Upload 11 files
Browse files- config.json +133 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +5 -0
- trainer_state.json +2270 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "../../save/marinda-default-ep0.4-26m/checkpoint-25000",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MarindaForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"ep_add_linear_projection": true,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "noacc",
|
| 16 |
+
"1": "base(int)",
|
| 17 |
+
"2": "base(char)**",
|
| 18 |
+
"3": "base(char)*",
|
| 19 |
+
"4": "base(_Bool)",
|
| 20 |
+
"5": "base(unsigned int)",
|
| 21 |
+
"6": "base(long unsigned int)",
|
| 22 |
+
"7": "struct*",
|
| 23 |
+
"8": "void*",
|
| 24 |
+
"9": "base(unsigned char)*",
|
| 25 |
+
"10": "enum",
|
| 26 |
+
"11": "base(unsigned char)",
|
| 27 |
+
"12": "base(char)",
|
| 28 |
+
"13": "base(unsigned int)*",
|
| 29 |
+
"14": "base(long int)",
|
| 30 |
+
"15": "base(short int)*",
|
| 31 |
+
"16": "union*",
|
| 32 |
+
"17": "subroutine*",
|
| 33 |
+
"18": "base(long int)*",
|
| 34 |
+
"19": "base(int)*",
|
| 35 |
+
"20": "array*",
|
| 36 |
+
"21": "struct**",
|
| 37 |
+
"22": "base(long unsigned int)*",
|
| 38 |
+
"23": "base(double)*",
|
| 39 |
+
"24": "void**",
|
| 40 |
+
"25": "base(short unsigned int)",
|
| 41 |
+
"26": "struct",
|
| 42 |
+
"27": "base(_Bool)*",
|
| 43 |
+
"28": "base(char)***",
|
| 44 |
+
"29": "base(long unsigned int)**",
|
| 45 |
+
"30": "base(long double)",
|
| 46 |
+
"31": "struct***",
|
| 47 |
+
"32": "enum*",
|
| 48 |
+
"33": "base(unsigned int)**",
|
| 49 |
+
"34": "base(long double)*",
|
| 50 |
+
"35": "base(float)*",
|
| 51 |
+
"36": "base(long long unsigned int)*",
|
| 52 |
+
"37": "base(short unsigned int)*",
|
| 53 |
+
"38": "base(signed char)*",
|
| 54 |
+
"39": "base(long long int)",
|
| 55 |
+
"40": "array",
|
| 56 |
+
"41": "base(double)",
|
| 57 |
+
"42": "base(unsigned char)**",
|
| 58 |
+
"43": "union",
|
| 59 |
+
"44": "base(short int)",
|
| 60 |
+
"45": "base(long long unsigned int)",
|
| 61 |
+
"46": "subroutine**",
|
| 62 |
+
"47": "array**",
|
| 63 |
+
"48": "base(signed char)",
|
| 64 |
+
"49": "base(float)"
|
| 65 |
+
},
|
| 66 |
+
"initializer_range": 0.02,
|
| 67 |
+
"intermediate_size": 3072,
|
| 68 |
+
"label2id": {
|
| 69 |
+
"array": 40,
|
| 70 |
+
"array*": 20,
|
| 71 |
+
"array**": 47,
|
| 72 |
+
"base(_Bool)": 4,
|
| 73 |
+
"base(_Bool)*": 27,
|
| 74 |
+
"base(char)": 12,
|
| 75 |
+
"base(char)*": 3,
|
| 76 |
+
"base(char)**": 2,
|
| 77 |
+
"base(char)***": 28,
|
| 78 |
+
"base(double)": 41,
|
| 79 |
+
"base(double)*": 23,
|
| 80 |
+
"base(float)": 49,
|
| 81 |
+
"base(float)*": 35,
|
| 82 |
+
"base(int)": 1,
|
| 83 |
+
"base(int)*": 19,
|
| 84 |
+
"base(long double)": 30,
|
| 85 |
+
"base(long double)*": 34,
|
| 86 |
+
"base(long int)": 14,
|
| 87 |
+
"base(long int)*": 18,
|
| 88 |
+
"base(long long int)": 39,
|
| 89 |
+
"base(long long unsigned int)": 45,
|
| 90 |
+
"base(long long unsigned int)*": 36,
|
| 91 |
+
"base(long unsigned int)": 6,
|
| 92 |
+
"base(long unsigned int)*": 22,
|
| 93 |
+
"base(long unsigned int)**": 29,
|
| 94 |
+
"base(short int)": 44,
|
| 95 |
+
"base(short int)*": 15,
|
| 96 |
+
"base(short unsigned int)": 25,
|
| 97 |
+
"base(short unsigned int)*": 37,
|
| 98 |
+
"base(signed char)": 48,
|
| 99 |
+
"base(signed char)*": 38,
|
| 100 |
+
"base(unsigned char)": 11,
|
| 101 |
+
"base(unsigned char)*": 9,
|
| 102 |
+
"base(unsigned char)**": 42,
|
| 103 |
+
"base(unsigned int)": 5,
|
| 104 |
+
"base(unsigned int)*": 13,
|
| 105 |
+
"base(unsigned int)**": 33,
|
| 106 |
+
"enum": 10,
|
| 107 |
+
"enum*": 32,
|
| 108 |
+
"noacc": 0,
|
| 109 |
+
"struct": 26,
|
| 110 |
+
"struct*": 7,
|
| 111 |
+
"struct**": 21,
|
| 112 |
+
"struct***": 31,
|
| 113 |
+
"subroutine*": 17,
|
| 114 |
+
"subroutine**": 46,
|
| 115 |
+
"union": 43,
|
| 116 |
+
"union*": 16,
|
| 117 |
+
"void*": 8,
|
| 118 |
+
"void**": 24
|
| 119 |
+
},
|
| 120 |
+
"layer_norm_eps": 1e-12,
|
| 121 |
+
"max_position_embeddings": 600,
|
| 122 |
+
"max_relative_position_embeddings": 8,
|
| 123 |
+
"model_type": "marinda",
|
| 124 |
+
"num_attention_heads": 12,
|
| 125 |
+
"num_hidden_layers": 12,
|
| 126 |
+
"pad_token_id": 3,
|
| 127 |
+
"position_embedding_type": "mixed",
|
| 128 |
+
"torch_dtype": "float32",
|
| 129 |
+
"transformers_version": "4.31.0",
|
| 130 |
+
"type_vocab_size": 2,
|
| 131 |
+
"use_cache": true,
|
| 132 |
+
"vocab_size": 30523
|
| 133 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c6c359584564d39606f50ed193011679de488eca34b6dacdaf2b64c1e64a487
|
| 3 |
+
size 872119157
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a55d137f37aec062ea3f13b4418d6202d865dcdf8190fb17a45a0d7c7440e0d
|
| 3 |
+
size 436069275
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89c017bde6bf374f1bec9a07b1d8eb67d80df2b31c1b33a5d9db56a423a20c06
|
| 3 |
+
size 15523
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98653a31e0fb4d97c9aa0bfd1ed5be1f9259faf760b7344b822634758f4aa5a5
|
| 3 |
+
size 15523
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2010999371ee18f44f30927de69efe4fc9b7c47e3c73e5601a7c9d6e567b329f
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"model_max_length": 512,
|
| 4 |
+
"tokenizer_class": "MarindaTokenizer"
|
| 5 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2270 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9180364705120548,
|
| 3 |
+
"best_model_checkpoint": "../save/marinda-default-ep0.4-26m-ti-all-O2-shuffle/checkpoint-700",
|
| 4 |
+
"epoch": 4.761904761904762,
|
| 5 |
+
"global_step": 700,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 9.972789115646259e-05,
|
| 13 |
+
"loss": 3.7949,
|
| 14 |
+
"step": 2
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 9.945578231292518e-05,
|
| 19 |
+
"loss": 3.3775,
|
| 20 |
+
"step": 4
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.04,
|
| 24 |
+
"learning_rate": 9.918367346938776e-05,
|
| 25 |
+
"loss": 2.5674,
|
| 26 |
+
"step": 6
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.05,
|
| 30 |
+
"learning_rate": 9.891156462585035e-05,
|
| 31 |
+
"loss": 1.3071,
|
| 32 |
+
"step": 8
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.07,
|
| 36 |
+
"learning_rate": 9.863945578231294e-05,
|
| 37 |
+
"loss": 0.5747,
|
| 38 |
+
"step": 10
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08,
|
| 42 |
+
"learning_rate": 9.836734693877552e-05,
|
| 43 |
+
"loss": 0.4116,
|
| 44 |
+
"step": 12
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1,
|
| 48 |
+
"learning_rate": 9.80952380952381e-05,
|
| 49 |
+
"loss": 0.387,
|
| 50 |
+
"step": 14
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.11,
|
| 54 |
+
"learning_rate": 9.782312925170068e-05,
|
| 55 |
+
"loss": 0.3709,
|
| 56 |
+
"step": 16
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.12,
|
| 60 |
+
"learning_rate": 9.755102040816328e-05,
|
| 61 |
+
"loss": 0.3384,
|
| 62 |
+
"step": 18
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.14,
|
| 66 |
+
"learning_rate": 9.727891156462585e-05,
|
| 67 |
+
"loss": 0.3449,
|
| 68 |
+
"step": 20
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.15,
|
| 72 |
+
"learning_rate": 9.700680272108844e-05,
|
| 73 |
+
"loss": 0.31,
|
| 74 |
+
"step": 22
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.16,
|
| 78 |
+
"learning_rate": 9.673469387755102e-05,
|
| 79 |
+
"loss": 0.2991,
|
| 80 |
+
"step": 24
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.18,
|
| 84 |
+
"learning_rate": 9.646258503401361e-05,
|
| 85 |
+
"loss": 0.2726,
|
| 86 |
+
"step": 26
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.19,
|
| 90 |
+
"learning_rate": 9.61904761904762e-05,
|
| 91 |
+
"loss": 0.2695,
|
| 92 |
+
"step": 28
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.2,
|
| 96 |
+
"learning_rate": 9.591836734693878e-05,
|
| 97 |
+
"loss": 0.2748,
|
| 98 |
+
"step": 30
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.22,
|
| 102 |
+
"learning_rate": 9.564625850340137e-05,
|
| 103 |
+
"loss": 0.2599,
|
| 104 |
+
"step": 32
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.23,
|
| 108 |
+
"learning_rate": 9.537414965986395e-05,
|
| 109 |
+
"loss": 0.237,
|
| 110 |
+
"step": 34
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.24,
|
| 114 |
+
"learning_rate": 9.510204081632653e-05,
|
| 115 |
+
"loss": 0.2351,
|
| 116 |
+
"step": 36
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.26,
|
| 120 |
+
"learning_rate": 9.482993197278913e-05,
|
| 121 |
+
"loss": 0.2282,
|
| 122 |
+
"step": 38
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.27,
|
| 126 |
+
"learning_rate": 9.455782312925171e-05,
|
| 127 |
+
"loss": 0.2113,
|
