579956055,
567
+ "learning_rate": 4.966822852971493e-06,
568
+ "loss": 0.311,
569
+ "step": 2528
570
+ },
571
+ {
572
+ "epoch": 0.45,
573
+ "grad_norm": 1.787014365196228,
574
+ "learning_rate": 4.964139189824232e-06,
575
+ "loss": 0.2992,
576
+ "step": 2560
577
+ },
578
+ {
579
+ "epoch": 0.45,
580
+ "grad_norm": 1.68462073802948,
581
+ "learning_rate": 4.961351949550722e-06,
582
+ "loss": 0.3054,
583
+ "step": 2592
584
+ },
585
+ {
586
+ "epoch": 0.46,
587
+ "grad_norm": 1.7559980154037476,
588
+ "learning_rate": 4.958461249309258e-06,
589
+ "loss": 0.3119,
590
+ "step": 2624
591
+ },
592
+ {
593
+ "epoch": 0.46,
594
+ "grad_norm": 1.9941719770431519,
595
+ "learning_rate": 4.955467210606944e-06,
596
+ "loss": 0.3122,
597
+ "step": 2656
598
+ },
599
+ {
600
+ "epoch": 0.47,
601
+ "grad_norm": 1.6227741241455078,
602
+ "learning_rate": 4.9523699592945966e-06,
603
+ "loss": 0.3094,
604
+ "step": 2688
605
+ },
606
+ {
607
+ "epoch": 0.47,
608
+ "grad_norm": 1.8108834028244019,
609
+ "learning_rate": 4.9491696255614475e-06,
610
+ "loss": 0.3079,
611
+ "step": 2720
612
+ },
613
+ {
614
+ "epoch": 0.48,
615
+ "grad_norm": 1.871539831161499,
616
+ "learning_rate": 4.945866343929675e-06,
617
+ "loss": 0.3085,
618
+ "step": 2752
619
+ },
620
+ {
621
+ "epoch": 0.48,
622
+ "grad_norm": 1.8067561388015747,
623
+ "learning_rate": 4.94246025324875e-06,
624
+ "loss": 0.3138,
625
+ "step": 2784
626
+ },
627
+ {
628
+ "epoch": 0.49,
629
+ "grad_norm": 1.4682188034057617,
630
+ "learning_rate": 4.938951496689593e-06,
631
+ "loss": 0.3141,
632
+ "step": 2816
633
+ },
634
+ {
635
+ "epoch": 0.5,
636
+ "grad_norm": 1.8749171495437622,
637
+ "learning_rate": 4.935340221738568e-06,
638
+ "loss": 0.2903,
639
+ "step": 2848
640
+ },
641
+ {
642
+ "epoch": 0.5,
643
+ "grad_norm": 1.780875563621521,
644
+ "learning_rate": 4.931626580191271e-06,
645
+ "loss": 0.3086,
646
+ "step": 2880
647
+ },
648
+ {
649
+ "epoch": 0.51,
650
+ "grad_norm": 1.468619465827942,
651
+ "learning_rate": 4.927810728146158e-06,
652
+ "loss": 0.3016,
653
+ "step": 2912
654
+ },
655
+ {
656
+ "epoch": 0.51,
657
+ "grad_norm": 1.5029264688491821,
658
+ "learning_rate": 4.923892825997976e-06,
659
+ "loss": 0.2962,
660
+ "step": 2944
661
+ },
662
+ {
663
+ "epoch": 0.52,
664
+ "grad_norm": 1.9954643249511719,
665
+ "learning_rate": 4.919873038431031e-06,
666
+ "loss": 0.3135,
667
+ "step": 2976
668
+ },
669
+ {
670
+ "epoch": 0.52,
671
+ "grad_norm": 1.7070242166519165,
672
+ "learning_rate": 4.915751534412256e-06,
673
+ "loss": 0.3216,
674
+ "step": 3008
675
+ },
676
+ {
677
+ "epoch": 0.53,
678
+ "grad_norm": 1.9191008806228638,
679
+ "learning_rate": 4.911528487184115e-06,
680
+ "loss": 0.2814,
681
+ "step": 3040
682
+ },
683
+ {
684
+ "epoch": 0.53,
685
+ "grad_norm": 1.5027116537094116,
686
+ "learning_rate": 4.9072040742573154e-06,
687
+ "loss": 0.2917,
688
+ "step": 3072
689
+ },
690
+ {
691
+ "epoch": 0.54,
692
+ "grad_norm": 1.5248404741287231,
693
+ "learning_rate": 4.902778477403354e-06,
694
+ "loss": 0.3001,
695
+ "step": 3104
696
+ },
697
+ {
698
+ "epoch": 0.55,
699
+ "grad_norm": 1.996079921722412,
700
+ "learning_rate": 4.89825188264687e-06,
701
+ "loss": 0.2951,
702
+ "step": 3136
703
+ },
704
+ {
705
+ "epoch": 0.55,
706
+ "grad_norm": 1.7733569145202637,
707
+ "learning_rate": 4.893624480257826e-06,
708
+ "loss": 0.3031,
709
+ "step": 3168
710
+ },
711
+ {
712
+ "epoch": 0.56,
713
+ "grad_norm": 1.3993550539016724,
714
+ "learning_rate": 4.888896464743515e-06,
715
+ "loss": 0.2941,
716
+ "step": 3200
717
+ },
718
+ {
719
+ "epoch": 0.56,
720
+ "grad_norm": 1.37386953830719,
721
+ "learning_rate": 4.884068034840382e-06,
722
+ "loss": 0.2917,
723
+ "step": 3232
724
+ },
725
+ {
726
+ "epoch": 0.57,
727
+ "grad_norm": 1.7720749378204346,
728
+ "learning_rate": 4.879139393505669e-06,
729
+ "loss": 0.3038,
730
+ "step": 3264
731
+ },
732
+ {
733
+ "epoch": 0.57,
734
+ "grad_norm": 1.4496855735778809,
735
+ "learning_rate": 4.874110747908883e-06,
736
+ "loss": 0.3019,
737
+ "step": 3296
738
+ },
739
+ {
740
+ "epoch": 0.58,
741
+ "grad_norm": 1.70554518699646,
742
+ "learning_rate": 4.868982309423094e-06,
743
+ "loss": 0.2824,
744
+ "step": 3328
745
+ },
746
+ {
747
+ "epoch": 0.59,
748
+ "grad_norm": 1.6426483392715454,
749
+ "learning_rate": 4.863754293616043e-06,
750
+ "loss": 0.3064,
751
+ "step": 3360
752
+ },
753
+ {
754
+ "epoch": 0.59,
755
+ "grad_norm": 1.9177954196929932,
756
+ "learning_rate": 4.858426920241083e-06,
757
+ "loss": 0.3046,
758
+ "step": 3392
759
+ },
760
+ {
761
+ "epoch": 0.6,
762
+ "grad_norm": 1.8572829961776733,
763
+ "learning_rate": 4.853000413227946e-06,
764
+ "loss": 0.3032,
765
+ "step": 3424
766
+ },
767
+ {
768
+ "epoch": 0.6,
769
+ "grad_norm": 1.548661708831787,
770
+ "learning_rate": 4.8474750006733265e-06,
771
+ "loss": 0.2997,
772
+ "step": 3456
773
+ },
774
+ {
775
+ "epoch": 0.61,
776
+ "grad_norm": 1.4153339862823486,
777
+ "learning_rate": 4.841850914831291e-06,
778
+ "loss": 0.2939,
779
+ "step": 3488
780
+ },
781
+ {
782
+ "epoch": 0.61,
783
+ "grad_norm": 1.7126343250274658,
784
+ "learning_rate": 4.836128392103524e-06,
785
+ "loss": 0.3181,
786
+ "step": 3520
787
+ },
788
+ {
789
+ "epoch": 0.62,
790
+ "grad_norm": 1.8360246419906616,
791
+ "learning_rate": 4.830307673029383e-06,
792
+ "loss": 0.3026,
793
+ "step": 3552
794
+ },
795
+ {
796
+ "epoch": 0.62,
797
+ "grad_norm": 1.6076633930206299,
798
+ "learning_rate": 4.82438900227579e-06,
799
+ "loss": 0.3092,
800
+ "step": 3584
801
+ },
802
+ {
803
+ "epoch": 0.63,
804
+ "grad_norm": 1.890261173248291,
805
+ "learning_rate": 4.8183726286269515e-06,
806
+ "loss": 0.2965,
807
+ "step": 3616
808
+ },
809
+ {
810
+ "epoch": 0.64,
811
+ "grad_norm": 1.462218999862671,
812
+ "learning_rate": 4.812258804973895e-06,
813
+ "loss": 0.2851,
814
+ "step": 3648
815
+ },
816
+ {
817
+ "epoch": 0.64,
818
+ "grad_norm": 1.5263981819152832,
819
+ "learning_rate": 4.806047788303841e-06,
820
+ "loss": 0.3002,
821
+ "step": 3680
822
+ },
823
+ {
824
+ "epoch": 0.65,
825
+ "grad_norm": 1.9360984563827515,
826
+ "learning_rate": 4.799739839689404e-06,
827
+ "loss": 0.2918,
828
+ "step": 3712
829
+ },
830
+ {
831
+ "epoch": 0.65,
832
+ "grad_norm": 1.7371431589126587,
833
+ "learning_rate": 4.7933352242776136e-06,
834
+ "loss": 0.2962,
835
+ "step": 3744
836
+ },
837
+ {
838
+ "epoch": 0.66,
839
+ "grad_norm": 2.1363890171051025,
840
+ "learning_rate": 4.786834211278775e-06,
841
+ "loss": 0.2844,
842
+ "step": 3776
843
+ },
844
+ {
845
+ "epoch": 0.66,
846
+ "grad_norm": 1.2848248481750488,
847
+ "learning_rate": 4.780237073955147e-06,
848
+ "loss": 0.2927,
849
+ "step": 3808
850
+ },
851
+ {
852
+ "epoch": 0.67,
853
+ "grad_norm": 1.685262680053711,
854
+ "learning_rate": 4.773544089609462e-06,
855
+ "loss": 0.3018,
856
+ "step": 3840
857
+ },
858
+ {
859
+ "epoch": 0.67,
860
+ "grad_norm": 1.3517770767211914,
861
+ "learning_rate": 4.766755539573261e-06,
862
+ "loss": 0.2936,
863
+ "step": 3872
864
+ },
865
+ {
866
+ "epoch": 0.68,
867
+ "grad_norm": 1.723820447921753,
868
+ "learning_rate": 4.759871709195081e-06,
869
+ "loss": 0.2974,
870
+ "step": 3904
871
+ },
872
+ {
873
+ "epoch": 0.69,
874
+ "grad_norm": 1.8562276363372803,
875
+ "learning_rate": 4.752892887828448e-06,
876
+ "loss": 0.2967,
877
+ "step": 3936
878
+ },
879
+ {
880
+ "epoch": 0.69,
881
+ "grad_norm": 1.9959107637405396,
882
+ "learning_rate": 4.745819368819723e-06,
883
+ "loss": 0.2929,
884
+ "step": 3968
885
+ },
886
+ {
887
+ "epoch": 0.7,
888
+ "grad_norm": 2.034578323364258,
889
+ "learning_rate": 4.738651449495767e-06,
890
+ "loss": 0.2978,
891
+ "step": 4000
892
+ },
893
+ {
894
+ "epoch": 0.7,
895
+ "grad_norm": 1.2981053590774536,
896
+ "learning_rate": 4.731389431151445e-06,
897
+ "loss": 0.2951,
898
+ "step": 4032
899
+ },
900
+ {
901
+ "epoch": 0.71,
902
+ "grad_norm": 1.5861812829971313,
903
+ "learning_rate": 4.72403361903696e-06,
904
+ "loss": 0.2896,
905
+ "step": 4064
906
+ },
907
+ {
908
+ "epoch": 0.71,
909
+ "grad_norm": 1.2682240009307861,
910
+ "learning_rate": 4.716584322345028e-06,
911
+ "loss": 0.2973,
912
+ "step": 4096
913
+ },
914
+ {
915
+ "epoch": 0.72,
916
+ "grad_norm": 2.147078275680542,
917
+ "learning_rate": 4.70904185419787e-06,
918
+ "loss": 0.2944,
919
+ "step": 4128
920
+ },
921
+ {
922
+ "epoch": 0.72,
923
+ "grad_norm": 1.5924174785614014,
924
+ "learning_rate": 4.7014065316340606e-06,
925
+ "loss": 0.2859,
926
+ "step": 4160
927
+ },
928
+ {
929
+ "epoch": 0.73,
930
+ "grad_norm": 1.7698993682861328,
931
+ "learning_rate": 4.693678675595199e-06,
932
+ "loss": 0.2943,
933
+ "step": 4192
934
+ },
935
+ {
936
+ "epoch": 0.74,
937
+ "grad_norm": 1.599900245666504,
938
+ "learning_rate": 4.685858610912416e-06,
939
+ "loss": 0.3045,
940
+ "step": 4224
941
+ },
942
+ {
943
+ "epoch": 0.74,
944
+ "grad_norm": 1.6287124156951904,
945
+ "learning_rate": 4.677946666292722e-06,
946
+ "loss": 0.2884,
947
+ "step": 4256
948
+ },
949
+ {
950
+ "epoch": 0.75,
951
+ "grad_norm": 1.712890386581421,
952
+ "learning_rate": 4.66994317430519e-06,
953
+ "loss": 0.2946,
954
+ "step": 4288
955
+ },
956
+ {
957
+ "epoch": 0.75,
958
+ "grad_norm": 1.7418298721313477,
959
+ "learning_rate": 4.661848471366977e-06,
960
+ "loss": 0.2933,
961
+ "step": 4320
962
+ },
963
+ {
964
+ "epoch": 0.76,
965
+ "grad_norm": 1.7066587209701538,
966
+ "learning_rate": 4.653662897729183e-06,
967
+ "loss": 0.2934,
968
+ "step": 4352
969
+ },
970
+ {
971
+ "epoch": 0.76,
972
+ "grad_norm": 1.9766113758087158,
973
+ "learning_rate": 4.645386797462547e-06,
974
+ "loss": 0.3055,
975
+ "step": 4384
976
+ },
977
+ {
978
+ "epoch": 0.77,
979
+ "grad_norm": 1.7087821960449219,
980
+ "learning_rate": 4.637020518442986e-06,
981
+ "loss": 0.2857,
982
+ "step": 4416
983
+ },
984
+ {
985
+ "epoch": 0.77,
986
+ "grad_norm": 2.085517168045044,
987
+ "learning_rate": 4.628564412336975e-06,
988
