Hugging Face's logo

stillerman
/
instruct-aurora-alpaca

PEFT
Safetensors
gpt_bigcode
Generated from Trainer
Model card Files
xet
Community
stillerman commited on
Commit
9383522
·
verified ·
1 Parent(s): 594bfc2

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. README.md +155 -0
  2. adapter_config.json +31 -0
  3. adapter_model.bin +3 -0
  4. added_tokens.json +6 -0
  5. checkpoint-728/README.md +204 -0
  6. checkpoint-728/adapter_config.json +31 -0
  7. checkpoint-728/adapter_model.safetensors +3 -0
  8. checkpoint-728/optimizer.pt +3 -0
  9. checkpoint-728/rng_state.pth +3 -0
  10. checkpoint-728/scheduler.pt +3 -0
  11. checkpoint-728/trainer_state.json +4469 -0
  12. checkpoint-728/training_args.bin +3 -0
  13. config.json +29 -0
  14. merges.txt +0 -0
  15. special_tokens_map.json +51 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +218 -0
  18. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bigcode-openrail-m
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: aurora-m/aurora-m-v0.1
7
+ model-index:
8
+ - name: lora-out
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.4.0`
19
+ ```yaml
20
+ base_model: aurora-m/aurora-m-v0.1 # this can be swapped for mdel model when the model is released
21
+ model_type: AutoModelForCausalLM
22
+ tokenizer_type: AutoTokenizer
23
+ is_llama_derived_model: false
24
+
25
+ load_in_8bit: false # when this is true inference quality is terrible
26
+ load_in_4bit: false
27
+ strict: false
28
+
29
+ datasets:
30
+ - path: tatsu-lab/alpaca # change this to where your dataset is
31
+ type: alpaca # change this to 'alpaca' if you are using alpaca formatting
32
+
33
+ lora_modules_to_save:
34
+ - embed_tokens
35
+ - lm_head
36
+
37
+ dataset_prepared_path:
38
+ val_set_size: 0.05
39
+ output_dir: ./lora-out
40
+
41
+ sequence_len: 4096 # this can be tweaked for efficiency
42
+ sample_packing: true
43
+ pad_to_sequence_len: true
44
+
45
+ adapter: lora
46
+ lora_model_dir:
47
+ lora_r: 32
48
+ lora_alpha: 16
49
+ lora_dropout: 0.05
50
+ lora_target_linear: true
51
+ lora_fan_in_fan_out:
52
+
53
+ wandb_project: aurora-instruct-alpaca # give this a name
54
+ wandb_entity:
55
+ wandb_watch:
56
+ wandb_name:
57
+ wandb_log_model:
58
+
59
+ gradient_accumulation_steps: 2 # this can be tweaked for efficiency
60
+ micro_batch_size: 1 # this can be tweaked for efficiency
61
+ num_epochs: 1 # this can be experimented with
62
+ optimizer: adamw_bnb_8bit
63
+ lr_scheduler: cosine
64
+ learning_rate: 0.0002
65
+
66
+ train_on_inputs: true
67
+ group_by_length: false
68
+ bf16: true
69
+ fp16: false
70
+ tf32: false
71
+
72
+ gradient_checkpointing: true
73
+ early_stopping_patience:
74
+ resume_from_checkpoint:
75
+ local_rank:
76
+ logging_steps: 1
77
+ xformers_attention:
78
+ flash_attention: false # when this is true, inference quality is terrible
79
+ s2_attention:
80
+
81
+ warmup_steps: 10 # this can be tweaked for efficiency
82
+ evals_per_epoch: 10 # this can be tweaked for efficiency
83
+ eval_table_size:
84
+ eval_table_max_new_tokens: 128
85
+ saves_per_epoch: 1
86
+ debug:
87
+ deepspeed:
88
+ weight_decay: 0.0
89
+ fsdp:
90
+ fsdp_config:
91
+ special_tokens:
92
+ pad_token: "<|endoftext|>"
93
+ eos_token: "<|endoftext|>"
94
+
95
+ ```
96
+
97
+ </details><br>
98
+
99
+ # lora-out
100
+
101
+ This model is a fine-tuned version of [aurora-m/aurora-m-v0.1](https://huggingface.co/aurora-m/aurora-m-v0.1) on the None dataset.
102
+ It achieves the following results on the evaluation set:
103
+ - Loss: 0.9600
104
+
105
+ ## Model description
106
+
107
+ More information needed
108
+
109
+ ## Intended uses & limitations
110
+
111
+ More information needed
112
+
113
+ ## Training and evaluation data
114
+
115
+ More information needed
116
+
117
+ ## Training procedure
118
+
119
+ ### Training hyperparameters
120
+
121
+ The following hyperparameters were used during training:
122
+ - learning_rate: 0.0002
123
+ - train_batch_size: 1
124
+ - eval_batch_size: 1
125
+ - seed: 42
126
+ - gradient_accumulation_steps: 2
127
+ - total_train_batch_size: 2
128
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
129
+ - lr_scheduler_type: cosine
130
+ - lr_scheduler_warmup_steps: 10
131
+ - num_epochs: 1
132
+
133
+ ### Training results
134
+
135
+ | Training Loss | Epoch | Step | Validation Loss |
136
+ |:-------------:|:-----:|:----:|:---------------:|
137
+ | 3.9777 | 0.0 | 1 | 3.8904 |
138
+ | 1.228 | 0.1 | 73 | 1.1761 |
139
+ | 1.2383 | 0.2 | 146 | 1.0635 |
140
+ | 0.9985 | 0.3 | 219 | 1.0268 |
141
+ | 1.0444 | 0.4 | 292 | 1.0058 |
142
+ | 0.9859 | 0.5 | 365 | 0.9904 |
143
+ | 0.9736 | 0.6 | 438 | 0.9759 |
144
+ | 1.0146 | 0.7 | 511 | 0.9655 |
145
+ | 1.0007 | 0.8 | 584 | 0.9610 |
146
+ | 0.9943 | 0.9 | 657 | 0.9600 |
147
+
148
+
149
+ ### Framework versions
150
+
151
+ - PEFT 0.8.2
152
+ - Transformers 4.38.0.dev0
153
+ - Pytorch 2.1.2+cu118
154
+ - Datasets 2.16.1
155
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "aurora-m/aurora-m-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": [
17
+ "embed_tokens",
18
+ "lm_head"
19
+ ],
20
+ "peft_type": "LORA",
21
+ "r": 32,
22
+ "rank_pattern": {},
23
+ "revision": null,
24
+ "target_modules": [
25
+ "c_proj",
26
+ "c_attn",
27
+ "c_fc"
28
+ ],
29
+ "task_type": "CAUSAL_LM",
30
+ "use_rslora": false
31
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6324ab47a2f7814ff081bce00c97940e32d8c8d150c92d10bae06c3b9b8a26ae
3
+ size 1429029714
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<filename>": 49152,
3
+ "<gh_stars>": 49153,
4
+ "<issue_comment>": 49155,
5
+ "<issue_start>": 49154
6
+ }
checkpoint-728/README.md ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: aurora-m/aurora-m-v0.1
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+
201
+
202
+ ### Framework versions
203
+
204
+ - PEFT 0.8.2
checkpoint-728/adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "aurora-m/aurora-m-v0.1",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 16,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": [
17
+ "embed_tokens",
18
+ "lm_head"
19
+ ],
20
+ "peft_type": "LORA",
21
+ "r": 32,
22
+ "rank_pattern": {},
23
+ "revision": null,
24
+ "target_modules": [
25
+ "c_proj",
26
+ "c_attn",
27
+ "c_fc"
28
+ ],
29
+ "task_type": "CAUSAL_LM",
30
+ "use_rslora": false
31
+ }
checkpoint-728/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0697ef0a8a135250938f1557c407987031ab4bfefb5f464b66da28f02b0df7aa
3
+ size 2637015752
checkpoint-728/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d511db5ce7f8a9a985b92f3422cf2f0979f47b13176b2c586aaad4b39c77b361
3
+ size 826872024
checkpoint-728/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d75bfc8bb304a30fad1e8f8c1564e83c8bd250a286adc6e4081ae55681042b7
3
+ size 14244
checkpoint-728/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:359eed4dbd2cf7cb37ec4c6282c77dec24966f389d9a650ba7119c3c919c942a
3
+ size 1064
checkpoint-728/trainer_state.json ADDED
@@ -0,0 +1,4469 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 73,
6
+ "global_step": 728,
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
+ "learning_rate": 2e-05,
14
+ "loss": 3.9777,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "eval_loss": 3.890418291091919,
20
+ "eval_runtime": 99.0237,
21
+ "eval_samples_per_second": 26.266,
22
+ "eval_steps_per_second": 26.266,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.0,
27
+ "learning_rate": 4e-05,
28
+ "loss": 3.827,
29
+ "step": 2
30
+ },
31
+ {
32
+ "epoch": 0.0,
33
+ "learning_rate": 6e-05,
34
+ "loss": 3.9703,
35
+ "step": 3
36
+ },
37
+ {
38
+ "epoch": 0.01,
39
+ "learning_rate": 8e-05,
40
+ "loss": 4.0761,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.01,
45
+ "learning_rate": 0.0001,
46
+ "loss": 3.8475,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.01,
51
+ "learning_rate": 0.00012,
52
+ "loss": 3.8447,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.01,
57
+ "learning_rate": 0.00014,
58
+ "loss": 3.6974,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.01,
63
+ "learning_rate": 0.00016,
64
+ "loss": 3.3727,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.01,
69
+ "learning_rate": 0.00018,
70
+ "loss": 3.5621,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.01,
75
+ "learning_rate": 0.0002,
76
+ "loss": 3.2381,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.02,
81
+ "learning_rate": 0.00019999904276147618,
82
+ "loss": 3.2151,
83
+ "step": 11
84
+ },
85
+ {
86
+ "epoch": 0.02,
87
+ "learning_rate": 0.00019999617106423082,
88
+ "loss": 3.0308,
89
+ "step": 12
90
+ },
91
+ {
92
+ "epoch": 0.02,
93
+ "learning_rate": 0.0001999913849632419,
94
+ "loss": 2.9489,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 0.02,
99
+ "learning_rate": 0.00019998468455013823,
100
+ "loss": 2.9578,
101
+ "step": 14
102
+ },
103
+ {
104
+ "epoch": 0.02,
105
+ "learning_rate": 0.00019997606995319768,
106
+ "loss": 2.7989,
107
+ "step": 15
108
+ },
109
+ {
110
+ "epoch": 0.02,
111
+ "learning_rate": 0.00019996554133734474,
112
+ "loss": 2.8254,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 0.02,
117
+ "learning_rate": 0.00019995309890414732,
118
+ "loss": 2.7308,
119
+ "step": 17
120
+ },
121
+ {
122
+ "epoch": 0.02,
123
+ "learning_rate": 0.000199938742891813,
124
+ "loss": 2.6023,
125
+ "step": 18
126
+ },
127
+ {
128
+ "epoch": 0.03,
129
+ "learning_rate": 0.00019992247357518428,
130
+ "loss": 2.6212,
131
+ "step": 19
132
+ },
133
+ {
134
+ "epoch": 0.03,
135
+ "learning_rate": 0.0001999042912657335,
136
+ "loss": 2.5534,
137
+ "step": 20
138
+ },
139
+ {
140
+ "epoch": 0.03,
141
+ "learning_rate": 0.00019988419631155683,
142
+ "loss": 2.5989,
143
+ "step": 21
144
+ },
145
+ {
146
+ "epoch": 0.03,
147
+ "learning_rate": 0.00019986218909736757,
148
+ "loss": 2.3559,
149
+ "step": 22
150
+ },
151
+ {
152
+ "epoch": 0.03,
153
+ "learning_rate": 0.00019983827004448873,
154
+ "loss": 2.2642,
155
+ "step": 23
156
+ },
157
+ {
158
+ "epoch": 0.03,
159
+ "learning_rate": 0.00019981243961084515,
160
+ "loss": 2.0885,
161
+ "step": 24
162
+ },
163
+ {
164
+ "epoch": 0.03,
165
+ "learning_rate": 0.0001997846982909545,
166
+ "loss": 2.1034,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 0.04,
171
+ "learning_rate": 0.000199755046615918,
172
+ "loss": 2.0273,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 0.04,
177
+ "learning_rate": 0.00019972348515341016,
178
+ "loss": 1.8354,
179
+ "step": 27
180
+ },
181
+ {
182
+ "epoch": 0.04,
183
+ "learning_rate": 0.00019969001450766794,
184
+ "loss": 2.0669,
185
+ "step": 28
186
+ },
187
+ {
188
+ "epoch": 0.04,
189
+ "learning_rate": 0.0001996546353194792,
190
+ "loss": 1.9695,
191
+ "step": 29
192
+ },
193
+ {
194
+ "epoch": 0.04,
195
+ "learning_rate": 0.00019961734826617035,
196
+ "loss": 1.8305,
197
+ "step": 30
198
+ },
199
+ {
200
+ "epoch": 0.04,
201
+ "learning_rate": 0.0001995781540615934,
202
+ "loss": 1.8108,
203
+ "step": 31
204
+ },
205
+ {
206
+ "epoch": 0.04,
207
+ "learning_rate": 0.0001995370534561125,
208
+ "loss": 1.8106,
209
+ "step": 32
210
+ },
211
+ {
212
+ "epoch": 0.05,
213
+ "learning_rate": 0.0001994940472365893,
214
+ "loss": 1.8123,
215
+ "step": 33
216
+ },
217
+ {
218
+ "epoch": 0.05,
219
+ "learning_rate": 0.00019944913622636795,
220
+ "loss": 1.7346,
221
+ "step": 34
222
+ },
223
+ {
224
+ "epoch": 0.05,
225
+ "learning_rate": 0.0001994023212852595,
226
+ "loss": 1.6058,
227
+ "step": 35
228
+ },
229
+ {
230
+ "epoch": 0.05,
231
+ "learning_rate": 0.00019935360330952518,
232
+ "loss": 1.6905,
233
+ "step": 36
234
+ },
235
+ {
236
+ "epoch": 0.05,
237
+ "learning_rate": 0.00019930298323185945,
238
+ "loss": 1.6655,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 0.05,
243
+ "learning_rate": 0.00019925046202137216,
244
+ "loss": 1.6512,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 0.05,
249
+ "learning_rate": 0.00019919604068356978,
250
+ "loss": 1.6666,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 0.05,
255
+ "learning_rate": 0.00019913972026033632,
256
+ "loss": 1.5269,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 0.06,
261
+ "learning_rate": 0.00019908150182991339,
262
+ "loss": 1.6329,
263
+ "step": 41
264
+ },
265
+ {
266
+ "epoch": 0.06,
267
+ "learning_rate": 0.00019902138650687942,
268
+ "loss": 1.5822,
269
+ "step": 42
270
+ },
271
+ {
272
+ "epoch": 0.06,
273
+ "learning_rate": 0.00019895937544212858,
274
+ "loss": 1.4317,
275
+ "step": 43
276
+ },
277
+ {
278
+ "epoch": 0.06,
279
+ "learning_rate": 0.00019889546982284834,
280
+ "loss": 1.5239,
281
+ "step": 44
282
+ },
283
+ {
284
+ "epoch": 0.06,
285
+ "learning_rate": 0.00019882967087249718,
286
+ "loss": 1.379,
287
+ "step": 45
288
+ },
289
+ {
290
+ "epoch": 0.06,
291
+ "learning_rate": 0.0001987619798507809,
292
+ "loss": 1.4776,
293
+ "step": 46
294
+ },
295
+ {
296
+ "epoch": 0.06,
297
+ "learning_rate": 0.0001986923980536286,
298
+ "loss": 1.4635,
299
+ "step": 47
300
+ },
301
+ {
302
+ "epoch": 0.07,
303
+ "learning_rate": 0.00019862092681316776,
304
+ "loss": 1.3562,
305
+ "step": 48
306
+ },
307
+ {
308
+ "epoch": 0.07,
309
+ "learning_rate": 0.0001985475674976989,
310
+ "loss": 1.3898,
311
+ "step": 49
312
+ },
313
+ {
314
+ "epoch": 0.07,
315
+ "learning_rate": 0.0001984723215116693,
316
+ "loss": 1.4218,
317
+ "step": 50
318
+ },
319
+ {
320
+ "epoch": 0.07,
321
+ "learning_rate": 0.00019839519029564605,
322
+ "loss": 1.3989,
323
+ "step": 51
324
+ },
