Upload 7 files
Browse files- config.json +46 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +356 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "nghuyong/ernie-2.0-large-en",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ErnieForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3",
|
| 16 |
+
"4": "LABEL_4",
|
| 17 |
+
"5": "LABEL_5",
|
| 18 |
+
"6": "LABEL_6"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 4096,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"LABEL_0": 0,
|
| 24 |
+
"LABEL_1": 1,
|
| 25 |
+
"LABEL_2": 2,
|
| 26 |
+
"LABEL_3": 3,
|
| 27 |
+
"LABEL_4": 4,
|
| 28 |
+
"LABEL_5": 5,
|
| 29 |
+
"LABEL_6": 6
|
| 30 |
+
},
|
| 31 |
+
"layer_norm_eps": 1e-05,
|
| 32 |
+
"max_position_embeddings": 512,
|
| 33 |
+
"model_type": "ernie",
|
| 34 |
+
"num_attention_heads": 16,
|
| 35 |
+
"num_hidden_layers": 24,
|
| 36 |
+
"pad_token_id": 0,
|
| 37 |
+
"position_embedding_type": "absolute",
|
| 38 |
+
"problem_type": "single_label_classification",
|
| 39 |
+
"task_type_vocab_size": 3,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.39.3",
|
| 42 |
+
"type_vocab_size": 4,
|
| 43 |
+
"use_cache": true,
|
| 44 |
+
"use_task_id": false,
|
| 45 |
+
"vocab_size": 30522
|
| 46 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf8cb705990c7ff74b68ee69cc4f995c0e9b40506837a029f2a950cf39cfbdc2
|
| 3 |
+
size 1340651828
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5c095483bcf7ac0b5204d4bba63560969675e5dda64147eb2dcd4f7810819ef
|
| 3 |
+
size 2681537773
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af6f0e8cbd310734dad35c668bf5ebcaeb1243c6928c90c9f05af325d2830818
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1bff8abef249bd509cb543521c08c66a962cce3dc996e55e4e41e05875ae5c4
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,356 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8981744694017328,
|
| 3 |
+
"best_model_checkpoint": "en_output/run-1/checkpoint-4015",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4015,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.12,
|
| 13 |
+
"grad_norm": 9.016681671142578,
|
| 14 |
+
"learning_rate": 3.137975621127507e-05,
|
| 15 |
+
"loss": 1.3969,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.25,
|
| 20 |
+
"grad_norm": 11.532567024230957,
|
| 21 |
+
"learning_rate": 3.057822987126805e-05,
|
| 22 |
+
"loss": 1.12,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.37,
|
| 27 |
+
"grad_norm": 13.854158401489258,
|
| 28 |
+
"learning_rate": 2.977670353126102e-05,
|
| 29 |
+
"loss": 1.0118,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.5,
|
| 34 |
+
"grad_norm": 15.174864768981934,
|
| 35 |
+
"learning_rate": 2.8975177191253995e-05,
|
| 36 |
+
"loss": 0.8854,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.62,
|
| 41 |
+
"grad_norm": 10.61332893371582,
|
| 42 |
+
"learning_rate": 2.8173650851246964e-05,
|
| 43 |
+
"loss": 0.8194,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.75,
|
| 48 |
+
"grad_norm": 8.371576309204102,
|
| 49 |
+
"learning_rate": 2.737212451123994e-05,
|
| 50 |
+
"loss": 0.8095,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.87,
|
| 55 |
+
"grad_norm": 7.02115535736084,
|
| 56 |
+
"learning_rate": 2.6570598171232915e-05,
|
| 57 |
+
"loss": 0.7585,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.0,
|
| 62 |
+
"grad_norm": 9.261237144470215,
|
| 63 |
+
"learning_rate": 2.5769071831225887e-05,
|
| 64 |
+
"loss": 0.6611,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.0,
|
| 69 |
+
"eval_accuracy": 0.7717528373266078,
|
| 70 |
+
"eval_f1": 0.8197696469069372,
|
| 71 |
+
"eval_loss": 0.631992518901825,
|
| 72 |
+
"eval_runtime": 6.3017,
|
| 73 |
+
"eval_samples_per_second": 503.354,
|
| 74 |
+
"eval_steps_per_second": 15.869,
|
| 75 |
+
"step": 803
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.12,
|
| 79 |
+
"grad_norm": 11.751930236816406,
|
| 80 |
+
"learning_rate": 2.4967545491218862e-05,
|
| 81 |
+
"loss": 0.5042,
|
| 82 |
+
"step": 900
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.25,
|
| 86 |
+
"grad_norm": 9.949508666992188,
|
| 87 |
+
"learning_rate": 2.4166019151211838e-05,
|
| 88 |
+
"loss": 0.4727,
|
| 89 |
+