+ "loss": 0.3509,
989
+ "step": 4448
990
+ },
991
+ {
992
+ "epoch": 0.78,
993
+ "grad_norm": 1.586540699005127,
994
+ "learning_rate": 4.620018834586759e-06,
995
+ "loss": 0.3071,
996
+ "step": 4480
997
+ },
998
+ {
999
+ "epoch": 0.79,
1000
+ "grad_norm": 1.5229309797286987,
1001
+ "learning_rate": 4.611384144395419e-06,
1002
+ "loss": 0.2978,
1003
+ "step": 4512
1004
+ },
1005
+ {
1006
+ "epoch": 0.79,
1007
+ "grad_norm": 1.5610827207565308,
1008
+ "learning_rate": 4.602660704711768e-06,
1009
+ "loss": 0.3,
1010
+ "step": 4544
1011
+ },
1012
+ {
1013
+ "epoch": 0.8,
1014
+ "grad_norm": 1.3079458475112915,
1015
+ "learning_rate": 4.593848882215098e-06,
1016
+ "loss": 0.3023,
1017
+ "step": 4576
1018
+ },
1019
+ {
1020
+ "epoch": 0.8,
1021
+ "grad_norm": 1.243058204650879,
1022
+ "learning_rate": 4.584949047299766e-06,
1023
+ "loss": 0.282,
1024
+ "step": 4608
1025
+ },
1026
+ {
1027
+ "epoch": 0.81,
1028
+ "grad_norm": 1.5151655673980713,
1029
+ "learning_rate": 4.5759615740596265e-06,
1030
+ "loss": 0.2863,
1031
+ "step": 4640
1032
+ },
1033
+ {
1034
+ "epoch": 0.81,
1035
+ "grad_norm": 1.6148176193237305,
1036
+ "learning_rate": 4.5668868402723024e-06,
1037
+ "loss": 0.29,
1038
+ "step": 4672
1039
+ },
1040
+ {
1041
+ "epoch": 0.82,
1042
+ "grad_norm": 1.3599457740783691,
1043
+ "learning_rate": 4.557725227383313e-06,
1044
+ "loss": 0.292,
1045
+ "step": 4704
1046
+ },
1047
+ {
1048
+ "epoch": 0.82,
1049
+ "grad_norm": 1.7854079008102417,
1050
+ "learning_rate": 4.548477120490031e-06,
1051
+ "loss": 0.3065,
1052
+ "step": 4736
1053
+ },
1054
+ {
1055
+ "epoch": 0.83,
1056
+ "grad_norm": 1.7878711223602295,
1057
+ "learning_rate": 4.539142908325506e-06,
1058
+ "loss": 0.2986,
1059
+ "step": 4768
1060
+ },
1061
+ {
1062
+ "epoch": 0.84,
1063
+ "grad_norm": 1.9896265268325806,
1064
+ "learning_rate": 4.529722983242114e-06,
1065
+ "loss": 0.3025,
1066
+ "step": 4800
1067
+ },
1068
+ {
1069
+ "epoch": 0.84,
1070
+ "grad_norm": 1.5168676376342773,
1071
+ "learning_rate": 4.5202177411950745e-06,
1072
+ "loss": 0.2847,
1073
+ "step": 4832
1074
+ },
1075
+ {
1076
+ "epoch": 0.85,
1077
+ "grad_norm": 1.6856423616409302,
1078
+ "learning_rate": 4.5106275817258e-06,
1079
+ "loss": 0.3038,
1080
+ "step": 4864
1081
+ },
1082
+ {
1083
+ "epoch": 0.85,
1084
+ "grad_norm": 1.329127550125122,
1085
+ "learning_rate": 4.5009529079451085e-06,
1086
+ "loss": 0.2829,
1087
+ "step": 4896
1088
+ },
1089
+ {
1090
+ "epoch": 0.86,
1091
+ "grad_norm": 1.9718722105026245,
1092
+ "learning_rate": 4.4911941265162695e-06,
1093
+ "loss": 0.2976,
1094
+ "step": 4928
1095
+ },
1096
+ {
1097
+ "epoch": 0.86,
1098
+ "grad_norm": 1.4611300230026245,
1099
+ "learning_rate": 4.481351647637921e-06,
1100
+ "loss": 0.2829,
1101
+ "step": 4960
1102
+ },
1103
+ {
1104
+ "epoch": 0.87,
1105
+ "grad_norm": 1.7366551160812378,
1106
+ "learning_rate": 4.471425885026822e-06,
1107
+ "loss": 0.2916,
1108
+ "step": 4992
1109
+ },
1110
+ {
1111
+ "epoch": 0.87,
1112
+ "grad_norm": 1.381406307220459,
1113
+ "learning_rate": 4.46141725590046e-06,
1114
+ "loss": 0.2908,
1115
+ "step": 5024
1116
+ },
1117
+ {
1118
+ "epoch": 0.88,
1119
+ "grad_norm": 1.4315983057022095,
1120
+ "learning_rate": 4.451326180959521e-06,
1121
+ "loss": 0.2705,
1122
+ "step": 5056
1123
+ },
1124
+ {
1125
+ "epoch": 0.89,
1126
+ "grad_norm": 1.7121741771697998,
1127
+ "learning_rate": 4.4411530843702e-06,
1128
+ "loss": 0.2956,
1129
+ "step": 5088
1130
+ },
1131
+ {
1132
+ "epoch": 0.89,
1133
+ "grad_norm": 1.845123529434204,
1134
+ "learning_rate": 4.430898393746371e-06,
1135
+ "loss": 0.2876,
1136
+ "step": 5120
1137
+ },
1138
+ {
1139
+ "epoch": 0.9,
1140
+ "grad_norm": 1.3543351888656616,
1141
+ "learning_rate": 4.420562540131618e-06,
1142
+ "loss": 0.2962,
1143
+ "step": 5152
1144
+ },
1145
+ {
1146
+ "epoch": 0.9,
1147
+ "grad_norm": 2.028374195098877,
1148
+ "learning_rate": 4.410145957981112e-06,
1149
+ "loss": 0.2937,
1150
+ "step": 5184
1151
+ },
1152
+ {
1153
+ "epoch": 0.91,
1154
+ "grad_norm": 1.5300021171569824,
1155
+ "learning_rate": 4.399649085143354e-06,
1156
+ "loss": 0.2883,
1157
+ "step": 5216
1158
+ },
1159
+ {
1160
+ "epoch": 0.91,
1161
+ "grad_norm": 1.8156017065048218,
1162
+ "learning_rate": 4.3890723628417605e-06,
1163
+ "loss": 0.2903,
1164
+ "step": 5248
1165
+ },
1166
+ {
1167
+ "epoch": 0.92,
1168
+ "grad_norm": 1.8335083723068237,
1169
+ "learning_rate": 4.378416235656133e-06,
1170
+ "loss": 0.2964,
1171
+ "step": 5280
1172
+ },
1173
+ {
1174
+ "epoch": 0.92,
1175
+ "grad_norm": 1.6856135129928589,
1176
+ "learning_rate": 4.3676811515039554e-06,
1177
+ "loss": 0.284,
1178
+ "step": 5312
1179
+ },
1180
+ {
1181
+ "epoch": 0.93,
1182
+ "grad_norm": 1.8075724840164185,
1183
+ "learning_rate": 4.356867561621575e-06,
1184
+ "loss": 0.274,
1185
+ "step": 5344
1186
+ },
1187
+ {
1188
+ "epoch": 0.94,
1189
+ "grad_norm": 2.1280436515808105,
1190
+ "learning_rate": 4.345975920545232e-06,
1191
+ "loss": 0.2781,
1192
+ "step": 5376
1193
+ },
1194
+ {
1195
+ "epoch": 0.94,
1196
+ "grad_norm": 1.8782936334609985,
1197
+ "learning_rate": 4.335006686091956e-06,
1198
+ "loss": 0.2796,
1199
+ "step": 5408
1200
+ },
1201
+ {
1202
+ "epoch": 0.95,
1203
+ "grad_norm": 1.802985429763794,
1204
+ "learning_rate": 4.323960319340321e-06,
1205
+ "loss": 0.2795,
1206
+ "step": 5440
1207
+ },
1208
+ {
1209
+ "epoch": 0.95,
1210
+ "grad_norm": 1.6335434913635254,
1211
+ "learning_rate": 4.312837284611062e-06,
1212
+ "loss": 0.3002,
1213
+ "step": 5472
1214
+ },
1215
+ {
1216
+ "epoch": 0.96,
1217
+ "grad_norm": 1.5709927082061768,
1218
+ "learning_rate": 4.301638049447563e-06,
1219
+ "loss": 0.2912,
1220
+ "step": 5504
1221
+ },
1222
+ {
1223
+ "epoch": 0.96,
1224
+ "grad_norm": 1.890569806098938,
1225
+ "learning_rate": 4.290363084596199e-06,
1226
+ "loss": 0.2995,
1227
+ "step": 5536
1228
+ },
1229
+ {
1230
+ "epoch": 0.97,
1231
+ "grad_norm": 1.405389666557312,
1232
+ "learning_rate": 4.279012863986554e-06,
1233
+ "loss": 0.2818,
1234
+ "step": 5568
1235
+ },
1236
+ {
1237
+ "epoch": 0.98,
1238
+ "grad_norm": 1.4392948150634766,
1239
+ "learning_rate": 4.267587864711496e-06,
1240
+ "loss": 0.2944,
1241
+ "step": 5600
1242
+ },
1243
+ {
1244
+ "epoch": 0.98,
1245
+ "grad_norm": 1.3795379400253296,
1246
+ "learning_rate": 4.256088567007123e-06,
1247
+ "loss": 0.2754,
1248
+ "step": 5632
1249
+ },
1250
+ {
1251
+ "epoch": 0.99,
1252
+ "grad_norm": 1.4689635038375854,
1253
+ "learning_rate": 4.244515454232579e-06,
1254
+ "loss": 0.2935,
1255
+ "step": 5664
1256
+ },
1257
+ {
1258
+ "epoch": 0.99,
1259
+ "grad_norm": 1.6686134338378906,
1260
+ "learning_rate": 4.232869012849739e-06,
1261
+ "loss": 0.2945,
1262
+ "step": 5696
1263
+ },
1264
+ {
1265
+ "epoch": 1.0,
1266
+ "grad_norm": 1.3574343919754028,
1267
+ "learning_rate": 4.22114973240275e-06,
1268
+ "loss": 0.2899,
1269
+ "step": 5728
1270
+ },
1271
+ {
1272
+ "epoch": 1.0,
1273
+ "grad_norm": 1.4560518264770508,
1274
+ "learning_rate": 4.20935810549747e-06,
1275
+ "loss": 0.2737,
1276
+ "step": 5760
1277
+ },
1278
+ {
1279
+ "epoch": 1.01,
1280
+ "grad_norm": 1.5906906127929688,
1281
+ "learning_rate": 4.1974946277807485e-06,
1282
+ "loss": 0.2523,
1283
+ "step": 5792
1284
+ },
1285
+ {
1286
+ "epoch": 1.01,
1287
+ "grad_norm": 2.1945157051086426,
1288
+ "learning_rate": 4.185559797919597e-06,
1289
+ "loss": 0.2449,
1290
+ "step": 5824
1291
+ },
1292
+ {
1293
+ "epoch": 1.02,
1294
+ "grad_norm": 2.203098773956299,
1295
+ "learning_rate": 4.173554117580231e-06,
1296
+ "loss": 0.2434,
1297
+ "step": 5856
1298
+ },
1299
+ {
1300
+ "epoch": 1.03,
1301
+ "grad_norm": 2.0016815662384033,
1302
+ "learning_rate": 4.16147809140698e-06,
1303
+ "loss": 0.2408,
1304
+ "step": 5888
1305
+ },
1306
+ {
1307
+ "epoch": 1.03,
1308
+ "grad_norm": 1.8361921310424805,
1309
+ "learning_rate": 4.149332227001075e-06,
1310
+ "loss": 0.2466,
1311
+ "step": 5920
1312
+ },
1313
+ {
1314
+ "epoch": 1.04,
1315
+ "grad_norm": 1.681320071220398,
1316
+ "learning_rate": 4.137117034899314e-06,
1317
+ "loss": 0.2437,
1318
+ "step": 5952
1319
+ },
1320
+ {
1321
+ "epoch": 1.04,
1322
+ "grad_norm": 2.212421178817749,
1323
+ "learning_rate": 4.124833028552601e-06,
1324
+ "loss": 0.2488,
1325
+ "step": 5984
1326
+ },
1327
+ {
1328
+ "epoch": 1.05,
1329
+ "grad_norm": 3.8892650604248047,
1330
+ "learning_rate": 4.112480724304362e-06,
1331
+ "loss": 0.2382,
1332
+ "step": 6016
1333
+ },
1334
+ {
1335
+ "epoch": 1.05,
1336
+ "grad_norm": 1.904011607170105,
1337
+ "learning_rate": 4.100060641368848e-06,
1338
+ "loss": 0.2461,
1339
+ "step": 6048
1340
+ },
1341
+ {
1342
+ "epoch": 1.06,
1343
+ "grad_norm": 1.6115171909332275,
1344
+ "learning_rate": 4.087573301809301e-06,
1345
+ "loss": 0.2475,
1346
+ "step": 6080
1347
+ },
1348
+ {
1349
+ "epoch": 1.06,
1350
+ "grad_norm": 1.625502109527588,
1351
+ "learning_rate": 4.075019230516016e-06,
1352
+ "loss": 0.2535,
1353
+ "step": 6112
1354
+ },
1355
+ {
1356
+ "epoch": 1.07,
1357
+ "grad_norm": 1.7666929960250854,
1358
+ "learning_rate": 4.062398955184277e-06,
1359
+ "loss": 0.2471,
1360
+ "step": 6144
1361
+ },
1362
+ {
1363
+ "epoch": 1.08,
1364
+ "grad_norm": 1.4440840482711792,
1365
+ "learning_rate": 4.049713006292174e-06,
1366
+ "loss": 0.2346,
1367
+ "step": 6176
1368
+ },
1369
+ {
1370
+ "epoch": 1.08,
1371
+ "grad_norm": 1.6042975187301636,
1372
+ "learning_rate": 4.036961917078305e-06,
1373
+ "loss": 0.2452,
1374
+ "step": 6208
1375
+ },
1376
+ {
1377
+ "epoch": 1.09,
1378
+ "grad_norm": 1.5292000770568848,
1379
+ "learning_rate": 4.024146223519365e-06,
1380
+ "loss": 0.2303,
1381
+ "step": 6240
1382
+ },
1383
+ {
1384
+ "epoch": 1.09,
1385
+ "grad_norm": 1.6863032579421997,
1386
+ "learning_rate": 4.011266464307615e-06,
1387
+ "loss": 0.2454,
1388
+ "step": 6272
1389
+ },
1390
+ {
1391
+ "epoch": 1.1,
1392
+ "grad_norm": 1.8112516403198242,
1393
+ "learning_rate": 3.998323180828236e-06,
1394