325
+ {
326
+ "epoch": 0.07,
327
+ "learning_rate": 0.00019831617532628862,
328
+ "loss": 1.3795,
329
+ "step": 52
330
+ },
331
+ {
332
+ "epoch": 0.07,
333
+ "learning_rate": 0.00019823527811632042,
334
+ "loss": 1.3212,
335
+ "step": 53
336
+ },
337
+ {
338
+ "epoch": 0.07,
339
+ "learning_rate": 0.00019815250021449997,
340
+ "loss": 1.3278,
341
+ "step": 54
342
+ },
343
+ {
344
+ "epoch": 0.08,
345
+ "learning_rate": 0.00019806784320559127,
346
+ "loss": 1.4751,
347
+ "step": 55
348
+ },
349
+ {
350
+ "epoch": 0.08,
351
+ "learning_rate": 0.00019798130871033322,
352
+ "loss": 1.2749,
353
+ "step": 56
354
+ },
355
+ {
356
+ "epoch": 0.08,
357
+ "learning_rate": 0.00019789289838540897,
358
+ "loss": 1.4285,
359
+ "step": 57
360
+ },
361
+ {
362
+ "epoch": 0.08,
363
+ "learning_rate": 0.00019780261392341383,
364
+ "loss": 1.3442,
365
+ "step": 58
366
+ },
367
+ {
368
+ "epoch": 0.08,
369
+ "learning_rate": 0.0001977104570528231,
370
+ "loss": 1.3276,
371
+ "step": 59
372
+ },
373
+ {
374
+ "epoch": 0.08,
375
+ "learning_rate": 0.00019761642953795895,
376
+ "loss": 1.301,
377
+ "step": 60
378
+ },
379
+ {
380
+ "epoch": 0.08,
381
+ "learning_rate": 0.0001975205331789566,
382
+ "loss": 1.2477,
383
+ "step": 61
384
+ },
385
+ {
386
+ "epoch": 0.09,
387
+ "learning_rate": 0.00019742276981172976,
388
+ "loss": 1.2495,
389
+ "step": 62
390
+ },
391
+ {
392
+ "epoch": 0.09,
393
+ "learning_rate": 0.00019732314130793568,
394
+ "loss": 1.2521,
395
+ "step": 63
396
+ },
397
+ {
398
+ "epoch": 0.09,
399
+ "learning_rate": 0.00019722164957493922,
400
+ "loss": 1.2892,
401
+ "step": 64
402
+ },
403
+ {
404
+ "epoch": 0.09,
405
+ "learning_rate": 0.0001971182965557763,
406
+ "loss": 1.1946,
407
+ "step": 65
408
+ },
409
+ {
410
+ "epoch": 0.09,
411
+ "learning_rate": 0.00019701308422911672,
412
+ "loss": 1.3191,
413
+ "step": 66
414
+ },
415
+ {
416
+ "epoch": 0.09,
417
+ "learning_rate": 0.0001969060146092264,
418
+ "loss": 1.2873,
419
+ "step": 67
420
+ },
421
+ {
422
+ "epoch": 0.09,
423
+ "learning_rate": 0.0001967970897459286,
424
+ "loss": 1.2794,
425
+ "step": 68
426
+ },
427
+ {
428
+ "epoch": 0.09,
429
+ "learning_rate": 0.0001966863117245648,
430
+ "loss": 1.3496,
431
+ "step": 69
432
+ },
433
+ {
434
+ "epoch": 0.1,
435
+ "learning_rate": 0.00019657368266595476,
436
+ "loss": 1.2554,
437
+ "step": 70
438
+ },
439
+ {
440
+ "epoch": 0.1,
441
+ "learning_rate": 0.00019645920472635608,
442
+ "loss": 1.4029,
443
+ "step": 71
444
+ },
445
+ {
446
+ "epoch": 0.1,
447
+ "learning_rate": 0.00019634288009742255,
448
+ "loss": 1.3973,
449
+ "step": 72
450
+ },
451
+ {
452
+ "epoch": 0.1,
453
+ "learning_rate": 0.0001962247110061625,
454
+ "loss": 1.228,
455
+ "step": 73
456
+ },
457
+ {
458
+ "epoch": 0.1,
459
+ "eval_loss": 1.1760683059692383,
460
+ "eval_runtime": 100.5851,
461
+ "eval_samples_per_second": 25.859,
462
+ "eval_steps_per_second": 25.859,
463
+ "step": 73
464
+ },
465
+ {
466
+ "epoch": 0.1,
467
+ "learning_rate": 0.00019610469971489608,
468
+ "loss": 1.1915,
469
+ "step": 74
470
+ },
471
+ {
472
+ "epoch": 0.1,
473
+ "learning_rate": 0.00019598284852121188,
474
+ "loss": 1.2774,
475
+ "step": 75
476
+ },
477
+ {
478
+ "epoch": 0.1,
479
+ "learning_rate": 0.0001958591597579231,
480
+ "loss": 1.1898,
481
+ "step": 76
482
+ },
483
+ {
484
+ "epoch": 0.11,
485
+ "learning_rate": 0.00019573363579302266,
486
+ "loss": 1.2981,
487
+ "step": 77
488
+ },
489
+ {
490
+ "epoch": 0.11,
491
+ "learning_rate": 0.00019560627902963807,
492
+ "loss": 1.1753,
493
+ "step": 78
494
+ },
495
+ {
496
+ "epoch": 0.11,
497
+ "learning_rate": 0.00019547709190598534,
498
+ "loss": 1.1694,
499
+ "step": 79
500
+ },
501
+ {
502
+ "epoch": 0.11,
503
+ "learning_rate": 0.00019534607689532233,
504
+ "loss": 1.3327,
505
+ "step": 80
506
+ },
507
+ {
508
+ "epoch": 0.11,
509
+ "learning_rate": 0.00019521323650590133,
510
+ "loss": 1.2408,
511
+ "step": 81
512
+ },
513
+ {
514
+ "epoch": 0.11,
515
+ "learning_rate": 0.00019507857328092108,
516
+ "loss": 1.1947,
517
+ "step": 82
518
+ },
519
+ {
520
+ "epoch": 0.11,
521
+ "learning_rate": 0.00019494208979847812,
522
+ "loss": 1.3749,
523
+ "step": 83
524
+ },
525
+ {
526
+ "epoch": 0.12,
527
+ "learning_rate": 0.00019480378867151746,
528
+ "loss": 4.8929,
529
+ "step": 84
530
+ },
531
+ {
532
+ "epoch": 0.12,
533
+ "learning_rate": 0.00019466367254778233,
534
+ "loss": 1.2734,
535
+ "step": 85
536
+ },
537
+ {
538
+ "epoch": 0.12,
539
+ "learning_rate": 0.0001945217441097638,
540
+ "loss": 1.1469,
541
+ "step": 86
542
+ },
543
+ {
544
+ "epoch": 0.12,
545
+ "learning_rate": 0.00019437800607464932,
546
+ "loss": 1.2254,
547
+ "step": 87
548
+ },
549
+ {
550
+ "epoch": 0.12,
551
+ "learning_rate": 0.00019423246119427043,
552
+ "loss": 1.1261,
553
+ "step": 88
554
+ },
555
+ {
556
+ "epoch": 0.12,
557
+ "learning_rate": 0.00019408511225505056,
558
+ "loss": 1.3727,
559
+ "step": 89
560
+ },
561
+ {
562
+ "epoch": 0.12,
563
+ "learning_rate": 0.00019393596207795136,
564
+ "loss": 1.2165,
565
+ "step": 90
566
+ },
567
+ {
568
+ "epoch": 0.12,
569
+ "learning_rate": 0.00019378501351841865,
570
+ "loss": 1.2039,
571
+ "step": 91
572
+ },
573
+ {
574
+ "epoch": 0.13,
575
+ "learning_rate": 0.000193632269466328,
576
+ "loss": 3.9674,
577
+ "step": 92
578
+ },
579
+ {
580
+ "epoch": 0.13,
581
+ "learning_rate": 0.0001934777328459292,
582
+ "loss": 1.5776,
583
+ "step": 93
584
+ },
585
+ {
586
+ "epoch": 0.13,
587
+ "learning_rate": 0.00019332140661579042,
588
+ "loss": 1.15,
589
+ "step": 94
590
+ },
591
+ {
592
+ "epoch": 0.13,
593
+ "learning_rate": 0.00019316329376874145,
594
+ "loss": 1.2978,
595
+ "step": 95
596
+ },
597
+ {
598
+ "epoch": 0.13,
599
+ "learning_rate": 0.00019300339733181642,
600
+ "loss": 1.1202,
601
+ "step": 96
602
+ },
603
+ {
604
+ "epoch": 0.13,
605
+ "learning_rate": 0.00019284172036619594,
606
+ "loss": 1.2209,
607
+ "step": 97
608
+ },
609
+ {
610
+ "epoch": 0.13,
611
+ "learning_rate": 0.0001926782659671484,
612
+ "loss": 1.2685,
613
+ "step": 98
614
+ },
615
+ {
616
+ "epoch": 0.14,
617
+ "learning_rate": 0.00019251303726397078,
618
+ "loss": 1.1449,
619
+ "step": 99
620
+ },
621
+ {
622
+ "epoch": 0.14,
623
+ "learning_rate": 0.00019234603741992862,
624
+ "loss": 1.1309,
625
+ "step": 100
626
+ },
627
+ {
628
+ "epoch": 0.14,
629
+ "learning_rate": 0.00019217726963219567,
630
+ "loss": 1.1552,
631
+ "step": 101
632
+ },
633
+ {
634
+ "epoch": 0.14,
635
+ "learning_rate": 0.00019200673713179245,
636
+ "loss": 1.1851,
637
+ "step": 102
638
+ },
639
+ {
640
+ "epoch": 0.14,
641
+ "learning_rate": 0.00019183444318352457,
642
+ "loss": 1.1582,
643
+ "step": 103
644
+ },
645
+ {
646
+ "epoch": 0.14,
647
+ "learning_rate": 0.0001916603910859201,
648
+ "loss": 1.1166,
649
+ "step": 104
650
+ },
651
+ {
652
+ "epoch": 0.14,
653
+ "learning_rate": 0.00019148458417116645,
654
+ "loss": 1.1617,
655
+ "step": 105
656
+ },
657
+ {
658
+ "epoch": 0.15,
659
+ "learning_rate": 0.00019130702580504676,
660
+ "loss": 1.2401,
661
+ "step": 106
662
+ },
663
+ {
664
+ "epoch": 0.15,
665
+ "learning_rate": 0.0001911277193868751,
666
+ "loss": 1.1731,
667
+ "step": 107
668
+ },
669
+ {
670
+ "epoch": 0.15,
671
+ "learning_rate": 0.00019094666834943179,
672
+ "loss": 1.1363,
673
+ "step": 108
674
+ },
675
+ {
676
+ "epoch": 0.15,
677
+ "learning_rate": 0.00019076387615889727,
678
+ "loss": 1.2122,
679
+ "step": 109
680
+ },
681
+ {
682
+ "epoch": 0.15,
683
+ "learning_rate": 0.00019057934631478617,
684
+ "loss": 1.1438,
685
+ "step": 110
686
+ },
687
+ {
688
+ "epoch": 0.15,
689
+ "learning_rate": 0.00019039308234987992,
690
+ "loss": 1.1777,
691
+ "step": 111
692
+ },
693
+ {
694
+ "epoch": 0.15,
695
+ "learning_rate": 0.00019020508783015942,
696
+ "loss": 1.1926,
697
+ "step": 112
698
+ },
699
+ {
700
+ "epoch": 0.16,
701
+ "learning_rate": 0.00019001536635473664,
702
+ "loss": 1.1566,
703
+ "step": 113
704
+ },
705
+ {
706
+ "epoch": 0.16,
707
+ "learning_rate": 0.0001898239215557856,
708
+ "loss": 1.0669,
709
+ "step": 114
710
+ },
711
+ {
712
+ "epoch": 0.16,
713
+ "learning_rate": 0.0001896307570984731,
714
+ "loss": 1.1532,
715
+ "step": 115
716
+ },
717
+ {
718
+ "epoch": 0.16,
719
+ "learning_rate": 0.00018943587668088832,
720
+ "loss": 1.2491,
721
+ "step": 116
722
+ },
723
+ {
724
+ "epoch": 0.16,
725
+ "learning_rate": 0.00018923928403397208,
726
+ "loss": 1.1626,
727
+ "step": 117
728
+ },
729
+ {
730
+ "epoch": 0.16,
731
+ "learning_rate": 0.00018904098292144554,
732
+ "loss": 1.1217,
733
+ "step": 118
734
+ },
735
+ {
736
+ "epoch": 0.16,
737
+ "learning_rate": 0.00018884097713973798,
738
+ "loss": 1.1031,
739
+ "step": 119
740
+ },
741
+ {
742
+ "epoch": 0.16,
743
+ "learning_rate": 0.00018863927051791416,
744
+ "loss": 1.2038,
745
+ "step": 120
746
+ },
747
+ {
748
+ "epoch": 0.17,
749
+ "learning_rate": 0.00018843586691760108,
750
+ "loss": 1.1579,
751
+ "step": 121
752
+ },
753
+ {
754
+ "epoch": 0.17,
755
+ "learning_rate": 0.00018823077023291397,
756
+ "loss": 1.1149,
757
+ "step": 122
758
+ },
759
+ {
760
+ "epoch": 0.17,
761
+ "learning_rate": 0.00018802398439038176,
762
+ "loss": 1.1874,
763
+ "step": 123
764
+ },
765
+ {
766
+ "epoch": 0.17,
767
+ "learning_rate": 0.00018781551334887201,
768
+ "loss": 1.0774,
769
+ "step": 124
770
+ },
771
+ {
772
+ "epoch": 0.17,
773
+ "learning_rate": 0.0001876053610995149,
774
+ "loss": 1.0934,
775
+ "step": 125
776
+ },
777
+ {
778
+ "epoch": 0.17,
779
+ "learning_rate": 0.000187393531665627,
780
+ "loss": 1.0837,
781
+ "step": 126
782
+ },
783
+ {
784
+ "epoch": 0.17,
785
+ "learning_rate": 0.00018718002910263426,
786
+ "loss": 1.1787,
787
+ "step": 127
788
+ },
789
+ {
790
+ "epoch": 0.18,
791
+ "learning_rate": 0.0001869648574979942,
792
+ "loss": 1.0997,
793
+ "step": 128
794
+ },
795
+ {
796
+ "epoch": 0.18,
797
+ "learning_rate": 0.00018674802097111784,
798
+ "loss": 1.0795,
799
+ "step": 129
800
+ },
801
+ {
802
+ "epoch": 0.18,
803
+ "learning_rate": 0.0001865295236732907,
804
+ "loss": 1.1547,
805
+ "step": 130
806
+ },
807
+ {
808
+ "epoch": 0.18,
809
+ "learning_rate": 0.00018630936978759338,
810
+ "loss": 1.0748,
811
+ "step": 131
812
+ },
813
+ {
814
+ "epoch": 0.18,
815
+ "learning_rate": 0.00018608756352882152,
816
+ "loss": 1.1896,
817
+ "step": 132
818
+ },
819
+ {
820
+ "epoch": 0.18,
821
+ "learning_rate": 0.00018586410914340497,
822
+ "loss": 1.4642,
823
+ "step": 133
824
+ },
825
+ {
826
+ "epoch": 0.18,
827
+ "learning_rate": 0.00018563901090932672,
828
+ "loss": 1.0802,
829
+ "step": 134
830
+ },
831
+ {
832
+ "epoch": 0.19,
833
+ "learning_rate": 0.00018541227313604078,
834
+ "loss": 1.1233,
835
+ "step": 135
836
+ },
837
+ {
838
+ "epoch": 0.19,
839
+ "learning_rate": 0.0001851839001643898,
840
+ "loss": 1.09,
841
+ "step": 136
842
+ },
843
+ {
844
+ "epoch": 0.19,
845
+ "learning_rate": 0.00018495389636652185,
846
+ "loss": 1.0771,
847
+ "step": 137
848
+ },
849
+ {
850
+ "epoch": 0.19,
851
+ "learning_rate": 0.0001847222661458069,
852
+ "loss": 1.0762,
853
+ "step": 138
854
+ },
855
+ {
856
+ "epoch": 0.19,
857
+ "learning_rate": 0.00018448901393675233,
858
+ "loss": 1.1743,
859
+ "step": 139
860
+ },
861
+ {
862
+ "epoch": 0.19,
863
+ "learning_rate": 0.00018425414420491815,
864
+ "loss": 1.1005,
865
+ "step": 140
866
+ },
867
+ {
868
+ "epoch": 0.19,
869
+ "learning_rate": 0.00018401766144683147,
870
+ "loss": 1.0498,
871
+ "step": 141
872
+ },
873
+ {
874
+ "epoch": 0.2,
875
+ "learning_rate": 0.0001837795701899004,
876
+ "loss": 1.1314,
877
+ "step": 142
878
+ },
879
+ {
880
+ "epoch": 0.2,
881
+ "learning_rate": 0.00018353987499232746,
882
+ "loss": 1.0867,
883
+ "step": 143
884
+ },
885
+ {
886
+ "epoch": 0.2,
887
+ "learning_rate": 0.00018329858044302213,
888
+ "loss": 1.0504,
889
+ "step": 144
890
+ },
891
+ {
892
+ "epoch": 0.2,
893
+ "learning_rate": 0.0001830556911615132,
894
+ "loss": 1.095,
895
+ "step": 145
896
+ },
897
+ {
898
+ "epoch": 0.2,
899
+ "learning_rate": 0.00018281121179786024,
900
+ "loss": 1.2383,
901
+ "step": 146
902
+ },
903
+ {
904
+ "epoch": 0.2,
905
+ "eval_loss": 1.0634887218475342,
906
+ "eval_runtime": 100.3116,
907
+ "eval_samples_per_second": 25.929,
908
+ "eval_steps_per_second": 25.929,
909
+ "step": 146
910
+ },
911
+ {
912
+ "epoch": 0.2,
913
+ "learning_rate": 0.0001825651470325645,
914
+ "loss": 1.1865,
915
+ "step": 147
916
+ },
917
+ {
918
+ "epoch": 0.2,
919
+ "learning_rate": 0.0001823175015764795,
920
+ "loss": 1.1114,
921
+ "step": 148
922
+ },
923
+ {
924
+ "epoch": 0.2,
925
+ "learning_rate": 0.00018206828017072057,
926
+ "loss": 1.0832,
927
+ "step": 149
928
+ },
929
+ {
930
+ "epoch": 0.21,
931
+ "learning_rate": 0.00018181748758657438,
932
+ "loss": 1.0374,
933
+ "step": 150
934
+ },
935
+ {
936
+ "epoch": 0.21,
937
+ "learning_rate": 0.0001815651286254074,
938
+ "loss": 1.0762,
939
+ "step": 151
940
+ },
941
+ {
942
+ "epoch": 0.21,
943
+ "learning_rate": 0.000181311208118574,
944
+ "loss": 1.0557,
945
+ "step": 152
946
+ },
947
+ {
948
+ "epoch": 0.21,
949
+ "learning_rate": 0.000181055730927324,
950
+ "loss": 1.0443,
951
+ "step": 153
952
+ },
953
+ {
954
+ "epoch": 0.21,
955
+ "learning_rate": 0.00018079870194270958,
956
+ "loss": 1.105,
957
+ "step": 154
958
+ },
959
+ {
960
+ "epoch": 0.21,
961
+ "learning_rate": 0.00018054012608549166,
962
+ "loss": 1.0623,
963
+ "step": 155
964
+ },
965
+ {
966
+ "epoch": 0.21,
967
+ "learning_rate": 0.0001802800083060457,
968
+ "loss": 1.1301,