| 128 |
+
"step": 40
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.29,
|
| 132 |
+
"learning_rate": 9.428571428571429e-05,
|
| 133 |
+
"loss": 0.2064,
|
| 134 |
+
"step": 42
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.3,
|
| 138 |
+
"learning_rate": 9.401360544217687e-05,
|
| 139 |
+
"loss": 0.2039,
|
| 140 |
+
"step": 44
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.31,
|
| 144 |
+
"learning_rate": 9.374149659863946e-05,
|
| 145 |
+
"loss": 0.1884,
|
| 146 |
+
"step": 46
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.33,
|
| 150 |
+
"learning_rate": 9.346938775510204e-05,
|
| 151 |
+
"loss": 0.1805,
|
| 152 |
+
"step": 48
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.34,
|
| 156 |
+
"learning_rate": 9.319727891156463e-05,
|
| 157 |
+
"loss": 0.1864,
|
| 158 |
+
"step": 50
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.34,
|
| 162 |
+
"eval_f1": 0.34935683381798105,
|
| 163 |
+
"eval_loss": 0.16132193803787231,
|
| 164 |
+
"eval_precision": 0.4228036171158445,
|
| 165 |
+
"eval_recall": 0.29765784863362554,
|
| 166 |
+
"eval_runtime": 11.4327,
|
| 167 |
+
"eval_samples_per_second": 129.628,
|
| 168 |
+
"eval_steps_per_second": 0.525,
|
| 169 |
+
"step": 50
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.35,
|
| 173 |
+
"learning_rate": 9.292517006802722e-05,
|
| 174 |
+
"loss": 0.1711,
|
| 175 |
+
"step": 52
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.37,
|
| 179 |
+
"learning_rate": 9.26530612244898e-05,
|
| 180 |
+
"loss": 0.1747,
|
| 181 |
+
"step": 54
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.38,
|
| 185 |
+
"learning_rate": 9.238095238095239e-05,
|
| 186 |
+
"loss": 0.1688,
|
| 187 |
+
"step": 56
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.39,
|
| 191 |
+
"learning_rate": 9.210884353741497e-05,
|
| 192 |
+
"loss": 0.1676,
|
| 193 |
+
"step": 58
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.41,
|
| 197 |
+
"learning_rate": 9.183673469387756e-05,
|
| 198 |
+
"loss": 0.1564,
|
| 199 |
+
"step": 60
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.42,
|
| 203 |
+
"learning_rate": 9.156462585034013e-05,
|
| 204 |
+
"loss": 0.1585,
|
| 205 |
+
"step": 62
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.44,
|
| 209 |
+
"learning_rate": 9.129251700680272e-05,
|
| 210 |
+
"loss": 0.1452,
|
| 211 |
+
"step": 64
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.45,
|
| 215 |
+
"learning_rate": 9.102040816326532e-05,
|
| 216 |
+
"loss": 0.1384,
|
| 217 |
+
"step": 66
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.46,
|
| 221 |
+
"learning_rate": 9.074829931972789e-05,
|
| 222 |
+
"loss": 0.1508,
|
| 223 |
+
"step": 68
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.48,
|
| 227 |
+
"learning_rate": 9.047619047619048e-05,
|
| 228 |
+
"loss": 0.1359,
|
| 229 |
+
"step": 70
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.49,
|
| 233 |
+
"learning_rate": 9.020408163265308e-05,
|
| 234 |
+
"loss": 0.1475,
|
| 235 |
+
"step": 72
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.5,
|
| 239 |
+
"learning_rate": 8.993197278911565e-05,
|
| 240 |
+
"loss": 0.1259,
|
| 241 |
+
"step": 74
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.52,
|
| 245 |
+
"learning_rate": 8.965986394557823e-05,
|
| 246 |
+
"loss": 0.1328,
|
| 247 |
+
"step": 76
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.53,
|
| 251 |
+
"learning_rate": 8.938775510204082e-05,
|
| 252 |
+
"loss": 0.1334,
|
| 253 |
+
"step": 78
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.54,
|
| 257 |
+
"learning_rate": 8.911564625850341e-05,
|
| 258 |
+
"loss": 0.1244,
|
| 259 |
+
"step": 80
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.56,
|
| 263 |
+
"learning_rate": 8.884353741496599e-05,
|
| 264 |
+
"loss": 0.1247,
|
| 265 |
+
"step": 82
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.57,
|
| 269 |
+
"learning_rate": 8.857142857142857e-05,
|
| 270 |
+
"loss": 0.1168,
|
| 271 |
+
"step": 84
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.59,
|
| 275 |
+
"learning_rate": 8.829931972789117e-05,
|
| 276 |
+
"loss": 0.1216,
|
| 277 |
+
"step": 86
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.6,
|
| 281 |
+
"learning_rate": 8.802721088435375e-05,
|
| 282 |
+
"loss": 0.1245,
|
| 283 |
+
"step": 88
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.61,
|
| 287 |
+
"learning_rate": 8.775510204081632e-05,
|
| 288 |
+
"loss": 0.1167,
|
| 289 |
+
"step": 90
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.63,
|
| 293 |
+
"learning_rate": 8.748299319727892e-05,
|
| 294 |
+
"loss": 0.0986,
|
| 295 |
+
"step": 92
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.64,
|
| 299 |
+
"learning_rate": 8.72108843537415e-05,
|
| 300 |
+
"loss": 0.1065,
|
| 301 |
+
"step": 94
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 0.65,
|
| 305 |
+
"learning_rate": 8.693877551020408e-05,
|
| 306 |
+
"loss": 0.1121,
|
| 307 |
+
"step": 96
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.67,
|
| 311 |
+
"learning_rate": 8.666666666666667e-05,
|
| 312 |
+
"loss": 0.1101,
|
| 313 |
+
"step": 98
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.68,
|
| 317 |
+
"learning_rate": 8.639455782312925e-05,
|
| 318 |
+
"loss": 0.0995,
|
| 319 |
+
"step": 100
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 0.68,
|
| 323 |
+
"eval_f1": 0.651423571104831,
|
| 324 |
+
"eval_loss": 0.09403873980045319,
|
| 325 |
+
"eval_precision": 0.6548211682202488,
|
| 326 |
+
"eval_recall": 0.6480709462229433,
|
| 327 |
+
"eval_runtime": 11.2473,
|
| 328 |
+
"eval_samples_per_second": 131.765,
|
| 329 |
+
"eval_steps_per_second": 0.533,
|
| 330 |
+
"step": 100
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.69,
|
| 334 |
+
"learning_rate": 8.612244897959184e-05,
|
| 335 |
+
"loss": 0.1104,
|
| 336 |
+
"step": 102
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.71,
|
| 340 |
+
"learning_rate": 8.585034013605443e-05,
|
| 341 |
+
"loss": 0.1175,
|
| 342 |
+
"step": 104
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.72,
|
| 346 |
+
"learning_rate": 8.557823129251701e-05,
|
| 347 |
+
"loss": 0.1007,
|
| 348 |
+
"step": 106
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.73,
|
| 352 |
+
"learning_rate": 8.53061224489796e-05,
|
| 353 |
+
"loss": 0.0911,
|
| 354 |
+
"step": 108
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.75,
|
| 358 |
+
"learning_rate": 8.503401360544217e-05,
|
| 359 |
+
"loss": 0.0969,
|
| 360 |
+
"step": 110
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.76,
|
| 364 |
+
"learning_rate": 8.476190476190477e-05,
|
| 365 |
+
"loss": 0.0924,
|
| 366 |
+
"step": 112
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.78,
|
| 370 |
+
"learning_rate": 8.448979591836736e-05,
|
| 371 |
+
"loss": 0.0949,
|
| 372 |
+
"step": 114
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.79,
|
| 376 |
+
"learning_rate": 8.421768707482993e-05,
|
| 377 |
+
"loss": 0.0858,
|
| 378 |
+
"step": 116
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.8,
|
| 382 |
+
"learning_rate": 8.394557823129252e-05,
|
| 383 |
+
"loss": 0.0945,
|
| 384 |
+
"step": 118
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.82,
|
| 388 |
+
"learning_rate": 8.367346938775511e-05,
|
| 389 |
+
"loss": 0.0961,
|
| 390 |
+
"step": 120
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.83,
|
| 394 |
+
"learning_rate": 8.340136054421769e-05,
|
| 395 |
+
"loss": 0.0913,
|
| 396 |
+
"step": 122
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.84,
|
| 400 |
+
"learning_rate": 8.312925170068027e-05,
|
| 401 |
+
"loss": 0.0845,
|
| 402 |
+
"step": 124
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.86,
|
| 406 |
+
"learning_rate": 8.285714285714287e-05,
|
| 407 |
+
"loss": 0.0873,
|
| 408 |
+
"step": 126
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.87,
|
| 412 |
+
"learning_rate": 8.258503401360545e-05,
|
| 413 |
+
"loss": 0.0837,
|
| 414 |
+
"step": 128
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.88,
|
| 418 |
+
"learning_rate": 8.231292517006803e-05,
|
| 419 |
+
"loss": 0.0779,
|
| 420 |
+
"step": 130
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.9,
|
| 424 |
+
"learning_rate": 8.204081632653062e-05,
|
| 425 |
+
"loss": 0.0839,
|
| 426 |
+
"step": 132
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.91,
|
| 430 |
+
"learning_rate": 8.17687074829932e-05,
|
| 431 |
+
"loss": 0.0872,
|
| 432 |
+
"step": 134
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.93,
|
| 436 |
+
"learning_rate": 8.149659863945579e-05,
|
| 437 |
+
"loss": 0.0882,
|
| 438 |
+
"step": 136
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.94,
|
| 442 |
+