+ "loss": 0.2335,
1395
+ "step": 6304
1396
+ },
1397
+ {
1398
+ "epoch": 1.1,
1399
+ "grad_norm": 1.5118499994277954,
1400
+ "learning_rate": 3.985316917136579e-06,
1401
+ "loss": 0.2534,
1402
+ "step": 6336
1403
+ },
1404
+ {
1405
+ "epoch": 1.11,
1406
+ "grad_norm": 1.620071291923523,
1407
+ "learning_rate": 3.972248219935289e-06,
1408
+ "loss": 0.2311,
1409
+ "step": 6368
1410
+ },
1411
+ {
1412
+ "epoch": 1.11,
1413
+ "grad_norm": 1.4030137062072754,
1414
+ "learning_rate": 3.959117638551331e-06,
1415
+ "loss": 0.2411,
1416
+ "step": 6400
1417
+ },
1418
+ {
1419
+ "epoch": 1.12,
1420
+ "grad_norm": 1.6774815320968628,
1421
+ "learning_rate": 3.945925724912896e-06,
1422
+ "loss": 0.2546,
1423
+ "step": 6432
1424
+ },
1425
+ {
1426
+ "epoch": 1.13,
1427
+ "grad_norm": 2.215942144393921,
1428
+ "learning_rate": 3.932673033526203e-06,
1429
+ "loss": 0.2453,
1430
+ "step": 6464
1431
+ },
1432
+ {
1433
+ "epoch": 1.13,
1434
+ "grad_norm": 1.5397557020187378,
1435
+ "learning_rate": 3.919360121452188e-06,
1436
+ "loss": 0.2455,
1437
+ "step": 6496
1438
+ },
1439
+ {
1440
+ "epoch": 1.14,
1441
+ "grad_norm": 1.6343345642089844,
1442
+ "learning_rate": 3.905987548283097e-06,
1443
+ "loss": 0.2345,
1444
+ "step": 6528
1445
+ },
1446
+ {
1447
+ "epoch": 1.14,
1448
+ "grad_norm": 1.7040832042694092,
1449
+ "learning_rate": 3.892555876118951e-06,
1450
+ "loss": 0.2456,
1451
+ "step": 6560
1452
+ },
1453
+ {
1454
+ "epoch": 1.15,
1455
+ "grad_norm": 1.6422055959701538,
1456
+ "learning_rate": 3.879065669543931e-06,
1457
+ "loss": 0.2464,
1458
+ "step": 6592
1459
+ },
1460
+ {
1461
+ "epoch": 1.15,
1462
+ "grad_norm": 1.47724187374115,
1463
+ "learning_rate": 3.865517495602642e-06,
1464
+ "loss": 0.2379,
1465
+ "step": 6624
1466
+ },
1467
+ {
1468
+ "epoch": 1.16,
1469
+ "grad_norm": 1.5706995725631714,
1470
+ "learning_rate": 3.851911923776274e-06,
1471
+ "loss": 0.2542,
1472
+ "step": 6656
1473
+ },
1474
+ {
1475
+ "epoch": 1.16,
1476
+ "grad_norm": 1.3481061458587646,
1477
+ "learning_rate": 3.83824952595867e-06,
1478
+ "loss": 0.2358,
1479
+ "step": 6688
1480
+ },
1481
+ {
1482
+ "epoch": 1.17,
1483
+ "grad_norm": 1.7855818271636963,
1484
+ "learning_rate": 3.824530876432287e-06,
1485
+ "loss": 0.2506,
1486
+ "step": 6720
1487
+ },
1488
+ {
1489
+ "epoch": 1.18,
1490
+ "grad_norm": 1.661627173423767,
1491
+ "learning_rate": 3.81075655184405e-06,
1492
+ "loss": 0.2477,
1493
+ "step": 6752
1494
+ },
1495
+ {
1496
+ "epoch": 1.18,
1497
+ "grad_norm": 1.3250243663787842,
1498
+ "learning_rate": 3.796927131181124e-06,
1499
+ "loss": 0.236,
1500
+ "step": 6784
1501
+ },
1502
+ {
1503
+ "epoch": 1.19,
1504
+ "grad_norm": 1.5946906805038452,
1505
+ "learning_rate": 3.7830431957465673e-06,
1506
+ "loss": 0.2405,
1507
+ "step": 6816
1508
+ },
1509
+ {
1510
+ "epoch": 1.19,
1511
+ "grad_norm": 1.4719637632369995,
1512
+ "learning_rate": 3.7691053291349012e-06,
1513
+ "loss": 0.2444,
1514
+ "step": 6848
1515
+ },
1516
+ {
1517
+ "epoch": 1.2,
1518
+ "grad_norm": 2.088393211364746,
1519
+ "learning_rate": 3.755114117207582e-06,
1520
+ "loss": 0.238,
1521
+ "step": 6880
1522
+ },
1523
+ {
1524
+ "epoch": 1.2,
1525
+ "grad_norm": 1.853722333908081,
1526
+ "learning_rate": 3.7410701480683693e-06,
1527
+ "loss": 0.2496,
1528
+ "step": 6912
1529
+ },
1530
+ {
1531
+ "epoch": 1.21,
1532
+ "grad_norm": 1.338397741317749,
1533
+ "learning_rate": 3.726974012038609e-06,
1534
+ "loss": 0.2482,
1535
+ "step": 6944
1536
+ },
1537
+ {
1538
+ "epoch": 1.21,
1539
+ "grad_norm": 1.6698582172393799,
1540
+ "learning_rate": 3.7128263016324205e-06,
1541
+ "loss": 0.2501,
1542
+ "step": 6976
1543
+ },
1544
+ {
1545
+ "epoch": 1.22,
1546
+ "grad_norm": 2.1817092895507812,
1547
+ "learning_rate": 3.698627611531791e-06,
1548
+ "loss": 0.2382,
1549
+ "step": 7008
1550
+ },
1551
+ {
1552
+ "epoch": 1.23,
1553
+ "grad_norm": 1.6343122720718384,
1554
+ "learning_rate": 3.684378538561575e-06,
1555
+ "loss": 0.2447,
1556
+ "step": 7040
1557
+ },
1558
+ {
1559
+ "epoch": 1.23,
1560
+ "grad_norm": 1.335663080215454,
1561
+ "learning_rate": 3.6700796816644115e-06,
1562
+ "loss": 0.245,
1563
+ "step": 7072
1564
+ },
1565
+ {
1566
+ "epoch": 1.24,
1567
+ "grad_norm": 1.7304885387420654,
1568
+ "learning_rate": 3.655731641875549e-06,
1569
+ "loss": 0.2541,
1570
+ "step": 7104
1571
+ },
1572
+ {
1573
+ "epoch": 1.24,
1574
+ "grad_norm": 1.6443067789077759,
1575
+ "learning_rate": 3.641335022297576e-06,
1576
+ "loss": 0.249,
1577
+ "step": 7136
1578
+ },
1579
+ {
1580
+ "epoch": 1.25,
1581
+ "grad_norm": 1.5171420574188232,
1582
+ "learning_rate": 3.626890428075077e-06,
1583
+ "loss": 0.248,
1584
+ "step": 7168
1585
+ },
1586
+ {
1587
+ "epoch": 1.25,
1588
+ "grad_norm": 1.6931904554367065,
1589
+ "learning_rate": 3.6123984663691925e-06,
1590
+ "loss": 0.2404,
1591
+ "step": 7200
1592
+ },
1593
+ {
1594
+ "epoch": 1.26,
1595
+ "grad_norm": 1.7795478105545044,
1596
+ "learning_rate": 3.5978597463320964e-06,
1597
+ "loss": 0.2462,
1598
+ "step": 7232
1599
+ },
1600
+ {
1601
+ "epoch": 1.26,
1602
+ "grad_norm": 1.7948668003082275,
1603
+ "learning_rate": 3.5832748790813945e-06,
1604
+ "loss": 0.2507,
1605
+ "step": 7264
1606
+ },
1607
+ {
1608
+ "epoch": 1.27,
1609
+ "grad_norm": 1.6601665019989014,
1610
+ "learning_rate": 3.5686444776744346e-06,
1611
+ "loss": 0.2463,
1612
+ "step": 7296
1613
+ },
1614
+ {
1615
+ "epoch": 1.28,
1616
+ "grad_norm": 1.675183892250061,
1617
+ "learning_rate": 3.5539691570825374e-06,
1618
+ "loss": 0.2514,
1619
+ "step": 7328
1620
+ },
1621
+ {
1622
+ "epoch": 1.28,
1623
+ "grad_norm": 1.5422120094299316,
1624
+ "learning_rate": 3.5392495341651497e-06,
1625
+ "loss": 0.247,
1626
+ "step": 7360
1627
+ },
1628
+ {
1629
+ "epoch": 1.29,
1630
+ "grad_norm": 1.522061824798584,
1631
+ "learning_rate": 3.5244862276439102e-06,
1632
+ "loss": 0.2455,
1633
+ "step": 7392
1634
+ },
1635
+ {
1636
+ "epoch": 1.29,
1637
+ "grad_norm": 1.5597782135009766,
1638
+ "learning_rate": 3.5096798580766476e-06,
1639
+ "loss": 0.2514,
1640
+ "step": 7424
1641
+ },
1642
+ {
1643
+ "epoch": 1.3,
1644
+ "grad_norm": 2.3420979976654053,
1645
+ "learning_rate": 3.494831047831293e-06,
1646
+ "loss": 0.2486,
1647
+ "step": 7456
1648
+ },
1649
+ {
1650
+ "epoch": 1.3,
1651
+ "grad_norm": 1.397116780281067,
1652
+ "learning_rate": 3.479940421059721e-06,
1653
+ "loss": 0.2388,
1654
+ "step": 7488
1655
+ },
1656
+ {
1657
+ "epoch": 1.31,
1658
+ "grad_norm": 1.9889482259750366,
1659
+ "learning_rate": 3.4650086036715123e-06,
1660
+ "loss": 0.2521,
1661
+ "step": 7520
1662
+ },
1663
+ {
1664
+ "epoch": 1.31,
1665
+ "grad_norm": 1.3389945030212402,
1666
+ "learning_rate": 3.450036223307647e-06,
1667
+ "loss": 0.254,
1668
+ "step": 7552
1669
+ },
1670
+ {
1671
+ "epoch": 1.32,
1672
+ "grad_norm": 1.550194263458252,
1673
+ "learning_rate": 3.435023909314119e-06,
1674
+ "loss": 0.2411,
1675
+ "step": 7584
1676
+ },
1677
+ {
1678
+ "epoch": 1.33,
1679
+ "grad_norm": 1.39427649974823,
1680
+ "learning_rate": 3.4199722927154876e-06,
1681
+ "loss": 0.2421,
1682
+ "step": 7616
1683
+ },
1684
+ {
1685
+ "epoch": 1.33,
1686
+ "grad_norm": 1.647886037826538,
1687
+ "learning_rate": 3.4048820061883475e-06,
1688
+ "loss": 0.2546,
1689
+ "step": 7648
1690
+ },
1691
+ {
1692
+ "epoch": 1.34,
1693
+ "grad_norm": 1.4851469993591309,
1694
+ "learning_rate": 3.3897536840347384e-06,
1695
+ "loss": 0.2543,
1696
+ "step": 7680
1697
+ },
1698
+ {
1699
+ "epoch": 1.34,
1700
+ "grad_norm": 1.5985283851623535,
1701
+ "learning_rate": 3.3745879621554793e-06,
1702
+ "loss": 0.2505,
1703
+ "step": 7712
1704
+ },
1705
+ {
1706
+ "epoch": 1.35,
1707
+ "grad_norm": 1.467861294746399,
1708
+ "learning_rate": 3.3593854780234446e-06,
1709
+ "loss": 0.2408,
1710
+ "step": 7744
1711
+ },
1712
+ {
1713
+ "epoch": 1.35,
1714
+ "grad_norm": 1.5086297988891602,
1715
+ "learning_rate": 3.3441468706567655e-06,
1716
+ "loss": 0.2492,
1717
+ "step": 7776
1718
+ },
1719
+ {
1720
+ "epoch": 1.36,
1721
+ "grad_norm": 1.6549632549285889,
1722
+ "learning_rate": 3.328872780591968e-06,
1723
+ "loss": 0.2431,
1724
+ "step": 7808
1725
+ },
1726
+ {
1727
+ "epoch": 1.37,
1728
+ "grad_norm": 1.413674235343933,
1729
+ "learning_rate": 3.313563849857052e-06,
1730
+ "loss": 0.2539,
1731
+ "step": 7840
1732
+ },
1733
+ {
1734
+ "epoch": 1.37,
1735
+ "grad_norm": 1.547775387763977,
1736
+ "learning_rate": 3.298220721944504e-06,
1737
+ "loss": 0.2376,
1738
+ "step": 7872
1739
+ },
1740
+ {
1741
+ "epoch": 1.38,
1742
+ "grad_norm": 1.834301471710205,
1743
+ "learning_rate": 3.282844041784245e-06,
1744
+ "loss": 0.2465,
1745
+ "step": 7904
1746
+ },
1747
+ {
1748
+ "epoch": 1.38,
1749
+ "grad_norm": 1.5492215156555176,
1750
+ "learning_rate": 3.2674344557165268e-06,
1751
+ "loss": 0.2462,
1752
+ "step": 7936
1753
+ },
1754
+ {
1755
+ "epoch": 1.39,
1756
+ "grad_norm": 1.691975474357605,
1757
+ "learning_rate": 3.2519926114647597e-06,
1758
+ "loss": 0.2423,
1759
+ "step": 7968
1760
+ },
1761
+ {
1762
+ "epoch": 1.39,
1763
+ "grad_norm": 1.4883307218551636,
1764
+ "learning_rate": 3.2365191581082894e-06,
1765
+ "loss": 0.2431,
1766
+ "step": 8000
1767
+ },
1768
+ {
1769
+ "epoch": 1.4,
1770
+ "grad_norm": 1.9474862813949585,
1771
+ "learning_rate": 3.221014746055112e-06,
1772
+ "loss": 0.2409,
1773
+ "step": 8032
1774
+ },
1775
+ {
1776
+ "epoch": 1.4,
1777
+ "grad_norm": 1.7408241033554077,
1778
+ "learning_rate": 3.205480027014535e-06,
1779
+ "loss": 0.2529,
1780
+ "step": 8064
1781
+ },
1782
+ {
1783
+ "epoch": 1.41,
1784
+ "grad_norm": 1.9496859312057495,
1785
+ "learning_rate": 3.1899156539697817e-06,
1786
+ "loss": 0.244,
1787
+ "step": 8096
1788
+ },
1789
+ {
1790
+ "epoch": 1.42,
1791
+ "grad_norm": 1.5115084648132324,
1792
+ "learning_rate": 3.174322281150549e-06,
1793
+ "loss": 0.2355,
1794
+ "step": 8128
1795
+ },
1796
+ {
1797
+ "epoch": 1.42,
1798
+ "grad_norm": 1.5742942094802856,
1799
+ "learning_rate": 3.1587005640055035e-06,