969
+ "step": 156
970
+ },
971
+ {
972
+ "epoch": 0.22,
973
+ "learning_rate": 0.00018001835358426687,
974
+ "loss": 1.1074,
975
+ "step": 157
976
+ },
977
+ {
978
+ "epoch": 0.22,
979
+ "learning_rate": 0.00017975516692947475,
980
+ "loss": 1.094,
981
+ "step": 158
982
+ },
983
+ {
984
+ "epoch": 0.22,
985
+ "learning_rate": 0.00017949045338031745,
986
+ "loss": 1.0659,
987
+ "step": 159
988
+ },
989
+ {
990
+ "epoch": 0.22,
991
+ "learning_rate": 0.00017922421800467512,
992
+ "loss": 1.1161,
993
+ "step": 160
994
+ },
995
+ {
996
+ "epoch": 0.22,
997
+ "learning_rate": 0.0001789564658995629,
998
+ "loss": 1.0625,
999
+ "step": 161
1000
+ },
1001
+ {
1002
+ "epoch": 0.22,
1003
+ "learning_rate": 0.00017868720219103344,
1004
+ "loss": 1.1171,
1005
+ "step": 162
1006
+ },
1007
+ {
1008
+ "epoch": 0.22,
1009
+ "learning_rate": 0.00017841643203407852,
1010
+ "loss": 1.0967,
1011
+ "step": 163
1012
+ },
1013
+ {
1014
+ "epoch": 0.23,
1015
+ "learning_rate": 0.00017814416061253077,
1016
+ "loss": 1.1404,
1017
+ "step": 164
1018
+ },
1019
+ {
1020
+ "epoch": 0.23,
1021
+ "learning_rate": 0.000177870393138964,
1022
+ "loss": 1.0898,
1023
+ "step": 165
1024
+ },
1025
+ {
1026
+ "epoch": 0.23,
1027
+ "learning_rate": 0.00017759513485459367,
1028
+ "loss": 1.1869,
1029
+ "step": 166
1030
+ },
1031
+ {
1032
+ "epoch": 0.23,
1033
+ "learning_rate": 0.00017731839102917644,
1034
+ "loss": 1.0731,
1035
+ "step": 167
1036
+ },
1037
+ {
1038
+ "epoch": 0.23,
1039
+ "learning_rate": 0.00017704016696090937,
1040
+ "loss": 1.1158,
1041
+ "step": 168
1042
+ },
1043
+ {
1044
+ "epoch": 0.23,
1045
+ "learning_rate": 0.00017676046797632835,
1046
+ "loss": 1.072,
1047
+ "step": 169
1048
+ },
1049
+ {
1050
+ "epoch": 0.23,
1051
+ "learning_rate": 0.00017647929943020625,
1052
+ "loss": 1.1266,
1053
+ "step": 170
1054
+ },
1055
+ {
1056
+ "epoch": 0.23,
1057
+ "learning_rate": 0.00017619666670545033,
1058
+ "loss": 1.0624,
1059
+ "step": 171
1060
+ },
1061
+ {
1062
+ "epoch": 0.24,
1063
+ "learning_rate": 0.00017591257521299932,
1064
+ "loss": 1.1007,
1065
+ "step": 172
1066
+ },
1067
+ {
1068
+ "epoch": 0.24,
1069
+ "learning_rate": 0.00017562703039171955,
1070
+ "loss": 0.9943,
1071
+ "step": 173
1072
+ },
1073
+ {
1074
+ "epoch": 0.24,
1075
+ "learning_rate": 0.0001753400377083011,
1076
+ "loss": 1.1336,
1077
+ "step": 174
1078
+ },
1079
+ {
1080
+ "epoch": 0.24,
1081
+ "learning_rate": 0.00017505160265715304,
1082
+ "loss": 1.0376,
1083
+ "step": 175
1084
+ },
1085
+ {
1086
+ "epoch": 0.24,
1087
+ "learning_rate": 0.0001747617307602982,
1088
+ "loss": 1.0645,
1089
+ "step": 176
1090
+ },
1091
+ {
1092
+ "epoch": 0.24,
1093
+ "learning_rate": 0.00017447042756726754,
1094
+ "loss": 1.057,
1095
+ "step": 177
1096
+ },
1097
+ {
1098
+ "epoch": 0.24,
1099
+ "learning_rate": 0.0001741776986549938,
1100
+ "loss": 1.0968,
1101
+ "step": 178
1102
+ },
1103
+ {
1104
+ "epoch": 0.25,
1105
+ "learning_rate": 0.00017388354962770487,
1106
+ "loss": 1.044,
1107
+ "step": 179
1108
+ },
1109
+ {
1110
+ "epoch": 0.25,
1111
+ "learning_rate": 0.0001735879861168163,
1112
+ "loss": 1.0892,
1113
+ "step": 180
1114
+ },
1115
+ {
1116
+ "epoch": 0.25,
1117
+ "learning_rate": 0.00017329101378082374,
1118
+ "loss": 1.1191,
1119
+ "step": 181
1120
+ },
1121
+ {
1122
+ "epoch": 0.25,
1123
+ "learning_rate": 0.0001729926383051943,
1124
+ "loss": 1.0676,
1125
+ "step": 182
1126
+ },
1127
+ {
1128
+ "epoch": 0.25,
1129
+ "learning_rate": 0.00017269286540225805,
1130
+ "loss": 1.0517,
1131
+ "step": 183
1132
+ },
1133
+ {
1134
+ "epoch": 0.25,
1135
+ "learning_rate": 0.0001723917008110984,
1136
+ "loss": 0.9741,
1137
+ "step": 184
1138
+ },
1139
+ {
1140
+ "epoch": 0.25,
1141
+ "learning_rate": 0.0001720891502974423,
1142
+ "loss": 1.1387,
1143
+ "step": 185
1144
+ },
1145
+ {
1146
+ "epoch": 0.26,
1147
+ "learning_rate": 0.00017178521965354992,
1148
+ "loss": 1.1113,
1149
+ "step": 186
1150
+ },
1151
+ {
1152
+ "epoch": 0.26,
1153
+ "learning_rate": 0.00017147991469810368,
1154
+ "loss": 0.9924,
1155
+ "step": 187
1156
+ },
1157
+ {
1158
+ "epoch": 0.26,
1159
+ "learning_rate": 0.00017117324127609686,
1160
+ "loss": 1.0768,
1161
+ "step": 188
1162
+ },
1163
+ {
1164
+ "epoch": 0.26,
1165
+ "learning_rate": 0.00017086520525872172,
1166
+ "loss": 1.0771,
1167
+ "step": 189
1168
+ },
1169
+ {
1170
+ "epoch": 0.26,
1171
+ "learning_rate": 0.00017055581254325715,
1172
+ "loss": 1.0321,
1173
+ "step": 190
1174
+ },
1175
+ {
1176
+ "epoch": 0.26,
1177
+ "learning_rate": 0.00017024506905295565,
1178
+ "loss": 1.0744,
1179
+ "step": 191
1180
+ },
1181
+ {
1182
+ "epoch": 0.26,
1183
+ "learning_rate": 0.00016993298073693003,
1184
+ "loss": 0.9841,
1185
+ "step": 192
1186
+ },
1187
+ {
1188
+ "epoch": 0.27,
1189
+ "learning_rate": 0.00016961955357003947,
1190
+ "loss": 1.0684,
1191
+ "step": 193
1192
+ },
1193
+ {
1194
+ "epoch": 0.27,
1195
+ "learning_rate": 0.0001693047935527751,
1196
+ "loss": 1.0483,
1197
+ "step": 194
1198
+ },
1199
+ {
1200
+ "epoch": 0.27,
1201
+ "learning_rate": 0.00016898870671114527,
1202
+ "loss": 1.0955,
1203
+ "step": 195
1204
+ },
1205
+ {
1206
+ "epoch": 0.27,
1207
+ "learning_rate": 0.00016867129909655998,
1208
+ "loss": 1.0859,
1209
+ "step": 196
1210
+ },
1211
+ {
1212
+ "epoch": 0.27,
1213
+ "learning_rate": 0.00016835257678571514,
1214
+ "loss": 1.0852,
1215
+ "step": 197
1216
+ },
1217
+ {
1218
+ "epoch": 0.27,
1219
+ "learning_rate": 0.0001680325458804763,
1220
+ "loss": 1.0153,
1221
+ "step": 198
1222
+ },
1223
+ {
1224
+ "epoch": 0.27,
1225
+ "learning_rate": 0.0001677112125077616,
1226
+ "loss": 1.0825,
1227
+ "step": 199
1228
+ },
1229
+ {
1230
+ "epoch": 0.27,
1231
+ "learning_rate": 0.00016738858281942478,
1232
+ "loss": 1.0923,
1233
+ "step": 200
1234
+ },
1235
+ {
1236
+ "epoch": 0.28,
1237
+ "learning_rate": 0.00016706466299213715,
1238
+ "loss": 1.0794,
1239
+ "step": 201
1240
+ },
1241
+ {
1242
+ "epoch": 0.28,
1243
+ "learning_rate": 0.00016673945922726944,
1244
+ "loss": 1.0375,
1245
+ "step": 202
1246
+ },
1247
+ {
1248
+ "epoch": 0.28,
1249
+ "learning_rate": 0.00016641297775077312,
1250
+ "loss": 1.0138,
1251
+ "step": 203
1252
+ },
1253
+ {
1254
+ "epoch": 0.28,
1255
+ "learning_rate": 0.00016608522481306108,
1256
+ "loss": 1.0362,
1257
+ "step": 204
1258
+ },
1259
+ {
1260
+ "epoch": 0.28,
1261
+ "learning_rate": 0.00016575620668888812,
1262
+ "loss": 1.1891,
1263
+ "step": 205
1264
+ },
1265
+ {
1266
+ "epoch": 0.28,
1267
+ "learning_rate": 0.00016542592967723065,
1268
+ "loss": 1.0172,
1269
+ "step": 206
1270
+ },
1271
+ {
1272
+ "epoch": 0.28,
1273
+ "learning_rate": 0.00016509440010116632,
1274
+ "loss": 1.0085,
1275
+ "step": 207
1276
+ },
1277
+ {
1278
+ "epoch": 0.29,
1279
+ "learning_rate": 0.00016476162430775277,
1280
+ "loss": 1.1463,
1281
+ "step": 208
1282
+ },
1283
+ {
1284
+ "epoch": 0.29,
1285
+ "learning_rate": 0.00016442760866790617,
1286
+ "loss": 1.1111,
1287
+ "step": 209
1288
+ },
1289
+ {
1290
+ "epoch": 0.29,
1291
+ "learning_rate": 0.00016409235957627925,
1292
+ "loss": 1.1617,
1293
+ "step": 210
1294
+ },
1295
+ {
1296
+ "epoch": 0.29,
1297
+ "learning_rate": 0.00016375588345113892,
1298
+ "loss": 1.0932,
1299
+ "step": 211
1300
+ },
1301
+ {
1302
+ "epoch": 0.29,
1303
+ "learning_rate": 0.00016341818673424344,
1304
+ "loss": 1.0653,
1305
+ "step": 212
1306
+ },
1307
+ {
1308
+ "epoch": 0.29,
1309
+ "learning_rate": 0.00016307927589071888,
1310
+ "loss": 1.0422,
1311
+ "step": 213
1312
+ },
1313
+ {
1314
+ "epoch": 0.29,
1315
+ "learning_rate": 0.00016273915740893554,
1316
+ "loss": 0.95,
1317
+ "step": 214
1318
+ },
1319
+ {
1320
+ "epoch": 0.3,
1321
+ "learning_rate": 0.00016239783780038373,
1322
+ "loss": 1.1407,
1323
+ "step": 215
1324
+ },
1325
+ {
1326
+ "epoch": 0.3,
1327
+ "learning_rate": 0.00016205532359954902,
1328
+ "loss": 0.9992,
1329
+ "step": 216
1330
+ },
1331
+ {
1332
+ "epoch": 0.3,
1333
+ "learning_rate": 0.00016171162136378715,
1334
+ "loss": 1.0726,
1335
+ "step": 217
1336
+ },
1337
+ {
1338
+ "epoch": 0.3,
1339
+ "learning_rate": 0.0001613667376731985,
1340
+ "loss": 1.0273,
1341
+ "step": 218
1342
+ },
1343
+ {
1344
+ "epoch": 0.3,
1345
+ "learning_rate": 0.00016102067913050224,
1346
+ "loss": 0.9985,
1347
+ "step": 219
1348
+ },
1349
+ {
1350
+ "epoch": 0.3,
1351
+ "eval_loss": 1.026813268661499,
1352
+ "eval_runtime": 100.3412,
1353
+ "eval_samples_per_second": 25.922,
1354
+ "eval_steps_per_second": 25.922,
1355
+ "step": 219
1356
+ },
1357
+ {
1358
+ "epoch": 0.3,
1359
+ "learning_rate": 0.0001606734523609097,
1360
+ "loss": 1.1252,
1361
+ "step": 220
1362
+ },
1363
+ {
1364
+ "epoch": 0.3,
1365
+ "learning_rate": 0.0001603250640119977,
1366
+ "loss": 1.125,
1367
+ "step": 221
1368
+ },
1369
+ {
1370
+ "epoch": 0.3,
1371
+ "learning_rate": 0.0001599755207535812,
1372
+ "loss": 1.0625,
1373
+ "step": 222
1374
+ },
1375
+ {
1376
+ "epoch": 0.31,
1377
+ "learning_rate": 0.00015962482927758568,
1378
+ "loss": 1.0133,
1379
+ "step": 223
1380
+ },
1381
+ {
1382
+ "epoch": 0.31,
1383
+ "learning_rate": 0.0001592729962979189,
1384
+ "loss": 1.0717,
1385
+ "step": 224
1386
+ },
1387
+ {
1388
+ "epoch": 0.31,
1389
+ "learning_rate": 0.0001589200285503426,
1390
+ "loss": 1.0399,
1391
+ "step": 225
1392
+ },
1393
+ {
1394
+ "epoch": 0.31,
1395
+ "learning_rate": 0.00015856593279234317,
1396
+ "loss": 1.0406,
1397
+ "step": 226
1398
+ },
1399
+ {
1400
+ "epoch": 0.31,
1401
+ "learning_rate": 0.00015821071580300272,
1402
+ "loss": 1.0934,
1403
+ "step": 227
1404
+ },
1405
+ {
1406
+ "epoch": 0.31,
1407
+ "learning_rate": 0.00015785438438286893,
1408
+ "loss": 1.0357,
1409
+ "step": 228
1410
+ },
1411
+ {
1412
+ "epoch": 0.31,
1413
+ "learning_rate": 0.00015749694535382509,
1414
+ "loss": 0.9772,
1415
+ "step": 229
1416
+ },
1417
+ {
1418
+ "epoch": 0.32,
1419
+ "learning_rate": 0.00015713840555895935,
1420
+ "loss": 1.0397,
1421
+ "step": 230
1422
+ },
1423
+ {
1424
+ "epoch": 0.32,
1425
+ "learning_rate": 0.0001567787718624338,
1426
+ "loss": 1.0323,
1427
+ "step": 231
1428
+ },
1429
+ {
1430
+ "epoch": 0.32,
1431
+ "learning_rate": 0.00015641805114935297,
1432
+ "loss": 1.0734,
1433
+ "step": 232
1434
+ },
1435
+ {
1436
+ "epoch": 0.32,
1437
+ "learning_rate": 0.00015605625032563217,
1438
+ "loss": 1.0693,
1439
+ "step": 233
1440
+ },
1441
+ {
1442
+ "epoch": 0.32,
1443
+ "learning_rate": 0.00015569337631786512,
1444
+ "loss": 1.0856,
1445
+ "step": 234
1446
+ },
1447
+ {
1448
+ "epoch": 0.32,
1449
+ "learning_rate": 0.00015532943607319142,
1450
+ "loss": 1.0136,
1451
+ "step": 235
1452
+ },
1453
+ {
1454
+ "epoch": 0.32,
1455
+ "learning_rate": 0.00015496443655916347,
1456
+ "loss": 0.991,
1457
+ "step": 236
1458
+ },
1459
+ {
1460
+ "epoch": 0.33,
1461
+ "learning_rate": 0.00015459838476361324,
1462
+ "loss": 1.1415,
1463
+ "step": 237
1464
+ },
1465
+ {
1466
+ "epoch": 0.33,
1467
+ "learning_rate": 0.0001542312876945183,
1468
+ "loss": 1.0516,
1469
+ "step": 238
1470
+ },
1471
+ {
1472
+ "epoch": 0.33,
1473
+ "learning_rate": 0.00015386315237986783,
1474
+ "loss": 0.981,
1475
+ "step": 239
1476
+ },
1477
+ {
1478
+ "epoch": 0.33,
1479
+ "learning_rate": 0.00015349398586752793,
1480
+ "loss": 1.0824,
1481
+ "step": 240
1482
+ },
1483
+ {
1484
+ "epoch": 0.33,
1485
+ "learning_rate": 0.00015312379522510668,
1486
+ "loss": 1.0428,
1487
+ "step": 241
1488
+ },
1489
+ {
1490
+ "epoch": 0.33,
1491
+ "learning_rate": 0.000152752587539819,
1492
+ "loss": 1.0528,
1493
+ "step": 242
1494
+ },
1495
+ {
1496
+ "epoch": 0.33,
1497
+ "learning_rate": 0.00015238036991835086,
1498
+ "loss": 0.991,
1499
+ "step": 243
1500
+ },
1501
+ {
1502
+ "epoch": 0.34,
1503
+ "learning_rate": 0.0001520071494867231,
1504
+ "loss": 1.1019,
1505
+ "step": 244
1506
+ },
1507
+ {
1508
+ "epoch": 0.34,
1509
+ "learning_rate": 0.00015163293339015533,
1510
+ "loss": 1.0146,
1511
+ "step": 245
1512
+ },
1513
+ {
1514
+ "epoch": 0.34,
1515
+ "learning_rate": 0.00015125772879292878,
1516
+ "loss": 1.047,
1517
+ "step": 246
1518
+ },
1519
+ {
1520
+ "epoch": 0.34,
1521
+ "learning_rate": 0.00015088154287824933,
1522
+ "loss": 0.9275,
1523
+ "step": 247
1524
+ },
1525
+ {
1526
+ "epoch": 0.34,
1527
+ "learning_rate": 0.00015050438284811002,
1528
+ "loss": 0.9802,
1529
+ "step": 248
1530
+ },
1531
+ {
1532
+ "epoch": 0.34,
1533
+ "learning_rate": 0.00015012625592315297,
1534
+ "loss": 0.998,
1535
+ "step": 249
1536
+ },
1537
+ {
1538
+ "epoch": 0.34,
1539
+ "learning_rate": 0.00014974716934253147,
1540
+ "loss": 0.9713,
1541
+ "step": 250
1542
+ },
1543
+ {
1544
+ "epoch": 0.34,
1545
+ "learning_rate": 0.00014936713036377102,
1546
+ "loss": 1.0032,
1547
+ "step": 251
1548
+ },
1549
+ {
1550
+ "epoch": 0.35,
1551
+ "learning_rate": 0.00014898614626263066,
1552
+ "loss": 1.049,
1553
+ "step": 252
1554
+ },
1555
+ {
1556
+ "epoch": 0.35,
1557
+ "learning_rate": 0.00014860422433296363,
1558
+ "loss": 1.002,
1559
+ "step": 253
1560
+ },
1561
+ {
1562
+ "epoch": 0.35,
1563
+ "learning_rate": 0.00014822137188657752,
1564
+ "loss": 0.9839,
1565
+ "step": 254
1566
+ },
1567
+ {
1568
+ "epoch": 0.35,
1569
+ "learning_rate": 0.00014783759625309453,
1570
+ "loss": 0.9655,
1571
+ "step": 255
1572
+ },
1573
+ {
1574
+ "epoch": 0.35,
1575
+ "learning_rate": 0.0001474529047798112,
1576
+ "loss": 0.9989,
1577
+ "step": 256
1578
+ },
1579
+ {
1580
+ "epoch": 0.35,
1581
+ "learning_rate": 0.00014706730483155737,
1582
+ "loss": 1.0357,
1583
+ "step": 257
1584