"learning_rate": 8.122448979591836e-05,
|
| 443 |
+
"loss": 0.0829,
|
| 444 |
+
"step": 138
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.95,
|
| 448 |
+
"learning_rate": 8.095238095238096e-05,
|
| 449 |
+
"loss": 0.0726,
|
| 450 |
+
"step": 140
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.97,
|
| 454 |
+
"learning_rate": 8.068027210884355e-05,
|
| 455 |
+
"loss": 0.0828,
|
| 456 |
+
"step": 142
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.98,
|
| 460 |
+
"learning_rate": 8.040816326530612e-05,
|
| 461 |
+
"loss": 0.0872,
|
| 462 |
+
"step": 144
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.99,
|
| 466 |
+
"learning_rate": 8.013605442176872e-05,
|
| 467 |
+
"loss": 0.0838,
|
| 468 |
+
"step": 146
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.01,
|
| 472 |
+
"learning_rate": 7.986394557823129e-05,
|
| 473 |
+
"loss": 0.0763,
|
| 474 |
+
"step": 148
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.02,
|
| 478 |
+
"learning_rate": 7.959183673469388e-05,
|
| 479 |
+
"loss": 0.076,
|
| 480 |
+
"step": 150
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.02,
|
| 484 |
+
"eval_f1": 0.7706927100252173,
|
| 485 |
+
"eval_loss": 0.06672389805316925,
|
| 486 |
+
"eval_precision": 0.7788096890497564,
|
| 487 |
+
"eval_recall": 0.7627529744843834,
|
| 488 |
+
"eval_runtime": 11.0605,
|
| 489 |
+
"eval_samples_per_second": 133.991,
|
| 490 |
+
"eval_steps_per_second": 0.542,
|
| 491 |
+
"step": 150
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.03,
|
| 495 |
+
"learning_rate": 7.931972789115646e-05,
|
| 496 |
+
"loss": 0.0737,
|
| 497 |
+
"step": 152
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.05,
|
| 501 |
+
"learning_rate": 7.904761904761905e-05,
|
| 502 |
+
"loss": 0.0597,
|
| 503 |
+
"step": 154
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.06,
|
| 507 |
+
"learning_rate": 7.877551020408164e-05,
|
| 508 |
+
"loss": 0.0746,
|
| 509 |
+
"step": 156
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.07,
|
| 513 |
+
"learning_rate": 7.850340136054422e-05,
|
| 514 |
+
"loss": 0.0739,
|
| 515 |
+
"step": 158
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.09,
|
| 519 |
+
"learning_rate": 7.823129251700681e-05,
|
| 520 |
+
"loss": 0.0791,
|
| 521 |
+
"step": 160
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.1,
|
| 525 |
+
"learning_rate": 7.79591836734694e-05,
|
| 526 |
+
"loss": 0.0784,
|
| 527 |
+
"step": 162
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.12,
|
| 531 |
+
"learning_rate": 7.768707482993197e-05,
|
| 532 |
+
"loss": 0.0731,
|
| 533 |
+
"step": 164
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.13,
|
| 537 |
+
"learning_rate": 7.741496598639457e-05,
|
| 538 |
+
"loss": 0.0684,
|
| 539 |
+
"step": 166
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.14,
|
| 543 |
+
"learning_rate": 7.714285714285715e-05,
|
| 544 |
+
"loss": 0.0576,
|
| 545 |
+
"step": 168
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.16,
|
| 549 |
+
"learning_rate": 7.687074829931973e-05,
|
| 550 |
+
"loss": 0.0682,
|
| 551 |
+
"step": 170
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.17,
|
| 555 |
+
"learning_rate": 7.659863945578231e-05,
|
| 556 |
+
"loss": 0.0725,
|
| 557 |
+
"step": 172
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.18,
|
| 561 |
+
"learning_rate": 7.632653061224491e-05,
|
| 562 |
+
"loss": 0.0692,
|
| 563 |
+
"step": 174
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.2,
|
| 567 |
+
"learning_rate": 7.605442176870748e-05,
|
| 568 |
+
"loss": 0.069,
|
| 569 |
+
"step": 176
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.21,
|
| 573 |
+
"learning_rate": 7.578231292517007e-05,
|
| 574 |
+
"loss": 0.0702,
|
| 575 |
+
"step": 178
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.22,
|
| 579 |
+
"learning_rate": 7.551020408163266e-05,
|
| 580 |
+
"loss": 0.0629,
|
| 581 |
+
"step": 180
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.24,
|
| 585 |
+
"learning_rate": 7.523809523809524e-05,
|
| 586 |
+
"loss": 0.0679,
|
| 587 |
+
"step": 182
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.25,
|
| 591 |
+
"learning_rate": 7.496598639455783e-05,
|
| 592 |
+
"loss": 0.0601,
|
| 593 |
+
"step": 184
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.27,
|
| 597 |
+
"learning_rate": 7.469387755102041e-05,
|
| 598 |
+
"loss": 0.0681,
|
| 599 |
+
"step": 186
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.28,
|
| 603 |
+
"learning_rate": 7.4421768707483e-05,
|
| 604 |
+
"loss": 0.0596,
|
| 605 |
+
"step": 188
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.29,
|
| 609 |
+
"learning_rate": 7.414965986394559e-05,
|
| 610 |
+
"loss": 0.0693,
|
| 611 |
+
"step": 190
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 1.31,
|
| 615 |
+
"learning_rate": 7.387755102040816e-05,
|
| 616 |
+
"loss": 0.0653,
|
| 617 |
+
"step": 192
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 1.32,
|
| 621 |
+
"learning_rate": 7.360544217687076e-05,
|
| 622 |
+
"loss": 0.0541,
|
| 623 |
+
"step": 194
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.33,
|
| 627 |
+
"learning_rate": 7.333333333333333e-05,
|
| 628 |
+
"loss": 0.0639,
|
| 629 |
+
"step": 196
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.35,
|
| 633 |
+
"learning_rate": 7.306122448979592e-05,
|
| 634 |
+
"loss": 0.0568,
|
| 635 |
+
"step": 198
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1.36,
|
| 639 |
+
"learning_rate": 7.27891156462585e-05,
|
| 640 |
+
"loss": 0.0613,
|
| 641 |
+
"step": 200
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1.36,
|
| 645 |
+
"eval_f1": 0.8183980412867451,
|
| 646 |
+
"eval_loss": 0.053818028420209885,
|
| 647 |
+
"eval_precision": 0.8210879676347845,
|
| 648 |
+
"eval_recall": 0.8157356167545399,
|
| 649 |
+
"eval_runtime": 10.9366,
|
| 650 |
+
"eval_samples_per_second": 135.509,
|
| 651 |
+
"eval_steps_per_second": 0.549,
|
| 652 |
+
"step": 200
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 1.37,
|
| 656 |
+
"learning_rate": 7.251700680272109e-05,
|
| 657 |
+
"loss": 0.0601,
|
| 658 |
+
"step": 202
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.39,
|
| 662 |
+
"learning_rate": 7.224489795918368e-05,
|
| 663 |
+
"loss": 0.071,
|
| 664 |
+
"step": 204
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.4,
|
| 668 |
+
"learning_rate": 7.197278911564626e-05,
|
| 669 |
+
"loss": 0.0623,
|
| 670 |
+
"step": 206
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.41,
|
| 674 |
+
"learning_rate": 7.170068027210885e-05,
|
| 675 |
+
"loss": 0.0579,
|
| 676 |
+
"step": 208
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.43,
|
| 680 |
+
"learning_rate": 7.142857142857143e-05,
|
| 681 |
+
"loss": 0.0622,
|
| 682 |
+
"step": 210
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.44,
|
| 686 |
+
"learning_rate": 7.1156462585034e-05,
|
| 687 |
+
"loss": 0.0558,
|
| 688 |
+
"step": 212
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.46,
|
| 692 |
+
"learning_rate": 7.08843537414966e-05,
|
| 693 |
+
"loss": 0.0584,
|
| 694 |
+
"step": 214
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 1.47,
|
| 698 |
+
"learning_rate": 7.061224489795919e-05,
|
| 699 |
+
"loss": 0.0537,
|
| 700 |
+
"step": 216
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 1.48,
|
| 704 |
+
"learning_rate": 7.034013605442176e-05,
|
| 705 |
+
"loss": 0.0485,
|
| 706 |
+
"step": 218
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.5,
|
| 710 |
+
"learning_rate": 7.006802721088435e-05,
|
| 711 |
+
"loss": 0.0617,
|
| 712 |
+
"step": 220
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 1.51,
|
| 716 |
+
"learning_rate": 6.979591836734695e-05,
|
| 717 |
+
"loss": 0.0548,
|
| 718 |
+
"step": 222
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.52,
|
| 722 |
+
"learning_rate": 6.952380952380952e-05,
|
| 723 |
+
"loss": 0.0497,
|
| 724 |
+
"step": 224
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.54,
|
| 728 |
+
"learning_rate": 6.925170068027211e-05,
|
| 729 |
+
"loss": 0.0519,
|
| 730 |
+
"step": 226
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.55,
|
| 734 |
+
"learning_rate": 6.897959183673471e-05,
|
| 735 |
+
"loss": 0.0531,
|
| 736 |
+
"step": 228
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.56,
|
| 740 |
+
"learning_rate": 6.870748299319728e-05,
|
| 741 |
+
"loss": 0.053,
|
| 742 |
+
"step": 230
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 1.58,
|
| 746 |
+
"learning_rate": 6.843537414965987e-05,
|
| 747 |
+
"loss": 0.0558,
|
| 748 |
+
"step": 232
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 1.59,
|
| 752 |
+
"learning_rate": 6.816326530612245e-05,
|
| 753 |
+
"loss": 0.0508,
|