1800
+ "loss": 0.237,
1801
+ "step": 8160
1802
+ },
1803
+ {
1804
+ "epoch": 1.43,
1805
+ "grad_norm": 1.6793855428695679,
1806
+ "learning_rate": 3.14305115917473e-06,
1807
+ "loss": 0.2357,
1808
+ "step": 8192
1809
+ },
1810
+ {
1811
+ "epoch": 1.43,
1812
+ "grad_norm": 1.359031081199646,
1813
+ "learning_rate": 3.1273747244621333e-06,
1814
+ "loss": 0.2507,
1815
+ "step": 8224
1816
+ },
1817
+ {
1818
+ "epoch": 1.44,
1819
+ "grad_norm": 1.3813912868499756,
1820
+ "learning_rate": 3.1116719188077867e-06,
1821
+ "loss": 0.2455,
1822
+ "step": 8256
1823
+ },
1824
+ {
1825
+ "epoch": 1.44,
1826
+ "grad_norm": 1.2507054805755615,
1827
+ "learning_rate": 3.0959434022602326e-06,
1828
+ "loss": 0.2376,
1829
+ "step": 8288
1830
+ },
1831
+ {
1832
+ "epoch": 1.45,
1833
+ "grad_norm": 1.6926429271697998,
1834
+ "learning_rate": 3.080189835948742e-06,
1835
+ "loss": 0.243,
1836
+ "step": 8320
1837
+ },
1838
+ {
1839
+ "epoch": 1.45,
1840
+ "grad_norm": 1.7547937631607056,
1841
+ "learning_rate": 3.0644118820555217e-06,
1842
+ "loss": 0.2418,
1843
+ "step": 8352
1844
+ },
1845
+ {
1846
+ "epoch": 1.46,
1847
+ "grad_norm": 1.5827124118804932,
1848
+ "learning_rate": 3.048610203787881e-06,
1849
+ "loss": 0.2422,
1850
+ "step": 8384
1851
+ },
1852
+ {
1853
+ "epoch": 1.47,
1854
+ "grad_norm": 1.5525377988815308,
1855
+ "learning_rate": 3.0327854653503554e-06,
1856
+ "loss": 0.2382,
1857
+ "step": 8416
1858
+ },
1859
+ {
1860
+ "epoch": 1.47,
1861
+ "grad_norm": 1.502051830291748,
1862
+ "learning_rate": 3.0169383319167866e-06,
1863
+ "loss": 0.2343,
1864
+ "step": 8448
1865
+ },
1866
+ {
1867
+ "epoch": 1.48,
1868
+ "grad_norm": 1.5819698572158813,
1869
+ "learning_rate": 3.001069469602361e-06,
1870
+ "loss": 0.2307,
1871
+ "step": 8480
1872
+ },
1873
+ {
1874
+ "epoch": 1.48,
1875
+ "grad_norm": 1.678463339805603,
1876
+ "learning_rate": 2.9851795454356164e-06,
1877
+ "loss": 0.2395,
1878
+ "step": 8512
1879
+ },
1880
+ {
1881
+ "epoch": 1.49,
1882
+ "grad_norm": 1.5477441549301147,
1883
+ "learning_rate": 2.969269227330397e-06,
1884
+ "loss": 0.2458,
1885
+ "step": 8544
1886
+ },
1887
+ {
1888
+ "epoch": 1.49,
1889
+ "grad_norm": 1.6442259550094604,
1890
+ "learning_rate": 2.953339184057783e-06,
1891
+ "loss": 0.2454,
1892
+ "step": 8576
1893
+ },
1894
+ {
1895
+ "epoch": 1.5,
1896
+ "grad_norm": 1.751511573791504,
1897
+ "learning_rate": 2.9373900852179784e-06,
1898
+ "loss": 0.2286,
1899
+ "step": 8608
1900
+ },
1901
+ {
1902
+ "epoch": 1.5,
1903
+ "grad_norm": 1.5601673126220703,
1904
+ "learning_rate": 2.9214226012121638e-06,
1905
+ "loss": 0.2389,
1906
+ "step": 8640
1907
+ },
1908
+ {
1909
+ "epoch": 1.51,
1910
+ "grad_norm": 1.3844302892684937,
1911
+ "learning_rate": 2.905437403214319e-06,
1912
+ "loss": 0.2454,
1913
+ "step": 8672
1914
+ },
1915
+ {
1916
+ "epoch": 1.52,
1917
+ "grad_norm": 1.2684638500213623,
1918
+ "learning_rate": 2.88943516314301e-06,
1919
+ "loss": 0.2376,
1920
+ "step": 8704
1921
+ },
1922
+ {
1923
+ "epoch": 1.52,
1924
+ "grad_norm": 2.507758617401123,
1925
+ "learning_rate": 2.873416553633147e-06,
1926
+ "loss": 0.2269,
1927
+ "step": 8736
1928
+ },
1929
+ {
1930
+ "epoch": 1.53,
1931
+ "grad_norm": 1.6755341291427612,
1932
+ "learning_rate": 2.857382248007708e-06,
1933
+ "loss": 0.2236,
1934
+ "step": 8768
1935
+ },
1936
+ {
1937
+ "epoch": 1.53,
1938
+ "grad_norm": 1.9231692552566528,
1939
+ "learning_rate": 2.8413329202494396e-06,
1940
+ "loss": 0.2541,
1941
+ "step": 8800
1942
+ },
1943
+ {
1944
+ "epoch": 1.54,
1945
+ "grad_norm": 1.528493046760559,
1946
+ "learning_rate": 2.825269244972525e-06,
1947
+ "loss": 0.2271,
1948
+ "step": 8832
1949
+ },
1950
+ {
1951
+ "epoch": 1.54,
1952
+ "grad_norm": 1.3824098110198975,
1953
+ "learning_rate": 2.8091918973942276e-06,
1954
+ "loss": 0.2451,
1955
+ "step": 8864
1956
+ },
1957
+ {
1958
+ "epoch": 1.55,
1959
+ "grad_norm": 1.4477118253707886,
1960
+ "learning_rate": 2.7931015533065116e-06,
1961
+ "loss": 0.2382,
1962
+ "step": 8896
1963
+ },
1964
+ {
1965
+ "epoch": 1.55,
1966
+ "grad_norm": 1.9449779987335205,
1967
+ "learning_rate": 2.776998889047631e-06,
1968
+ "loss": 0.2543,
1969
+ "step": 8928
1970
+ },
1971
+ {
1972
+ "epoch": 1.56,
1973
+ "grad_norm": 1.2107715606689453,
1974
+ "learning_rate": 2.760884581473706e-06,
1975
+ "loss": 0.2388,
1976
+ "step": 8960
1977
+ },
1978
+ {
1979
+ "epoch": 1.57,
1980
+ "grad_norm": 1.4030863046646118,
1981
+ "learning_rate": 2.744759307930268e-06,
1982
+ "loss": 0.24,
1983
+ "step": 8992
1984
+ },
1985
+ {
1986
+ "epoch": 1.57,
1987
+ "grad_norm": 1.8753631114959717,
1988
+ "learning_rate": 2.7286237462237907e-06,
1989
+ "loss": 0.2401,
1990
+ "step": 9024
1991
+ },
1992
+ {
1993
+ "epoch": 1.58,
1994
+ "grad_norm": 1.5679469108581543,
1995
+ "learning_rate": 2.7124785745931974e-06,
1996
+ "loss": 0.2519,
1997
+ "step": 9056
1998
+ },
1999
+ {
2000
+ "epoch": 1.58,
2001
+ "grad_norm": 1.4486414194107056,
2002
+ "learning_rate": 2.696324471681353e-06,
2003
+ "loss": 0.2457,
2004
+ "step": 9088
2005
+ },
2006
+ {
2007
+ "epoch": 1.59,
2008
+ "grad_norm": 1.8142122030258179,
2009
+ "learning_rate": 2.6801621165065384e-06,
2010
+ "loss": 0.2385,
2011
+ "step": 9120
2012
+ },
2013
+ {
2014
+ "epoch": 1.59,
2015
+ "grad_norm": 1.4930641651153564,
2016
+ "learning_rate": 2.6639921884339094e-06,
2017
+ "loss": 0.2411,
2018
+ "step": 9152
2019
+ },
2020
+ {
2021
+ "epoch": 1.6,
2022
+ "grad_norm": 1.5598373413085938,
2023
+ "learning_rate": 2.647815367146937e-06,
2024
+ "loss": 0.2265,
2025
+ "step": 9184
2026
+ },
2027
+ {
2028
+ "epoch": 1.6,
2029
+ "grad_norm": 1.7909144163131714,
2030
+ "learning_rate": 2.631632332618844e-06,
2031
+ "loss": 0.2502,
2032
+ "step": 9216
2033
+ },
2034
+ {
2035
+ "epoch": 1.61,
2036
+ "grad_norm": 1.6813157796859741,
2037
+ "learning_rate": 2.6154437650840153e-06,
2038
+ "loss": 0.2368,
2039
+ "step": 9248
2040
+ },
2041
+ {
2042
+ "epoch": 1.62,
2043
+ "grad_norm": 1.4486907720565796,
2044
+ "learning_rate": 2.599250345009411e-06,
2045
+ "loss": 0.2423,
2046
+ "step": 9280
2047
+ },
2048
+ {
2049
+ "epoch": 1.62,
2050
+ "grad_norm": 1.7712582349777222,
2051
+ "learning_rate": 2.583052753065962e-06,
2052
+ "loss": 0.2312,
2053
+ "step": 9312
2054
+ },
2055
+ {
2056
+ "epoch": 1.63,
2057
+ "grad_norm": 1.3970569372177124,
2058
+ "learning_rate": 2.5668516700999585e-06,
2059
+ "loss": 0.2415,
2060
+ "step": 9344
2061
+ },
2062
+ {
2063
+ "epoch": 1.63,
2064
+ "grad_norm": 1.3571640253067017,
2065
+ "learning_rate": 2.5506477771044313e-06,
2066
+ "loss": 0.2254,
2067
+ "step": 9376
2068
+ },
2069
+ {
2070
+ "epoch": 1.64,
2071
+ "grad_norm": 1.6543464660644531,
2072
+ "learning_rate": 2.5344417551905276e-06,
2073
+ "loss": 0.2358,
2074
+ "step": 9408
2075
+ },
2076
+ {
2077
+ "epoch": 1.64,
2078
+ "grad_norm": 2.0646538734436035,
2079
+ "learning_rate": 2.518234285558882e-06,
2080
+ "loss": 0.2433,
2081
+ "step": 9440
2082
+ },
2083
+ {
2084
+ "epoch": 1.65,
2085
+ "grad_norm": 1.5231086015701294,
2086
+ "learning_rate": 2.50202604947098e-06,
2087
+ "loss": 0.2289,
2088
+ "step": 9472
2089
+ },
2090
+ {
2091
+ "epoch": 1.65,
2092
+ "grad_norm": 1.7834982872009277,
2093
+ "learning_rate": 2.485817728220526e-06,
2094
+ "loss": 0.2366,
2095
+ "step": 9504
2096
+ },
2097
+ {
2098
+ "epoch": 1.66,
2099
+ "grad_norm": 1.4642645120620728,
2100
+ "learning_rate": 2.469610003104804e-06,
2101
+ "loss": 0.2354,
2102
+ "step": 9536
2103
+ },
2104
+ {
2105
+ "epoch": 1.67,
2106
+ "grad_norm": 1.4511359930038452,
2107
+ "learning_rate": 2.453403555396038e-06,
2108
+ "loss": 0.2394,
2109
+ "step": 9568
2110
+ },
2111
+ {
2112
+ "epoch": 1.67,
2113
+ "grad_norm": 1.9833004474639893,
2114
+ "learning_rate": 2.4371990663127613e-06,
2115
+ "loss": 0.2453,
2116
+ "step": 9600
2117
+ },
2118
+ {
2119
+ "epoch": 1.68,
2120
+ "grad_norm": 2.215998888015747,
2121
+ "learning_rate": 2.420997216991178e-06,
2122
+ "loss": 0.2345,
2123
+ "step": 9632
2124
+ },
2125
+ {
2126
+ "epoch": 1.68,
2127
+ "grad_norm": 1.5565507411956787,
2128
+ "learning_rate": 2.404798688456529e-06,
2129
+ "loss": 0.2465,
2130
+ "step": 9664
2131
+ },
2132
+ {
2133
+ "epoch": 1.69,
2134
+ "grad_norm": 1.583949327468872,
2135
+ "learning_rate": 2.3886041615944753e-06,
2136
+ "loss": 0.2442,
2137
+ "step": 9696
2138
+ },
2139
+ {
2140
+ "epoch": 1.69,
2141
+ "grad_norm": 1.6056400537490845,
2142
+ "learning_rate": 2.3724143171224684e-06,
2143
+ "loss": 0.2346,
2144
+ "step": 9728
2145
+ },
2146
+ {
2147
+ "epoch": 1.7,
2148
+ "grad_norm": 1.5098297595977783,
2149
+ "learning_rate": 2.3562298355611444e-06,
2150
+ "loss": 0.2444,
2151
+ "step": 9760
2152
+ },
2153
+ {
2154
+ "epoch": 1.71,
2155
+ "grad_norm": 1.4785221815109253,
2156
+ "learning_rate": 2.3400513972057117e-06,
2157
+ "loss": 0.245,
2158
+ "step": 9792
2159
+ },
2160
+ {
2161
+ "epoch": 1.71,
2162
+ "grad_norm": 1.4235949516296387,
2163
+ "learning_rate": 2.323879682097365e-06,
2164
+ "loss": 0.2386,
2165
+ "step": 9824
2166
+ },
2167
+ {
2168
+ "epoch": 1.72,
2169
+ "grad_norm": 1.4386334419250488,
2170
+ "learning_rate": 2.3077153699946912e-06,
2171
+ "loss": 0.2303,
2172
+ "step": 9856
2173
+ },
2174
+ {
2175
+ "epoch": 1.72,
2176
+ "grad_norm": 1.6986160278320312,
2177
+ "learning_rate": 2.291559140345102e-06,
2178
+ "loss": 0.2329,
2179
+ "step": 9888
2180
+ },
2181
+ {
2182
+ "epoch": 1.73,
2183
+ "grad_norm": 1.5963070392608643,
2184
+ "learning_rate": 2.2754116722562756e-06,
2185
+ "loss": 0.2352,
2186
+ "step": 9920
2187
+ },
2188
+ {
2189
+ "epoch": 1.73,
2190
+ "grad_norm": 1.5542904138565063,
2191
+ "learning_rate": 2.2592736444676035e-06,
2192
+ "loss": 0.2378,
2193
+ "step": 9952
2194
+ },
2195
+ {
2196
+ "epoch": 1.74,
2197
+ "grad_norm": 2.3971989154815674,
2198
+ "learning_rate": 2.243145735321669e-06,
2199
+ "loss": 0.2347,
2200
+ "step": 9984
2201
+ },
2202
+ {
2203
+ "epoch": 1.74,
2204