"step": 1000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.37,
|
| 93 |
+
"grad_norm": 9.066802024841309,
|
| 94 |
+
"learning_rate": 2.336449281120481e-05,
|
| 95 |
+
"loss": 0.4475,
|
| 96 |
+
"step": 1100
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.49,
|
| 100 |
+
"grad_norm": 13.22970962524414,
|
| 101 |
+
"learning_rate": 2.2562966471197785e-05,
|
| 102 |
+
"loss": 0.4549,
|
| 103 |
+
"step": 1200
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.62,
|
| 107 |
+
"grad_norm": 5.078187942504883,
|
| 108 |
+
"learning_rate": 2.176144013119076e-05,
|
| 109 |
+
"loss": 0.4522,
|
| 110 |
+
"step": 1300
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.74,
|
| 114 |
+
"grad_norm": 10.427614212036133,
|
| 115 |
+
"learning_rate": 2.0959913791183733e-05,
|
| 116 |
+
"loss": 0.4271,
|
| 117 |
+
"step": 1400
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.87,
|
| 121 |
+
"grad_norm": 4.8712615966796875,
|
| 122 |
+
"learning_rate": 2.0158387451176705e-05,
|
| 123 |
+
"loss": 0.4391,
|
| 124 |
+
"step": 1500
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.99,
|
| 128 |
+
"grad_norm": 6.465252876281738,
|
| 129 |
+
"learning_rate": 1.9356861111169677e-05,
|
| 130 |
+
"loss": 0.4389,
|
| 131 |
+
"step": 1600
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 2.0,
|
| 135 |
+
"eval_accuracy": 0.8193568726355611,
|
| 136 |
+
"eval_f1": 0.8738583019819207,
|
| 137 |
+
"eval_loss": 0.486948698759079,
|
| 138 |
+
"eval_runtime": 6.3232,
|
| 139 |
+
"eval_samples_per_second": 501.641,
|
| 140 |
+
"eval_steps_per_second": 15.815,
|
| 141 |
+
"step": 1606
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 2.12,
|
| 145 |
+
"grad_norm": 4.6454176902771,
|
| 146 |
+
"learning_rate": 1.8555334771162652e-05,
|
| 147 |
+
"loss": 0.284,
|
| 148 |
+
"step": 1700
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.24,
|
| 152 |
+
"grad_norm": 8.212606430053711,
|
| 153 |
+
"learning_rate": 1.7753808431155628e-05,
|
| 154 |
+
"loss": 0.276,
|
| 155 |
+
"step": 1800
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 2.37,
|
| 159 |
+
"grad_norm": 5.965590000152588,
|
| 160 |
+
"learning_rate": 1.69522820911486e-05,
|
| 161 |
+
"loss": 0.2434,
|
| 162 |
+
"step": 1900
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.49,
|
| 166 |
+
"grad_norm": 9.97062873840332,
|
| 167 |
+
"learning_rate": 1.6150755751141575e-05,
|
| 168 |
+
"loss": 0.249,
|
| 169 |
+
"step": 2000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 2.62,
|
| 173 |
+
"grad_norm": 7.969445705413818,
|
| 174 |
+
"learning_rate": 1.534922941113455e-05,
|
| 175 |
+
"loss": 0.244,
|
| 176 |
+
"step": 2100
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.74,
|
| 180 |
+
"grad_norm": 8.639568328857422,
|
| 181 |
+
"learning_rate": 1.4547703071127523e-05,
|
| 182 |
+
"loss": 0.244,
|
| 183 |
+
"step": 2200
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 2.86,
|
| 187 |
+
"grad_norm": 9.686100006103516,
|
| 188 |
+
"learning_rate": 1.3746176731120497e-05,
|
| 189 |
+
"loss": 0.2373,
|
| 190 |
+
"step": 2300
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 2.99,
|
| 194 |
+
"grad_norm": 9.704062461853027,
|
| 195 |
+
"learning_rate": 1.294465039111347e-05,
|
| 196 |
+
"loss": 0.2389,
|
| 197 |
+
"step": 2400
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.0,
|
| 201 |
+
"eval_accuracy": 0.8199873896595208,
|
| 202 |
+
"eval_f1": 0.8793961295450606,
|
| 203 |
+
"eval_loss": 0.5388198494911194,
|
| 204 |
+
"eval_runtime": 6.3147,
|
| 205 |
+
"eval_samples_per_second": 502.323,
|
| 206 |
+
"eval_steps_per_second": 15.836,
|
| 207 |
+
"step": 2409
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 3.11,
|
| 211 |
+
"grad_norm": 7.037457466125488,
|
| 212 |
+
"learning_rate": 1.2143124051106446e-05,
|
| 213 |
+
"loss": 0.1588,
|
| 214 |
+
"step": 2500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 3.24,
|
| 218 |
+
"grad_norm": 6.776266574859619,
|
| 219 |
+
"learning_rate": 1.134159771109942e-05,
|
| 220 |
+
"loss": 0.128,
|
| 221 |
+
"step": 2600
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 3.36,
|
| 225 |
+
"grad_norm": 6.907045841217041,
|
| 226 |
+
"learning_rate": 1.0540071371092392e-05,
|
| 227 |
+
"loss": 0.1408,
|
| 228 |
+
"step": 2700
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 3.49,
|
| 232 |
+
"grad_norm": 7.6478800773620605,
|
| 233 |
+
"learning_rate": 9.738545031085367e-06,
|
| 234 |
+
"loss": 0.1214,
|
| 235 |
+
"step": 2800
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 3.61,
|
| 239 |
+
"grad_norm": 13.469510078430176,
|
| 240 |
+
"learning_rate": 8.93701869107834e-06,
|
| 241 |
+
"loss": 0.1395,
|
| 242 |
+
"step": 2900
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.74,
|
| 246 |
+
"grad_norm": 9.527716636657715,
|
| 247 |
+
"learning_rate": 8.135492351071314e-06,
|
| 248 |
+
"loss": 0.1342,
|
| 249 |
+
"step": 3000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 3.86,
|
| 253 |
+
"grad_norm": 4.901115417480469,
|
| 254 |
+
"learning_rate": 7.333966011064288e-06,
|
| 255 |
+
"loss": 0.1263,
|
| 256 |
+
"step": 3100
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 3.99,
|
| 260 |
+
"grad_norm": 7.46558141708374,
|
| 261 |
+
"learning_rate": 6.532439671057263e-06,
|
| 262 |
+
"loss": 0.1405,
|
| 263 |
+
"step": 3200
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 4.0,
|
| 267 |
+
"eval_accuracy": 0.8354350567465322,
|
| 268 |
+
"eval_f1": 0.8956331776920504,
|
| 269 |
+
"eval_loss": 0.5953832268714905,
|
| 270 |
+
"eval_runtime": 6.2939,
|
| 271 |
+
"eval_samples_per_second": 503.981,
|
| 272 |
+
"eval_steps_per_second": 15.888,
|
| 273 |
+
"step": 3212
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 4.11,
|
| 277 |
+
"grad_norm": 0.39140334725379944,
|
| 278 |
+
"learning_rate": 5.7309133310502365e-06,
|
| 279 |
+
"loss": 0.0853,
|
| 280 |
+
"step": 3300
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 4.23,
|
| 284 |
+
"grad_norm": 7.5608391761779785,
|
| 285 |
+
"learning_rate": 4.92938699104321e-06,
|
| 286 |
+
"loss": 0.0715,
|
| 287 |
+
"step": 3400
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 4.36,
|
| 291 |
+
"grad_norm": 15.901948928833008,
|
| 292 |
+
"learning_rate": 4.127860651036185e-06,
|
| 293 |
+
"loss": 0.0504,
|
| 294 |
+
"step": 3500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 4.48,
|
| 298 |
+
"grad_norm": 1.3447962999343872,
|
| 299 |
+
"learning_rate": 3.326334311029158e-06,
|
| 300 |
+
"loss": 0.0616,
|
| 301 |
+
"step": 3600
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 4.61,
|
| 305 |
+
"grad_norm": 0.6756995916366577,
|
| 306 |
+
"learning_rate": 2.524807971022132e-06,
|
| 307 |
+
"loss": 0.0783,
|
| 308 |
+
"step": 3700
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.73,
|
| 312 |
+
"grad_norm": 0.16733744740486145,
|
| 313 |
+
"learning_rate": 1.723281631015106e-06,
|
| 314 |
+
"loss": 0.0812,
|
| 315 |
+
"step": 3800
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 4.86,
|
| 319 |
+
"grad_norm": 0.649143636226654,
|
| 320 |
+
"learning_rate": 9.2175529100808e-07,
|
| 321 |
+
"loss": 0.0674,
|
| 322 |
+
"step": 3900
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 4.98,
|
| 326 |
+
"grad_norm": 0.20296114683151245,
|
| 327 |
+
"learning_rate": 1.202289510010539e-07,
|
| 328 |
+
"loss": 0.0685,
|
| 329 |
+
"step": 4000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 5.0,
|
| 333 |
+
"eval_accuracy": 0.8385876418663304,
|
| 334 |
+
"eval_f1": 0.8981744694017328,
|
| 335 |
+
"eval_loss": 0.7969151735305786,
|
| 336 |
+
"eval_runtime": 6.2809,
|
| 337 |
+
"eval_samples_per_second": 505.024,
|
| 338 |
+
"eval_steps_per_second": 15.921,
|
| 339 |
+
"step": 4015
|
| 340 |
+
}
|
| 341 |
+
],
|
| 342 |
+
"logging_steps": 100,
|
| 343 |
+
"max_steps": 4015,
|
| 344 |
+
"num_input_tokens_seen": 0,
|
| 345 |
+
"num_train_epochs": 5,
|
| 346 |
+
"save_steps": 500,
|
| 347 |
+
"total_flos": 3783455887092102.0,
|
| 348 |
+
"train_batch_size": 32,
|
| 349 |
+
"trial_name": null,
|
| 350 |
+
"trial_params": {
|
| 351 |
+
"learning_rate": 3.21812825512821e-05,
|
| 352 |
+
"lr_scheduler_type": "linear",
|
| 353 |
+
"num_train_epochs": 5,
|
| 354 |
+
"per_device_train_batch_size": 32
|
| 355 |
+
}
|
| 356 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e5b645db948e76ff390ca7f6e03ac1b5ac952ff1b277643f220b3de0ac2b434
|
| 3 |
+
size 4920
|