+ },
1585
+ {
1586
+ "epoch": 0.35,
1587
+ "learning_rate": 0.00014668080379055562,
1588
+ "loss": 1.0034,
1589
+ "step": 258
1590
+ },
1591
+ {
1592
+ "epoch": 0.36,
1593
+ "learning_rate": 0.00014629340905627963,
1594
+ "loss": 1.057,
1595
+ "step": 259
1596
+ },
1597
+ {
1598
+ "epoch": 0.36,
1599
+ "learning_rate": 0.0001459051280453127,
1600
+ "loss": 1.0433,
1601
+ "step": 260
1602
+ },
1603
+ {
1604
+ "epoch": 0.36,
1605
+ "learning_rate": 0.00014551596819120563,
1606
+ "loss": 1.0533,
1607
+ "step": 261
1608
+ },
1609
+ {
1610
+ "epoch": 0.36,
1611
+ "learning_rate": 0.00014512593694433453,
1612
+ "loss": 1.0171,
1613
+ "step": 262
1614
+ },
1615
+ {
1616
+ "epoch": 0.36,
1617
+ "learning_rate": 0.0001447350417717581,
1618
+ "loss": 1.0624,
1619
+ "step": 263
1620
+ },
1621
+ {
1622
+ "epoch": 0.36,
1623
+ "learning_rate": 0.00014434329015707467,
1624
+ "loss": 1.0048,
1625
+ "step": 264
1626
+ },
1627
+ {
1628
+ "epoch": 0.36,
1629
+ "learning_rate": 0.000143950689600279,
1630
+ "loss": 0.9818,
1631
+ "step": 265
1632
+ },
1633
+ {
1634
+ "epoch": 0.37,
1635
+ "learning_rate": 0.0001435572476176187,
1636
+ "loss": 0.9939,
1637
+ "step": 266
1638
+ },
1639
+ {
1640
+ "epoch": 0.37,
1641
+ "learning_rate": 0.00014316297174145017,
1642
+ "loss": 1.0682,
1643
+ "step": 267
1644
+ },
1645
+ {
1646
+ "epoch": 0.37,
1647
+ "learning_rate": 0.00014276786952009451,
1648
+ "loss": 1.0418,
1649
+ "step": 268
1650
+ },
1651
+ {
1652
+ "epoch": 0.37,
1653
+ "learning_rate": 0.00014237194851769318,
1654
+ "loss": 0.9997,
1655
+ "step": 269
1656
+ },
1657
+ {
1658
+ "epoch": 0.37,
1659
+ "learning_rate": 0.0001419752163140628,
1660
+ "loss": 0.9738,
1661
+ "step": 270
1662
+ },
1663
+ {
1664
+ "epoch": 0.37,
1665
+ "learning_rate": 0.00014157768050455038,
1666
+ "loss": 0.9472,
1667
+ "step": 271
1668
+ },
1669
+ {
1670
+ "epoch": 0.37,
1671
+ "learning_rate": 0.00014117934869988777,
1672
+ "loss": 1.015,
1673
+ "step": 272
1674
+ },
1675
+ {
1676
+ "epoch": 0.38,
1677
+ "learning_rate": 0.00014078022852604592,
1678
+ "loss": 0.9248,
1679
+ "step": 273
1680
+ },
1681
+ {
1682
+ "epoch": 0.38,
1683
+ "learning_rate": 0.00014038032762408897,
1684
+ "loss": 1.0097,
1685
+ "step": 274
1686
+ },
1687
+ {
1688
+ "epoch": 0.38,
1689
+ "learning_rate": 0.00013997965365002789,
1690
+ "loss": 1.0222,
1691
+ "step": 275
1692
+ },
1693
+ {
1694
+ "epoch": 0.38,
1695
+ "learning_rate": 0.00013957821427467392,
1696
+ "loss": 1.0065,
1697
+ "step": 276
1698
+ },
1699
+ {
1700
+ "epoch": 0.38,
1701
+ "learning_rate": 0.00013917601718349182,
1702
+ "loss": 0.9966,
1703
+ "step": 277
1704
+ },
1705
+ {
1706
+ "epoch": 0.38,
1707
+ "learning_rate": 0.00013877307007645256,
1708
+ "loss": 0.9886,
1709
+ "step": 278
1710
+ },
1711
+ {
1712
+ "epoch": 0.38,
1713
+ "learning_rate": 0.000138369380667886,
1714
+ "loss": 0.9562,
1715
+ "step": 279
1716
+ },
1717
+ {
1718
+ "epoch": 0.38,
1719
+ "learning_rate": 0.00013796495668633326,
1720
+ "loss": 0.9743,
1721
+ "step": 280
1722
+ },
1723
+ {
1724
+ "epoch": 0.39,
1725
+ "learning_rate": 0.00013755980587439856,
1726
+ "loss": 1.0166,
1727
+ "step": 281
1728
+ },
1729
+ {
1730
+ "epoch": 0.39,
1731
+ "learning_rate": 0.0001371539359886013,
1732
+ "loss": 0.9972,
1733
+ "step": 282
1734
+ },
1735
+ {
1736
+ "epoch": 0.39,
1737
+ "learning_rate": 0.0001367473547992272,
1738
+ "loss": 1.0211,
1739
+ "step": 283
1740
+ },
1741
+ {
1742
+ "epoch": 0.39,
1743
+ "learning_rate": 0.00013634007009017985,
1744
+ "loss": 1.0183,
1745
+ "step": 284
1746
+ },
1747
+ {
1748
+ "epoch": 0.39,
1749
+ "learning_rate": 0.00013593208965883156,
1750
+ "loss": 1.0951,
1751
+ "step": 285
1752
+ },
1753
+ {
1754
+ "epoch": 0.39,
1755
+ "learning_rate": 0.00013552342131587398,
1756
+ "loss": 0.9398,
1757
+ "step": 286
1758
+ },
1759
+ {
1760
+ "epoch": 0.39,
1761
+ "learning_rate": 0.0001351140728851688,
1762
+ "loss": 0.9839,
1763
+ "step": 287
1764
+ },
1765
+ {
1766
+ "epoch": 0.4,
1767
+ "learning_rate": 0.00013470405220359773,
1768
+ "loss": 1.013,
1769
+ "step": 288
1770
+ },
1771
+ {
1772
+ "epoch": 0.4,
1773
+ "learning_rate": 0.0001342933671209126,
1774
+ "loss": 1.0354,
1775
+ "step": 289
1776
+ },
1777
+ {
1778
+ "epoch": 0.4,
1779
+ "learning_rate": 0.00013388202549958507,
1780
+ "loss": 0.9477,
1781
+ "step": 290
1782
+ },
1783
+ {
1784
+ "epoch": 0.4,
1785
+ "learning_rate": 0.0001334700352146561,
1786
+ "loss": 1.0727,
1787
+ "step": 291
1788
+ },
1789
+ {
1790
+ "epoch": 0.4,
1791
+ "learning_rate": 0.00013305740415358504,
1792
+ "loss": 1.0444,
1793
+ "step": 292
1794
+ },
1795
+ {
1796
+ "epoch": 0.4,
1797
+ "eval_loss": 1.0057971477508545,
1798
+ "eval_runtime": 100.9413,
1799
+ "eval_samples_per_second": 25.767,
1800
+ "eval_steps_per_second": 25.767,
1801
+ "step": 292
1802
+ },
1803
+ {
1804
+ "epoch": 0.4,
1805
+ "learning_rate": 0.000132644140216099,
1806
+ "loss": 1.0494,
1807
+ "step": 293
1808
+ },
1809
+ {
1810
+ "epoch": 0.4,
1811
+ "learning_rate": 0.00013223025131404106,
1812
+ "loss": 0.9747,
1813
+ "step": 294
1814
+ },
1815
+ {
1816
+ "epoch": 0.41,
1817
+ "learning_rate": 0.00013181574537121933,
1818
+ "loss": 1.0492,
1819
+ "step": 295
1820
+ },
1821
+ {
1822
+ "epoch": 0.41,
1823
+ "learning_rate": 0.0001314006303232549,
1824
+ "loss": 1.0598,
1825
+ "step": 296
1826
+ },
1827
+ {
1828
+ "epoch": 0.41,
1829
+ "learning_rate": 0.00013098491411743014,
1830
+ "loss": 1.0176,
1831
+ "step": 297
1832
+ },
1833
+ {
1834
+ "epoch": 0.41,
1835
+ "learning_rate": 0.00013056860471253638,
1836
+ "loss": 0.9767,
1837
+ "step": 298
1838
+ },
1839
+ {
1840
+ "epoch": 0.41,
1841
+ "learning_rate": 0.0001301517100787216,
1842
+ "loss": 1.0456,
1843
+ "step": 299
1844
+ },
1845
+ {
1846
+ "epoch": 0.41,
1847
+ "learning_rate": 0.0001297342381973379,
1848
+ "loss": 1.0599,
1849
+ "step": 300
1850
+ },
1851
+ {
1852
+ "epoch": 0.41,
1853
+ "learning_rate": 0.00012931619706078862,
1854
+ "loss": 1.1931,
1855
+ "step": 301
1856
+ },
1857
+ {
1858
+ "epoch": 0.41,
1859
+ "learning_rate": 0.00012889759467237533,
1860
+ "loss": 0.9616,
1861
+ "step": 302
1862
+ },
1863
+ {
1864
+ "epoch": 0.42,
1865
+ "learning_rate": 0.00012847843904614475,
1866
+ "loss": 1.0623,
1867
+ "step": 303
1868
+ },
1869
+ {
1870
+ "epoch": 0.42,
1871
+ "learning_rate": 0.0001280587382067351,
1872
+ "loss": 1.3584,
1873
+ "step": 304
1874
+ },
1875
+ {
1876
+ "epoch": 0.42,
1877
+ "learning_rate": 0.00012763850018922257,
1878
+ "loss": 1.0544,
1879
+ "step": 305
1880
+ },
1881
+ {
1882
+ "epoch": 0.42,
1883
+ "learning_rate": 0.00012721773303896763,
1884
+ "loss": 0.9356,
1885
+ "step": 306
1886
+ },
1887
+ {
1888
+ "epoch": 0.42,
1889
+ "learning_rate": 0.00012679644481146081,
1890
+ "loss": 1.0383,
1891
+ "step": 307
1892
+ },
1893
+ {
1894
+ "epoch": 0.42,
1895
+ "learning_rate": 0.00012637464357216846,
1896
+ "loss": 1.0767,
1897
+ "step": 308
1898
+ },
1899
+ {
1900
+ "epoch": 0.42,
1901
+ "learning_rate": 0.0001259523373963785,
1902
+ "loss": 0.9915,
1903
+ "step": 309
1904
+ },
1905
+ {
1906
+ "epoch": 0.43,
1907
+ "learning_rate": 0.00012552953436904577,
1908
+ "loss": 1.0185,
1909
+ "step": 310
1910
+ },
1911
+ {
1912
+ "epoch": 0.43,
1913
+ "learning_rate": 0.00012510624258463718,
1914
+ "loss": 1.0892,
1915
+ "step": 311
1916
+ },
1917
+ {
1918
+ "epoch": 0.43,
1919
+ "learning_rate": 0.0001246824701469768,
1920
+ "loss": 0.9911,
1921
+ "step": 312
1922
+ },
1923
+ {
1924
+ "epoch": 0.43,
1925
+ "learning_rate": 0.00012425822516909065,
1926
+ "loss": 1.0903,
1927
+ "step": 313
1928
+ },
1929
+ {
1930
+ "epoch": 0.43,
1931
+ "learning_rate": 0.00012383351577305147,
1932
+ "loss": 1.009,
1933
+ "step": 314
1934
+ },
1935
+ {
1936
+ "epoch": 0.43,
1937
+ "learning_rate": 0.00012340835008982313,
1938
+ "loss": 0.9667,
1939
+ "step": 315
1940
+ },
1941
+ {
1942
+ "epoch": 0.43,
1943
+ "learning_rate": 0.0001229827362591051,
1944
+ "loss": 0.9867,
1945
+ "step": 316
1946
+ },
1947
+ {
1948
+ "epoch": 0.44,
1949
+ "learning_rate": 0.0001225566824291765,
1950
+ "loss": 1.0415,
1951
+ "step": 317
1952
+ },
1953
+ {
1954
+ "epoch": 0.44,
1955
+ "learning_rate": 0.00012213019675674008,
1956
+ "loss": 1.0223,
1957
+ "step": 318
1958
+ },
1959
+ {
1960
+ "epoch": 0.44,
1961
+ "learning_rate": 0.00012170328740676613,
1962
+ "loss": 0.9171,
1963
+ "step": 319
1964
+ },
1965
+ {
1966
+ "epoch": 0.44,
1967
+ "learning_rate": 0.00012127596255233622,
1968
+ "loss": 0.942,
1969
+ "step": 320
1970
+ },
1971
+ {
1972
+ "epoch": 0.44,
1973
+ "learning_rate": 0.00012084823037448654,
1974
+ "loss": 1.5578,
1975
+ "step": 321
1976
+ },
1977
+ {
1978
+ "epoch": 0.44,
1979
+ "learning_rate": 0.00012042009906205152,
1980
+ "loss": 1.0146,
1981
+ "step": 322
1982
+ },
1983
+ {
1984
+ "epoch": 0.44,
1985
+ "learning_rate": 0.00011999157681150684,
1986
+ "loss": 1.0,
1987
+ "step": 323
1988
+ },
1989
+ {
1990
+ "epoch": 0.45,
1991
+ "learning_rate": 0.00011956267182681264,
1992
+ "loss": 0.9967,
1993
+ "step": 324
1994
+ },
1995
+ {
1996
+ "epoch": 0.45,
1997
+ "learning_rate": 0.00011913339231925643,
1998
+ "loss": 1.0059,
1999
+ "step": 325
2000
+ },
2001
+ {
2002
+ "epoch": 0.45,
2003
+ "learning_rate": 0.0001187037465072958,
2004
+ "loss": 1.0728,
2005
+ "step": 326
2006
+ },
2007
+ {
2008
+ "epoch": 0.45,
2009
+ "learning_rate": 0.00011827374261640127,
2010
+ "loss": 1.0387,
2011
+ "step": 327
2012
+ },
2013
+ {
2014
+ "epoch": 0.45,
2015
+ "learning_rate": 0.00011784338887889858,
2016
+ "loss": 0.9076,
2017
+ "step": 328
2018
+ },
2019
+ {
2020
+ "epoch": 0.45,
2021
+ "learning_rate": 0.00011741269353381128,
2022
+ "loss": 1.091,
2023
+ "step": 329
2024
+ },
2025
+ {
2026
+ "epoch": 0.45,
2027
+ "learning_rate": 0.00011698166482670292,
2028
+ "loss": 0.9802,
2029
+ "step": 330
2030
+ },
2031
+ {
2032
+ "epoch": 0.45,
2033
+ "learning_rate": 0.0001165503110095191,
2034
+ "loss": 0.9754,
2035
+ "step": 331
2036
+ },
2037
+ {
2038
+ "epoch": 0.46,
2039
+ "learning_rate": 0.00011611864034042972,
2040
+ "loss": 1.0418,
2041
+ "step": 332
2042
+ },
2043
+ {
2044
+ "epoch": 0.46,
2045
+ "learning_rate": 0.00011568666108367065,
2046
+ "loss": 1.0417,
2047
+ "step": 333
2048
+ },
2049
+ {
2050
+ "epoch": 0.46,
2051
+ "learning_rate": 0.00011525438150938554,
2052
+ "loss": 1.067,
2053
+ "step": 334
2054
+ },
2055
+ {
2056
+ "epoch": 0.46,
2057
+ "learning_rate": 0.00011482180989346771,
2058
+ "loss": 1.0691,
2059
+ "step": 335
2060
+ },
2061
+ {
2062
+ "epoch": 0.46,
2063
+ "learning_rate": 0.00011438895451740142,
2064
+ "loss": 0.9444,
2065
+ "step": 336
2066
+ },
2067
+ {
2068
+ "epoch": 0.46,
2069
+ "learning_rate": 0.00011395582366810346,
2070
+ "loss": 1.0091,
2071
+ "step": 337
2072
+ },
2073
+ {
2074
+ "epoch": 0.46,
2075
+ "learning_rate": 0.0001135224256377646,
2076
+ "loss": 0.9904,
2077
+ "step": 338
2078
+ },
2079
+ {
2080
+ "epoch": 0.47,
2081
+ "learning_rate": 0.0001130887687236906,
2082
+ "loss": 0.9653,
2083
+ "step": 339
2084
+ },
2085
+ {
2086
+ "epoch": 0.47,
2087
+ "learning_rate": 0.00011265486122814359,
2088
+ "loss": 1.0356,
2089
+ "step": 340
2090
+ },
2091
+ {
2092
+ "epoch": 0.47,
2093
+ "learning_rate": 0.00011222071145818294,
2094
+ "loss": 0.9989,
2095
+ "step": 341
2096
+ },
2097
+ {
2098
+ "epoch": 0.47,
2099
+ "learning_rate": 0.00011178632772550635,
2100
+ "loss": 0.8506,
2101
+ "step": 342
2102
+ },
2103
+ {
2104
+ "epoch": 0.47,
2105
+ "learning_rate": 0.00011135171834629071,
2106
+ "loss": 1.0392,
2107
+ "step": 343
2108
+ },
2109
+ {
2110
+ "epoch": 0.47,
2111
+ "learning_rate": 0.00011091689164103281,
2112
+ "loss": 1.0395,
2113
+ "step": 344
2114
+ },
2115
+ {
2116
+ "epoch": 0.47,
2117
+ "learning_rate": 0.00011048185593439014,
2118
+ "loss": 0.9951,
2119
+ "step": 345
2120
+ },
2121
+ {
2122
+ "epoch": 0.48,
2123
+ "learning_rate": 0.00011004661955502142,
2124
+ "loss": 1.0261,
2125
+ "step": 346
2126
+ },
2127
+ {
2128
+ "epoch": 0.48,
2129
+ "learning_rate": 0.00010961119083542726,
2130
+ "loss": 0.9471,
2131
+ "step": 347
2132
+ },
2133
+ {
2134
+ "epoch": 0.48,
2135
+ "learning_rate": 0.00010917557811179056,
2136
+ "loss": 0.9406,
2137
+ "step": 348
2138
+ },
2139
+ {
2140
+ "epoch": 0.48,
2141
+ "learning_rate": 0.0001087397897238169,
2142
+ "loss": 1.0012,
2143
+ "step": 349
2144
+ },
2145
+ {
2146
+ "epoch": 0.48,
2147
+ "learning_rate": 0.00010830383401457498,
2148
+ "loss": 0.9658,
2149
+ "step": 350
2150
+ },
2151
+ {
2152
+ "epoch": 0.48,
2153
+ "learning_rate": 0.00010786771933033677,
2154
+ "loss": 0.9748,
2155
+ "step": 351
2156
+ },
2157
+ {
2158
+ "epoch": 0.48,
2159
+ "learning_rate": 0.00010743145402041781,
2160
+ "loss": 0.9379,
2161
+ "step": 352
2162
+ },
2163
+ {
2164
+ "epoch": 0.48,
2165
+ "learning_rate": 0.00010699504643701732,
2166
+ "loss": 1.0641,
2167
+ "step": 353
2168
+ },
2169
+ {
2170
+ "epoch": 0.49,
2171
+ "learning_rate": 0.00010655850493505834,
2172
+ "loss": 0.9371,
2173
+ "step": 354
2174
+ },
2175
+ {
2176
+ "epoch": 0.49,
2177
+ "learning_rate": 0.00010612183787202767,
2178
+ "loss": 1.0629,
2179
+ "step": 355
2180
+ },
2181
+ {
2182
+ "epoch": 0.49,
2183
+ "learning_rate": 0.00010568505360781606,
2184
+ "loss": 0.995,
2185
+ "step": 356
2186
+ },
2187
+ {
2188
+ "epoch": 0.49,
2189
+ "learning_rate": 0.00010524816050455801,
2190
+ "loss": 0.9778,
2191
+ "step": 357
2192
+ },
2193
+ {
2194
+ "epoch": 0.49,
2195
+ "learning_rate": 0.00010481116692647164,
2196
+ "loss": 1.0197,
2197
+ "step": 358