+ "grad_norm": 1.5635007619857788,
2205
+ "learning_rate": 2.2270286227357306e-06,
2206
+ "loss": 0.2406,
2207
+ "step": 10016
2208
+ },
2209
+ {
2210
+ "epoch": 1.75,
2211
+ "grad_norm": 1.545464038848877,
2212
+ "learning_rate": 2.210922984173223e-06,
2213
+ "loss": 0.2329,
2214
+ "step": 10048
2215
+ },
2216
+ {
2217
+ "epoch": 1.76,
2218
+ "grad_norm": 1.3175172805786133,
2219
+ "learning_rate": 2.19482949661529e-06,
2220
+ "loss": 0.2448,
2221
+ "step": 10080
2222
+ },
2223
+ {
2224
+ "epoch": 1.76,
2225
+ "grad_norm": 1.4598995447158813,
2226
+ "learning_rate": 2.1787488365323163e-06,
2227
+ "loss": 0.2294,
2228
+ "step": 10112
2229
+ },
2230
+ {
2231
+ "epoch": 1.77,
2232
+ "grad_norm": 1.50557279586792,
2233
+ "learning_rate": 2.1626816798555035e-06,
2234
+ "loss": 0.2427,
2235
+ "step": 10144
2236
+ },
2237
+ {
2238
+ "epoch": 1.77,
2239
+ "grad_norm": 1.596571683883667,
2240
+ "learning_rate": 2.14662870194845e-06,
2241
+ "loss": 0.2187,
2242
+ "step": 10176
2243
+ },
2244
+ {
2245
+ "epoch": 1.78,
2246
+ "grad_norm": 1.5053282976150513,
2247
+ "learning_rate": 2.1305905775787713e-06,
2248
+ "loss": 0.2394,
2249
+ "step": 10208
2250
+ },
2251
+ {
2252
+ "epoch": 1.78,
2253
+ "grad_norm": 1.6713193655014038,
2254
+ "learning_rate": 2.1145679808897297e-06,
2255
+ "loss": 0.2333,
2256
+ "step": 10240
2257
+ },
2258
+ {
2259
+ "epoch": 1.79,
2260
+ "grad_norm": 1.394679069519043,
2261
+ "learning_rate": 2.098561585371898e-06,
2262
+ "loss": 0.236,
2263
+ "step": 10272
2264
+ },
2265
+ {
2266
+ "epoch": 1.79,
2267
+ "grad_norm": 1.6781407594680786,
2268
+ "learning_rate": 2.082572063834857e-06,
2269
+ "loss": 0.2461,
2270
+ "step": 10304
2271
+ },
2272
+ {
2273
+ "epoch": 1.8,
2274
+ "grad_norm": 1.6299934387207031,
2275
+ "learning_rate": 2.066600088378906e-06,
2276
+ "loss": 0.2464,
2277
+ "step": 10336
2278
+ },
2279
+ {
2280
+ "epoch": 1.81,
2281
+ "grad_norm": 1.309910774230957,
2282
+ "learning_rate": 2.0506463303668182e-06,
2283
+ "loss": 0.2395,
2284
+ "step": 10368
2285
+ },
2286
+ {
2287
+ "epoch": 1.81,
2288
+ "grad_norm": 1.5353403091430664,
2289
+ "learning_rate": 2.0347114603956184e-06,
2290
+ "loss": 0.2396,
2291
+ "step": 10400
2292
+ },
2293
+ {
2294
+ "epoch": 1.82,
2295
+ "grad_norm": 1.5149140357971191,
2296
+ "learning_rate": 2.018796148268393e-06,
2297
+ "loss": 0.2267,
2298
+ "step": 10432
2299
+ },
2300
+ {
2301
+ "epoch": 1.82,
2302
+ "grad_norm": 1.8665707111358643,
2303
+ "learning_rate": 2.002901062966141e-06,
2304
+ "loss": 0.2343,
2305
+ "step": 10464
2306
+ },
2307
+ {
2308
+ "epoch": 1.83,
2309
+ "grad_norm": 1.7906211614608765,
2310
+ "learning_rate": 1.9870268726196493e-06,
2311
+ "loss": 0.2332,
2312
+ "step": 10496
2313
+ },
2314
+ {
2315
+ "epoch": 1.83,
2316
+ "grad_norm": 1.6433167457580566,
2317
+ "learning_rate": 1.971174244481411e-06,
2318
+ "loss": 0.2387,
2319
+ "step": 10528
2320
+ },
2321
+ {
2322
+ "epoch": 1.84,
2323
+ "grad_norm": 1.7116189002990723,
2324
+ "learning_rate": 1.9553438448975766e-06,
2325
+ "loss": 0.244,
2326
+ "step": 10560
2327
+ },
2328
+ {
2329
+ "epoch": 1.84,
2330
+ "grad_norm": 1.4329649209976196,
2331
+ "learning_rate": 1.9395363392799486e-06,
2332
+ "loss": 0.2301,
2333
+ "step": 10592
2334
+ },
2335
+ {
2336
+ "epoch": 1.85,
2337
+ "grad_norm": 1.4449670314788818,
2338
+ "learning_rate": 1.9237523920780077e-06,
2339
+ "loss": 0.2258,
2340
+ "step": 10624
2341
+ },
2342
+ {
2343
+ "epoch": 1.86,
2344
+ "grad_norm": 1.8179880380630493,
2345
+ "learning_rate": 1.9079926667509833e-06,
2346
+ "loss": 0.2353,
2347
+ "step": 10656
2348
+ },
2349
+ {
2350
+ "epoch": 1.86,
2351
+ "grad_norm": 1.6381878852844238,
2352
+ "learning_rate": 1.892257825739971e-06,
2353
+ "loss": 0.2263,
2354
+ "step": 10688
2355
+ },
2356
+ {
2357
+ "epoch": 1.87,
2358
+ "grad_norm": 1.6362228393554688,
2359
+ "learning_rate": 1.8765485304400804e-06,
2360
+ "loss": 0.2312,
2361
+ "step": 10720
2362
+ },
2363
+ {
2364
+ "epoch": 1.87,
2365
+ "grad_norm": 1.6400152444839478,
2366
+ "learning_rate": 1.8608654411726407e-06,
2367
+ "loss": 0.2313,
2368
+ "step": 10752
2369
+ },
2370
+ {
2371
+ "epoch": 1.88,
2372
+ "grad_norm": 1.1943421363830566,
2373
+ "learning_rate": 1.8452092171574418e-06,
2374
+ "loss": 0.2239,
2375
+ "step": 10784
2376
+ },
2377
+ {
2378
+ "epoch": 1.88,
2379
+ "grad_norm": 1.8176000118255615,
2380
+ "learning_rate": 1.8295805164850217e-06,
2381
+ "loss": 0.231,
2382
+ "step": 10816
2383
+ },
2384
+ {
2385
+ "epoch": 1.89,
2386
+ "grad_norm": 1.5386502742767334,
2387
+ "learning_rate": 1.8139799960890132e-06,
2388
+ "loss": 0.233,
2389
+ "step": 10848
2390
+ },
2391
+ {
2392
+ "epoch": 1.89,
2393
+ "grad_norm": 1.666212558746338,
2394
+ "learning_rate": 1.79840831171852e-06,
2395
+ "loss": 0.2387,
2396
+ "step": 10880
2397
+ },
2398
+ {
2399
+ "epoch": 1.9,
2400
+ "grad_norm": 2.0908565521240234,
2401
+ "learning_rate": 1.7828661179105618e-06,
2402
+ "loss": 0.2301,
2403
+ "step": 10912
2404
+ },
2405
+ {
2406
+ "epoch": 1.91,
2407
+ "grad_norm": 1.824118733406067,
2408
+ "learning_rate": 1.767354067962555e-06,
2409
+ "loss": 0.2211,
2410
+ "step": 10944
2411
+ },
2412
+ {
2413
+ "epoch": 1.91,
2414
+ "grad_norm": 1.6803866624832153,
2415
+ "learning_rate": 1.7518728139048585e-06,
2416
+ "loss": 0.2283,
2417
+ "step": 10976
2418
+ },
2419
+ {
2420
+ "epoch": 1.92,
2421
+ "grad_norm": 1.5006029605865479,
2422
+ "learning_rate": 1.7364230064733606e-06,
2423
+ "loss": 0.2376,
2424
+ "step": 11008
2425
+ },
2426
+ {
2427
+ "epoch": 1.92,
2428
+ "grad_norm": 1.6305315494537354,
2429
+ "learning_rate": 1.7210052950821276e-06,
2430
+ "loss": 0.2274,
2431
+ "step": 11040
2432
+ },
2433
+ {
2434
+ "epoch": 1.93,
2435
+ "grad_norm": 1.4924837350845337,
2436
+ "learning_rate": 1.7056203277961112e-06,
2437
+ "loss": 0.2301,
2438
+ "step": 11072
2439
+ },
2440
+ {
2441
+ "epoch": 1.93,
2442
+ "grad_norm": 1.7117606401443481,
2443
+ "learning_rate": 1.6902687513039002e-06,
2444
+ "loss": 0.2391,
2445
+ "step": 11104
2446
+ },
2447
+ {
2448
+ "epoch": 1.94,
2449
+ "grad_norm": 1.9313896894454956,
2450
+ "learning_rate": 1.6749512108905424e-06,
2451
+ "loss": 0.2268,
2452
+ "step": 11136
2453
+ },
2454
+ {
2455
+ "epoch": 1.94,
2456
+ "grad_norm": 1.4171528816223145,
2457
+ "learning_rate": 1.6596683504104228e-06,
2458
+ "loss": 0.2327,
2459
+ "step": 11168
2460
+ },
2461
+ {
2462
+ "epoch": 1.95,
2463
+ "grad_norm": 1.576985478401184,
2464
+ "learning_rate": 1.6444208122601933e-06,
2465
+ "loss": 0.2352,
2466
+ "step": 11200
2467
+ },
2468
+ {
2469
+ "epoch": 1.96,
2470
+ "grad_norm": 1.453007698059082,
2471
+ "learning_rate": 1.6292092373517765e-06,
2472
+ "loss": 0.2315,
2473
+ "step": 11232
2474
+ },
2475
+ {
2476
+ "epoch": 1.96,
2477
+ "grad_norm": 1.5981701612472534,
2478
+ "learning_rate": 1.6140342650854218e-06,
2479
+ "loss": 0.2304,
2480
+ "step": 11264
2481
+ },
2482
+ {
2483
+ "epoch": 1.97,
2484
+ "grad_norm": 2.0827910900115967,
2485
+ "learning_rate": 1.5988965333228323e-06,
2486
+ "loss": 0.2338,
2487
+ "step": 11296
2488
+ },
2489
+ {
2490
+ "epoch": 1.97,
2491
+ "grad_norm": 1.5926817655563354,
2492
+ "learning_rate": 1.5837966783603494e-06,
2493
+ "loss": 0.2498,
2494
+ "step": 11328
2495
+ },
2496
+ {
2497
+ "epoch": 1.98,
2498
+ "grad_norm": 1.82351815700531,
2499
+ "learning_rate": 1.5687353349022114e-06,
2500
+ "loss": 0.2379,
2501
+ "step": 11360
2502
+ },
2503
+ {
2504
+ "epoch": 1.98,
2505
+ "grad_norm": 1.5781277418136597,
2506
+ "learning_rate": 1.5537131360338697e-06,
2507
+ "loss": 0.2421,
2508
+ "step": 11392
2509
+ },
2510
+ {
2511
+ "epoch": 1.99,
2512
+ "grad_norm": 1.4788808822631836,
2513
+ "learning_rate": 1.5387307131953793e-06,
2514
+ "loss": 0.2371,
2515
+ "step": 11424
2516
+ },
2517
+ {
2518
+ "epoch": 1.99,
2519
+ "grad_norm": 1.8411000967025757,
2520
+ "learning_rate": 1.5237886961548615e-06,
2521
+ "loss": 0.2371,
2522
+ "step": 11456
2523
+ },
2524
+ {
2525
+ "epoch": 2.0,
2526
+ "grad_norm": 1.7383184432983398,
2527
+ "learning_rate": 1.508887712982024e-06,
2528
+ "loss": 0.2307,
2529
+ "step": 11488
2530
+ },
2531
+ {
2532
+ "epoch": 2.01,
2533
+ "grad_norm": 1.6967484951019287,
2534
+ "learning_rate": 1.4940283900217667e-06,
2535
+ "loss": 0.1677,
2536
+ "step": 11520
2537
+ },
2538
+ {
2539
+ "epoch": 2.01,
2540
+ "grad_norm": 1.5547412633895874,
2541
+ "learning_rate": 1.4792113518678553e-06,
2542
+ "loss": 0.1562,
2543
+ "step": 11552
2544
+ },
2545
+ {
2546
+ "epoch": 2.02,
2547
+ "grad_norm": 1.484421730041504,
2548
+ "learning_rate": 1.46443722133666e-06,
2549
+ "loss": 0.1644,
2550
+ "step": 11584
2551
+ },
2552
+ {
2553
+ "epoch": 2.02,
2554
+ "grad_norm": 1.7713335752487183,
2555
+ "learning_rate": 1.4497066194409849e-06,
2556
+ "loss": 0.1703,
2557
+ "step": 11616
2558
+ },
2559
+ {
2560
+ "epoch": 2.03,
2561
+ "grad_norm": 1.6081045866012573,
2562
+ "learning_rate": 1.435020165363956e-06,
2563
+ "loss": 0.1621,
2564
+ "step": 11648
2565
+ },
2566
+ {
2567
+ "epoch": 2.03,
2568
+ "grad_norm": 1.6781724691390991,
2569
+ "learning_rate": 1.4203784764330033e-06,
2570
+ "loss": 0.1706,
2571
+ "step": 11680
2572
+ },
2573
+ {
2574
+ "epoch": 2.04,
2575
+ "grad_norm": 1.5613493919372559,
2576
+ "learning_rate": 1.4057821680939049e-06,
2577
+ "loss": 0.1594,
2578
+ "step": 11712
2579
+ },
2580
+ {
2581
+ "epoch": 2.04,
2582
+ "grad_norm": 1.6171530485153198,
2583
+ "learning_rate": 1.3912318538849207e-06,
2584
+ "loss": 0.1598,
2585
+ "step": 11744
2586
+ },
2587
+ {
2588
+ "epoch": 2.05,
2589
+ "grad_norm": 1.4825495481491089,
2590
+ "learning_rate": 1.3767281454110037e-06,
2591
+ "loss": 0.1738,
2592
+ "step": 11776
2593
+ },
2594
+ {
2595
+ "epoch": 2.06,
2596
+ "grad_norm": 1.7642580270767212,
2597
+ "learning_rate": 1.3622716523180898e-06,
2598
+ "loss": 0.1563,
2599
+ "step": 11808
2600
+ },
2601
+ {
2602
+ "epoch": 2.06,
2603
+ "grad_norm": 1.3485716581344604,
2604
+ "learning_rate": 1.347862982267475e-06,