| 754 |
+
"step": 234
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.61,
|
| 758 |
+
"learning_rate": 6.789115646258504e-05,
|
| 759 |
+
"loss": 0.059,
|
| 760 |
+
"step": 236
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 1.62,
|
| 764 |
+
"learning_rate": 6.761904761904763e-05,
|
| 765 |
+
"loss": 0.0566,
|
| 766 |
+
"step": 238
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.63,
|
| 770 |
+
"learning_rate": 6.73469387755102e-05,
|
| 771 |
+
"loss": 0.0504,
|
| 772 |
+
"step": 240
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.65,
|
| 776 |
+
"learning_rate": 6.70748299319728e-05,
|
| 777 |
+
"loss": 0.0569,
|
| 778 |
+
"step": 242
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 1.66,
|
| 782 |
+
"learning_rate": 6.680272108843538e-05,
|
| 783 |
+
"loss": 0.0504,
|
| 784 |
+
"step": 244
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 1.67,
|
| 788 |
+
"learning_rate": 6.653061224489796e-05,
|
| 789 |
+
"loss": 0.0492,
|
| 790 |
+
"step": 246
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.69,
|
| 794 |
+
"learning_rate": 6.625850340136056e-05,
|
| 795 |
+
"loss": 0.0477,
|
| 796 |
+
"step": 248
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.7,
|
| 800 |
+
"learning_rate": 6.598639455782313e-05,
|
| 801 |
+
"loss": 0.0531,
|
| 802 |
+
"step": 250
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.7,
|
| 806 |
+
"eval_f1": 0.8437027128569305,
|
| 807 |
+
"eval_loss": 0.0455990694463253,
|
| 808 |
+
"eval_precision": 0.836850346106293,
|
| 809 |
+
"eval_recall": 0.8506783894105371,
|
| 810 |
+
"eval_runtime": 11.2699,
|
| 811 |
+
"eval_samples_per_second": 131.501,
|
| 812 |
+
"eval_steps_per_second": 0.532,
|
| 813 |
+
"step": 250
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.71,
|
| 817 |
+
"learning_rate": 6.571428571428571e-05,
|
| 818 |
+
"loss": 0.053,
|
| 819 |
+
"step": 252
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.73,
|
| 823 |
+
"learning_rate": 6.54421768707483e-05,
|
| 824 |
+
"loss": 0.0451,
|
| 825 |
+
"step": 254
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.74,
|
| 829 |
+
"learning_rate": 6.517006802721089e-05,
|
| 830 |
+
"loss": 0.0366,
|
| 831 |
+
"step": 256
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.76,
|
| 835 |
+
"learning_rate": 6.489795918367347e-05,
|
| 836 |
+
"loss": 0.0465,
|
| 837 |
+
"step": 258
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.77,
|
| 841 |
+
"learning_rate": 6.462585034013606e-05,
|
| 842 |
+
"loss": 0.051,
|
| 843 |
+
"step": 260
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.78,
|
| 847 |
+
"learning_rate": 6.435374149659864e-05,
|
| 848 |
+
"loss": 0.0484,
|
| 849 |
+
"step": 262
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.8,
|
| 853 |
+
"learning_rate": 6.408163265306123e-05,
|
| 854 |
+
"loss": 0.0503,
|
| 855 |
+
"step": 264
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 1.81,
|
| 859 |
+
"learning_rate": 6.38095238095238e-05,
|
| 860 |
+
"loss": 0.0518,
|
| 861 |
+
"step": 266
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.82,
|
| 865 |
+
"learning_rate": 6.35374149659864e-05,
|
| 866 |
+
"loss": 0.0471,
|
| 867 |
+
"step": 268
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.84,
|
| 871 |
+
"learning_rate": 6.326530612244899e-05,
|
| 872 |
+
"loss": 0.0519,
|
| 873 |
+
"step": 270
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.85,
|
| 877 |
+
"learning_rate": 6.299319727891156e-05,
|
| 878 |
+
"loss": 0.0475,
|
| 879 |
+
"step": 272
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.86,
|
| 883 |
+
"learning_rate": 6.272108843537415e-05,
|
| 884 |
+
"loss": 0.0532,
|
| 885 |
+
"step": 274
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.88,
|
| 889 |
+
"learning_rate": 6.244897959183675e-05,
|
| 890 |
+
"loss": 0.0572,
|
| 891 |
+
"step": 276
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.89,
|
| 895 |
+
"learning_rate": 6.217687074829932e-05,
|
| 896 |
+
"loss": 0.0521,
|
| 897 |
+
"step": 278
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.9,
|
| 901 |
+
"learning_rate": 6.19047619047619e-05,
|
| 902 |
+
"loss": 0.0499,
|
| 903 |
+
"step": 280
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.92,
|
| 907 |
+
"learning_rate": 6.163265306122449e-05,
|
| 908 |
+
"loss": 0.0453,
|
| 909 |
+
"step": 282
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.93,
|
| 913 |
+
"learning_rate": 6.136054421768708e-05,
|
| 914 |
+
"loss": 0.0484,
|
| 915 |
+
"step": 284
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 1.95,
|
| 919 |
+
"learning_rate": 6.108843537414966e-05,
|
| 920 |
+
"loss": 0.0477,
|
| 921 |
+
"step": 286
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 1.96,
|
| 925 |
+
"learning_rate": 6.081632653061224e-05,
|
| 926 |
+
"loss": 0.0457,
|
| 927 |
+
"step": 288
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.97,
|
| 931 |
+
"learning_rate": 6.0544217687074836e-05,
|
| 932 |
+
"loss": 0.0425,
|
| 933 |
+
"step": 290
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.99,
|
| 937 |
+
"learning_rate": 6.027210884353742e-05,
|
| 938 |
+
"loss": 0.0487,
|
| 939 |
+
"step": 292
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 2.0,
|
| 943 |
+
"learning_rate": 6e-05,
|
| 944 |
+
"loss": 0.0499,
|
| 945 |
+
"step": 294
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 2.01,
|
| 949 |
+
"learning_rate": 5.972789115646259e-05,
|
| 950 |
+
"loss": 0.0428,
|
| 951 |
+
"step": 296
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 2.03,
|
| 955 |
+
"learning_rate": 5.945578231292517e-05,
|
| 956 |
+
"loss": 0.047,
|
| 957 |
+
"step": 298
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.04,
|
| 961 |
+
"learning_rate": 5.918367346938776e-05,
|
| 962 |
+
"loss": 0.0414,
|
| 963 |
+
"step": 300
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.04,
|
| 967 |
+
"eval_f1": 0.8653020451693569,
|
| 968 |
+
"eval_loss": 0.039749592542648315,
|
| 969 |
+
"eval_precision": 0.8607319627563133,
|
| 970 |
+
"eval_recall": 0.8699310233685053,
|
| 971 |
+
"eval_runtime": 11.2277,
|
| 972 |
+
"eval_samples_per_second": 131.995,
|
| 973 |
+
"eval_steps_per_second": 0.534,
|
| 974 |
+
"step": 300
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 2.05,
|
| 978 |
+
"learning_rate": 5.8911564625850346e-05,
|
| 979 |
+
"loss": 0.0381,
|
| 980 |
+
"step": 302
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 2.07,
|
| 984 |
+
"learning_rate": 5.8639455782312925e-05,
|
| 985 |
+
"loss": 0.0445,
|
| 986 |
+
"step": 304
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 2.08,
|
| 990 |
+
"learning_rate": 5.836734693877551e-05,
|
| 991 |
+
"loss": 0.0413,
|
| 992 |
+
"step": 306
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 2.1,
|
| 996 |
+
"learning_rate": 5.8095238095238104e-05,
|
| 997 |
+
"loss": 0.0444,
|
| 998 |
+
"step": 308
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.11,
|
| 1002 |
+
"learning_rate": 5.782312925170068e-05,
|
| 1003 |
+
"loss": 0.0489,
|
| 1004 |
+
"step": 310
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.12,
|
| 1008 |
+
"learning_rate": 5.755102040816327e-05,
|
| 1009 |
+
"loss": 0.0465,
|
| 1010 |
+
"step": 312
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 2.14,
|
| 1014 |
+
"learning_rate": 5.727891156462585e-05,
|
| 1015 |
+
"loss": 0.0379,
|
| 1016 |
+
"step": 314
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 2.15,
|
| 1020 |
+
"learning_rate": 5.7006802721088435e-05,
|
| 1021 |
+
"loss": 0.0307,
|
| 1022 |
+
"step": 316
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 2.16,
|
| 1026 |
+
"learning_rate": 5.673469387755103e-05,
|
| 1027 |
+
"loss": 0.0484,
|
| 1028 |
+
"step": 318
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 2.18,
|
| 1032 |
+
"learning_rate": 5.646258503401361e-05,
|
| 1033 |
+
"loss": 0.04,
|
| 1034 |
+
"step": 320
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.19,
|
| 1038 |
+
"learning_rate": 5.619047619047619e-05,
|
| 1039 |
+
"loss": 0.0368,
|
| 1040 |
+
"step": 322
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 2.2,
|
| 1044 |
+
"learning_rate": 5.5918367346938786e-05,
|
| 1045 |
+
"loss": 0.0387,
|
| 1046 |
+
"step": 324
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 2.22,
|
| 1050 |
+
"learning_rate": 5.564625850340136e-05,
|
| 1051 |
+
"loss": 0.0357,
|
| 1052 |
+
"step": 326
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 2.23,
|
| 1056 |
+
"learning_rate": 5.537414965986395e-05,
|
| 1057 |
+
"loss": 0.0364,
|
| 1058 |
+
"step": 328
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 2.24,
|
| 1062 |
+
"learning_rate": 5.510204081632653e-05,
|
| 1063 |
+
"loss": 0.0404,
|
| 1064 |
+
"step": 330