2198
+ },
2199
+ {
2200
+ "epoch": 0.49,
2201
+ "learning_rate": 0.00010437408123969877,
2202
+ "loss": 1.1073,
2203
+ "step": 359
2204
+ },
2205
+ {
2206
+ "epoch": 0.49,
2207
+ "learning_rate": 0.0001039369118121445,
2208
+ "loss": 1.0282,
2209
+ "step": 360
2210
+ },
2211
+ {
2212
+ "epoch": 0.5,
2213
+ "learning_rate": 0.00010349966701331721,
2214
+ "loss": 0.9491,
2215
+ "step": 361
2216
+ },
2217
+ {
2218
+ "epoch": 0.5,
2219
+ "learning_rate": 0.0001030623552141682,
2220
+ "loss": 0.9811,
2221
+ "step": 362
2222
+ },
2223
+ {
2224
+ "epoch": 0.5,
2225
+ "learning_rate": 0.00010262498478693147,
2226
+ "loss": 0.9036,
2227
+ "step": 363
2228
+ },
2229
+ {
2230
+ "epoch": 0.5,
2231
+ "learning_rate": 0.00010218756410496354,
2232
+ "loss": 0.9629,
2233
+ "step": 364
2234
+ },
2235
+ {
2236
+ "epoch": 0.5,
2237
+ "learning_rate": 0.00010175010154258289,
2238
+ "loss": 0.9859,
2239
+ "step": 365
2240
+ },
2241
+ {
2242
+ "epoch": 0.5,
2243
+ "eval_loss": 0.9903626441955566,
2244
+ "eval_runtime": 101.0064,
2245
+ "eval_samples_per_second": 25.751,
2246
+ "eval_steps_per_second": 25.751,
2247
+ "step": 365
2248
+ },
2249
+ {
2250
+ "epoch": 0.5,
2251
+ "learning_rate": 0.00010131260547490991,
2252
+ "loss": 0.9933,
2253
+ "step": 366
2254
+ },
2255
+ {
2256
+ "epoch": 0.5,
2257
+ "learning_rate": 0.00010087508427770638,
2258
+ "loss": 0.9796,
2259
+ "step": 367
2260
+ },
2261
+ {
2262
+ "epoch": 0.51,
2263
+ "learning_rate": 0.00010043754632721518,
2264
+ "loss": 0.9695,
2265
+ "step": 368
2266
+ },
2267
+ {
2268
+ "epoch": 0.51,
2269
+ "learning_rate": 0.0001,
2270
+ "loss": 0.9768,
2271
+ "step": 369
2272
+ },
2273
+ {
2274
+ "epoch": 0.51,
2275
+ "learning_rate": 9.956245367278482e-05,
2276
+ "loss": 0.9649,
2277
+ "step": 370
2278
+ },
2279
+ {
2280
+ "epoch": 0.51,
2281
+ "learning_rate": 9.912491572229367e-05,
2282
+ "loss": 0.9816,
2283
+ "step": 371
2284
+ },
2285
+ {
2286
+ "epoch": 0.51,
2287
+ "learning_rate": 9.868739452509011e-05,
2288
+ "loss": 1.0418,
2289
+ "step": 372
2290
+ },
2291
+ {
2292
+ "epoch": 0.51,
2293
+ "learning_rate": 9.824989845741713e-05,
2294
+ "loss": 0.9845,
2295
+ "step": 373
2296
+ },
2297
+ {
2298
+ "epoch": 0.51,
2299
+ "learning_rate": 9.781243589503649e-05,
2300
+ "loss": 0.9785,
2301
+ "step": 374
2302
+ },
2303
+ {
2304
+ "epoch": 0.52,
2305
+ "learning_rate": 9.737501521306854e-05,
2306
+ "loss": 1.0384,
2307
+ "step": 375
2308
+ },
2309
+ {
2310
+ "epoch": 0.52,
2311
+ "learning_rate": 9.693764478583185e-05,
2312
+ "loss": 0.967,
2313
+ "step": 376
2314
+ },
2315
+ {
2316
+ "epoch": 0.52,
2317
+ "learning_rate": 9.65003329866828e-05,
2318
+ "loss": 1.0646,
2319
+ "step": 377
2320
+ },
2321
+ {
2322
+ "epoch": 0.52,
2323
+ "learning_rate": 9.606308818785551e-05,
2324
+ "loss": 1.0834,
2325
+ "step": 378
2326
+ },
2327
+ {
2328
+ "epoch": 0.52,
2329
+ "learning_rate": 9.562591876030127e-05,
2330
+ "loss": 0.9736,
2331
+ "step": 379
2332
+ },
2333
+ {
2334
+ "epoch": 0.52,
2335
+ "learning_rate": 9.518883307352839e-05,
2336
+ "loss": 0.9935,
2337
+ "step": 380
2338
+ },
2339
+ {
2340
+ "epoch": 0.52,
2341
+ "learning_rate": 9.475183949544204e-05,
2342
+ "loss": 0.9923,
2343
+ "step": 381
2344
+ },
2345
+ {
2346
+ "epoch": 0.52,
2347
+ "learning_rate": 9.431494639218397e-05,
2348
+ "loss": 0.9805,
2349
+ "step": 382
2350
+ },
2351
+ {
2352
+ "epoch": 0.53,
2353
+ "learning_rate": 9.387816212797233e-05,
2354
+ "loss": 1.0232,
2355
+ "step": 383
2356
+ },
2357
+ {
2358
+ "epoch": 0.53,
2359
+ "learning_rate": 9.344149506494168e-05,
2360
+ "loss": 0.9832,
2361
+ "step": 384
2362
+ },
2363
+ {
2364
+ "epoch": 0.53,
2365
+ "learning_rate": 9.300495356298269e-05,
2366
+ "loss": 1.0594,
2367
+ "step": 385
2368
+ },
2369
+ {
2370
+ "epoch": 0.53,
2371
+ "learning_rate": 9.256854597958221e-05,
2372
+ "loss": 1.0373,
2373
+ "step": 386
2374
+ },
2375
+ {
2376
+ "epoch": 0.53,
2377
+ "learning_rate": 9.213228066966327e-05,
2378
+ "loss": 0.9991,
2379
+ "step": 387
2380
+ },
2381
+ {
2382
+ "epoch": 0.53,
2383
+ "learning_rate": 9.169616598542503e-05,
2384
+ "loss": 1.0766,
2385
+ "step": 388
2386
+ },
2387
+ {
2388
+ "epoch": 0.53,
2389
+ "learning_rate": 9.126021027618311e-05,
2390
+ "loss": 1.0221,
2391
+ "step": 389
2392
+ },
2393
+ {
2394
+ "epoch": 0.54,
2395
+ "learning_rate": 9.082442188820946e-05,
2396
+ "loss": 1.1112,
2397
+ "step": 390
2398
+ },
2399
+ {
2400
+ "epoch": 0.54,
2401
+ "learning_rate": 9.038880916457276e-05,
2402
+ "loss": 0.9194,
2403
+ "step": 391
2404
+ },
2405
+ {
2406
+ "epoch": 0.54,
2407
+ "learning_rate": 8.99533804449786e-05,
2408
+ "loss": 1.0417,
2409
+ "step": 392
2410
+ },
2411
+ {
2412
+ "epoch": 0.54,
2413
+ "learning_rate": 8.951814406560987e-05,
2414
+ "loss": 1.003,
2415
+ "step": 393
2416
+ },
2417
+ {
2418
+ "epoch": 0.54,
2419
+ "learning_rate": 8.90831083589672e-05,
2420
+ "loss": 0.9771,
2421
+ "step": 394
2422
+ },
2423
+ {
2424
+ "epoch": 0.54,
2425
+ "learning_rate": 8.86482816537093e-05,
2426
+ "loss": 1.0317,
2427
+ "step": 395
2428
+ },
2429
+ {
2430
+ "epoch": 0.54,
2431
+ "learning_rate": 8.821367227449367e-05,
2432
+ "loss": 1.0092,
2433
+ "step": 396
2434
+ },
2435
+ {
2436
+ "epoch": 0.55,
2437
+ "learning_rate": 8.77792885418171e-05,
2438
+ "loss": 1.0435,
2439
+ "step": 397
2440
+ },
2441
+ {
2442
+ "epoch": 0.55,
2443
+ "learning_rate": 8.734513877185644e-05,
2444
+ "loss": 1.0095,
2445
+ "step": 398
2446
+ },
2447
+ {
2448
+ "epoch": 0.55,
2449
+ "learning_rate": 8.691123127630942e-05,
2450
+ "loss": 0.9569,
2451
+ "step": 399
2452
+ },
2453
+ {
2454
+ "epoch": 0.55,
2455
+ "learning_rate": 8.647757436223543e-05,
2456
+ "loss": 1.0973,
2457
+ "step": 400
2458
+ },
2459
+ {
2460
+ "epoch": 0.55,
2461
+ "learning_rate": 8.604417633189656e-05,
2462
+ "loss": 0.9935,
2463
+ "step": 401
2464
+ },
2465
+ {
2466
+ "epoch": 0.55,
2467
+ "learning_rate": 8.561104548259863e-05,
2468
+ "loss": 1.0229,
2469
+ "step": 402
2470
+ },
2471
+ {
2472
+ "epoch": 0.55,
2473
+ "learning_rate": 8.517819010653234e-05,
2474
+ "loss": 0.9657,
2475
+ "step": 403
2476
+ },
2477
+ {
2478
+ "epoch": 0.55,
2479
+ "learning_rate": 8.474561849061445e-05,
2480
+ "loss": 1.0713,
2481
+ "step": 404
2482
+ },
2483
+ {
2484
+ "epoch": 0.56,
2485
+ "learning_rate": 8.431333891632937e-05,
2486
+ "loss": 0.9502,
2487
+ "step": 405
2488
+ },
2489
+ {
2490
+ "epoch": 0.56,
2491
+ "learning_rate": 8.38813596595703e-05,
2492
+ "loss": 0.9417,
2493
+ "step": 406
2494
+ },
2495
+ {
2496
+ "epoch": 0.56,
2497
+ "learning_rate": 8.344968899048093e-05,
2498
+ "loss": 1.0023,
2499
+ "step": 407
2500
+ },
2501
+ {
2502
+ "epoch": 0.56,
2503
+ "learning_rate": 8.301833517329714e-05,
2504
+ "loss": 0.9944,
2505
+ "step": 408
2506
+ },
2507
+ {
2508
+ "epoch": 0.56,
2509
+ "learning_rate": 8.258730646618872e-05,
2510
+ "loss": 0.9596,
2511
+ "step": 409
2512
+ },
2513
+ {
2514
+ "epoch": 0.56,
2515
+ "learning_rate": 8.215661112110143e-05,
2516
+ "loss": 0.9718,
2517
+ "step": 410
2518
+ },
2519
+ {
2520
+ "epoch": 0.56,
2521
+ "learning_rate": 8.172625738359875e-05,
2522
+ "loss": 0.916,
2523
+ "step": 411
2524
+ },
2525
+ {
2526
+ "epoch": 0.57,
2527
+ "learning_rate": 8.12962534927042e-05,
2528
+ "loss": 1.1029,
2529
+ "step": 412
2530
+ },
2531
+ {
2532
+ "epoch": 0.57,
2533
+ "learning_rate": 8.086660768074358e-05,
2534
+ "loss": 0.9749,
2535
+ "step": 413
2536
+ },
2537
+ {
2538
+ "epoch": 0.57,
2539
+ "learning_rate": 8.043732817318736e-05,
2540
+ "loss": 1.0224,
2541
+ "step": 414
2542
+ },
2543
+ {
2544
+ "epoch": 0.57,
2545
+ "learning_rate": 8.000842318849317e-05,
2546
+ "loss": 0.9796,
2547
+ "step": 415
2548
+ },
2549
+ {
2550
+ "epoch": 0.57,
2551
+ "learning_rate": 7.957990093794849e-05,
2552
+ "loss": 0.9958,
2553
+ "step": 416
2554
+ },
2555
+ {
2556
+ "epoch": 0.57,
2557
+ "learning_rate": 7.915176962551347e-05,
2558
+ "loss": 1.0022,
2559
+ "step": 417
2560
+ },
2561
+ {
2562
+ "epoch": 0.57,
2563
+ "learning_rate": 7.872403744766383e-05,
2564
+ "loss": 0.9067,
2565
+ "step": 418
2566
+ },
2567
+ {
2568
+ "epoch": 0.58,
2569
+ "learning_rate": 7.82967125932339e-05,
2570
+ "loss": 1.0851,
2571
+ "step": 419
2572
+ },
2573
+ {
2574
+ "epoch": 0.58,
2575
+ "learning_rate": 7.786980324325995e-05,
2576
+ "loss": 1.006,
2577
+ "step": 420
2578
+ },
2579
+ {
2580
+ "epoch": 0.58,
2581
+ "learning_rate": 7.74433175708235e-05,
2582
+ "loss": 0.959,
2583
+ "step": 421
2584
+ },
2585
+ {
2586
+ "epoch": 0.58,
2587
+ "learning_rate": 7.70172637408949e-05,
2588
+ "loss": 0.9662,
2589
+ "step": 422
2590
+ },
2591
+ {
2592
+ "epoch": 0.58,
2593
+ "learning_rate": 7.659164991017689e-05,
2594
+ "loss": 0.9645,
2595
+ "step": 423
2596
+ },
2597
+ {
2598
+ "epoch": 0.58,
2599
+ "learning_rate": 7.616648422694858e-05,
2600
+ "loss": 0.9561,
2601
+ "step": 424
2602
+ },
2603
+ {
2604
+ "epoch": 0.58,
2605
+ "learning_rate": 7.574177483090937e-05,
2606
+ "loss": 0.9696,
2607
+ "step": 425
2608
+ },
2609
+ {
2610
+ "epoch": 0.59,
2611
+ "learning_rate": 7.531752985302323e-05,
2612
+ "loss": 1.0259,
2613
+ "step": 426
2614
+ },
2615
+ {
2616
+ "epoch": 0.59,
2617
+ "learning_rate": 7.489375741536283e-05,
2618
+ "loss": 1.049,
2619
+ "step": 427
2620
+ },
2621
+ {
2622
+ "epoch": 0.59,
2623
+ "learning_rate": 7.447046563095424e-05,
2624
+ "loss": 0.9997,
2625
+ "step": 428
2626
+ },
2627
+ {
2628
+ "epoch": 0.59,
2629
+ "learning_rate": 7.404766260362152e-05,
2630
+ "loss": 1.0851,
2631
+ "step": 429
2632
+ },
2633
+ {
2634
+ "epoch": 0.59,
2635
+ "learning_rate": 7.362535642783155e-05,
2636
+ "loss": 0.9559,
2637
+ "step": 430
2638
+ },
2639
+ {
2640
+ "epoch": 0.59,
2641
+ "learning_rate": 7.320355518853921e-05,
2642
+ "loss": 0.9315,
2643
+ "step": 431
2644
+ },
2645
+ {
2646
+ "epoch": 0.59,
2647
+ "learning_rate": 7.278226696103239e-05,
2648
+ "loss": 0.9169,
2649
+ "step": 432
2650
+ },
2651
+ {
2652
+ "epoch": 0.59,
2653
+ "learning_rate": 7.236149981077745e-05,
2654
+ "loss": 0.9385,
2655
+ "step": 433
2656
+ },
2657
+ {
2658
+ "epoch": 0.6,
2659
+ "learning_rate": 7.194126179326497e-05,
2660
+ "loss": 0.983,
2661
+ "step": 434
2662
+ },
2663
+ {
2664
+ "epoch": 0.6,
2665
+ "learning_rate": 7.152156095385527e-05,
2666
+ "loss": 0.9762,
2667
+ "step": 435
2668
+ },
2669
+ {
2670
+ "epoch": 0.6,
2671
+ "learning_rate": 7.110240532762469e-05,
2672
+ "loss": 0.9837,
2673
+ "step": 436
2674
+ },
2675
+ {
2676
+ "epoch": 0.6,
2677
+ "learning_rate": 7.068380293921142e-05,
2678
+ "loss": 0.9637,
2679
+ "step": 437
2680
+ },
2681
+ {
2682
+ "epoch": 0.6,
2683
+ "learning_rate": 7.026576180266214e-05,
2684
+ "loss": 0.9736,
2685
+ "step": 438
2686
+ },
2687
+ {
2688
+ "epoch": 0.6,
2689
+ "eval_loss": 0.975894570350647,
2690
+ "eval_runtime": 101.0013,
2691
+ "eval_samples_per_second": 25.752,
2692
+ "eval_steps_per_second": 25.752,
2693
+ "step": 438
2694
+ },
2695
+ {
2696
+ "epoch": 0.6,
2697
+ "learning_rate": 6.984828992127842e-05,
2698
+ "loss": 0.9429,
2699
+ "step": 439
2700
+ },
2701
+ {
2702
+ "epoch": 0.6,
2703
+ "learning_rate": 6.943139528746366e-05,
2704
+ "loss": 0.9894,
2705
+ "step": 440
2706
+ },
2707
+ {
2708
+ "epoch": 0.61,
2709
+ "learning_rate": 6.901508588256986e-05,
2710
+ "loss": 0.9412,
2711
+ "step": 441
2712
+ },
2713
+ {
2714
+ "epoch": 0.61,
2715
+ "learning_rate": 6.859936967674509e-05,
2716
+ "loss": 1.0248,
2717
+ "step": 442
2718
+ },
2719
+ {
2720
+ "epoch": 0.61,
2721
+ "learning_rate": 6.81842546287807e-05,
2722
+ "loss": 1.0098,
2723
+ "step": 443
2724
+ },
2725
+ {
2726
+ "epoch": 0.61,
2727
+ "learning_rate": 6.776974868595898e-05,
2728
+ "loss": 1.0222,
2729
+ "step": 444
2730
+ },
2731
+ {
2732
+ "epoch": 0.61,
2733
+ "learning_rate": 6.735585978390105e-05,
2734
+ "loss": 0.9272,
2735
+ "step": 445
2736
+ },
2737
+ {
2738
+ "epoch": 0.61,
2739
+ "learning_rate": 6.694259584641496e-05,
2740
+ "loss": 0.946,
2741
+ "step": 446
2742
+ },
2743
+ {
2744
+ "epoch": 0.61,
2745
+ "learning_rate": 6.652996478534394e-05,
2746
+ "loss": 0.9261,
2747
+ "step": 447
2748
+ },
2749
+ {
2750
+ "epoch": 0.62,
2751
+ "learning_rate": 6.611797450041495e-05,
2752
+ "loss": 0.9883,
2753
+ "step": 448
2754
+ },
2755
+ {
2756
+ "epoch": 0.62,
2757
+ "learning_rate": 6.570663287908743e-05,
2758
+ "loss": 0.9505,
2759
+ "step": 449
2760
+ },
2761
+ {
2762
+ "epoch": 0.62,
2763
+ "learning_rate": 6.52959477964023e-05,
2764
+ "loss": 0.9932,
2765
+ "step": 450
2766
+ },
2767
+ {
2768
+ "epoch": 0.62,
2769
+ "learning_rate": 6.488592711483121e-05,
2770
+ "loss": 0.957,
2771
+ "step": 451
2772
+ },
2773
+ {
2774
+ "epoch": 0.62,
2775
+ "learning_rate": 6.447657868412602e-05,
2776
+ "loss": 0.9795,
2777
+ "step": 452
2778
+ },
2779
+ {
2780
+ "epoch": 0.62,
2781
+ "learning_rate": 6.406791034116846e-05,
2782
+ "loss": 1.06,
2783
+ "step": 453
2784
+ },
2785
+ {
2786
+ "epoch": 0.62,
2787
+ "learning_rate": 6.365992990982015e-05,
2788
+ "loss": 0.9767,
2789
+ "step": 454
2790
+ },
2791
+ {
2792
+ "epoch": 0.62,
2793
+ "learning_rate": 6.325264520077284e-05,
2794
+ "loss": 1.0287,
2795
+ "step": 455
2796
+ },
2797
+ {
2798
+ "epoch": 0.63,
2799
+ "learning_rate": 6.284606401139875e-05,
2800
+ "loss": 0.9473,
2801
+ "step": 456
2802
+ },
2803
+ {
2804
+ "epoch": 0.63,
2805
+ "learning_rate": 6.244019412560144e-05,
2806
+ "loss": 0.939,
2807
+ "step": 457
2808
+ },
2809
+ {
2810
+ "epoch": 0.63,
2811
+ "learning_rate": 6.203504331366677e-05,
2812
+ "loss": 1.0363,
2813
+ "step": 458
2814
+ },
2815