2605
+ "loss": 0.1571,
2606
+ "step": 11840
2607
+ },
2608
+ {
2609
+ "epoch": 2.07,
2610
+ "grad_norm": 1.6963993310928345,
2611
+ "learning_rate": 1.3335027409102663e-06,
2612
+ "loss": 0.1567,
2613
+ "step": 11872
2614
+ },
2615
+ {
2616
+ "epoch": 2.07,
2617
+ "grad_norm": 1.5955970287322998,
2618
+ "learning_rate": 1.3191915318619357e-06,
2619
+ "loss": 0.1675,
2620
+ "step": 11904
2621
+ },
2622
+ {
2623
+ "epoch": 2.08,
2624
+ "grad_norm": 2.1548969745635986,
2625
+ "learning_rate": 1.304929956676938e-06,
2626
+ "loss": 0.1666,
2627
+ "step": 11936
2628
+ },
2629
+ {
2630
+ "epoch": 2.08,
2631
+ "grad_norm": 1.442049503326416,
2632
+ "learning_rate": 1.2907186148234246e-06,
2633
+ "loss": 0.1505,
2634
+ "step": 11968
2635
+ },
2636
+ {
2637
+ "epoch": 2.09,
2638
+ "grad_norm": 1.654685139656067,
2639
+ "learning_rate": 1.276558103658057e-06,
2640
+ "loss": 0.1642,
2641
+ "step": 12000
2642
+ },
2643
+ {
2644
+ "epoch": 2.1,
2645
+ "grad_norm": 2.396730422973633,
2646
+ "learning_rate": 1.262449018400883e-06,
2647
+ "loss": 0.1641,
2648
+ "step": 12032
2649
+ },
2650
+ {
2651
+ "epoch": 2.1,
2652
+ "grad_norm": 1.4008959531784058,
2653
+ "learning_rate": 1.248391952110327e-06,
2654
+ "loss": 0.1631,
2655
+ "step": 12064
2656
+ },
2657
+ {
2658
+ "epoch": 2.11,
2659
+ "grad_norm": 1.4454419612884521,
2660
+ "learning_rate": 1.2343874956582586e-06,
2661
+ "loss": 0.1599,
2662
+ "step": 12096
2663
+ },
2664
+ {
2665
+ "epoch": 2.11,
2666
+ "grad_norm": 2.054921865463257,
2667
+ "learning_rate": 1.2204362377051562e-06,
2668
+ "loss": 0.1639,
2669
+ "step": 12128
2670
+ },
2671
+ {
2672
+ "epoch": 2.12,
2673
+ "grad_norm": 1.5172858238220215,
2674
+ "learning_rate": 1.2065387646753637e-06,
2675
+ "loss": 0.159,
2676
+ "step": 12160
2677
+ },
2678
+ {
2679
+ "epoch": 2.12,
2680
+ "grad_norm": 1.640461802482605,
2681
+ "learning_rate": 1.192695660732439e-06,
2682
+ "loss": 0.1607,
2683
+ "step": 12192
2684
+ },
2685
+ {
2686
+ "epoch": 2.13,
2687
+ "grad_norm": 1.2705048322677612,
2688
+ "learning_rate": 1.1789075077546033e-06,
2689
+ "loss": 0.1691,
2690
+ "step": 12224
2691
+ },
2692
+ {
2693
+ "epoch": 2.13,
2694
+ "grad_norm": 1.6255841255187988,
2695
+ "learning_rate": 1.1651748853102757e-06,
2696
+ "loss": 0.1572,
2697
+ "step": 12256
2698
+ },
2699
+ {
2700
+ "epoch": 2.14,
2701
+ "grad_norm": 1.617698073387146,
2702
+ "learning_rate": 1.1514983706337212e-06,
2703
+ "loss": 0.1664,
2704
+ "step": 12288
2705
+ },
2706
+ {
2707
+ "epoch": 2.15,
2708
+ "grad_norm": 2.176952362060547,
2709
+ "learning_rate": 1.137878538600781e-06,
2710
+ "loss": 0.1642,
2711
+ "step": 12320
2712
+ },
2713
+ {
2714
+ "epoch": 2.15,
2715
+ "grad_norm": 2.0179526805877686,
2716
+ "learning_rate": 1.1243159617047051e-06,
2717
+ "loss": 0.1555,
2718
+ "step": 12352
2719
+ },
2720
+ {
2721
+ "epoch": 2.16,
2722
+ "grad_norm": 1.6655995845794678,
2723
+ "learning_rate": 1.1108112100321002e-06,
2724
+ "loss": 0.1704,
2725
+ "step": 12384
2726
+ },
2727
+ {
2728
+ "epoch": 2.16,
2729
+ "grad_norm": 1.541496992111206,
2730
+ "learning_rate": 1.0973648512389526e-06,
2731
+ "loss": 0.1611,
2732
+ "step": 12416
2733
+ },
2734
+ {
2735
+ "epoch": 2.17,
2736
+ "grad_norm": 1.7085323333740234,
2737
+ "learning_rate": 1.0839774505267777e-06,
2738
+ "loss": 0.1663,
2739
+ "step": 12448
2740
+ },
2741
+ {
2742
+ "epoch": 2.17,
2743
+ "grad_norm": 1.993090033531189,
2744
+ "learning_rate": 1.0706495706188584e-06,
2745
+ "loss": 0.1569,
2746
+ "step": 12480
2747
+ },
2748
+ {
2749
+ "epoch": 2.18,
2750
+ "grad_norm": 1.4851964712142944,
2751
+ "learning_rate": 1.0573817717365914e-06,
2752
+ "loss": 0.1651,
2753
+ "step": 12512
2754
+ },
2755
+ {
2756
+ "epoch": 2.18,
2757
+ "grad_norm": 1.714492917060852,
2758
+ "learning_rate": 1.0441746115759407e-06,
2759
+ "loss": 0.1572,
2760
+ "step": 12544
2761
+ },
2762
+ {
2763
+ "epoch": 2.19,
2764
+ "grad_norm": 1.7523784637451172,
2765
+ "learning_rate": 1.031028645283994e-06,
2766
+ "loss": 0.1736,
2767
+ "step": 12576
2768
+ },
2769
+ {
2770
+ "epoch": 2.2,
2771
+ "grad_norm": 1.5587310791015625,
2772
+ "learning_rate": 1.0179444254356294e-06,
2773
+ "loss": 0.168,
2774
+ "step": 12608
2775
+ },
2776
+ {
2777
+ "epoch": 2.2,
2778
+ "grad_norm": 1.5781267881393433,
2779
+ "learning_rate": 1.004922502010284e-06,
2780
+ "loss": 0.1606,
2781
+ "step": 12640
2782
+ },
2783
+ {
2784
+ "epoch": 2.21,
2785
+ "grad_norm": 1.6072574853897095,
2786
+ "learning_rate": 9.919634223688452e-07,
2787
+ "loss": 0.1614,
2788
+ "step": 12672
2789
+ },
2790
+ {
2791
+ "epoch": 2.21,
2792
+ "grad_norm": 1.9626734256744385,
2793
+ "learning_rate": 9.790677312306346e-07,
2794
+ "loss": 0.1711,
2795
+ "step": 12704
2796
+ },
2797
+ {
2798
+ "epoch": 2.22,
2799
+ "grad_norm": 1.87946355342865,
2800
+ "learning_rate": 9.662359706505113e-07,
2801
+ "loss": 0.1652,
2802
+ "step": 12736
2803
+ },
2804
+ {
2805
+ "epoch": 2.22,
2806
+ "grad_norm": 2.207897186279297,
2807
+ "learning_rate": 9.534686799960977e-07,
2808
+ "loss": 0.1558,
2809
+ "step": 12768
2810
+ },
2811
+ {
2812
+ "epoch": 2.23,
2813
+ "grad_norm": 1.8241429328918457,
2814
+ "learning_rate": 9.407663959250932e-07,
2815
+ "loss": 0.1572,
2816
+ "step": 12800
2817
+ },
2818
+ {
2819
+ "epoch": 2.23,
2820
+ "grad_norm": 1.6716265678405762,
2821
+ "learning_rate": 9.281296523627276e-07,
2822
+ "loss": 0.1558,
2823
+ "step": 12832
2824
+ },
2825
+ {
2826
+ "epoch": 2.24,
2827
+ "grad_norm": 1.7584782838821411,
2828
+ "learning_rate": 9.15558980479313e-07,
2829
+ "loss": 0.1532,
2830
+ "step": 12864
2831
+ },
2832
+ {
2833
+ "epoch": 2.25,
2834
+ "grad_norm": 1.6568748950958252,
2835
+ "learning_rate": 9.030549086679188e-07,
2836
+ "loss": 0.167,
2837
+ "step": 12896
2838
+ },
2839
+ {
2840
+ "epoch": 2.25,
2841
+ "grad_norm": 1.6095608472824097,
2842
+ "learning_rate": 8.906179625221597e-07,
2843
+ "loss": 0.1585,
2844
+ "step": 12928
2845
+ },
2846
+ {
2847
+ "epoch": 2.26,
2848
+ "grad_norm": 1.4875459671020508,
2849
+ "learning_rate": 8.782486648141042e-07,
2850
+ "loss": 0.1626,
2851
+ "step": 12960
2852
+ },
2853
+ {
2854
+ "epoch": 2.26,
2855
+ "grad_norm": 1.884362816810608,
2856
+ "learning_rate": 8.659475354723007e-07,
2857
+ "loss": 0.1596,
2858
+ "step": 12992
2859
+ },
2860
+ {
2861
+ "epoch": 2.27,
2862
+ "grad_norm": 2.296562433242798,
2863
+ "learning_rate": 8.53715091559919e-07,
2864
+ "loss": 0.1652,
2865
+ "step": 13024
2866
+ },
2867
+ {
2868
+ "epoch": 2.27,
2869
+ "grad_norm": 2.080160140991211,
2870
+ "learning_rate": 8.415518472530251e-07,
2871
+ "loss": 0.1535,
2872
+ "step": 13056
2873
+ },
2874
+ {
2875
+ "epoch": 2.28,
2876
+ "grad_norm": 1.603214979171753,
2877
+ "learning_rate": 8.294583138189597e-07,
2878
+ "loss": 0.1699,
2879
+ "step": 13088
2880
+ },
2881
+ {
2882
+ "epoch": 2.28,
2883
+ "grad_norm": 1.718169927597046,
2884
+ "learning_rate": 8.174349995948483e-07,
2885
+ "loss": 0.1688,
2886
+ "step": 13120
2887
+ },
2888
+ {
2889
+ "epoch": 2.29,
2890
+ "grad_norm": 1.613429307937622,
2891
+ "learning_rate": 8.054824099662429e-07,
2892
+ "loss": 0.1643,
2893
+ "step": 13152
2894
+ },
2895
+ {
2896
+ "epoch": 2.3,
2897
+ "grad_norm": 1.3368054628372192,
2898
+ "learning_rate": 7.936010473458653e-07,
2899
+ "loss": 0.1556,
2900
+ "step": 13184
2901
+ },
2902
+ {
2903
+ "epoch": 2.3,
2904
+ "grad_norm": 1.404004454612732,
2905
+ "learning_rate": 7.817914111524999e-07,
2906
+ "loss": 0.1588,
2907
+ "step": 13216
2908
+ },
2909
+ {
2910
+ "epoch": 2.31,
2911
+ "grad_norm": 1.7263784408569336,
2912
+ "learning_rate": 7.700539977899962e-07,
2913
+ "loss": 0.1525,
2914
+ "step": 13248
2915
+ },
2916
+ {
2917
+ "epoch": 2.31,
2918
+ "grad_norm": 1.7289042472839355,
2919
+ "learning_rate": 7.583893006264035e-07,
2920
+ "loss": 0.1633,
2921
+ "step": 13280
2922
+ },
2923
+ {
2924
+ "epoch": 2.32,
2925
+ "grad_norm": 1.5951069593429565,
2926
+ "learning_rate": 7.467978099732331e-07,
2927
+ "loss": 0.1539,
2928
+ "step": 13312
2929
+ },
2930
+ {
2931
+ "epoch": 2.32,
2932
+ "grad_norm": 2.1001362800598145,
2933
+ "learning_rate": 7.352800130648494e-07,
2934
+ "loss": 0.1627,
2935
+ "step": 13344
2936
+ },
2937
+ {
2938
+ "epoch": 2.33,
2939
+ "grad_norm": 1.5156986713409424,
2940
+ "learning_rate": 7.238363940379881e-07,
2941
+ "loss": 0.156,
2942
+ "step": 13376
2943
+ },
2944
+ {
2945
+ "epoch": 2.33,
2946
+ "grad_norm": 1.8548262119293213,
2947
+ "learning_rate": 7.124674339114071e-07,
2948
+ "loss": 0.1758,
2949
+ "step": 13408
2950
+ },
2951
+ {
2952
+ "epoch": 2.34,
2953
+ "grad_norm": 1.5202828645706177,
2954
+ "learning_rate": 7.011736105656675e-07,
2955
+ "loss": 0.1562,
2956
+ "step": 13440
2957
+ },
2958
+ {
2959
+ "epoch": 2.35,
2960
+ "grad_norm": 1.8769176006317139,
2961
+ "learning_rate": 6.89955398723047e-07,
2962
+ "loss": 0.1598,
2963
+ "step": 13472
2964
+ },
2965
+ {
2966
+ "epoch": 2.35,
2967
+ "grad_norm": 1.5129636526107788,
2968
+ "learning_rate": 6.788132699275813e-07,
2969
+ "loss": 0.1675,
2970
+ "step": 13504
2971
+ },
2972
+ {
2973
+ "epoch": 2.36,
2974
+ "grad_norm": 1.8350058794021606,
2975
+ "learning_rate": 6.677476925252524e-07,
2976
+ "loss": 0.1658,
2977
+ "step": 13536
2978
+ },
2979
+ {
2980
+ "epoch": 2.36,
2981
+ "grad_norm": 1.9995418787002563,
2982
+ "learning_rate": 6.567591316442911e-07,
2983
+ "loss": 0.1722,
2984
+ "step": 13568
2985
+ },
2986
+ {
2987
+ "epoch": 2.37,
2988
+ "grad_norm": 1.6814707517623901,
2989
+ "learning_rate": 6.458480491756347e-07,
2990
+ "loss": 0.1615,
2991
+ "step": 13600
2992
+ },
2993
+ {
2994
+ "epoch": 2.37,
2995
+ "grad_norm": 1.6658669710159302,
2996
+ "learning_rate": 6.350149037535075e-07,
2997
+ "loss": 0.1544,
2998
+ "step": 13632
2999
+ },
3000
+ {
3001
+ "epoch": 2.38,
3002
+ "grad_norm": 1.5126328468322754,
3003
+ "learning_rate": 6.242601507361442e-07,
3004
+ "loss": 0.1577,
3005
+ "step": 13664
3006
+ },
3007
+ {
3008
+ "epoch": 2.38,