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 2.26,
|
| 1068 |
+
"learning_rate": 5.4829931972789117e-05,
|
| 1069 |
+
"loss": 0.0379,
|
| 1070 |
+
"step": 332
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 2.27,
|
| 1074 |
+
"learning_rate": 5.455782312925171e-05,
|
| 1075 |
+
"loss": 0.0472,
|
| 1076 |
+
"step": 334
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 2.29,
|
| 1080 |
+
"learning_rate": 5.428571428571428e-05,
|
| 1081 |
+
"loss": 0.0394,
|
| 1082 |
+
"step": 336
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 2.3,
|
| 1086 |
+
"learning_rate": 5.4013605442176875e-05,
|
| 1087 |
+
"loss": 0.0389,
|
| 1088 |
+
"step": 338
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.31,
|
| 1092 |
+
"learning_rate": 5.374149659863946e-05,
|
| 1093 |
+
"loss": 0.0362,
|
| 1094 |
+
"step": 340
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.33,
|
| 1098 |
+
"learning_rate": 5.346938775510204e-05,
|
| 1099 |
+
"loss": 0.0359,
|
| 1100 |
+
"step": 342
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 2.34,
|
| 1104 |
+
"learning_rate": 5.319727891156463e-05,
|
| 1105 |
+
"loss": 0.0356,
|
| 1106 |
+
"step": 344
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 2.35,
|
| 1110 |
+
"learning_rate": 5.292517006802722e-05,
|
| 1111 |
+
"loss": 0.0408,
|
| 1112 |
+
"step": 346
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 2.37,
|
| 1116 |
+
"learning_rate": 5.26530612244898e-05,
|
| 1117 |
+
"loss": 0.0382,
|
| 1118 |
+
"step": 348
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 2.38,
|
| 1122 |
+
"learning_rate": 5.2380952380952384e-05,
|
| 1123 |
+
"loss": 0.0315,
|
| 1124 |
+
"step": 350
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 2.38,
|
| 1128 |
+
"eval_f1": 0.8847392138215896,
|
| 1129 |
+
"eval_loss": 0.0348842516541481,
|
| 1130 |
+
"eval_precision": 0.8886000451956572,
|
| 1131 |
+
"eval_recall": 0.8809217002342745,
|
| 1132 |
+
"eval_runtime": 11.2848,
|
| 1133 |
+
"eval_samples_per_second": 131.327,
|
| 1134 |
+
"eval_steps_per_second": 0.532,
|
| 1135 |
+
"step": 350
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 2.39,
|
| 1139 |
+
"learning_rate": 5.2108843537414964e-05,
|
| 1140 |
+
"loss": 0.0381,
|
| 1141 |
+
"step": 352
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 2.41,
|
| 1145 |
+
"learning_rate": 5.1836734693877557e-05,
|
| 1146 |
+
"loss": 0.0356,
|
| 1147 |
+
"step": 354
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 2.42,
|
| 1151 |
+
"learning_rate": 5.156462585034014e-05,
|
| 1152 |
+
"loss": 0.041,
|
| 1153 |
+
"step": 356
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 2.44,
|
| 1157 |
+
"learning_rate": 5.129251700680272e-05,
|
| 1158 |
+
"loss": 0.0387,
|
| 1159 |
+
"step": 358
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 2.45,
|
| 1163 |
+
"learning_rate": 5.102040816326531e-05,
|
| 1164 |
+
"loss": 0.0364,
|
| 1165 |
+
"step": 360
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.46,
|
| 1169 |
+
"learning_rate": 5.07482993197279e-05,
|
| 1170 |
+
"loss": 0.0342,
|
| 1171 |
+
"step": 362
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 2.48,
|
| 1175 |
+
"learning_rate": 5.047619047619048e-05,
|
| 1176 |
+
"loss": 0.04,
|
| 1177 |
+
"step": 364
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 2.49,
|
| 1181 |
+
"learning_rate": 5.0204081632653066e-05,
|
| 1182 |
+
"loss": 0.039,
|
| 1183 |
+
"step": 366
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 2.5,
|
| 1187 |
+
"learning_rate": 4.993197278911565e-05,
|
| 1188 |
+
"loss": 0.0434,
|
| 1189 |
+
"step": 368
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 2.52,
|
| 1193 |
+
"learning_rate": 4.965986394557823e-05,
|
| 1194 |
+
"loss": 0.0346,
|
| 1195 |
+
"step": 370
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 2.53,
|
| 1199 |
+
"learning_rate": 4.938775510204082e-05,
|
| 1200 |
+
"loss": 0.0423,
|
| 1201 |
+
"step": 372
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 2.54,
|
| 1205 |
+
"learning_rate": 4.9115646258503404e-05,
|
| 1206 |
+
"loss": 0.0368,
|
| 1207 |
+
"step": 374
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.56,
|
| 1211 |
+
"learning_rate": 4.884353741496599e-05,
|
| 1212 |
+
"loss": 0.0382,
|
| 1213 |
+
"step": 376
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 2.57,
|
| 1217 |
+
"learning_rate": 4.8571428571428576e-05,
|
| 1218 |
+
"loss": 0.0387,
|
| 1219 |
+
"step": 378
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 2.59,
|
| 1223 |
+
"learning_rate": 4.8299319727891155e-05,
|
| 1224 |
+
"loss": 0.0394,
|
| 1225 |
+
"step": 380
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 2.6,
|
| 1229 |
+
"learning_rate": 4.802721088435375e-05,
|
| 1230 |
+
"loss": 0.0364,
|
| 1231 |
+
"step": 382
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 2.61,
|
| 1235 |
+
"learning_rate": 4.775510204081633e-05,
|
| 1236 |
+
"loss": 0.0465,
|
| 1237 |
+
"step": 384
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 2.63,
|
| 1241 |
+
"learning_rate": 4.7482993197278913e-05,
|
| 1242 |
+
"loss": 0.0269,
|
| 1243 |
+
"step": 386
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 2.64,
|
| 1247 |
+
"learning_rate": 4.72108843537415e-05,
|
| 1248 |
+
"loss": 0.0391,
|
| 1249 |
+
"step": 388
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.65,
|
| 1253 |
+
"learning_rate": 4.6938775510204086e-05,
|
| 1254 |
+
"loss": 0.0343,
|
| 1255 |
+
"step": 390
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 2.67,
|
| 1259 |
+
"learning_rate": 4.666666666666667e-05,
|
| 1260 |
+
"loss": 0.0358,
|
| 1261 |
+
"step": 392
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 2.68,
|
| 1265 |
+
"learning_rate": 4.639455782312925e-05,
|
| 1266 |
+
"loss": 0.0409,
|
| 1267 |
+
"step": 394
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 2.69,
|
| 1271 |
+
"learning_rate": 4.612244897959184e-05,
|
| 1272 |
+
"loss": 0.0273,
|
| 1273 |
+
"step": 396
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 2.71,
|
| 1277 |
+
"learning_rate": 4.585034013605442e-05,
|
| 1278 |
+
"loss": 0.0336,
|
| 1279 |
+
"step": 398
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 2.72,
|
| 1283 |
+
"learning_rate": 4.557823129251701e-05,
|
| 1284 |
+
"loss": 0.0318,
|
| 1285 |
+
"step": 400
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 2.72,
|
| 1289 |
+
"eval_f1": 0.8934494072355922,
|
| 1290 |
+
"eval_loss": 0.03241937607526779,
|
| 1291 |
+
"eval_precision": 0.8919694788154646,
|
| 1292 |
+
"eval_recall": 0.8949442879595663,
|
| 1293 |
+
"eval_runtime": 11.1708,
|
| 1294 |
+
"eval_samples_per_second": 132.667,
|
| 1295 |
+
"eval_steps_per_second": 0.537,
|
| 1296 |
+
"step": 400
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 2.73,
|
| 1300 |
+
"learning_rate": 4.5306122448979595e-05,
|
| 1301 |
+
"loss": 0.0377,
|
| 1302 |
+
"step": 402
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 2.75,
|
| 1306 |
+
"learning_rate": 4.5034013605442174e-05,
|
| 1307 |
+
"loss": 0.0335,
|
| 1308 |
+
"step": 404
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 2.76,
|
| 1312 |
+
"learning_rate": 4.476190476190477e-05,
|
| 1313 |
+
"loss": 0.0326,
|
| 1314 |
+
"step": 406
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 2.78,
|
| 1318 |
+
"learning_rate": 4.448979591836735e-05,
|
| 1319 |
+
"loss": 0.0422,
|
| 1320 |
+
"step": 408
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.79,
|
| 1324 |
+
"learning_rate": 4.421768707482993e-05,
|
| 1325 |
+
"loss": 0.0329,
|
| 1326 |
+
"step": 410
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.8,
|
| 1330 |
+
"learning_rate": 4.394557823129252e-05,
|
| 1331 |
+
"loss": 0.0452,
|
| 1332 |
+
"step": 412
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 2.82,
|
| 1336 |
+
"learning_rate": 4.3673469387755105e-05,
|
| 1337 |
+
"loss": 0.0325,
|
| 1338 |
+
"step": 414
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 2.83,
|
| 1342 |
+
"learning_rate": 4.340136054421769e-05,
|
| 1343 |
+
"loss": 0.0355,
|
| 1344 |
+
"step": 416
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 2.84,
|
| 1348 |
+
"learning_rate": 4.312925170068027e-05,
|
| 1349 |
+
"loss": 0.0333,
|
| 1350 |
+
"step": 418
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 2.86,
|
| 1354 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 1355 |
+
"loss": 0.0348,
|
| 1356 |
+
"step": 420
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 2.87,
|
| 1360 |
+
"learning_rate": 4.258503401360545e-05,
|
| 1361 |
+
"loss": 0.0332,
|
| 1362 |
+
"step": 422
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 2.88,
|
| 1366 |
+
"learning_rate": 4.231292517006803e-05,
|
| 1367 |
+
"loss": 0.0336,