+ {
2816
+ "epoch": 0.63,
2817
+ "learning_rate": 6.163061933211403e-05,
2818
+ "loss": 0.9632,
2819
+ "step": 459
2820
+ },
2821
+ {
2822
+ "epoch": 0.63,
2823
+ "learning_rate": 6.122692992354748e-05,
2824
+ "loss": 0.9918,
2825
+ "step": 460
2826
+ },
2827
+ {
2828
+ "epoch": 0.63,
2829
+ "learning_rate": 6.082398281650823e-05,
2830
+ "loss": 0.9616,
2831
+ "step": 461
2832
+ },
2833
+ {
2834
+ "epoch": 0.63,
2835
+ "learning_rate": 6.042178572532609e-05,
2836
+ "loss": 1.0805,
2837
+ "step": 462
2838
+ },
2839
+ {
2840
+ "epoch": 0.64,
2841
+ "learning_rate": 6.002034634997213e-05,
2842
+ "loss": 0.9973,
2843
+ "step": 463
2844
+ },
2845
+ {
2846
+ "epoch": 0.64,
2847
+ "learning_rate": 5.9619672375911065e-05,
2848
+ "loss": 0.9644,
2849
+ "step": 464
2850
+ },
2851
+ {
2852
+ "epoch": 0.64,
2853
+ "learning_rate": 5.92197714739541e-05,
2854
+ "loss": 1.0664,
2855
+ "step": 465
2856
+ },
2857
+ {
2858
+ "epoch": 0.64,
2859
+ "learning_rate": 5.882065130011226e-05,
2860
+ "loss": 1.0244,
2861
+ "step": 466
2862
+ },
2863
+ {
2864
+ "epoch": 0.64,
2865
+ "learning_rate": 5.842231949544963e-05,
2866
+ "loss": 0.936,
2867
+ "step": 467
2868
+ },
2869
+ {
2870
+ "epoch": 0.64,
2871
+ "learning_rate": 5.80247836859372e-05,
2872
+ "loss": 0.9931,
2873
+ "step": 468
2874
+ },
2875
+ {
2876
+ "epoch": 0.64,
2877
+ "learning_rate": 5.762805148230688e-05,
2878
+ "loss": 0.9209,
2879
+ "step": 469
2880
+ },
2881
+ {
2882
+ "epoch": 0.65,
2883
+ "learning_rate": 5.723213047990552e-05,
2884
+ "loss": 0.9705,
2885
+ "step": 470
2886
+ },
2887
+ {
2888
+ "epoch": 0.65,
2889
+ "learning_rate": 5.68370282585499e-05,
2890
+ "loss": 0.9686,
2891
+ "step": 471
2892
+ },
2893
+ {
2894
+ "epoch": 0.65,
2895
+ "learning_rate": 5.6442752382381304e-05,
2896
+ "loss": 1.0195,
2897
+ "step": 472
2898
+ },
2899
+ {
2900
+ "epoch": 0.65,
2901
+ "learning_rate": 5.604931039972099e-05,
2902
+ "loss": 0.9344,
2903
+ "step": 473
2904
+ },
2905
+ {
2906
+ "epoch": 0.65,
2907
+ "learning_rate": 5.5656709842925335e-05,
2908
+ "loss": 1.027,
2909
+ "step": 474
2910
+ },
2911
+ {
2912
+ "epoch": 0.65,
2913
+ "learning_rate": 5.5264958228241924e-05,
2914
+ "loss": 1.0071,
2915
+ "step": 475
2916
+ },
2917
+ {
2918
+ "epoch": 0.65,
2919
+ "learning_rate": 5.487406305566549e-05,
2920
+ "loss": 0.9905,
2921
+ "step": 476
2922
+ },
2923
+ {
2924
+ "epoch": 0.66,
2925
+ "learning_rate": 5.44840318087944e-05,
2926
+ "loss": 1.0166,
2927
+ "step": 477
2928
+ },
2929
+ {
2930
+ "epoch": 0.66,
2931
+ "learning_rate": 5.40948719546873e-05,
2932
+ "loss": 0.9618,
2933
+ "step": 478
2934
+ },
2935
+ {
2936
+ "epoch": 0.66,
2937
+ "learning_rate": 5.370659094372036e-05,
2938
+ "loss": 0.9899,
2939
+ "step": 479
2940
+ },
2941
+ {
2942
+ "epoch": 0.66,
2943
+ "learning_rate": 5.331919620944438e-05,
2944
+ "loss": 1.0144,
2945
+ "step": 480
2946
+ },
2947
+ {
2948
+ "epoch": 0.66,
2949
+ "learning_rate": 5.293269516844263e-05,
2950
+ "loss": 0.9504,
2951
+ "step": 481
2952
+ },
2953
+ {
2954
+ "epoch": 0.66,
2955
+ "learning_rate": 5.2547095220188813e-05,
2956
+ "loss": 0.9404,
2957
+ "step": 482
2958
+ },
2959
+ {
2960
+ "epoch": 0.66,
2961
+ "learning_rate": 5.216240374690546e-05,
2962
+ "loss": 0.93,
2963
+ "step": 483
2964
+ },
2965
+ {
2966
+ "epoch": 0.66,
2967
+ "learning_rate": 5.177862811342253e-05,
2968
+ "loss": 0.9123,
2969
+ "step": 484
2970
+ },
2971
+ {
2972
+ "epoch": 0.67,
2973
+ "learning_rate": 5.1395775667036425e-05,
2974
+ "loss": 0.9619,
2975
+ "step": 485
2976
+ },
2977
+ {
2978
+ "epoch": 0.67,
2979
+ "learning_rate": 5.101385373736937e-05,
2980
+ "loss": 0.9756,
2981
+ "step": 486
2982
+ },
2983
+ {
2984
+ "epoch": 0.67,
2985
+ "learning_rate": 5.063286963622903e-05,
2986
+ "loss": 1.0233,
2987
+ "step": 487
2988
+ },
2989
+ {
2990
+ "epoch": 0.67,
2991
+ "learning_rate": 5.0252830657468556e-05,
2992
+ "loss": 1.0056,
2993
+ "step": 488
2994
+ },
2995
+ {
2996
+ "epoch": 0.67,
2997
+ "learning_rate": 4.987374407684703e-05,
2998
+ "loss": 0.8683,
2999
+ "step": 489
3000
+ },
3001
+ {
3002
+ "epoch": 0.67,
3003
+ "learning_rate": 4.949561715189e-05,
3004
+ "loss": 0.985,
3005
+ "step": 490
3006
+ },
3007
+ {
3008
+ "epoch": 0.67,
3009
+ "learning_rate": 4.911845712175067e-05,
3010
+ "loss": 0.9676,
3011
+ "step": 491
3012
+ },
3013
+ {
3014
+ "epoch": 0.68,
3015
+ "learning_rate": 4.874227120707122e-05,
3016
+ "loss": 1.0728,
3017
+ "step": 492
3018
+ },
3019
+ {
3020
+ "epoch": 0.68,
3021
+ "learning_rate": 4.836706660984467e-05,
3022
+ "loss": 1.0571,
3023
+ "step": 493
3024
+ },
3025
+ {
3026
+ "epoch": 0.68,
3027
+ "learning_rate": 4.7992850513276856e-05,
3028
+ "loss": 0.9421,
3029
+ "step": 494
3030
+ },
3031
+ {
3032
+ "epoch": 0.68,
3033
+ "learning_rate": 4.761963008164918e-05,
3034
+ "loss": 0.9517,
3035
+ "step": 495
3036
+ },
3037
+ {
3038
+ "epoch": 0.68,
3039
+ "learning_rate": 4.724741246018103e-05,
3040
+ "loss": 0.9678,
3041
+ "step": 496
3042
+ },
3043
+ {
3044
+ "epoch": 0.68,
3045
+ "learning_rate": 4.6876204774893375e-05,
3046
+ "loss": 0.937,
3047
+ "step": 497
3048
+ },
3049
+ {
3050
+ "epoch": 0.68,
3051
+ "learning_rate": 4.650601413247214e-05,
3052
+ "loss": 0.999,
3053
+ "step": 498
3054
+ },
3055
+ {
3056
+ "epoch": 0.69,
3057
+ "learning_rate": 4.613684762013217e-05,
3058
+ "loss": 1.0274,
3059
+ "step": 499
3060
+ },
3061
+ {
3062
+ "epoch": 0.69,
3063
+ "learning_rate": 4.57687123054817e-05,
3064
+ "loss": 0.9941,
3065
+ "step": 500
3066
+ },
3067
+ {
3068
+ "epoch": 0.69,
3069
+ "learning_rate": 4.540161523638679e-05,
3070
+ "loss": 0.965,
3071
+ "step": 501
3072
+ },
3073
+ {
3074
+ "epoch": 0.69,
3075
+ "learning_rate": 4.503556344083656e-05,
3076
+ "loss": 1.0083,
3077
+ "step": 502
3078
+ },
3079
+ {
3080
+ "epoch": 0.69,
3081
+ "learning_rate": 4.467056392680863e-05,
3082
+ "loss": 0.9598,
3083
+ "step": 503
3084
+ },
3085
+ {
3086
+ "epoch": 0.69,
3087
+ "learning_rate": 4.4306623682134873e-05,
3088
+ "loss": 0.974,
3089
+ "step": 504
3090
+ },
3091
+ {
3092
+ "epoch": 0.69,
3093
+ "learning_rate": 4.394374967436783e-05,
3094
+ "loss": 0.999,
3095
+ "step": 505
3096
+ },
3097
+ {
3098
+ "epoch": 0.7,
3099
+ "learning_rate": 4.3581948850647035e-05,
3100
+ "loss": 1.007,
3101
+ "step": 506
3102
+ },
3103
+ {
3104
+ "epoch": 0.7,
3105
+ "learning_rate": 4.322122813756623e-05,
3106
+ "loss": 0.983,
3107
+ "step": 507
3108
+ },
3109
+ {
3110
+ "epoch": 0.7,
3111
+ "learning_rate": 4.286159444104068e-05,
3112
+ "loss": 1.0965,
3113
+ "step": 508
3114
+ },
3115
+ {
3116
+ "epoch": 0.7,
3117
+ "learning_rate": 4.250305464617493e-05,
3118
+ "loss": 1.0,
3119
+ "step": 509
3120
+ },
3121
+ {
3122
+ "epoch": 0.7,
3123
+ "learning_rate": 4.2145615617131095e-05,
3124
+ "loss": 0.9064,
3125
+ "step": 510
3126
+ },
3127
+ {
3128
+ "epoch": 0.7,
3129
+ "learning_rate": 4.178928419699731e-05,
3130
+ "loss": 1.0146,
3131
+ "step": 511
3132
+ },
3133
+ {
3134
+ "epoch": 0.7,
3135
+ "eval_loss": 0.9655330777168274,
3136
+ "eval_runtime": 100.6328,
3137
+ "eval_samples_per_second": 25.846,
3138
+ "eval_steps_per_second": 25.846,
3139
+ "step": 511
3140
+ },
3141
+ {
3142
+ "epoch": 0.7,
3143
+ "learning_rate": 4.143406720765687e-05,
3144
+ "loss": 0.9676,
3145
+ "step": 512
3146
+ },
3147
+ {
3148
+ "epoch": 0.7,
3149
+ "learning_rate": 4.1079971449657476e-05,
3150
+ "loss": 1.0074,
3151
+ "step": 513
3152
+ },
3153
+ {
3154
+ "epoch": 0.71,
3155
+ "learning_rate": 4.072700370208115e-05,
3156
+ "loss": 0.9525,
3157
+ "step": 514
3158
+ },
3159
+ {
3160
+ "epoch": 0.71,
3161
+ "learning_rate": 4.037517072241435e-05,
3162
+ "loss": 1.0037,
3163
+ "step": 515
3164
+ },
3165
+ {
3166
+ "epoch": 0.71,
3167
+ "learning_rate": 4.0024479246418824e-05,
3168
+ "loss": 0.9671,
3169
+ "step": 516
3170
+ },
3171
+ {
3172
+ "epoch": 0.71,
3173
+ "learning_rate": 3.967493598800233e-05,
3174
+ "loss": 0.9874,
3175
+ "step": 517
3176
+ },
3177
+ {
3178
+ "epoch": 0.71,
3179
+ "learning_rate": 3.9326547639090315e-05,
3180
+ "loss": 0.9814,
3181
+ "step": 518
3182
+ },
3183
+ {
3184
+ "epoch": 0.71,
3185
+ "learning_rate": 3.897932086949778e-05,
3186
+ "loss": 0.9689,
3187
+ "step": 519
3188
+ },
3189
+ {
3190
+ "epoch": 0.71,
3191
+ "learning_rate": 3.863326232680148e-05,
3192
+ "loss": 0.9731,
3193
+ "step": 520
3194
+ },
3195
+ {
3196
+ "epoch": 0.72,
3197
+ "learning_rate": 3.828837863621286e-05,
3198
+ "loss": 0.9203,
3199
+ "step": 521
3200
+ },
3201
+ {
3202
+ "epoch": 0.72,
3203
+ "learning_rate": 3.794467640045102e-05,
3204
+ "loss": 0.9985,
3205
+ "step": 522
3206
+ },
3207
+ {
3208
+ "epoch": 0.72,
3209
+ "learning_rate": 3.76021621996163e-05,
3210
+ "loss": 0.9216,
3211
+ "step": 523
3212
+ },
3213
+ {
3214
+ "epoch": 0.72,
3215
+ "learning_rate": 3.7260842591064506e-05,
3216
+ "loss": 0.9627,
3217
+ "step": 524
3218
+ },
3219
+ {
3220
+ "epoch": 0.72,
3221
+ "learning_rate": 3.692072410928115e-05,
3222
+ "loss": 0.9733,
3223
+ "step": 525
3224
+ },
3225
+ {
3226
+ "epoch": 0.72,
3227
+ "learning_rate": 3.658181326575659e-05,
3228
+ "loss": 1.0104,
3229
+ "step": 526
3230
+ },
3231
+ {
3232
+ "epoch": 0.72,
3233
+ "learning_rate": 3.6244116548861085e-05,
3234
+ "loss": 1.0045,
3235
+ "step": 527
3236
+ },
3237
+ {
3238
+ "epoch": 0.73,
3239
+ "learning_rate": 3.590764042372079e-05,
3240
+ "loss": 1.038,
3241
+ "step": 528
3242
+ },
3243
+ {
3244
+ "epoch": 0.73,
3245
+ "learning_rate": 3.557239133209387e-05,
3246
+ "loss": 0.9092,
3247
+ "step": 529
3248
+ },
3249
+ {
3250
+ "epoch": 0.73,
3251
+ "learning_rate": 3.523837569224725e-05,
3252
+ "loss": 1.0129,
3253
+ "step": 530
3254
+ },
3255
+ {
3256
+ "epoch": 0.73,
3257
+ "learning_rate": 3.4905599898833664e-05,
3258
+ "loss": 0.9692,
3259
+ "step": 531
3260
+ },
3261
+ {
3262
+ "epoch": 0.73,
3263
+ "learning_rate": 3.457407032276935e-05,
3264
+ "loss": 0.9549,
3265
+ "step": 532
3266
+ },
3267
+ {
3268
+ "epoch": 0.73,
3269
+ "learning_rate": 3.4243793311111915e-05,
3270
+ "loss": 0.9558,
3271
+ "step": 533
3272
+ },
3273
+ {
3274
+ "epoch": 0.73,
3275
+ "learning_rate": 3.391477518693894e-05,
3276
+ "loss": 0.9768,
3277
+ "step": 534
3278
+ },
3279
+ {
3280
+ "epoch": 0.73,
3281
+ "learning_rate": 3.3587022249226904e-05,
3282
+ "loss": 0.8994,
3283
+ "step": 535
3284
+ },
3285
+ {
3286
+ "epoch": 0.74,
3287
+ "learning_rate": 3.3260540772730574e-05,
3288
+ "loss": 0.9699,
3289
+ "step": 536
3290
+ },
3291
+ {
3292
+ "epoch": 0.74,
3293
+ "learning_rate": 3.293533700786287e-05,
3294
+ "loss": 0.9209,
3295
+ "step": 537
3296
+ },
3297
+ {
3298
+ "epoch": 0.74,
3299
+ "learning_rate": 3.261141718057523e-05,
3300
+ "loss": 0.9231,
3301
+ "step": 538
3302
+ },
3303
+ {
3304
+ "epoch": 0.74,
3305
+ "learning_rate": 3.228878749223842e-05,
3306
+ "loss": 1.0118,
3307
+ "step": 539
3308
+ },
3309
+ {
3310
+ "epoch": 0.74,
3311
+ "learning_rate": 3.1967454119523744e-05,
3312
+ "loss": 0.9045,
3313
+ "step": 540
3314
+ },
3315
+ {
3316
+ "epoch": 0.74,
3317
+ "learning_rate": 3.1647423214284856e-05,
3318
+ "loss": 0.977,
3319
+ "step": 541
3320
+ },
3321
+ {
3322
+ "epoch": 0.74,
3323
+ "learning_rate": 3.1328700903440046e-05,
3324
+ "loss": 0.9388,
3325
+ "step": 542
3326
+ },
3327
+ {
3328
+ "epoch": 0.75,
3329
+ "learning_rate": 3.101129328885475e-05,
3330
+ "loss": 0.9922,
3331
+ "step": 543
3332
+ },
3333
+ {
3334
+ "epoch": 0.75,
3335
+ "learning_rate": 3.069520644722492e-05,
3336
+ "loss": 0.9335,
3337
+ "step": 544
3338
+ },
3339
+ {
3340
+ "epoch": 0.75,
3341
+ "learning_rate": 3.0380446429960575e-05,
3342
+ "loss": 1.0245,
3343
+ "step": 545
3344
+ },
3345
+ {
3346
+ "epoch": 0.75,
3347
+ "learning_rate": 3.0067019263069972e-05,
3348
+ "loss": 0.993,
3349
+ "step": 546
3350
+ },
3351
+ {
3352
+ "epoch": 0.75,
3353
+ "learning_rate": 2.9754930947044357e-05,
3354
+ "loss": 0.8618,
3355
+ "step": 547
3356
+ },
3357
+ {
3358
+ "epoch": 0.75,
3359
+ "learning_rate": 2.9444187456742855e-05,
3360
+ "loss": 0.9096,
3361
+ "step": 548
3362
+ },
3363
+ {
3364
+ "epoch": 0.75,
3365
+ "learning_rate": 2.9134794741278313e-05,
3366
+ "loss": 0.9819,
3367
+ "step": 549
3368
+ },
3369
+ {
3370
+ "epoch": 0.76,
3371
+ "learning_rate": 2.882675872390319e-05,
3372
+ "loss": 0.962,
3373
+ "step": 550
3374
+ },
3375
+ {
3376
+ "epoch": 0.76,
3377
+ "learning_rate": 2.852008530189637e-05,
3378
+ "loss": 0.9914,
3379
+ "step": 551
3380
+ },
3381
+ {
3382
+ "epoch": 0.76,
3383
+ "learning_rate": 2.8214780346450087e-05,
3384
+ "loss": 0.9862,
3385
+ "step": 552
3386
+ },
3387
+ {
3388
+ "epoch": 0.76,
3389
+ "learning_rate": 2.7910849702557717e-05,
3390
+ "loss": 1.066,
3391
+ "step": 553
3392
+ },
3393
+ {
3394
+ "epoch": 0.76,
3395
+ "learning_rate": 2.760829918890163e-05,
3396
+ "loss": 1.0484,
3397
+ "step": 554
3398
+ },
3399
+ {
3400
+ "epoch": 0.76,
3401
+ "learning_rate": 2.730713459774198e-05,
3402
+ "loss": 1.0159,
3403
+ "step": 555
3404
+ },
3405
+ {
3406
+ "epoch": 0.76,
3407
+ "learning_rate": 2.7007361694805733e-05,
3408
+ "loss": 0.9873,
3409
+ "step": 556
3410
+ },
3411
+ {
3412
+ "epoch": 0.77,
3413
+ "learning_rate": 2.670898621917629e-05,
3414
+ "loss": 1.0003,
3415
+ "step": 557
3416
+ },
3417
+ {
3418
+ "epoch": 0.77,
3419
+ "learning_rate": 2.6412013883183696e-05,
3420
+ "loss": 1.0869,
3421
+ "step": 558
3422
+ },
3423
+ {
3424
+ "epoch": 0.77,
3425
+ "learning_rate": 2.6116450372295144e-05,
3426
+ "loss": 0.9017,
3427
+ "step": 559
3428
+ },
3429
+ {
3430
+ "epoch": 0.77,
3431
+ "learning_rate": 2.5822301345006194e-05,