3009
+ "grad_norm": 1.7326850891113281,
3010
+ "learning_rate": 6.135842421866486e-07,
3011
+ "loss": 0.1538,
3012
+ "step": 13696
3013
+ },
3014
+ {
3015
+ "epoch": 2.39,
3016
+ "grad_norm": 1.641743779182434,
3017
+ "learning_rate": 6.029876268539925e-07,
3018
+ "loss": 0.1612,
3019
+ "step": 13728
3020
+ },
3021
+ {
3022
+ "epoch": 2.4,
3023
+ "grad_norm": 1.7537841796875,
3024
+ "learning_rate": 5.924707501541527e-07,
3025
+ "loss": 0.1607,
3026
+ "step": 13760
3027
+ },
3028
+ {
3029
+ "epoch": 2.4,
3030
+ "grad_norm": 1.8395192623138428,
3031
+ "learning_rate": 5.820340541513886e-07,
3032
+ "loss": 0.1621,
3033
+ "step": 13792
3034
+ },
3035
+ {
3036
+ "epoch": 2.41,
3037
+ "grad_norm": 1.7613660097122192,
3038
+ "learning_rate": 5.7167797753966e-07,
3039
+ "loss": 0.1586,
3040
+ "step": 13824
3041
+ },
3042
+ {
3043
+ "epoch": 2.41,
3044
+ "grad_norm": 1.8884879350662231,
3045
+ "learning_rate": 5.61402955624189e-07,
3046
+ "loss": 0.1639,
3047
+ "step": 13856
3048
+ },
3049
+ {
3050
+ "epoch": 2.42,
3051
+ "grad_norm": 1.3437737226486206,
3052
+ "learning_rate": 5.512094203031576e-07,
3053
+ "loss": 0.1537,
3054
+ "step": 13888
3055
+ },
3056
+ {
3057
+ "epoch": 2.42,
3058
+ "grad_norm": 1.8541299104690552,
3059
+ "learning_rate": 5.410978000495621e-07,
3060
+ "loss": 0.1609,
3061
+ "step": 13920
3062
+ },
3063
+ {
3064
+ "epoch": 2.43,
3065
+ "grad_norm": 1.6411800384521484,
3066
+ "learning_rate": 5.310685198931926e-07,
3067
+ "loss": 0.1597,
3068
+ "step": 13952
3069
+ },
3070
+ {
3071
+ "epoch": 2.43,
3072
+ "grad_norm": 1.4559264183044434,
3073
+ "learning_rate": 5.211220014027746e-07,
3074
+ "loss": 0.1563,
3075
+ "step": 13984
3076
+ },
3077
+ {
3078
+ "epoch": 2.44,
3079
+ "grad_norm": 1.6533401012420654,
3080
+ "learning_rate": 5.112586626682467e-07,
3081
+ "loss": 0.1614,
3082
+ "step": 14016
3083
+ },
3084
+ {
3085
+ "epoch": 2.45,
3086
+ "grad_norm": 1.519086241722107,
3087
+ "learning_rate": 5.014789182831858e-07,
3088
+ "loss": 0.1649,
3089
+ "step": 14048
3090
+ },
3091
+ {
3092
+ "epoch": 2.45,
3093
+ "grad_norm": 1.6548802852630615,
3094
+ "learning_rate": 4.917831793273814e-07,
3095
+ "loss": 0.1579,
3096
+ "step": 14080
3097
+ },
3098
+ {
3099
+ "epoch": 2.46,
3100
+ "grad_norm": 1.4974662065505981,
3101
+ "learning_rate": 4.821718533495553e-07,
3102
+ "loss": 0.1581,
3103
+ "step": 14112
3104
+ },
3105
+ {
3106
+ "epoch": 2.46,
3107
+ "grad_norm": 1.5565108060836792,
3108
+ "learning_rate": 4.7264534435023186e-07,
3109
+ "loss": 0.1664,
3110
+ "step": 14144
3111
+ },
3112
+ {
3113
+ "epoch": 2.47,
3114
+ "grad_norm": 1.8209164142608643,
3115
+ "learning_rate": 4.6320405276475524e-07,
3116
+ "loss": 0.1649,
3117
+ "step": 14176
3118
+ },
3119
+ {
3120
+ "epoch": 2.47,
3121
+ "grad_norm": 1.8029505014419556,
3122
+ "learning_rate": 4.5384837544645956e-07,
3123
+ "loss": 0.1691,
3124
+ "step": 14208
3125
+ },
3126
+ {
3127
+ "epoch": 2.48,
3128
+ "grad_norm": 2.0014963150024414,
3129
+ "learning_rate": 4.445787056499826e-07,
3130
+ "loss": 0.1588,
3131
+ "step": 14240
3132
+ },
3133
+ {
3134
+ "epoch": 2.49,
3135
+ "grad_norm": 1.701003909111023,
3136
+ "learning_rate": 4.3539543301474446e-07,
3137
+ "loss": 0.1653,
3138
+ "step": 14272
3139
+ },
3140
+ {
3141
+ "epoch": 2.49,
3142
+ "grad_norm": 1.8511948585510254,
3143
+ "learning_rate": 4.262989435485615e-07,
3144
+ "loss": 0.1554,
3145
+ "step": 14304
3146
+ },
3147
+ {
3148
+ "epoch": 2.5,
3149
+ "grad_norm": 2.2707128524780273,
3150
+ "learning_rate": 4.172896196114234e-07,
3151
+ "loss": 0.1555,
3152
+ "step": 14336
3153
+ },
3154
+ {
3155
+ "epoch": 2.5,
3156
+ "grad_norm": 1.784833550453186,
3157
+ "learning_rate": 4.083678398994237e-07,
3158
+ "loss": 0.1541,
3159
+ "step": 14368
3160
+ },
3161
+ {
3162
+ "epoch": 2.51,
3163
+ "grad_norm": 2.091581106185913,
3164
+ "learning_rate": 3.995339794288383e-07,
3165
+ "loss": 0.157,
3166
+ "step": 14400
3167
+ },
3168
+ {
3169
+ "epoch": 2.51,
3170
+ "grad_norm": 1.475711703300476,
3171
+ "learning_rate": 3.9078840952036455e-07,
3172
+ "loss": 0.1652,
3173
+ "step": 14432
3174
+ },
3175
+ {
3176
+ "epoch": 2.52,
3177
+ "grad_norm": 2.0263583660125732,
3178
+ "learning_rate": 3.8213149778351164e-07,
3179
+ "loss": 0.163,
3180
+ "step": 14464
3181
+ },
3182
+ {
3183
+ "epoch": 2.52,
3184
+ "grad_norm": 2.084484100341797,
3185
+ "learning_rate": 3.73563608101149e-07,
3186
+ "loss": 0.1589,
3187
+ "step": 14496
3188
+ },
3189
+ {
3190
+ "epoch": 2.53,
3191
+ "grad_norm": 1.5741300582885742,
3192
+ "learning_rate": 3.65085100614212e-07,
3193
+ "loss": 0.1547,
3194
+ "step": 14528
3195
+ },
3196
+ {
3197
+ "epoch": 2.54,
3198
+ "grad_norm": 1.7066149711608887,
3199
+ "learning_rate": 3.566963317065622e-07,
3200
+ "loss": 0.1628,
3201
+ "step": 14560
3202
+ },
3203
+ {
3204
+ "epoch": 2.54,
3205
+ "grad_norm": 1.4174087047576904,
3206
+ "learning_rate": 3.483976539900083e-07,
3207
+ "loss": 0.1589,
3208
+ "step": 14592
3209
+ },
3210
+ {
3211
+ "epoch": 2.55,
3212
+ "grad_norm": 1.6838244199752808,
3213
+ "learning_rate": 3.401894162894828e-07,
3214
+ "loss": 0.1492,
3215
+ "step": 14624
3216
+ },
3217
+ {
3218
+ "epoch": 2.55,
3219
+ "grad_norm": 1.6532583236694336,
3220
+ "learning_rate": 3.320719636283837e-07,
3221
+ "loss": 0.1589,
3222
+ "step": 14656
3223
+ },
3224
+ {
3225
+ "epoch": 2.56,
3226
+ "grad_norm": 1.447808861732483,
3227
+ "learning_rate": 3.240456372140674e-07,
3228
+ "loss": 0.1633,
3229
+ "step": 14688
3230
+ },
3231
+ {
3232
+ "epoch": 2.56,
3233
+ "grad_norm": 1.8401908874511719,
3234
+ "learning_rate": 3.161107744235067e-07,
3235
+ "loss": 0.1607,
3236
+ "step": 14720
3237
+ },
3238
+ {
3239
+ "epoch": 2.57,
3240
+ "grad_norm": 1.8145461082458496,
3241
+ "learning_rate": 3.082677087891148e-07,
3242
+ "loss": 0.1528,
3243
+ "step": 14752
3244
+ },
3245
+ {
3246
+ "epoch": 2.57,
3247
+ "grad_norm": 2.0109219551086426,
3248
+ "learning_rate": 3.0051676998471807e-07,
3249
+ "loss": 0.1611,
3250
+ "step": 14784
3251
+ },
3252
+ {
3253
+ "epoch": 2.58,
3254
+ "grad_norm": 1.9445598125457764,
3255
+ "learning_rate": 2.9285828381170443e-07,
3256
+ "loss": 0.1545,
3257
+ "step": 14816
3258
+ },
3259
+ {
3260
+ "epoch": 2.59,
3261
+ "grad_norm": 1.956513524055481,
3262
+ "learning_rate": 2.852925721853264e-07,
3263
+ "loss": 0.1515,
3264
+ "step": 14848
3265
+ },
3266
+ {
3267
+ "epoch": 2.59,
3268
+ "grad_norm": 1.5658009052276611,
3269
+ "learning_rate": 2.7781995312117005e-07,
3270
+ "loss": 0.1475,
3271
+ "step": 14880
3272
+ },
3273
+ {
3274
+ "epoch": 2.6,
3275
+ "grad_norm": 1.5122560262680054,
3276
+ "learning_rate": 2.704407407217871e-07,
3277
+ "loss": 0.1485,
3278
+ "step": 14912
3279
+ },
3280
+ {
3281
+ "epoch": 2.6,
3282
+ "grad_norm": 1.7659705877304077,
3283
+ "learning_rate": 2.631552451634931e-07,
3284
+ "loss": 0.1516,
3285
+ "step": 14944
3286
+ },
3287
+ {
3288
+ "epoch": 2.61,
3289
+ "grad_norm": 1.709915041923523,
3290
+ "learning_rate": 2.5596377268332916e-07,
3291
+ "loss": 0.1578,
3292
+ "step": 14976
3293
+ },
3294
+ {
3295
+ "epoch": 2.61,
3296
+ "grad_norm": 1.7999032735824585,
3297
+ "learning_rate": 2.488666255661873e-07,
3298
+ "loss": 0.1593,
3299
+ "step": 15008
3300
+ },
3301
+ {
3302
+ "epoch": 2.62,
3303
+ "grad_norm": 1.7251070737838745,
3304
+ "learning_rate": 2.418641021321097e-07,
3305
+ "loss": 0.1457,
3306
+ "step": 15040
3307
+ },
3308
+ {
3309
+ "epoch": 2.62,
3310
+ "grad_norm": 1.96919584274292,
3311
+ "learning_rate": 2.3495649672374442e-07,
3312
+ "loss": 0.158,
3313
+ "step": 15072
3314
+ },
3315
+ {
3316
+ "epoch": 2.63,
3317
+ "grad_norm": 1.7707350254058838,
3318
+ "learning_rate": 2.281440996939724e-07,
3319
+ "loss": 0.1522,
3320
+ "step": 15104
3321
+ },
3322
+ {
3323
+ "epoch": 2.64,
3324
+ "grad_norm": 1.8055440187454224,
3325
+ "learning_rate": 2.2142719739370876e-07,
3326
+ "loss": 0.1644,
3327
+ "step": 15136
3328
+ },
3329
+ {
3330
+ "epoch": 2.64,
3331
+ "grad_norm": 1.5484322309494019,
3332
+ "learning_rate": 2.1480607215985938e-07,
3333
+ "loss": 0.153,
3334
+ "step": 15168
3335
+ },
3336
+ {
3337
+ "epoch": 2.65,
3338
+ "grad_norm": 2.3656980991363525,
3339
+ "learning_rate": 2.0828100230345815e-07,
3340
+ "loss": 0.1666,
3341
+ "step": 15200
3342
+ },
3343
+ {
3344
+ "epoch": 2.65,
3345
+ "grad_norm": 2.2295897006988525,
3346
+ "learning_rate": 2.018522620979657e-07,
3347
+ "loss": 0.1598,
3348
+ "step": 15232
3349
+ },
3350
+ {
3351
+ "epoch": 2.66,
3352
+ "grad_norm": 1.66213858127594,
3353
+ "learning_rate": 1.95520121767743e-07,
3354
+ "loss": 0.1458,
3355
+ "step": 15264
3356
+ },
3357
+ {
3358
+ "epoch": 2.66,
3359
+ "grad_norm": 1.7052069902420044,
3360
+ "learning_rate": 1.8928484747669007e-07,
3361
+ "loss": 0.1582,
3362
+ "step": 15296
3363
+ },
3364
+ {
3365
+ "epoch": 2.67,
3366
+ "grad_norm": 2.455540895462036,
3367
+ "learning_rate": 1.8314670131706015e-07,
3368
+ "loss": 0.1626,
3369
+ "step": 15328
3370
+ },
3371
+ {
3372
+ "epoch": 2.67,
3373
+ "grad_norm": 1.7177009582519531,
3374
+ "learning_rate": 1.771059412984427e-07,
3375
+ "loss": 0.1489,
3376
+ "step": 15360
3377
+ },
3378
+ {
3379
+ "epoch": 2.68,
3380
+ "grad_norm": 1.9176840782165527,
3381
+ "learning_rate": 1.7116282133691624e-07,
3382
+ "loss": 0.155,
3383
+ "step": 15392
3384
+ },
3385
+ {
3386
+ "epoch": 2.69,
3387
+ "grad_norm": 1.6064426898956299,
3388
+ "learning_rate": 1.6531759124437967e-07,
3389
+ "loss": 0.1646,
3390
+ "step": 15424
3391
+ },
3392
+ {
3393
+ "epoch": 2.69,
3394
+ "grad_norm": 1.764961838722229,
3395
+ "learning_rate": 1.5957049671804753e-07,
3396
+ "loss": 0.1553,
3397
+ "step": 15456
3398
+ },
3399
+ {
3400
+ "epoch": 2.7,
3401
+ "grad_norm": 1.645261287689209,
3402
+ "learning_rate": 1.5392177933012258e-07,
3403
+ "loss": 0.1661,
3404
+ "step": 15488
3405
+ },
3406
+ {
3407
+ "epoch": 2.7,
3408
+ "grad_norm": 1.78240168094635,
3409
+ "learning_rate": 1.4837167651764573e-07,