|
| 1368 |
+
"step": 424
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.9,
|
| 1372 |
+
"learning_rate": 4.2040816326530615e-05,
|
| 1373 |
+
"loss": 0.0363,
|
| 1374 |
+
"step": 426
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.91,
|
| 1378 |
+
"learning_rate": 4.1768707482993194e-05,
|
| 1379 |
+
"loss": 0.0303,
|
| 1380 |
+
"step": 428
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 2.93,
|
| 1384 |
+
"learning_rate": 4.149659863945579e-05,
|
| 1385 |
+
"loss": 0.0308,
|
| 1386 |
+
"step": 430
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 2.94,
|
| 1390 |
+
"learning_rate": 4.122448979591837e-05,
|
| 1391 |
+
"loss": 0.0362,
|
| 1392 |
+
"step": 432
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 2.95,
|
| 1396 |
+
"learning_rate": 4.095238095238095e-05,
|
| 1397 |
+
"loss": 0.0385,
|
| 1398 |
+
"step": 434
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 2.97,
|
| 1402 |
+
"learning_rate": 4.068027210884354e-05,
|
| 1403 |
+
"loss": 0.0341,
|
| 1404 |
+
"step": 436
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 2.98,
|
| 1408 |
+
"learning_rate": 4.0408163265306124e-05,
|
| 1409 |
+
"loss": 0.0327,
|
| 1410 |
+
"step": 438
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.99,
|
| 1414 |
+
"learning_rate": 4.013605442176871e-05,
|
| 1415 |
+
"loss": 0.0365,
|
| 1416 |
+
"step": 440
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 3.01,
|
| 1420 |
+
"learning_rate": 3.9863945578231296e-05,
|
| 1421 |
+
"loss": 0.0373,
|
| 1422 |
+
"step": 442
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 3.02,
|
| 1426 |
+
"learning_rate": 3.9591836734693876e-05,
|
| 1427 |
+
"loss": 0.0305,
|
| 1428 |
+
"step": 444
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 3.03,
|
| 1432 |
+
"learning_rate": 3.931972789115647e-05,
|
| 1433 |
+
"loss": 0.0248,
|
| 1434 |
+
"step": 446
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 3.05,
|
| 1438 |
+
"learning_rate": 3.904761904761905e-05,
|
| 1439 |
+
"loss": 0.0333,
|
| 1440 |
+
"step": 448
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 3.06,
|
| 1444 |
+
"learning_rate": 3.8775510204081634e-05,
|
| 1445 |
+
"loss": 0.0335,
|
| 1446 |
+
"step": 450
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 3.06,
|
| 1450 |
+
"eval_f1": 0.9027128432459335,
|
| 1451 |
+
"eval_loss": 0.03037634864449501,
|
| 1452 |
+
"eval_precision": 0.9016257082029295,
|
| 1453 |
+
"eval_recall": 0.9038126272236696,
|
| 1454 |
+
"eval_runtime": 10.8474,
|
| 1455 |
+
"eval_samples_per_second": 136.623,
|
| 1456 |
+
"eval_steps_per_second": 0.553,
|
| 1457 |
+
"step": 450
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 3.07,
|
| 1461 |
+
"learning_rate": 3.850340136054422e-05,
|
| 1462 |
+
"loss": 0.0303,
|
| 1463 |
+
"step": 452
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 3.09,
|
| 1467 |
+
"learning_rate": 3.8231292517006806e-05,
|
| 1468 |
+
"loss": 0.0337,
|
| 1469 |
+
"step": 454
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 3.1,
|
| 1473 |
+
"learning_rate": 3.795918367346939e-05,
|
| 1474 |
+
"loss": 0.0298,
|
| 1475 |
+
"step": 456
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 3.12,
|
| 1479 |
+
"learning_rate": 3.768707482993197e-05,
|
| 1480 |
+
"loss": 0.0274,
|
| 1481 |
+
"step": 458
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 3.13,
|
| 1485 |
+
"learning_rate": 3.7414965986394564e-05,
|
| 1486 |
+
"loss": 0.0282,
|
| 1487 |
+
"step": 460
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 3.14,
|
| 1491 |
+
"learning_rate": 3.7142857142857143e-05,
|
| 1492 |
+
"loss": 0.0279,
|
| 1493 |
+
"step": 462
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 3.16,
|
| 1497 |
+
"learning_rate": 3.687074829931973e-05,
|
| 1498 |
+
"loss": 0.035,
|
| 1499 |
+
"step": 464
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 3.17,
|
| 1503 |
+
"learning_rate": 3.6598639455782316e-05,
|
| 1504 |
+
"loss": 0.0396,
|
| 1505 |
+
"step": 466
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 3.18,
|
| 1509 |
+
"learning_rate": 3.63265306122449e-05,
|
| 1510 |
+
"loss": 0.0291,
|
| 1511 |
+
"step": 468
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 3.2,
|
| 1515 |
+
"learning_rate": 3.605442176870749e-05,
|
| 1516 |
+
"loss": 0.0323,
|
| 1517 |
+
"step": 470
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 3.21,
|
| 1521 |
+
"learning_rate": 3.578231292517007e-05,
|
| 1522 |
+
"loss": 0.0303,
|
| 1523 |
+
"step": 472
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 3.22,
|
| 1527 |
+
"learning_rate": 3.551020408163265e-05,
|
| 1528 |
+
"loss": 0.0304,
|
| 1529 |
+
"step": 474
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 3.24,
|
| 1533 |
+
"learning_rate": 3.523809523809524e-05,
|
| 1534 |
+
"loss": 0.0339,
|
| 1535 |
+
"step": 476
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 3.25,
|
| 1539 |
+
"learning_rate": 3.4965986394557825e-05,
|
| 1540 |
+
"loss": 0.0326,
|
| 1541 |
+
"step": 478
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 3.27,
|
| 1545 |
+
"learning_rate": 3.469387755102041e-05,
|
| 1546 |
+
"loss": 0.0287,
|
| 1547 |
+
"step": 480
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 3.28,
|
| 1551 |
+
"learning_rate": 3.442176870748299e-05,
|
| 1552 |
+
"loss": 0.0273,
|
| 1553 |
+
"step": 482
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 3.29,
|
| 1557 |
+
"learning_rate": 3.4149659863945583e-05,
|
| 1558 |
+
"loss": 0.031,
|
| 1559 |
+
"step": 484
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 3.31,
|
| 1563 |
+
"learning_rate": 3.387755102040816e-05,
|
| 1564 |
+
"loss": 0.0274,
|
| 1565 |
+
"step": 486
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 3.32,
|
| 1569 |
+
"learning_rate": 3.360544217687075e-05,
|
| 1570 |
+
"loss": 0.0314,
|
| 1571 |
+
"step": 488
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 3.33,
|
| 1575 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 1576 |
+
"loss": 0.0238,
|
| 1577 |
+
"step": 490
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 3.35,
|
| 1581 |
+
"learning_rate": 3.306122448979592e-05,
|
| 1582 |
+
"loss": 0.0301,
|
| 1583 |
+
"step": 492
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 3.36,
|
| 1587 |
+
"learning_rate": 3.278911564625851e-05,
|
| 1588 |
+
"loss": 0.0326,
|
| 1589 |
+
"step": 494
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 3.37,
|
| 1593 |
+
"learning_rate": 3.2517006802721086e-05,
|
| 1594 |
+
"loss": 0.0322,
|
| 1595 |
+
"step": 496
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 3.39,
|
| 1599 |
+
"learning_rate": 3.224489795918367e-05,
|
| 1600 |
+
"loss": 0.0265,
|
| 1601 |
+
"step": 498
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 3.4,
|
| 1605 |
+
"learning_rate": 3.1972789115646265e-05,
|
| 1606 |
+
"loss": 0.0302,
|
| 1607 |
+
"step": 500
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 3.4,
|
| 1611 |
+
"eval_f1": 0.9087960923681575,
|
| 1612 |
+
"eval_loss": 0.02837410755455494,
|
| 1613 |
+
"eval_precision": 0.9100790506916395,
|
| 1614 |
+
"eval_recall": 0.9075267180265848,
|
| 1615 |
+
"eval_runtime": 10.84,
|
| 1616 |
+
"eval_samples_per_second": 136.716,
|
| 1617 |
+
"eval_steps_per_second": 0.554,
|
| 1618 |
+
"step": 500
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 3.41,
|
| 1622 |
+
"learning_rate": 3.1700680272108845e-05,
|
| 1623 |
+
"loss": 0.03,
|
| 1624 |
+
"step": 502
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 3.43,
|
| 1628 |
+
"learning_rate": 3.142857142857143e-05,
|
| 1629 |
+
"loss": 0.0302,
|
| 1630 |
+
"step": 504
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 3.44,
|
| 1634 |
+
"learning_rate": 3.115646258503401e-05,
|
| 1635 |
+
"loss": 0.0257,
|
| 1636 |
+
"step": 506
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 3.46,
|
| 1640 |
+
"learning_rate": 3.08843537414966e-05,
|
| 1641 |
+
"loss": 0.0288,
|
| 1642 |
+
"step": 508
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 3.47,
|
| 1646 |
+
"learning_rate": 3.061224489795919e-05,
|
| 1647 |
+
"loss": 0.0349,
|
| 1648 |
+
"step": 510
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 3.48,
|
| 1652 |
+
"learning_rate": 3.0340136054421768e-05,
|
| 1653 |
+
"loss": 0.0303,
|
| 1654 |
+
"step": 512
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 3.5,
|
| 1658 |
+
"learning_rate": 3.0068027210884354e-05,
|
| 1659 |
+
"loss": 0.0309,
|
| 1660 |
+
"step": 514
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"epoch": 3.51,
|
| 1664 |
+
"learning_rate": 2.9795918367346944e-05,
|
| 1665 |
+
"loss": 0.0271,
|
| 1666 |
+
"step": 516
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 3.52,
|
| 1670 |
+
"learning_rate": 2.9523809523809526e-05,