3432
+ "loss": 0.9831,
3433
+ "step": 560
3434
+ },
3435
+ {
3436
+ "epoch": 0.77,
3437
+ "learning_rate": 2.5529572432732474e-05,
3438
+ "loss": 0.9623,
3439
+ "step": 561
3440
+ },
3441
+ {
3442
+ "epoch": 0.77,
3443
+ "learning_rate": 2.5238269239701817e-05,
3444
+ "loss": 0.9567,
3445
+ "step": 562
3446
+ },
3447
+ {
3448
+ "epoch": 0.77,
3449
+ "learning_rate": 2.4948397342846985e-05,
3450
+ "loss": 0.9567,
3451
+ "step": 563
3452
+ },
3453
+ {
3454
+ "epoch": 0.77,
3455
+ "learning_rate": 2.4659962291698933e-05,
3456
+ "loss": 1.0876,
3457
+ "step": 564
3458
+ },
3459
+ {
3460
+ "epoch": 0.78,
3461
+ "learning_rate": 2.4372969608280482e-05,
3462
+ "loss": 0.9415,
3463
+ "step": 565
3464
+ },
3465
+ {
3466
+ "epoch": 0.78,
3467
+ "learning_rate": 2.4087424787000712e-05,
3468
+ "loss": 0.9095,
3469
+ "step": 566
3470
+ },
3471
+ {
3472
+ "epoch": 0.78,
3473
+ "learning_rate": 2.3803333294549646e-05,
3474
+ "loss": 0.9058,
3475
+ "step": 567
3476
+ },
3477
+ {
3478
+ "epoch": 0.78,
3479
+ "learning_rate": 2.352070056979375e-05,
3480
+ "loss": 0.9369,
3481
+ "step": 568
3482
+ },
3483
+ {
3484
+ "epoch": 0.78,
3485
+ "learning_rate": 2.323953202367166e-05,
3486
+ "loss": 0.9434,
3487
+ "step": 569
3488
+ },
3489
+ {
3490
+ "epoch": 0.78,
3491
+ "learning_rate": 2.295983303909065e-05,
3492
+ "loss": 0.9202,
3493
+ "step": 570
3494
+ },
3495
+ {
3496
+ "epoch": 0.78,
3497
+ "learning_rate": 2.2681608970823565e-05,
3498
+ "loss": 0.9544,
3499
+ "step": 571
3500
+ },
3501
+ {
3502
+ "epoch": 0.79,
3503
+ "learning_rate": 2.2404865145406352e-05,
3504
+ "loss": 0.915,
3505
+ "step": 572
3506
+ },
3507
+ {
3508
+ "epoch": 0.79,
3509
+ "learning_rate": 2.2129606861036e-05,
3510
+ "loss": 1.1772,
3511
+ "step": 573
3512
+ },
3513
+ {
3514
+ "epoch": 0.79,
3515
+ "learning_rate": 2.1855839387469233e-05,
3516
+ "loss": 0.9928,
3517
+ "step": 574
3518
+ },
3519
+ {
3520
+ "epoch": 0.79,
3521
+ "learning_rate": 2.158356796592147e-05,
3522
+ "loss": 1.0181,
3523
+ "step": 575
3524
+ },
3525
+ {
3526
+ "epoch": 0.79,
3527
+ "learning_rate": 2.131279780896662e-05,
3528
+ "loss": 0.9607,
3529
+ "step": 576
3530
+ },
3531
+ {
3532
+ "epoch": 0.79,
3533
+ "learning_rate": 2.1043534100437124e-05,
3534
+ "loss": 0.9911,
3535
+ "step": 577
3536
+ },
3537
+ {
3538
+ "epoch": 0.79,
3539
+ "learning_rate": 2.0775781995324882e-05,
3540
+ "loss": 0.9796,
3541
+ "step": 578
3542
+ },
3543
+ {
3544
+ "epoch": 0.8,
3545
+ "learning_rate": 2.050954661968255e-05,
3546
+ "loss": 0.9599,
3547
+ "step": 579
3548
+ },
3549
+ {
3550
+ "epoch": 0.8,
3551
+ "learning_rate": 2.024483307052526e-05,
3552
+ "loss": 0.8578,
3553
+ "step": 580
3554
+ },
3555
+ {
3556
+ "epoch": 0.8,
3557
+ "learning_rate": 1.9981646415733157e-05,
3558
+ "loss": 0.9559,
3559
+ "step": 581
3560
+ },
3561
+ {
3562
+ "epoch": 0.8,
3563
+ "learning_rate": 1.971999169395432e-05,
3564
+ "loss": 1.0144,
3565
+ "step": 582
3566
+ },
3567
+ {
3568
+ "epoch": 0.8,
3569
+ "learning_rate": 1.945987391450833e-05,
3570
+ "loss": 0.9629,
3571
+ "step": 583
3572
+ },
3573
+ {
3574
+ "epoch": 0.8,
3575
+ "learning_rate": 1.920129805729043e-05,
3576
+ "loss": 1.0007,
3577
+ "step": 584
3578
+ },
3579
+ {
3580
+ "epoch": 0.8,
3581
+ "eval_loss": 0.9610365629196167,
3582
+ "eval_runtime": 100.6011,
3583
+ "eval_samples_per_second": 25.855,
3584
+ "eval_steps_per_second": 25.855,
3585
+ "step": 584
3586
+ },
3587
+ {
3588
+ "epoch": 0.8,
3589
+ "learning_rate": 1.8944269072676012e-05,
3590
+ "loss": 0.957,
3591
+ "step": 585
3592
+ },
3593
+ {
3594
+ "epoch": 0.8,
3595
+ "learning_rate": 1.8688791881426017e-05,
3596
+ "loss": 0.9362,
3597
+ "step": 586
3598
+ },
3599
+ {
3600
+ "epoch": 0.81,
3601
+ "learning_rate": 1.843487137459261e-05,
3602
+ "loss": 1.041,
3603
+ "step": 587
3604
+ },
3605
+ {
3606
+ "epoch": 0.81,
3607
+ "learning_rate": 1.8182512413425625e-05,
3608
+ "loss": 1.0088,
3609
+ "step": 588
3610
+ },
3611
+ {
3612
+ "epoch": 0.81,
3613
+ "learning_rate": 1.7931719829279447e-05,
3614
+ "loss": 0.9602,
3615
+ "step": 589
3616
+ },
3617
+ {
3618
+ "epoch": 0.81,
3619
+ "learning_rate": 1.7682498423520543e-05,
3620
+ "loss": 0.9594,
3621
+ "step": 590
3622
+ },
3623
+ {
3624
+ "epoch": 0.81,
3625
+ "learning_rate": 1.7434852967435523e-05,
3626
+ "loss": 0.9314,
3627
+ "step": 591
3628
+ },
3629
+ {
3630
+ "epoch": 0.81,
3631
+ "learning_rate": 1.7188788202139792e-05,
3632
+ "loss": 0.9603,
3633
+ "step": 592
3634
+ },
3635
+ {
3636
+ "epoch": 0.81,
3637
+ "learning_rate": 1.6944308838486824e-05,
3638
+ "loss": 0.9909,
3639
+ "step": 593
3640
+ },
3641
+ {
3642
+ "epoch": 0.82,
3643
+ "learning_rate": 1.6701419556977883e-05,
3644
+ "loss": 0.9654,
3645
+ "step": 594
3646
+ },
3647
+ {
3648
+ "epoch": 0.82,
3649
+ "learning_rate": 1.6460125007672557e-05,
3650
+ "loss": 0.9883,
3651
+ "step": 595
3652
+ },
3653
+ {
3654
+ "epoch": 0.82,
3655
+ "learning_rate": 1.62204298100996e-05,
3656
+ "loss": 0.9559,
3657
+ "step": 596
3658
+ },
3659
+ {
3660
+ "epoch": 0.82,
3661
+ "learning_rate": 1.5982338553168563e-05,
3662
+ "loss": 0.9818,
3663
+ "step": 597
3664
+ },
3665
+ {
3666
+ "epoch": 0.82,
3667
+ "learning_rate": 1.5745855795081887e-05,
3668
+ "loss": 0.9844,
3669
+ "step": 598
3670
+ },
3671
+ {
3672
+ "epoch": 0.82,
3673
+ "learning_rate": 1.551098606324768e-05,
3674
+ "loss": 0.9778,
3675
+ "step": 599
3676
+ },
3677
+ {
3678
+ "epoch": 0.82,
3679
+ "learning_rate": 1.527773385419311e-05,
3680
+ "loss": 1.0635,
3681
+ "step": 600
3682
+ },
3683
+ {
3684
+ "epoch": 0.83,
3685
+ "learning_rate": 1.5046103633478148e-05,
3686
+ "loss": 0.9414,
3687
+ "step": 601
3688
+ },
3689
+ {
3690
+ "epoch": 0.83,
3691
+ "learning_rate": 1.4816099835610209e-05,
3692
+ "loss": 1.0286,
3693
+ "step": 602
3694
+ },
3695
+ {
3696
+ "epoch": 0.83,
3697
+ "learning_rate": 1.458772686395924e-05,
3698
+ "loss": 0.9871,
3699
+ "step": 603
3700
+ },
3701
+ {
3702
+ "epoch": 0.83,
3703
+ "learning_rate": 1.4360989090673283e-05,
3704
+ "loss": 0.8671,
3705
+ "step": 604
3706
+ },
3707
+ {
3708
+ "epoch": 0.83,
3709
+ "learning_rate": 1.4135890856595047e-05,
3710
+ "loss": 1.0134,
3711
+ "step": 605
3712
+ },
3713
+ {
3714
+ "epoch": 0.83,
3715
+ "learning_rate": 1.3912436471178526e-05,
3716
+ "loss": 0.9856,
3717
+ "step": 606
3718
+ },
3719
+ {
3720
+ "epoch": 0.83,
3721
+ "learning_rate": 1.3690630212406652e-05,
3722
+ "loss": 0.9419,
3723
+ "step": 607
3724
+ },
3725
+ {
3726
+ "epoch": 0.84,
3727
+ "learning_rate": 1.3470476326709336e-05,
3728
+ "loss": 0.94,
3729
+ "step": 608
3730
+ },
3731
+ {
3732
+ "epoch": 0.84,
3733
+ "learning_rate": 1.3251979028882177e-05,
3734
+ "loss": 0.9072,
3735
+ "step": 609
3736
+ },
3737
+ {
3738
+ "epoch": 0.84,
3739
+ "learning_rate": 1.3035142502005792e-05,
3740
+ "loss": 0.9871,
3741
+ "step": 610
3742
+ },
3743
+ {
3744
+ "epoch": 0.84,
3745
+ "learning_rate": 1.2819970897365741e-05,
3746
+ "loss": 0.9056,
3747
+ "step": 611
3748
+ },
3749
+ {
3750
+ "epoch": 0.84,
3751
+ "learning_rate": 1.2606468334373001e-05,
3752
+ "loss": 0.9823,
3753
+ "step": 612
3754
+ },
3755
+ {
3756
+ "epoch": 0.84,
3757
+ "learning_rate": 1.2394638900485123e-05,
3758
+ "loss": 1.0043,
3759
+ "step": 613
3760
+ },
3761
+ {
3762
+ "epoch": 0.84,
3763
+ "learning_rate": 1.2184486651128013e-05,
3764
+ "loss": 0.9391,
3765
+ "step": 614
3766
+ },
3767
+ {
3768
+ "epoch": 0.84,
3769
+ "learning_rate": 1.1976015609618241e-05,
3770
+ "loss": 1.0195,
3771
+ "step": 615
3772
+ },
3773
+ {
3774
+ "epoch": 0.85,
3775
+ "learning_rate": 1.1769229767086054e-05,
3776
+ "loss": 0.9847,
3777
+ "step": 616
3778
+ },
3779
+ {
3780
+ "epoch": 0.85,
3781
+ "learning_rate": 1.1564133082398942e-05,
3782
+ "loss": 0.9316,
3783
+ "step": 617
3784
+ },
3785
+ {
3786
+ "epoch": 0.85,
3787
+ "learning_rate": 1.1360729482085853e-05,
3788
+ "loss": 0.9344,
3789
+ "step": 618
3790
+ },
3791
+ {
3792
+ "epoch": 0.85,
3793
+ "learning_rate": 1.1159022860262036e-05,
3794
+ "loss": 0.8938,
3795
+ "step": 619
3796
+ },
3797
+ {
3798
+ "epoch": 0.85,
3799
+ "learning_rate": 1.0959017078554457e-05,
3800
+ "loss": 0.8865,
3801
+ "step": 620
3802
+ },
3803
+ {
3804
+ "epoch": 0.85,
3805
+ "learning_rate": 1.0760715966027923e-05,
3806
+ "loss": 1.0635,
3807
+ "step": 621
3808
+ },
3809
+ {
3810
+ "epoch": 0.85,
3811
+ "learning_rate": 1.0564123319111706e-05,
3812
+ "loss": 0.9327,
3813
+ "step": 622
3814
+ },
3815
+ {
3816
+ "epoch": 0.86,
3817
+ "learning_rate": 1.036924290152691e-05,
3818
+ "loss": 0.9559,
3819
+ "step": 623
3820
+ },
3821
+ {
3822
+ "epoch": 0.86,
3823
+ "learning_rate": 1.017607844421441e-05,
3824
+ "loss": 1.0743,
3825
+ "step": 624
3826
+ },
3827
+ {
3828
+ "epoch": 0.86,
3829
+ "learning_rate": 9.984633645263387e-06,
3830
+ "loss": 1.0261,
3831
+ "step": 625
3832
+ },
3833
+ {
3834
+ "epoch": 0.86,
3835
+ "learning_rate": 9.794912169840565e-06,
3836
+ "loss": 0.924,
3837
+ "step": 626
3838
+ },
3839
+ {
3840
+ "epoch": 0.86,
3841
+ "learning_rate": 9.606917650120084e-06,
3842
+ "loss": 0.9706,
3843
+ "step": 627
3844
+ },
3845
+ {
3846
+ "epoch": 0.86,
3847
+ "learning_rate": 9.420653685213855e-06,
3848
+ "loss": 0.9602,
3849
+ "step": 628
3850
+ },
3851
+ {
3852
+ "epoch": 0.86,
3853
+ "learning_rate": 9.236123841102762e-06,
3854
+ "loss": 0.9436,
3855
+ "step": 629
3856
+ },
3857
+ {
3858
+ "epoch": 0.87,
3859
+ "learning_rate": 9.053331650568265e-06,
3860
+ "loss": 0.9206,
3861
+ "step": 630
3862
+ },
3863
+ {
3864
+ "epoch": 0.87,
3865
+ "learning_rate": 8.872280613124895e-06,
3866
+ "loss": 0.9499,
3867
+ "step": 631
3868
+ },
3869
+ {
3870
+ "epoch": 0.87,
3871
+ "learning_rate": 8.692974194953263e-06,
3872
+ "loss": 0.9697,
3873
+ "step": 632
3874
+ },
3875
+ {
3876
+ "epoch": 0.87,
3877
+ "learning_rate": 8.515415828833561e-06,
3878
+ "loss": 0.9782,
3879
+ "step": 633
3880
+ },
3881
+ {
3882
+ "epoch": 0.87,
3883
+ "learning_rate": 8.339608914079944e-06,
3884
+ "loss": 0.979,
3885
+ "step": 634
3886
+ },
3887
+ {
3888
+ "epoch": 0.87,
3889
+ "learning_rate": 8.165556816475461e-06,
3890
+ "loss": 1.0111,
3891
+ "step": 635
3892
+ },
3893
+ {
3894
+ "epoch": 0.87,
3895
+ "learning_rate": 7.993262868207552e-06,
3896
+ "loss": 0.8815,
3897
+ "step": 636
3898
+ },
3899
+ {
3900
+ "epoch": 0.88,
3901
+ "learning_rate": 7.822730367804333e-06,
3902
+ "loss": 0.9365,
3903
+ "step": 637
3904
+ },
3905
+ {
3906
+ "epoch": 0.88,
3907
+ "learning_rate": 7.653962580071384e-06,
3908
+ "loss": 0.8716,
3909
+ "step": 638
3910
+ },
3911
+ {
3912
+ "epoch": 0.88,
3913
+ "learning_rate": 7.486962736029246e-06,
3914
+ "loss": 1.0132,
3915
+ "step": 639
3916
+ },
3917
+ {
3918
+ "epoch": 0.88,
3919
+ "learning_rate": 7.321734032851612e-06,
3920
+ "loss": 1.0057,
3921
+ "step": 640
3922
+ },
3923
+ {
3924
+ "epoch": 0.88,
3925
+ "learning_rate": 7.158279633804077e-06,
3926
+ "loss": 0.9397,
3927
+ "step": 641
3928
+ },
3929
+ {
3930
+ "epoch": 0.88,
3931
+ "learning_rate": 6.996602668183605e-06,
3932
+ "loss": 1.0111,
3933
+ "step": 642
3934
+ },
3935
+ {
3936
+ "epoch": 0.88,
3937
+ "learning_rate": 6.836706231258583e-06,
3938
+ "loss": 1.0025,
3939
+ "step": 643
3940
+ },
3941
+ {
3942
+ "epoch": 0.88,
3943
+ "learning_rate": 6.678593384209597e-06,
3944
+ "loss": 0.9942,
3945
+ "step": 644
3946
+ },
3947
+ {
3948
+ "epoch": 0.89,
3949
+ "learning_rate": 6.522267154070816e-06,
3950
+ "loss": 0.9836,
3951
+ "step": 645
3952
+ },
3953
+ {
3954
+ "epoch": 0.89,
3955
+ "learning_rate": 6.367730533672034e-06,
3956
+ "loss": 0.9222,
3957
+ "step": 646
3958
+ },
3959
+ {
3960
+ "epoch": 0.89,
3961
+ "learning_rate": 6.214986481581364e-06,
3962
+ "loss": 0.9768,
3963
+ "step": 647
3964
+ },
3965
+ {
3966
+ "epoch": 0.89,
3967
+ "learning_rate": 6.0640379220486595e-06,
3968
+ "loss": 0.9948,
3969
+ "step": 648
3970
+ },
3971
+ {
3972
+ "epoch": 0.89,
3973
+ "learning_rate": 5.914887744949427e-06,
3974
+ "loss": 0.9517,
3975
+ "step": 649
3976
+ },
3977
+ {
3978
+ "epoch": 0.89,
3979
+ "learning_rate": 5.767538805729578e-06,
3980
+ "loss": 1.0048,
3981
+ "step": 650
3982
+ },
3983
+ {
3984
+ "epoch": 0.89,
3985
+ "learning_rate": 5.621993925350721e-06,
3986
+ "loss": 0.9097,
3987
+ "step": 651
3988
+ },
3989
+ {
3990
+ "epoch": 0.9,
3991
+ "learning_rate": 5.478255890236184e-06,
3992
+ "loss": 1.0013,
3993
+ "step": 652
3994
+ },
3995
+ {
3996
+ "epoch": 0.9,
3997
+ "learning_rate": 5.336327452217682e-06,
3998
+ "loss": 0.935,
3999
+ "step": 653
4000
+ },
4001
+ {
4002
+ "epoch": 0.9,
4003
+ "learning_rate": 5.196211328482559e-06,
4004
+ "loss": 0.959,
4005
+ "step": 654
4006
+ },
4007
+ {
4008
+ "epoch": 0.9,
4009
+ "learning_rate": 5.057910201521876e-06,
4010
+ "loss": 0.9785,
4011
+ "step": 655
4012
+ },
4013
+ {
4014
+ "epoch": 0.9,
4015
+ "learning_rate": 4.921426719078948e-06,
4016
+ "loss": 0.9148,
4017
+ "step": 656
4018
+ },
4019
+ {
4020
+ "epoch": 0.9,
4021
+ "learning_rate": 4.786763494098689e-06,
4022
+ "loss": 0.9943,
4023
+ "step": 657
4024
+ },
4025
+ {
4026
+ "epoch": 0.9,
4027
+ "eval_loss": 0.9600038528442383,
4028
+ "eval_runtime": 100.5521,
4029
+ "eval_samples_per_second": 25.867,
4030
+ "eval_steps_per_second": 25.867,
4031
+ "step": 657
4032
+ },
4033
+ {
4034
+ "epoch": 0.9,
4035
+ "learning_rate": 4.653923104677671e-06,
4036
+ "loss": 0.9541,
4037
+ "step": 658
4038
+ },
4039
+ {
4040
+ "epoch": 0.91,
4041
+ "learning_rate": 4.522908094014655e-06,
4042
+ "loss": 0.9315,
4043
+ "step": 659
4044
+ },
4045
+ {