3410
+ "loss": 0.1724,
3411
+ "step": 15520
3412
+ },
3413
+ {
3414
+ "epoch": 2.71,
3415
+ "grad_norm": 2.0585949420928955,
3416
+ "learning_rate": 1.4292042157251023e-07,
3417
+ "loss": 0.1539,
3418
+ "step": 15552
3419
+ },
3420
+ {
3421
+ "epoch": 2.71,
3422
+ "grad_norm": 1.6157474517822266,
3423
+ "learning_rate": 1.3756824363165943e-07,
3424
+ "loss": 0.1574,
3425
+ "step": 15584
3426
+ },
3427
+ {
3428
+ "epoch": 2.72,
3429
+ "grad_norm": 1.6896705627441406,
3430
+ "learning_rate": 1.3231536766745517e-07,
3431
+ "loss": 0.1629,
3432
+ "step": 15616
3433
+ },
3434
+ {
3435
+ "epoch": 2.72,
3436
+ "grad_norm": 2.022658109664917,
3437
+ "learning_rate": 1.2716201447821763e-07,
3438
+ "loss": 0.1529,
3439
+ "step": 15648
3440
+ },
3441
+ {
3442
+ "epoch": 2.73,
3443
+ "grad_norm": 1.5828081369400024,
3444
+ "learning_rate": 1.2210840067894857e-07,
3445
+ "loss": 0.1633,
3446
+ "step": 15680
3447
+ },
3448
+ {
3449
+ "epoch": 2.74,
3450
+ "grad_norm": 1.9208072423934937,
3451
+ "learning_rate": 1.1715473869222393e-07,
3452
+ "loss": 0.159,
3453
+ "step": 15712
3454
+ },
3455
+ {
3456
+ "epoch": 2.74,
3457
+ "grad_norm": 1.5745195150375366,
3458
+ "learning_rate": 1.123012367392659e-07,
3459
+ "loss": 0.1641,
3460
+ "step": 15744
3461
+ },
3462
+ {
3463
+ "epoch": 2.75,
3464
+ "grad_norm": 1.5185731649398804,
3465
+ "learning_rate": 1.0754809883118916e-07,
3466
+ "loss": 0.1553,
3467
+ "step": 15776
3468
+ },
3469
+ {
3470
+ "epoch": 2.75,
3471
+ "grad_norm": 2.097116470336914,
3472
+ "learning_rate": 1.0289552476042768e-07,
3473
+ "loss": 0.1502,
3474
+ "step": 15808
3475
+ },
3476
+ {
3477
+ "epoch": 2.76,
3478
+ "grad_norm": 1.7868729829788208,
3479
+ "learning_rate": 9.83437100923354e-08,
3480
+ "loss": 0.1576,
3481
+ "step": 15840
3482
+ },
3483
+ {
3484
+ "epoch": 2.76,
3485
+ "grad_norm": 1.7661504745483398,
3486
+ "learning_rate": 9.389284615696464e-08,
3487
+ "loss": 0.1658,
3488
+ "step": 15872
3489
+ },
3490
+ {
3491
+ "epoch": 2.77,
3492
+ "grad_norm": 1.692753553390503,
3493
+ "learning_rate": 8.954312004102711e-08,
3494
+ "loss": 0.1586,
3495
+ "step": 15904
3496
+ },
3497
+ {
3498
+ "epoch": 2.77,
3499
+ "grad_norm": 1.4457049369812012,
3500
+ "learning_rate": 8.529471458002648e-08,
3501
+ "loss": 0.1659,
3502
+ "step": 15936
3503
+ },
3504
+ {
3505
+ "epoch": 2.78,
3506
+ "grad_norm": 1.9470157623291016,
3507
+ "learning_rate": 8.114780835057456e-08,
3508
+ "loss": 0.151,
3509
+ "step": 15968
3510
+ },
3511
+ {
3512
+ "epoch": 2.79,
3513
+ "grad_norm": 1.5848197937011719,
3514
+ "learning_rate": 7.710257566288681e-08,
3515
+ "loss": 0.1512,
3516
+ "step": 16000
3517
+ },
3518
+ {
3519
+ "epoch": 2.79,
3520
+ "grad_norm": 2.0228586196899414,
3521
+ "learning_rate": 7.315918655345117e-08,
3522
+ "loss": 0.1622,
3523
+ "step": 16032
3524
+ },
3525
+ {
3526
+ "epoch": 2.8,
3527
+ "grad_norm": 1.6379644870758057,
3528
+ "learning_rate": 6.931780677788546e-08,
3529
+ "loss": 0.1609,
3530
+ "step": 16064
3531
+ },
3532
+ {
3533
+ "epoch": 2.8,
3534
+ "grad_norm": 1.4579676389694214,
3535
+ "learning_rate": 6.557859780396663e-08,
3536
+ "loss": 0.1578,
3537
+ "step": 16096
3538
+ },
3539
+ {
3540
+ "epoch": 2.81,
3541
+ "grad_norm": 1.8530055284500122,
3542
+ "learning_rate": 6.194171680484556e-08,
3543
+ "loss": 0.1566,
3544
+ "step": 16128
3545
+ },
3546
+ {
3547
+ "epoch": 2.81,
3548
+ "grad_norm": 2.0496585369110107,
3549
+ "learning_rate": 5.8407316652438764e-08,
3550
+ "loss": 0.1613,
3551
+ "step": 16160
3552
+ },
3553
+ {
3554
+ "epoch": 2.82,
3555
+ "grad_norm": 1.8340975046157837,
3556
+ "learning_rate": 5.4975545911005176e-08,
3557
+ "loss": 0.1598,
3558
+ "step": 16192
3559
+ },
3560
+ {
3561
+ "epoch": 2.83,
3562
+ "grad_norm": 2.1443088054656982,
3563
+ "learning_rate": 5.164654883089926e-08,
3564
+ "loss": 0.1536,
3565
+ "step": 16224
3566
+ },
3567
+ {
3568
+ "epoch": 2.83,
3569
+ "grad_norm": 1.8571709394454956,
3570
+ "learning_rate": 4.842046534250716e-08,
3571
+ "loss": 0.1568,
3572
+ "step": 16256
3573
+ },
3574
+ {
3575
+ "epoch": 2.84,
3576
+ "grad_norm": 2.0833983421325684,
3577
+ "learning_rate": 4.529743105036844e-08,
3578
+ "loss": 0.1702,
3579
+ "step": 16288
3580
+ },
3581
+ {
3582
+ "epoch": 2.84,
3583
+ "grad_norm": 1.618950605392456,
3584
+ "learning_rate": 4.227757722747139e-08,
3585
+ "loss": 0.1471,
3586
+ "step": 16320
3587
+ },
3588
+ {
3589
+ "epoch": 2.85,
3590
+ "grad_norm": 1.9389454126358032,
3591
+ "learning_rate": 3.9361030809738074e-08,
3592
+ "loss": 0.1563,
3593
+ "step": 16352
3594
+ },
3595
+ {
3596
+ "epoch": 2.85,
3597
+ "grad_norm": 1.731814980506897,
3598
+ "learning_rate": 3.6547914390688835e-08,
3599
+ "loss": 0.159,
3600
+ "step": 16384
3601
+ },
3602
+ {
3603
+ "epoch": 2.86,
3604
+ "grad_norm": 2.0916991233825684,
3605
+ "learning_rate": 3.3838346216287785e-08,
3606
+ "loss": 0.1531,
3607
+ "step": 16416
3608
+ },
3609
+ {
3610
+ "epoch": 2.86,
3611
+ "grad_norm": 1.8886840343475342,
3612
+ "learning_rate": 3.1232440179972954e-08,
3613
+ "loss": 0.1494,
3614
+ "step": 16448
3615
+ },
3616
+ {
3617
+ "epoch": 2.87,
3618
+ "grad_norm": 1.890721321105957,
3619
+ "learning_rate": 2.8730305817869786e-08,
3620
+ "loss": 0.1544,
3621
+ "step": 16480
3622
+ },
3623
+ {
3624
+ "epoch": 2.88,
3625
+ "grad_norm": 1.5375641584396362,
3626
+ "learning_rate": 2.6332048304185677e-08,
3627
+ "loss": 0.1577,
3628
+ "step": 16512
3629
+ },
3630
+ {
3631
+ "epoch": 2.88,
3632
+ "grad_norm": 1.7129803895950317,
3633
+ "learning_rate": 2.40377684467899e-08,
3634
+ "loss": 0.161,
3635
+ "step": 16544
3636
+ },
3637
+ {
3638
+ "epoch": 2.89,
3639
+ "grad_norm": 1.6450425386428833,
3640
+ "learning_rate": 2.1847562682976166e-08,
3641
+ "loss": 0.1541,
3642
+ "step": 16576
3643
+ },
3644
+ {
3645
+ "epoch": 2.89,
3646
+ "grad_norm": 1.6297754049301147,
3647
+ "learning_rate": 1.976152307540863e-08,
3648
+ "loss": 0.1613,
3649
+ "step": 16608
3650
+ },
3651
+ {
3652
+ "epoch": 2.9,
3653
+ "grad_norm": 1.9899592399597168,
3654
+ "learning_rate": 1.777973730825222e-08,
3655
+ "loss": 0.1499,
3656
+ "step": 16640
3657
+ },
3658
+ {
3659
+ "epoch": 2.9,
3660
+ "grad_norm": 1.3760799169540405,
3661
+ "learning_rate": 1.590228868348781e-08,
3662
+ "loss": 0.1545,
3663
+ "step": 16672
3664
+ },
3665
+ {
3666
+ "epoch": 2.91,
3667
+ "grad_norm": 2.1230156421661377,
3668
+ "learning_rate": 1.4129256117409451e-08,
3669
+ "loss": 0.1669,
3670
+ "step": 16704
3671
+ },
3672
+ {
3673
+ "epoch": 2.91,
3674
+ "grad_norm": 1.7051235437393188,
3675
+ "learning_rate": 1.2460714137307594e-08,
3676
+ "loss": 0.1577,
3677
+ "step": 16736
3678
+ },
3679
+ {
3680
+ "epoch": 2.92,
3681
+ "grad_norm": 1.5741279125213623,
3682
+ "learning_rate": 1.08967328783377e-08,
3683
+ "loss": 0.1626,
3684
+ "step": 16768
3685
+ },
3686
+ {
3687
+ "epoch": 2.93,
3688
+ "grad_norm": 1.71488356590271,
3689
+ "learning_rate": 9.437378080569825e-09,
3690
+ "loss": 0.1576,
3691
+ "step": 16800
3692
+ },
3693
+ {
3694
+ "epoch": 2.93,
3695
+ "grad_norm": 1.9407358169555664,
3696
+ "learning_rate": 8.082711086226936e-09,
3697
+ "loss": 0.1656,
3698
+ "step": 16832
3699
+ },
3700
+ {
3701
+ "epoch": 2.94,
3702
+ "grad_norm": 2.023576259613037,
3703
+ "learning_rate": 6.832788837106974e-09,
3704
+ "loss": 0.2152,
3705
+ "step": 16864
3706
+ },
3707
+ {
3708
+ "epoch": 2.94,
3709
+ "grad_norm": 1.999402403831482,
3710
+ "learning_rate": 5.687663872187555e-09,
3711
+ "loss": 0.1555,
3712
+ "step": 16896
3713
+ },
3714
+ {
3715
+ "epoch": 2.95,
3716
+ "grad_norm": 1.8923932313919067,
3717
+ "learning_rate": 4.647384325418835e-09,
3718
+ "loss": 0.1519,
3719
+ "step": 16928
3720
+ },
3721
+ {
3722
+ "epoch": 2.95,
3723
+ "grad_norm": 1.6705876588821411,
3724
+ "learning_rate": 3.7119939237001412e-09,
3725
+ "loss": 0.1514,
3726
+ "step": 16960
3727
+ },
3728
+ {
3729
+ "epoch": 2.96,
3730
+ "grad_norm": 1.5758410692214966,
3731
+ "learning_rate": 2.8815319850414303e-09,
3732
+ "loss": 0.1642,
3733
+ "step": 16992
3734
+ },
3735
+ {
3736
+ "epoch": 2.96,
3737
+ "grad_norm": 1.5247572660446167,
3738
+ "learning_rate": 2.1560334169112852e-09,
3739
+ "loss": 0.1592,
3740
+ "step": 17024
3741
+ },
3742
+ {
3743
+ "epoch": 2.97,
3744
+ "grad_norm": 1.464015007019043,
3745
+ "learning_rate": 1.5355287147694742e-09,
3746
+ "loss": 0.1534,
3747
+ "step": 17056
3748
+ },
3749
+ {
3750
+ "epoch": 2.98,
3751
+ "grad_norm": 1.6785483360290527,
3752
+ "learning_rate": 1.020043960784367e-09,
3753
+ "loss": 0.162,
3754
+ "step": 17088
3755
+ },
3756
+ {
3757
+ "epoch": 2.98,
3758
+ "grad_norm": 1.7320752143859863,
3759
+ "learning_rate": 6.096008227371441e-10,
3760
+ "loss": 0.1565,
3761
+ "step": 17120
3762
+ },
3763
+ {
3764
+ "epoch": 2.99,
3765
+ "grad_norm": 1.4247487783432007,
3766
+ "learning_rate": 3.042165531116914e-10,
3767
+ "loss": 0.1616,
3768
+ "step": 17152
3769
+ },
3770
+ {
3771
+ "epoch": 2.99,
3772
+ "grad_norm": 1.5723894834518433,
3773
+ "learning_rate": 1.0390398836851446e-10,
3774
+ "loss": 0.1567,
3775
+ "step": 17184
3776
+ },
3777
+ {
3778
+ "epoch": 3.0,
3779
+ "grad_norm": 1.970982551574707,
3780
+ "learning_rate": 8.671548404615149e-12,
3781
+ "loss": 0.1556,
3782
+ "step": 17216
3783
+ }
3784
+ ],
3785
+ "logging_steps": 32,
3786
+ "max_steps": 17229,
3787
+ "num_input_tokens_seen": 0,
3788
+ "num_train_epochs": 3,
3789
+ "save_steps": 5743,
3790
+ "stateful_callbacks": {
3791
+ "TrainerControl": {
3792
+ "args": {
3793
+ "should_epoch_stop": false,
3794
+ "should_evaluate": false,
3795
+ "should_log": false,
3796
+ "should_save": true,
3797
+ "should_training_stop": true
3798
+ },
3799
+ "attributes": {}
3800
+ }
3801
+ },
3802
+ "total_flos": 0.0,
3803
+ "train_batch_size": 2,
3804
+ "trial_name": null,
3805
+ "trial_params": null
3806
+ }
checkpoint-17229/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d76a715adcf50741c88072b99f3a0358952f96d126c1612c9e91e86d9163f8d
3
+ size 7032