|
| 1671 |
+
"loss": 0.0291,
|
| 1672 |
+
"step": 518
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 3.54,
|
| 1676 |
+
"learning_rate": 2.925170068027211e-05,
|
| 1677 |
+
"loss": 0.0304,
|
| 1678 |
+
"step": 520
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 3.55,
|
| 1682 |
+
"learning_rate": 2.8979591836734692e-05,
|
| 1683 |
+
"loss": 0.0345,
|
| 1684 |
+
"step": 522
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 3.56,
|
| 1688 |
+
"learning_rate": 2.870748299319728e-05,
|
| 1689 |
+
"loss": 0.0276,
|
| 1690 |
+
"step": 524
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 3.58,
|
| 1694 |
+
"learning_rate": 2.8435374149659867e-05,
|
| 1695 |
+
"loss": 0.0299,
|
| 1696 |
+
"step": 526
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 3.59,
|
| 1700 |
+
"learning_rate": 2.816326530612245e-05,
|
| 1701 |
+
"loss": 0.0269,
|
| 1702 |
+
"step": 528
|
| 1703 |
+
},
|
| 1704 |
+
{
|
| 1705 |
+
"epoch": 3.61,
|
| 1706 |
+
"learning_rate": 2.7891156462585033e-05,
|
| 1707 |
+
"loss": 0.0281,
|
| 1708 |
+
"step": 530
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 3.62,
|
| 1712 |
+
"learning_rate": 2.7619047619047622e-05,
|
| 1713 |
+
"loss": 0.0329,
|
| 1714 |
+
"step": 532
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 3.63,
|
| 1718 |
+
"learning_rate": 2.7346938775510205e-05,
|
| 1719 |
+
"loss": 0.028,
|
| 1720 |
+
"step": 534
|
| 1721 |
+
},
|
| 1722 |
+
{
|
| 1723 |
+
"epoch": 3.65,
|
| 1724 |
+
"learning_rate": 2.707482993197279e-05,
|
| 1725 |
+
"loss": 0.0283,
|
| 1726 |
+
"step": 536
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 3.66,
|
| 1730 |
+
"learning_rate": 2.6802721088435374e-05,
|
| 1731 |
+
"loss": 0.0313,
|
| 1732 |
+
"step": 538
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 3.67,
|
| 1736 |
+
"learning_rate": 2.6530612244897963e-05,
|
| 1737 |
+
"loss": 0.027,
|
| 1738 |
+
"step": 540
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 3.69,
|
| 1742 |
+
"learning_rate": 2.6258503401360546e-05,
|
| 1743 |
+
"loss": 0.029,
|
| 1744 |
+
"step": 542
|
| 1745 |
+
},
|
| 1746 |
+
{
|
| 1747 |
+
"epoch": 3.7,
|
| 1748 |
+
"learning_rate": 2.598639455782313e-05,
|
| 1749 |
+
"loss": 0.0262,
|
| 1750 |
+
"step": 544
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 3.71,
|
| 1754 |
+
"learning_rate": 2.5714285714285714e-05,
|
| 1755 |
+
"loss": 0.0289,
|
| 1756 |
+
"step": 546
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 3.73,
|
| 1760 |
+
"learning_rate": 2.54421768707483e-05,
|
| 1761 |
+
"loss": 0.0326,
|
| 1762 |
+
"step": 548
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 3.74,
|
| 1766 |
+
"learning_rate": 2.5170068027210887e-05,
|
| 1767 |
+
"loss": 0.0289,
|
| 1768 |
+
"step": 550
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 3.74,
|
| 1772 |
+
"eval_f1": 0.912944557830135,
|
| 1773 |
+
"eval_loss": 0.027326099574565887,
|
| 1774 |
+
"eval_precision": 0.9129149606541497,
|
| 1775 |
+
"eval_recall": 0.9129841575737253,
|
| 1776 |
+
"eval_runtime": 11.1164,
|
| 1777 |
+
"eval_samples_per_second": 133.317,
|
| 1778 |
+
"eval_steps_per_second": 0.54,
|
| 1779 |
+
"step": 550
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 3.76,
|
| 1783 |
+
"learning_rate": 2.489795918367347e-05,
|
| 1784 |
+
"loss": 0.0277,
|
| 1785 |
+
"step": 552
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 3.77,
|
| 1789 |
+
"learning_rate": 2.4625850340136055e-05,
|
| 1790 |
+
"loss": 0.0269,
|
| 1791 |
+
"step": 554
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 3.78,
|
| 1795 |
+
"learning_rate": 2.4353741496598638e-05,
|
| 1796 |
+
"loss": 0.0263,
|
| 1797 |
+
"step": 556
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 3.8,
|
| 1801 |
+
"learning_rate": 2.4081632653061224e-05,
|
| 1802 |
+
"loss": 0.0342,
|
| 1803 |
+
"step": 558
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 3.81,
|
| 1807 |
+
"learning_rate": 2.380952380952381e-05,
|
| 1808 |
+
"loss": 0.0234,
|
| 1809 |
+
"step": 560
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 3.82,
|
| 1813 |
+
"learning_rate": 2.3537414965986396e-05,
|
| 1814 |
+
"loss": 0.0255,
|
| 1815 |
+
"step": 562
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 3.84,
|
| 1819 |
+
"learning_rate": 2.326530612244898e-05,
|
| 1820 |
+
"loss": 0.0329,
|
| 1821 |
+
"step": 564
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 3.85,
|
| 1825 |
+
"learning_rate": 2.2993197278911565e-05,
|
| 1826 |
+
"loss": 0.0287,
|
| 1827 |
+
"step": 566
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 3.86,
|
| 1831 |
+
"learning_rate": 2.272108843537415e-05,
|
| 1832 |
+
"loss": 0.0272,
|
| 1833 |
+
"step": 568
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 3.88,
|
| 1837 |
+
"learning_rate": 2.2448979591836737e-05,
|
| 1838 |
+
"loss": 0.0248,
|
| 1839 |
+
"step": 570
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 3.89,
|
| 1843 |
+
"learning_rate": 2.2176870748299323e-05,
|
| 1844 |
+
"loss": 0.0275,
|
| 1845 |
+
"step": 572
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 3.9,
|
| 1849 |
+
"learning_rate": 2.1904761904761906e-05,
|
| 1850 |
+
"loss": 0.0269,
|
| 1851 |
+
"step": 574
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 3.92,
|
| 1855 |
+
"learning_rate": 2.1632653061224492e-05,
|
| 1856 |
+
"loss": 0.0288,
|
| 1857 |
+
"step": 576
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 3.93,
|
| 1861 |
+
"learning_rate": 2.1360544217687075e-05,
|
| 1862 |
+
"loss": 0.0288,
|
| 1863 |
+
"step": 578
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 3.95,
|
| 1867 |
+
"learning_rate": 2.108843537414966e-05,
|
| 1868 |
+
"loss": 0.0244,
|
| 1869 |
+
"step": 580
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 3.96,
|
| 1873 |
+
"learning_rate": 2.0816326530612247e-05,
|
| 1874 |
+
"loss": 0.0255,
|
| 1875 |
+
"step": 582
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 3.97,
|
| 1879 |
+
"learning_rate": 2.0544217687074833e-05,
|
| 1880 |
+
"loss": 0.028,
|
| 1881 |
+
"step": 584
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 3.99,
|
| 1885 |
+
"learning_rate": 2.0272108843537416e-05,
|
| 1886 |
+
"loss": 0.0209,
|
| 1887 |
+
"step": 586
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 4.0,
|
| 1891 |
+
"learning_rate": 2e-05,
|
| 1892 |
+
"loss": 0.0288,
|
| 1893 |
+
"step": 588
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 4.01,
|
| 1897 |
+
"learning_rate": 1.9727891156462584e-05,
|
| 1898 |
+
"loss": 0.0266,
|
| 1899 |
+
"step": 590
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 4.03,
|
| 1903 |
+
"learning_rate": 1.945578231292517e-05,
|
| 1904 |
+
"loss": 0.025,
|
| 1905 |
+
"step": 592
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 4.04,
|
| 1909 |
+
"learning_rate": 1.9183673469387756e-05,
|
| 1910 |
+
"loss": 0.0242,
|
| 1911 |
+
"step": 594
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 4.05,
|
| 1915 |
+
"learning_rate": 1.8911564625850343e-05,
|
| 1916 |
+
"loss": 0.0296,
|
| 1917 |
+
"step": 596
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 4.07,
|
| 1921 |
+
"learning_rate": 1.8639455782312925e-05,
|
| 1922 |
+
"loss": 0.0253,
|
| 1923 |
+
"step": 598
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 4.08,
|
| 1927 |
+
"learning_rate": 1.836734693877551e-05,
|
| 1928 |
+
"loss": 0.0206,
|
| 1929 |
+
"step": 600
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 4.08,
|
| 1933 |
+
"eval_f1": 0.9121926864008709,
|
| 1934 |
+
"eval_loss": 0.027346264570951462,
|
| 1935 |
+
"eval_precision": 0.9039821355385321,
|
| 1936 |
+
"eval_recall": 0.9205639347225317,
|
| 1937 |
+
"eval_runtime": 11.0662,
|
| 1938 |
+
"eval_samples_per_second": 133.921,
|
| 1939 |
+
"eval_steps_per_second": 0.542,
|
| 1940 |
+
"step": 600
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 4.1,
|
| 1944 |
+
"learning_rate": 1.8095238095238094e-05,
|
| 1945 |
+
"loss": 0.0298,
|
| 1946 |
+
"step": 602
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 4.11,
|
| 1950 |
+
"learning_rate": 1.7823129251700683e-05,
|
| 1951 |
+
"loss": 0.0273,
|
| 1952 |
+
"step": 604
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 4.12,
|
| 1956 |
+
"learning_rate": 1.7551020408163266e-05,
|
| 1957 |
+
"loss": 0.0275,
|
| 1958 |
+
"step": 606
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 4.14,
|
| 1962 |
+
"learning_rate": 1.7278911564625852e-05,
|
| 1963 |
+
"loss": 0.0229,
|
| 1964 |
+
"step": 608
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 4.15,
|
| 1968 |
+
"learning_rate": 1.7006802721088435e-05,
|
| 1969 |
+
"loss": 0.026,
|
| 1970 |
+
"step": 610
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 4.16,
|
| 1974 |
+
"learning_rate": 1.673469387755102e-05,
|
| 1975 |
+
"loss": 0.0235,
|
| 1976 |
+
"step": 612
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 4.18,
|
| 1980 |
+
"learning_rate": 1.6462585034013607e-05,
|
| 1981 |
+
"loss": 0.0255,
|
| 1982 |
+
"step": 614
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 4.19,
|
| 1986 |
+
"learning_rate": 1.6190476190476193e-05,
|
| 1987 |
+
"loss": 0.0279,
|
| 1988 |
+
"step": 616
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 4.2,
|
| 1992 |
+
"learning_rate": 1.5918367346938776e-05,
|
| 1993 |
+
"loss": 0.0262,
|
| 1994 |
+
"step": 618
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 4.22,
|
| 1998 |
+
"learning_rate": 1.5646258503401362e-05,
|
| 1999 |
+
"loss": 0.0228,
|
| 2000 |
+
"step": 620
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 4.23,
|
| 2004 |
+
"learning_rate": 1.5374149659863945e-05,
|
| 2005 |
+
"loss": 0.0238,
|
| 2006 |
+
"step": 622
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 4.24,
|
| 2010 |
+
"learning_rate": 1.5102040816326532e-05,
|
| 2011 |
+
"loss": 0.0251,
|
| 2012 |
+
"step": 624
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 4.26,
|
| 2016 |
+
"learning_rate": 1.4829931972789115e-05,
|
| 2017 |
+
"loss": 0.0264,
|
| 2018 |
+
"step": 626
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 4.27,
|
| 2022 |
+
"learning_rate": 1.4557823129251703e-05,
|
| 2023 |
+
"loss": 0.0271,
|
| 2024 |
+
"step": 628
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 4.29,
|
| 2028 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 2029 |
+
"loss": 0.0269,
|
| 2030 |
+
"step": 630
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 4.3,
|
| 2034 |
+
"learning_rate": 1.4013605442176872e-05,
|
| 2035 |
+
"loss": 0.0301,
|
| 2036 |
+
"step": 632
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 4.31,
|
| 2040 |
+
"learning_rate": 1.3741496598639456e-05,
|
| 2041 |
+
"loss": 0.0261,
|
| 2042 |
+
"step": 634
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 4.33,
|
| 2046 |
+
"learning_rate": 1.3469387755102042e-05,
|
| 2047 |
+
"loss": 0.0273,
|
| 2048 |
+
"step": 636
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 4.34,
|
| 2052 |
+
"learning_rate": 1.3197278911564626e-05,
|
| 2053 |
+
"loss": 0.0236,
|
| 2054 |
+
"step": 638
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 4.35,
|
| 2058 |
+
"learning_rate": 1.2925170068027212e-05,
|
| 2059 |
+
"loss": 0.0289,
|
| 2060 |
+
"step": 640
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 4.37,
|
| 2064 |
+
"learning_rate": 1.2653061224489795e-05,
|
| 2065 |
+
"loss": 0.0234,
|
| 2066 |
+
"step": 642
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 4.38,
|
| 2070 |
+
"learning_rate": 1.2380952380952381e-05,
|
| 2071 |
+
"loss": 0.0237,
|
| 2072 |
+
"step": 644
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 4.39,
|
| 2076 |
+
"learning_rate": 1.2108843537414967e-05,
|
| 2077 |
+
"loss": 0.0291,
|
| 2078 |
+
"step": 646
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 4.41,
|
| 2082 |
+
"learning_rate": 1.1836734693877552e-05,
|
| 2083 |
+
"loss": 0.0229,
|
| 2084 |
+
"step": 648
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 4.42,
|
| 2088 |
+
"learning_rate": 1.1564625850340138e-05,
|
| 2089 |
+
"loss": 0.0287,
|
| 2090 |
+
"step": 650
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 4.42,
|
| 2094 |
+
"eval_f1": 0.9175770006975295,
|
| 2095 |
+
"eval_loss": 0.025734370574355125,
|
| 2096 |
+
"eval_precision": 0.917026269273203,
|
| 2097 |
+
"eval_recall": 0.9181384060349137,
|
| 2098 |
+
"eval_runtime": 10.957,
|
| 2099 |
+
"eval_samples_per_second": 135.256,
|
| 2100 |
+
"eval_steps_per_second": 0.548,
|
| 2101 |
+
"step": 650
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 4.44,
|
| 2105 |
+
"learning_rate": 1.1292517006802722e-05,
|
| 2106 |
+
"loss": 0.0277,
|
| 2107 |
+
"step": 652
|
| 2108 |
+
},
|
| 2109 |
+
{
|
| 2110 |
+
"epoch": 4.45,
|
| 2111 |
+
"learning_rate": 1.1020408163265306e-05,
|
| 2112 |
+
"loss": 0.0259,
|
| 2113 |
+
"step": 654
|
| 2114 |
+
},
|
| 2115 |
+
{
|
| 2116 |
+
"epoch": 4.46,
|
| 2117 |
+
"learning_rate": 1.0748299319727893e-05,
|
| 2118 |
+
"loss": 0.0263,
|
| 2119 |
+
"step": 656
|
| 2120 |
+
},
|
| 2121 |
+
{
|
| 2122 |
+
"epoch": 4.48,
|
| 2123 |
+
"learning_rate": 1.0476190476190477e-05,
|
| 2124 |
+
"loss": 0.0292,
|
| 2125 |
+
"step": 658
|
| 2126 |
+
},
|
| 2127 |
+
{
|
| 2128 |
+
"epoch": 4.49,
|
| 2129 |
+
"learning_rate": 1.0204081632653061e-05,
|
| 2130 |
+
"loss": 0.0303,
|
| 2131 |
+
"step": 660
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 4.5,
|
| 2135 |
+
"learning_rate": 9.931972789115647e-06,
|
| 2136 |
+
"loss": 0.0262,
|
| 2137 |
+
"step": 662
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 4.52,
|
| 2141 |
+
"learning_rate": 9.659863945578232e-06,
|
| 2142 |
+
"loss": 0.0245,
|
| 2143 |
+
"step": 664
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 4.53,
|
| 2147 |
+
"learning_rate": 9.387755102040816e-06,
|
| 2148 |
+
"loss": 0.0222,
|
| 2149 |
+
"step": 666
|
| 2150 |
+
},
|
| 2151 |
+
{
|
| 2152 |
+
"epoch": 4.54,
|
| 2153 |
+
"learning_rate": 9.115646258503402e-06,
|
| 2154 |
+
"loss": 0.0314,
|
| 2155 |
+
"step": 668
|
| 2156 |
+
},
|
| 2157 |
+
{
|
| 2158 |
+
"epoch": 4.56,
|
| 2159 |
+
"learning_rate": 8.843537414965987e-06,
|
| 2160 |
+
"loss": 0.0261,
|
| 2161 |
+
"step": 670
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 4.57,
|
| 2165 |
+
"learning_rate": 8.571428571428573e-06,
|
| 2166 |
+
"loss": 0.0235,
|
| 2167 |
+
"step": 672
|
| 2168 |
+
},
|
| 2169 |
+
{
|
| 2170 |
+
"epoch": 4.59,
|
| 2171 |
+
"learning_rate": 8.299319727891157e-06,
|
| 2172 |
+
"loss": 0.023,
|
| 2173 |
+
"step": 674
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 4.6,
|
| 2177 |
+
"learning_rate": 8.027210884353741e-06,
|
| 2178 |
+
"loss": 0.0263,
|
| 2179 |
+
"step": 676
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 4.61,
|
| 2183 |
+
"learning_rate": 7.755102040816327e-06,
|
| 2184 |
+
"loss": 0.026,
|
| 2185 |
+
"step": 678
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 4.63,
|
| 2189 |
+
"learning_rate": 7.482993197278912e-06,
|
| 2190 |
+
"loss": 0.0238,
|
| 2191 |
+
"step": 680
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 4.64,
|
| 2195 |
+
"learning_rate": 7.210884353741497e-06,
|
| 2196 |
+
"loss": 0.0278,
|
| 2197 |
+
"step": 682
|
| 2198 |
+
},
|
| 2199 |
+
{
|
| 2200 |
+
"epoch": 4.65,
|
| 2201 |
+
"learning_rate": 6.938775510204082e-06,
|
| 2202 |
+
"loss": 0.0283,
|
| 2203 |
+
"step": 684
|
| 2204 |
+
},
|
| 2205 |
+
{
|
| 2206 |
+
"epoch": 4.67,
|
| 2207 |
+
"learning_rate": 6.666666666666667e-06,
|
| 2208 |
+
"loss": 0.0274,
|
| 2209 |
+
"step": 686
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 4.68,
|
| 2213 |
+
"learning_rate": 6.394557823129252e-06,
|
| 2214 |
+
"loss": 0.0273,
|
| 2215 |
+
"step": 688
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 4.69,
|
| 2219 |
+
"learning_rate": 6.122448979591837e-06,
|
| 2220 |
+
"loss": 0.0238,
|
| 2221 |
+
"step": 690
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 4.71,
|
| 2225 |
+
"learning_rate": 5.8503401360544215e-06,
|
| 2226 |
+
"loss": 0.0316,
|
| 2227 |
+
"step": 692
|
| 2228 |
+
},
|
| 2229 |
+
{
|
| 2230 |
+
"epoch": 4.72,
|
| 2231 |
+
"learning_rate": 5.578231292517007e-06,
|
| 2232 |
+
"loss": 0.0239,
|
| 2233 |
+
"step": 694
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 4.73,
|
| 2237 |
+
"learning_rate": 5.306122448979592e-06,
|
| 2238 |
+
"loss": 0.0251,
|
| 2239 |
+
"step": 696
|
| 2240 |
+
},
|
| 2241 |
+
{
|
| 2242 |
+
"epoch": 4.75,
|
| 2243 |
+
"learning_rate": 5.034013605442177e-06,
|
| 2244 |
+
"loss": 0.0195,
|
| 2245 |
+
"step": 698
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 4.76,
|
| 2249 |
+
"learning_rate": 4.7619047619047615e-06,
|
| 2250 |
+
"loss": 0.0228,
|
| 2251 |
+
"step": 700
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 4.76,
|
| 2255 |
+
"eval_f1": 0.9180364705120548,
|
| 2256 |
+
"eval_loss": 0.02530401200056076,
|
| 2257 |
+
"eval_precision": 0.9165848123032982,
|
| 2258 |
+
"eval_recall": 0.9195027659216988,
|
| 2259 |
+
"eval_runtime": 11.9163,
|
| 2260 |
+
"eval_samples_per_second": 124.368,
|
| 2261 |
+
"eval_steps_per_second": 0.504,
|
| 2262 |
+
"step": 700
|
| 2263 |
+
}
|
| 2264 |
+
],
|
| 2265 |
+
"max_steps": 735,
|
| 2266 |
+
"num_train_epochs": 5,
|
| 2267 |
+
"total_flos": 3.51335241220096e+16,
|
| 2268 |
+
"trial_name": null,
|
| 2269 |
+
"trial_params": null
|
| 2270 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68fe86793979f26a71c8224cf32e95a8eceefbdbe611bf6bc5a7f892b689227f
|
| 3 |
+
size 4015
|