4046
+ "epoch": 0.91,
4047
+ "learning_rate": 4.393720970361948e-06,
4048
+ "loss": 0.9612,
4049
+ "step": 660
4050
+ },
4051
+ {
4052
+ "epoch": 0.91,
4053
+ "learning_rate": 4.266364206977369e-06,
4054
+ "loss": 1.0288,
4055
+ "step": 661
4056
+ },
4057
+ {
4058
+ "epoch": 0.91,
4059
+ "learning_rate": 4.140840242076926e-06,
4060
+ "loss": 0.9664,
4061
+ "step": 662
4062
+ },
4063
+ {
4064
+ "epoch": 0.91,
4065
+ "learning_rate": 4.017151478788117e-06,
4066
+ "loss": 0.9632,
4067
+ "step": 663
4068
+ },
4069
+ {
4070
+ "epoch": 0.91,
4071
+ "learning_rate": 3.895300285103931e-06,
4072
+ "loss": 0.9757,
4073
+ "step": 664
4074
+ },
4075
+ {
4076
+ "epoch": 0.91,
4077
+ "learning_rate": 3.7752889938375113e-06,
4078
+ "loss": 0.8962,
4079
+ "step": 665
4080
+ },
4081
+ {
4082
+ "epoch": 0.91,
4083
+ "learning_rate": 3.657119902577466e-06,
4084
+ "loss": 0.9502,
4085
+ "step": 666
4086
+ },
4087
+ {
4088
+ "epoch": 0.92,
4089
+ "learning_rate": 3.5407952736439265e-06,
4090
+ "loss": 0.9731,
4091
+ "step": 667
4092
+ },
4093
+ {
4094
+ "epoch": 0.92,
4095
+ "learning_rate": 3.4263173340452257e-06,
4096
+ "loss": 0.9455,
4097
+ "step": 668
4098
+ },
4099
+ {
4100
+ "epoch": 0.92,
4101
+ "learning_rate": 3.313688275435234e-06,
4102
+ "loss": 0.9803,
4103
+ "step": 669
4104
+ },
4105
+ {
4106
+ "epoch": 0.92,
4107
+ "learning_rate": 3.202910254071434e-06,
4108
+ "loss": 0.9623,
4109
+ "step": 670
4110
+ },
4111
+ {
4112
+ "epoch": 0.92,
4113
+ "learning_rate": 3.0939853907736126e-06,
4114
+ "loss": 0.9911,
4115
+ "step": 671
4116
+ },
4117
+ {
4118
+ "epoch": 0.92,
4119
+ "learning_rate": 2.986915770883281e-06,
4120
+ "loss": 1.0296,
4121
+ "step": 672
4122
+ },
4123
+ {
4124
+ "epoch": 0.92,
4125
+ "learning_rate": 2.8817034442237155e-06,
4126
+ "loss": 0.9288,
4127
+ "step": 673
4128
+ },
4129
+ {
4130
+ "epoch": 0.93,
4131
+ "learning_rate": 2.778350425060794e-06,
4132
+ "loss": 0.9651,
4133
+ "step": 674
4134
+ },
4135
+ {
4136
+ "epoch": 0.93,
4137
+ "learning_rate": 2.6768586920643324e-06,
4138
+ "loss": 0.9331,
4139
+ "step": 675
4140
+ },
4141
+ {
4142
+ "epoch": 0.93,
4143
+ "learning_rate": 2.577230188270263e-06,
4144
+ "loss": 0.9591,
4145
+ "step": 676
4146
+ },
4147
+ {
4148
+ "epoch": 0.93,
4149
+ "learning_rate": 2.4794668210434193e-06,
4150
+ "loss": 0.9949,
4151
+ "step": 677
4152
+ },
4153
+ {
4154
+ "epoch": 0.93,
4155
+ "learning_rate": 2.383570462041029e-06,
4156
+ "loss": 0.9396,
4157
+ "step": 678
4158
+ },
4159
+ {
4160
+ "epoch": 0.93,
4161
+ "learning_rate": 2.2895429471768926e-06,
4162
+ "loss": 0.9478,
4163
+ "step": 679
4164
+ },
4165
+ {
4166
+ "epoch": 0.93,
4167
+ "learning_rate": 2.197386076586183e-06,
4168
+ "loss": 0.9579,
4169
+ "step": 680
4170
+ },
4171
+ {
4172
+ "epoch": 0.94,
4173
+ "learning_rate": 2.107101614591045e-06,
4174
+ "loss": 0.9013,
4175
+ "step": 681
4176
+ },
4177
+ {
4178
+ "epoch": 0.94,
4179
+ "learning_rate": 2.018691289666774e-06,
4180
+ "loss": 0.9926,
4181
+ "step": 682
4182
+ },
4183
+ {
4184
+ "epoch": 0.94,
4185
+ "learning_rate": 1.932156794408757e-06,
4186
+ "loss": 0.9672,
4187
+ "step": 683
4188
+ },
4189
+ {
4190
+ "epoch": 0.94,
4191
+ "learning_rate": 1.8474997855000176e-06,
4192
+ "loss": 0.9919,
4193
+ "step": 684
4194
+ },
4195
+ {
4196
+ "epoch": 0.94,
4197
+ "learning_rate": 1.7647218836795875e-06,
4198
+ "loss": 0.9698,
4199
+ "step": 685
4200
+ },
4201
+ {
4202
+ "epoch": 0.94,
4203
+ "learning_rate": 1.6838246737113983e-06,
4204
+ "loss": 1.0075,
4205
+ "step": 686
4206
+ },
4207
+ {
4208
+ "epoch": 0.94,
4209
+ "learning_rate": 1.604809704353949e-06,
4210
+ "loss": 0.9974,
4211
+ "step": 687
4212
+ },
4213
+ {
4214
+ "epoch": 0.95,
4215
+ "learning_rate": 1.5276784883307082e-06,
4216
+ "loss": 0.9825,
4217
+ "step": 688
4218
+ },
4219
+ {
4220
+ "epoch": 0.95,
4221
+ "learning_rate": 1.4524325023010931e-06,
4222
+ "loss": 0.9936,
4223
+ "step": 689
4224
+ },
4225
+ {
4226
+ "epoch": 0.95,
4227
+ "learning_rate": 1.3790731868322471e-06,
4228
+ "loss": 0.9997,
4229
+ "step": 690
4230
+ },
4231
+ {
4232
+ "epoch": 0.95,
4233
+ "learning_rate": 1.3076019463714172e-06,
4234
+ "loss": 0.9528,
4235
+ "step": 691
4236
+ },
4237
+ {
4238
+ "epoch": 0.95,
4239
+ "learning_rate": 1.238020149219099e-06,
4240
+ "loss": 1.009,
4241
+ "step": 692
4242
+ },
4243
+ {
4244
+ "epoch": 0.95,
4245
+ "learning_rate": 1.1703291275028228e-06,
4246
+ "loss": 1.0098,
4247
+ "step": 693
4248
+ },
4249
+ {
4250
+ "epoch": 0.95,
4251
+ "learning_rate": 1.1045301771516747e-06,
4252
+ "loss": 1.0555,
4253
+ "step": 694
4254
+ },
4255
+ {
4256
+ "epoch": 0.95,
4257
+ "learning_rate": 1.0406245578714612e-06,
4258
+ "loss": 0.96,
4259
+ "step": 695
4260
+ },
4261
+ {
4262
+ "epoch": 0.96,
4263
+ "learning_rate": 9.786134931205726e-07,
4264
+ "loss": 0.9659,
4265
+ "step": 696
4266
+ },
4267
+ {
4268
+ "epoch": 0.96,
4269
+ "learning_rate": 9.184981700866346e-07,
4270
+ "loss": 1.0004,
4271
+ "step": 697
4272
+ },
4273
+ {
4274
+ "epoch": 0.96,
4275
+ "learning_rate": 8.602797396636942e-07,
4276
+ "loss": 0.9869,
4277
+ "step": 698
4278
+ },
4279
+ {
4280
+ "epoch": 0.96,
4281
+ "learning_rate": 8.039593164302362e-07,
4282
+ "loss": 1.0907,
4283
+ "step": 699
4284
+ },
4285
+ {
4286
+ "epoch": 0.96,
4287
+ "learning_rate": 7.495379786278456e-07,
4288
+ "loss": 0.9884,
4289
+ "step": 700
4290
+ },
4291
+ {
4292
+ "epoch": 0.96,
4293
+ "learning_rate": 6.97016768140546e-07,
4294
+ "loss": 0.9542,
4295
+ "step": 701
4296
+ },
4297
+ {
4298
+ "epoch": 0.96,
4299
+ "learning_rate": 6.463966904748486e-07,
4300
+ "loss": 0.9358,
4301
+ "step": 702
4302
+ },
4303
+ {
4304
+ "epoch": 0.97,
4305
+ "learning_rate": 5.97678714740535e-07,
4306
+ "loss": 0.97,
4307
+ "step": 703
4308
+ },
4309
+ {
4310
+ "epoch": 0.97,
4311
+ "learning_rate": 5.508637736320488e-07,
4312
+ "loss": 4.0832,
4313
+ "step": 704
4314
+ },
4315
+ {
4316
+ "epoch": 0.97,
4317
+ "learning_rate": 5.059527634107109e-07,
4318
+ "loss": 0.9434,
4319
+ "step": 705
4320
+ },
4321
+ {
4322
+ "epoch": 0.97,
4323
+ "learning_rate": 4.6294654388748804e-07,
4324
+ "loss": 1.1544,
4325
+ "step": 706
4326
+ },
4327
+ {
4328
+ "epoch": 0.97,
4329
+ "learning_rate": 4.2184593840659537e-07,
4330
+ "loss": 0.9443,
4331
+ "step": 707
4332
+ },
4333
+ {
4334
+ "epoch": 0.97,
4335
+ "learning_rate": 3.8265173382968644e-07,
4336
+ "loss": 0.9564,
4337
+ "step": 708
4338
+ },
4339
+ {
4340
+ "epoch": 0.97,
4341
+ "learning_rate": 3.45364680520821e-07,
4342
+ "loss": 0.9713,
4343
+ "step": 709
4344
+ },
4345
+ {
4346
+ "epoch": 0.98,
4347
+ "learning_rate": 3.0998549233205443e-07,
4348
+ "loss": 0.9417,
4349
+ "step": 710
4350
+ },
4351
+ {
4352
+ "epoch": 0.98,
4353
+ "learning_rate": 2.7651484658984816e-07,
4354
+ "loss": 0.9191,
4355
+ "step": 711
4356
+ },
4357
+ {
4358
+ "epoch": 0.98,
4359
+ "learning_rate": 2.4495338408201394e-07,
4360
+ "loss": 0.9749,
4361
+ "step": 712
4362
+ },
4363
+ {
4364
+ "epoch": 0.98,
4365
+ "learning_rate": 2.1530170904551228e-07,
4366
+ "loss": 0.98,
4367
+ "step": 713
4368
+ },
4369
+ {
4370
+ "epoch": 0.98,
4371
+ "learning_rate": 1.8756038915486163e-07,
4372
+ "loss": 0.919,
4373
+ "step": 714
4374
+ },
4375
+ {
4376
+ "epoch": 0.98,
4377
+ "learning_rate": 1.6172995551125837e-07,
4378
+ "loss": 0.9998,
4379
+ "step": 715
4380
+ },
4381
+ {
4382
+ "epoch": 0.98,
4383
+ "learning_rate": 1.3781090263242924e-07,
4384
+ "loss": 0.9527,
4385
+ "step": 716
4386
+ },
4387
+ {
4388
+ "epoch": 0.98,
4389
+ "learning_rate": 1.1580368844316125e-07,
4390
+ "loss": 1.032,
4391
+ "step": 717
4392
+ },
4393
+ {
4394
+ "epoch": 0.99,
4395
+ "learning_rate": 9.570873426649752e-08,
4396
+ "loss": 0.8956,
4397
+ "step": 718
4398
+ },
4399
+ {
4400
+ "epoch": 0.99,
4401
+ "learning_rate": 7.752642481573258e-08,
4402
+ "loss": 1.0051,
4403
+ "step": 719
4404
+ },
4405
+ {
4406
+ "epoch": 0.99,
4407
+ "learning_rate": 6.125710818701835e-08,
4408
+ "loss": 0.9296,
4409
+ "step": 720
4410
+ },
4411
+ {
4412
+ "epoch": 0.99,
4413
+ "learning_rate": 4.6901095852680544e-08,
4414
+ "loss": 0.9674,
4415
+ "step": 721
4416
+ },
4417
+ {
4418
+ "epoch": 0.99,
4419
+ "learning_rate": 3.4458662655267873e-08,
4420
+ "loss": 0.9771,
4421
+ "step": 722
4422
+ },
4423
+ {
4424
+ "epoch": 0.99,
4425
+ "learning_rate": 2.3930046802322913e-08,
4426
+ "loss": 1.0563,
4427
+ "step": 723
4428
+ },
4429
+ {
4430
+ "epoch": 0.99,
4431
+ "learning_rate": 1.5315449861774688e-08,
4432
+ "loss": 0.9874,
4433
+ "step": 724
4434
+ },
4435
+ {
4436
+ "epoch": 1.0,
4437
+ "learning_rate": 8.615036758108374e-09,
4438
+ "loss": 0.917,
4439
+ "step": 725
4440
+ },
4441
+ {
4442
+ "epoch": 1.0,
4443
+ "learning_rate": 3.828935769190078e-09,
4444
+ "loss": 1.0184,
4445
+ "step": 726
4446
+ },
4447
+ {
4448
+ "epoch": 1.0,
4449
+ "learning_rate": 9.572385238243442e-10,
4450
+ "loss": 0.9141,
4451
+ "step": 727
4452
+ },
4453
+ {
4454
+ "epoch": 1.0,
4455
+ "learning_rate": 0.0,
4456
+ "loss": 1.0034,
4457
+ "step": 728
4458
+ }
4459
+ ],
4460
+ "logging_steps": 1,
4461
+ "max_steps": 728,
4462
+ "num_input_tokens_seen": 0,
4463
+ "num_train_epochs": 1,
4464
+ "save_steps": 500,
4465
+ "total_flos": 5.574070959939256e+17,
4466
+ "train_batch_size": 1,
4467
+ "trial_name": null,
4468
+ "trial_params": null
4469
+ }
checkpoint-728/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:686eb8e0c3c54ba9801fb49226dc12817a17f36493fb2d37985521f720c4b238
3
+ size 5304
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "aurora-m/aurora-m-v0.1",
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "GPTBigCodeForCausalLM"
6
+ ],
7
+ "attention_softmax_in_fp32": true,
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 0,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 0,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt_bigcode",
15
+ "multi_query": true,
16
+ "n_embd": 6144,
17
+ "n_head": 48,
18
+ "n_inner": 24576,
19
+ "n_layer": 40,
20
+ "n_positions": 8192,
21
+ "pad_token_id": 0,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attention_softmax_in_fp32": true,
24
+ "scale_attn_weights": true,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.38.0.dev0",
27
+ "use_cache": false,
28
+ "vocab_size": 49156
29
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim_prefix>",
5
+ "<fim_middle>",
6
+ "<fim_suffix>",
7
+ "<fim_pad>",
8
+ "<filename>",
9
+ "<gh_stars>",
10
+ "<issue_start>",
11
+ "<issue_comment>",
12
+ "<issue_closed>",
13
+ "<jupyter_start>",
14
+ "<jupyter_text>",
15
+ "<jupyter_code>",
16
+ "<jupyter_output>",
17
+ "<empty_output>",
18
+ "<commit_before>",
19
+ "<commit_msg>",
20
+ "<commit_after>",
21
+ "<reponame>"
22
+ ],
23
+ "bos_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "eos_token": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "pad_token": {
38
+ "content": "<|endoftext|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<|endoftext|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,218 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<fim_prefix>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<fim_middle>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<fim_suffix>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<fim_pad>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<|rating-x|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<|rating-r|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<|rating-pg|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<|rating-g|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_closed>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<jupyter_start>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_text>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_code>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_output>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<empty_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<commit_before>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<commit_msg>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "17": {
141
+ "content": "<commit_after>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "18": {
149
+ "content": "<reponame>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "49152": {
157
+ "content": "<filename>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "49153": {
165
+ "content": "<gh_stars>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "49154": {
173
+ "content": "<issue_start>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "49155": {
181
+ "content": "<issue_comment>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ }
188
+ },
189
+ "additional_special_tokens": [
190
+ "<|endoftext|>",
191
+ "<fim_prefix>",
192
+ "<fim_middle>",
193
+ "<fim_suffix>",
194
+ "<fim_pad>",
195
+ "<filename>",
196
+ "<gh_stars>",
197
+ "<issue_start>",
198
+ "<issue_comment>",
199
+ "<issue_closed>",
200
+ "<jupyter_start>",
201
+ "<jupyter_text>",
202
+ "<jupyter_code>",
203
+ "<jupyter_output>",
204
+ "<empty_output>",
205
+ "<commit_before>",
206
+ "<commit_msg>",
207
+ "<commit_after>",
208
+ "<reponame>"
209
+ ],
210
+ "bos_token": "<|endoftext|>",
211
+ "clean_up_tokenization_spaces": true,
212
+ "eos_token": "<|endoftext|>",
213
+ "model_max_length": 1000000000000000019884624838656,
214
+ "pad_token": "<|endoftext|>",
215
+ "tokenizer_class": "GPT2Tokenizer",
216
+ "unk_token": "<|endoftext|>",
217
+ "vocab_size": 49152
218
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff