Upload 22 files
Browse files- .gitattributes +1 -0
- finetuned_xlm-roberta/checkpoint-296/config.json +31 -0
- finetuned_xlm-roberta/checkpoint-296/rng_state.pth +3 -0
- finetuned_xlm-roberta/checkpoint-296/scheduler.pt +3 -0
- finetuned_xlm-roberta/checkpoint-296/trainer_state.json +244 -0
- finetuned_xlm-roberta/checkpoint-296/training_args.bin +3 -0
- finetuned_xlm-roberta/checkpoint-592/config.json +31 -0
- finetuned_xlm-roberta/checkpoint-592/rng_state.pth +3 -0
- finetuned_xlm-roberta/checkpoint-592/scheduler.pt +3 -0
- finetuned_xlm-roberta/checkpoint-592/trainer_state.json +462 -0
- finetuned_xlm-roberta/checkpoint-592/training_args.bin +3 -0
- finetuned_xlm-roberta/checkpoint-888/config.json +31 -0
- finetuned_xlm-roberta/checkpoint-888/rng_state.pth +3 -0
- finetuned_xlm-roberta/checkpoint-888/scheduler.pt +3 -0
- finetuned_xlm-roberta/checkpoint-888/trainer_state.json +673 -0
- finetuned_xlm-roberta/checkpoint-888/training_args.bin +3 -0
- finetuned_xlm-roberta/config.json +31 -0
- finetuned_xlm-roberta/model.safetensors +3 -0
- finetuned_xlm-roberta/sentencepiece.bpe.model +3 -0
- finetuned_xlm-roberta/special_tokens_map.json +15 -0
- finetuned_xlm-roberta/tokenizer.json +3 -0
- finetuned_xlm-roberta/tokenizer_config.json +57 -0
- finetuned_xlm-roberta/training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
finetuned_xlm-roberta/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
finetuned_xlm-roberta/checkpoint-296/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "deepset/xlm-roberta-base-squad2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"language": "english",
|
| 17 |
+
"layer_norm_eps": 1e-05,
|
| 18 |
+
"max_position_embeddings": 514,
|
| 19 |
+
"model_type": "xlm-roberta",
|
| 20 |
+
"name": "XLMRoberta",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 1,
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.44.2",
|
| 28 |
+
"type_vocab_size": 1,
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 250002
|
| 31 |
+
}
|
finetuned_xlm-roberta/checkpoint-296/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef27724e92f4a601c78555dd7b091af07152355fde1761aac5aff11cd435d674
|
| 3 |
+
size 14645
|
finetuned_xlm-roberta/checkpoint-296/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24bcfdc3d90d61637f9d7d9b12647f0ac53359f6477d946c5c629f0ead314f62
|
| 3 |
+
size 1465
|
finetuned_xlm-roberta/checkpoint-296/trainer_state.json
ADDED
|
@@ -0,0 +1,244 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.00018429462215863168,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/My Drive/BonsAI/RAG/finetuned_xlm-roberta/checkpoint-296",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 296,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.033783783783783786,
|
| 13 |
+
"grad_norm": Infinity,
|
| 14 |
+
"learning_rate": 1.6853932584269663e-06,
|
| 15 |
+
"loss": 2.6886,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06756756756756757,
|
| 20 |
+
"grad_norm": 29.947162628173828,
|
| 21 |
+
"learning_rate": 5.056179775280899e-06,
|
| 22 |
+
"loss": 1.3345,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.10135135135135136,
|
| 27 |
+
"grad_norm": 19.499181747436523,
|
| 28 |
+
"learning_rate": 8.426966292134832e-06,
|
| 29 |
+
"loss": 0.7008,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.13513513513513514,
|
| 34 |
+
"grad_norm": 6.167481422424316,
|
| 35 |
+
"learning_rate": 1.1797752808988765e-05,
|
| 36 |
+
"loss": 0.2206,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.16891891891891891,
|
| 41 |
+
"grad_norm": 0.40867164731025696,
|
| 42 |
+
"learning_rate": 1.5168539325842698e-05,
|
| 43 |
+
"loss": 0.0447,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.20270270270270271,
|
| 48 |
+
"grad_norm": 9.221413612365723,
|
| 49 |
+
"learning_rate": 1.853932584269663e-05,
|
| 50 |
+
"loss": 0.0051,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.23648648648648649,
|
| 55 |
+
"grad_norm": 0.042814701795578,
|
| 56 |
+
"learning_rate": 2.1910112359550563e-05,
|
| 57 |
+
"loss": 0.0036,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2702702702702703,
|
| 62 |
+
"grad_norm": 0.12612159550189972,
|
| 63 |
+
"learning_rate": 2.5280898876404494e-05,
|
| 64 |
+
"loss": 0.0182,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.30405405405405406,
|
| 69 |
+
"grad_norm": 0.04947296157479286,
|
| 70 |
+
"learning_rate": 2.8314606741573034e-05,
|
| 71 |
+
"loss": 0.0101,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.33783783783783783,
|
| 76 |
+
"grad_norm": 0.18833085894584656,
|
| 77 |
+
"learning_rate": 2.9997101365406277e-05,
|
| 78 |
+
"loss": 0.0907,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3716216216216216,
|
| 83 |
+
"grad_norm": 1.308021903038025,
|
| 84 |
+
"learning_rate": 2.9973919009889526e-05,
|
| 85 |
+
"loss": 0.0533,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.40540540540540543,
|
| 90 |
+
"grad_norm": 0.051874082535505295,
|
| 91 |
+
"learning_rate": 2.9927590133888025e-05,
|
| 92 |
+
"loss": 0.0102,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4391891891891892,
|
| 97 |
+
"grad_norm": 0.06415823101997375,
|
| 98 |
+
"learning_rate": 2.985818635207236e-05,
|
| 99 |
+
"loss": 0.0066,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.47297297297297297,
|
| 104 |
+
"grad_norm": 0.13685275614261627,
|
| 105 |
+
"learning_rate": 2.9765814948050558e-05,
|
| 106 |
+
"loss": 0.0138,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5067567567567568,
|
| 111 |
+
"grad_norm": 0.012585842050611973,
|
| 112 |
+
"learning_rate": 2.9650618708530222e-05,
|
| 113 |
+
"loss": 0.0002,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5405405405405406,
|
| 118 |
+
"grad_norm": 0.007939927279949188,
|
| 119 |
+
"learning_rate": 2.9512775702600414e-05,
|
| 120 |
+
"loss": 0.0002,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5743243243243243,
|
| 125 |
+
"grad_norm": 0.0030424967408180237,
|
| 126 |
+
"learning_rate": 2.93524990064744e-05,
|
| 127 |
+
"loss": 0.0001,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6081081081081081,
|
| 132 |
+
"grad_norm": 0.006802604999393225,
|
| 133 |
+
"learning_rate": 2.917003637411878e-05,
|
| 134 |
+
"loss": 0.0002,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.6418918918918919,
|
| 139 |
+
"grad_norm": 0.004224637057632208,
|
| 140 |
+
"learning_rate": 2.896566985427809e-05,
|
| 141 |
+
"loss": 0.0106,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6756756756756757,
|
| 146 |
+
"grad_norm": 0.47990503907203674,
|
| 147 |
+
"learning_rate": 2.8739715354486934e-05,
|
| 148 |
+
"loss": 0.0061,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.7094594594594594,
|
| 153 |
+
"grad_norm": 3.0428385734558105,
|
| 154 |
+
"learning_rate": 2.8492522152743587e-05,
|
| 155 |
+
"loss": 0.0007,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.7432432432432432,
|
| 160 |
+
"grad_norm": 0.28697794675827026,
|
| 161 |
+
"learning_rate": 2.8224472357599862e-05,
|
| 162 |
+
"loss": 0.005,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.777027027027027,
|
| 167 |
+
"grad_norm": 10.434463500976562,
|
| 168 |
+
"learning_rate": 2.793598031750189e-05,
|
| 169 |
+
"loss": 0.0059,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.8108108108108109,
|
| 174 |
+
"grad_norm": 0.16486147046089172,
|
| 175 |
+
"learning_rate": 2.7627491980294813e-05,
|
| 176 |
+
"loss": 0.0048,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.8445945945945946,
|
| 181 |
+
"grad_norm": 0.014305876567959785,
|
| 182 |
+
"learning_rate": 2.7299484203881476e-05,
|
| 183 |
+
"loss": 0.0262,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.8783783783783784,
|
| 188 |
+
"grad_norm": 0.003319332841783762,
|
| 189 |
+
"learning_rate": 2.69524640191007e-05,
|
| 190 |
+
"loss": 0.0313,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.9121621621621622,
|
| 195 |
+
"grad_norm": 0.011635912582278252,
|
| 196 |
+
"learning_rate": 2.6586967845964528e-05,
|
| 197 |
+
"loss": 0.0022,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.9459459459459459,
|
| 202 |
+
"grad_norm": 0.04328622668981552,
|
| 203 |
+
"learning_rate": 2.6203560664466036e-05,
|
| 204 |
+
"loss": 0.0003,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.9797297297297297,
|
| 209 |
+
"grad_norm": 98.71577453613281,
|
| 210 |
+
"learning_rate": 2.580283514123944e-05,
|
| 211 |
+
"loss": 0.0112,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.0,
|
| 216 |
+
"eval_loss": 0.00018429462215863168,
|
| 217 |
+
"eval_runtime": 2.4293,
|
| 218 |
+
"eval_samples_per_second": 108.261,
|
| 219 |
+
"eval_steps_per_second": 27.168,
|
| 220 |
+
"step": 296
|
| 221 |
+
}
|
| 222 |
+
],
|
| 223 |
+
"logging_steps": 10,
|
| 224 |
+
"max_steps": 888,
|
| 225 |
+
"num_input_tokens_seen": 0,
|
| 226 |
+
"num_train_epochs": 3,
|
| 227 |
+
"save_steps": 500,
|
| 228 |
+
"stateful_callbacks": {
|
| 229 |
+
"TrainerControl": {
|
| 230 |
+
"args": {
|
| 231 |
+
"should_epoch_stop": false,
|
| 232 |
+
"should_evaluate": false,
|
| 233 |
+
"should_log": false,
|
| 234 |
+
"should_save": true,
|
| 235 |
+
"should_training_stop": false
|
| 236 |
+
},
|
| 237 |
+
"attributes": {}
|
| 238 |
+
}
|
| 239 |
+
},
|
| 240 |
+
"total_flos": 463475122260480.0,
|
| 241 |
+
"train_batch_size": 4,
|
| 242 |
+
"trial_name": null,
|
| 243 |
+
"trial_params": null
|
| 244 |
+
}
|
finetuned_xlm-roberta/checkpoint-296/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8369906ea6653c33f21f912c813f8bd76e66bb2c941c41c44ab07ead5ecf8f7
|
| 3 |
+
size 5649
|
finetuned_xlm-roberta/checkpoint-592/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "deepset/xlm-roberta-base-squad2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"language": "english",
|
| 17 |
+
"layer_norm_eps": 1e-05,
|
| 18 |
+
"max_position_embeddings": 514,
|
| 19 |
+
"model_type": "xlm-roberta",
|
| 20 |
+
"name": "XLMRoberta",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 1,
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.44.2",
|
| 28 |
+
"type_vocab_size": 1,
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 250002
|
| 31 |
+
}
|
finetuned_xlm-roberta/checkpoint-592/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cab0701137d774840b9274ff0c968aa227a2ed83fa41f99bfb65b2301453a1f
|
| 3 |
+
size 14645
|
finetuned_xlm-roberta/checkpoint-592/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19723118ddfcdc828016fb08fc77c880064cca83675620bf76876c9e8462fac4
|
| 3 |
+
size 1465
|
finetuned_xlm-roberta/checkpoint-592/trainer_state.json
ADDED
|
@@ -0,0 +1,462 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.5043016194103984e-06,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/My Drive/BonsAI/RAG/finetuned_xlm-roberta/checkpoint-592",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 592,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.033783783783783786,
|
| 13 |
+
"grad_norm": Infinity,
|
| 14 |
+
"learning_rate": 1.6853932584269663e-06,
|
| 15 |
+
"loss": 2.6886,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06756756756756757,
|
| 20 |
+
"grad_norm": 29.947162628173828,
|
| 21 |
+
"learning_rate": 5.056179775280899e-06,
|
| 22 |
+
"loss": 1.3345,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.10135135135135136,
|
| 27 |
+
"grad_norm": 19.499181747436523,
|
| 28 |
+
"learning_rate": 8.426966292134832e-06,
|
| 29 |
+
"loss": 0.7008,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.13513513513513514,
|
| 34 |
+
"grad_norm": 6.167481422424316,
|
| 35 |
+
"learning_rate": 1.1797752808988765e-05,
|
| 36 |
+
"loss": 0.2206,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.16891891891891891,
|
| 41 |
+
"grad_norm": 0.40867164731025696,
|
| 42 |
+
"learning_rate": 1.5168539325842698e-05,
|
| 43 |
+
"loss": 0.0447,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.20270270270270271,
|
| 48 |
+
"grad_norm": 9.221413612365723,
|
| 49 |
+
"learning_rate": 1.853932584269663e-05,
|
| 50 |
+
"loss": 0.0051,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.23648648648648649,
|
| 55 |
+
"grad_norm": 0.042814701795578,
|
| 56 |
+
"learning_rate": 2.1910112359550563e-05,
|
| 57 |
+
"loss": 0.0036,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2702702702702703,
|
| 62 |
+
"grad_norm": 0.12612159550189972,
|
| 63 |
+
"learning_rate": 2.5280898876404494e-05,
|
| 64 |
+
"loss": 0.0182,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.30405405405405406,
|
| 69 |
+
"grad_norm": 0.04947296157479286,
|
| 70 |
+
"learning_rate": 2.8314606741573034e-05,
|
| 71 |
+
"loss": 0.0101,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.33783783783783783,
|
| 76 |
+
"grad_norm": 0.18833085894584656,
|
| 77 |
+
"learning_rate": 2.9997101365406277e-05,
|
| 78 |
+
"loss": 0.0907,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3716216216216216,
|
| 83 |
+
"grad_norm": 1.308021903038025,
|
| 84 |
+
"learning_rate": 2.9973919009889526e-05,
|
| 85 |
+
"loss": 0.0533,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.40540540540540543,
|
| 90 |
+
"grad_norm": 0.051874082535505295,
|
| 91 |
+
"learning_rate": 2.9927590133888025e-05,
|
| 92 |
+
"loss": 0.0102,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4391891891891892,
|
| 97 |
+
"grad_norm": 0.06415823101997375,
|
| 98 |
+
"learning_rate": 2.985818635207236e-05,
|
| 99 |
+
"loss": 0.0066,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.47297297297297297,
|
| 104 |
+
"grad_norm": 0.13685275614261627,
|
| 105 |
+
"learning_rate": 2.9765814948050558e-05,
|
| 106 |
+
"loss": 0.0138,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5067567567567568,
|
| 111 |
+
"grad_norm": 0.012585842050611973,
|
| 112 |
+
"learning_rate": 2.9650618708530222e-05,
|
| 113 |
+
"loss": 0.0002,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5405405405405406,
|
| 118 |
+
"grad_norm": 0.007939927279949188,
|
| 119 |
+
"learning_rate": 2.9512775702600414e-05,
|
| 120 |
+
"loss": 0.0002,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5743243243243243,
|
| 125 |
+
"grad_norm": 0.0030424967408180237,
|
| 126 |
+
"learning_rate": 2.93524990064744e-05,
|
| 127 |
+
"loss": 0.0001,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6081081081081081,
|
| 132 |
+
"grad_norm": 0.006802604999393225,
|
| 133 |
+
"learning_rate": 2.917003637411878e-05,
|
| 134 |
+
"loss": 0.0002,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.6418918918918919,
|
| 139 |
+
"grad_norm": 0.004224637057632208,
|
| 140 |
+
"learning_rate": 2.896566985427809e-05,
|
| 141 |
+
"loss": 0.0106,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6756756756756757,
|
| 146 |
+
"grad_norm": 0.47990503907203674,
|
| 147 |
+
"learning_rate": 2.8739715354486934e-05,
|
| 148 |
+
"loss": 0.0061,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.7094594594594594,
|
| 153 |
+
"grad_norm": 3.0428385734558105,
|
| 154 |
+
"learning_rate": 2.8492522152743587e-05,
|
| 155 |
+
"loss": 0.0007,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.7432432432432432,
|
| 160 |
+
"grad_norm": 0.28697794675827026,
|
| 161 |
+
"learning_rate": 2.8224472357599862e-05,
|
| 162 |
+
"loss": 0.005,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.777027027027027,
|
| 167 |
+
"grad_norm": 10.434463500976562,
|
| 168 |
+
"learning_rate": 2.793598031750189e-05,
|
| 169 |
+
"loss": 0.0059,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.8108108108108109,
|
| 174 |
+
"grad_norm": 0.16486147046089172,
|
| 175 |
+
"learning_rate": 2.7627491980294813e-05,
|
| 176 |
+
"loss": 0.0048,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.8445945945945946,
|
| 181 |
+
"grad_norm": 0.014305876567959785,
|
| 182 |
+
"learning_rate": 2.7299484203881476e-05,
|
| 183 |
+
"loss": 0.0262,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.8783783783783784,
|
| 188 |
+
"grad_norm": 0.003319332841783762,
|
| 189 |
+
"learning_rate": 2.69524640191007e-05,
|
| 190 |
+
"loss": 0.0313,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.9121621621621622,
|
| 195 |
+
"grad_norm": 0.011635912582278252,
|
| 196 |
+
"learning_rate": 2.6586967845964528e-05,
|
| 197 |
+
"loss": 0.0022,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.9459459459459459,
|
| 202 |
+
"grad_norm": 0.04328622668981552,
|
| 203 |
+
"learning_rate": 2.6203560664466036e-05,
|
| 204 |
+
"loss": 0.0003,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.9797297297297297,
|
| 209 |
+
"grad_norm": 98.71577453613281,
|
| 210 |
+
"learning_rate": 2.580283514123944e-05,
|
| 211 |
+
"loss": 0.0112,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.0,
|
| 216 |
+
"eval_loss": 0.00018429462215863168,
|
| 217 |
+
"eval_runtime": 2.4293,
|
| 218 |
+
"eval_samples_per_second": 108.261,
|
| 219 |
+
"eval_steps_per_second": 27.168,
|
| 220 |
+
"step": 296
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.0135135135135136,
|
| 224 |
+
"grad_norm": 0.0028017598669975996,
|
| 225 |
+
"learning_rate": 2.5385410713422475e-05,
|
| 226 |
+
"loss": 0.0001,
|
| 227 |
+
"step": 300
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.0472972972972974,
|
| 231 |
+
"grad_norm": 0.0028585209511220455,
|
| 232 |
+
"learning_rate": 2.495193263113722e-05,
|
| 233 |
+
"loss": 0.0001,
|
| 234 |
+
"step": 310
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.0810810810810811,
|
| 238 |
+
"grad_norm": 0.0021099066361784935,
|
| 239 |
+
"learning_rate": 2.4503070960069545e-05,
|
| 240 |
+
"loss": 0.0,
|
| 241 |
+
"step": 320
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.114864864864865,
|
| 245 |
+
"grad_norm": 0.0021344744600355625,
|
| 246 |
+
"learning_rate": 2.4039519545688848e-05,
|
| 247 |
+
"loss": 0.0,
|
| 248 |
+
"step": 330
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.1486486486486487,
|
| 252 |
+
"grad_norm": 0.007050791289657354,
|
| 253 |
+
"learning_rate": 2.356199494070932e-05,
|
| 254 |
+
"loss": 0.0009,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.1824324324324325,
|
| 259 |
+
"grad_norm": 0.2592613697052002,
|
| 260 |
+
"learning_rate": 2.307123529745059e-05,
|
| 261 |
+
"loss": 0.0002,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.2162162162162162,
|
| 266 |
+
"grad_norm": 0.004164527636021376,
|
| 267 |
+
"learning_rate": 2.256799922680994e-05,
|
| 268 |
+
"loss": 0.0001,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.25,
|
| 273 |
+
"grad_norm": 0.009292829781770706,
|
| 274 |
+
"learning_rate": 2.2053064625609836e-05,
|
| 275 |
+
"loss": 0.0001,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.2837837837837838,
|
| 280 |
+
"grad_norm": 0.24080495536327362,
|
| 281 |
+
"learning_rate": 2.1527227474133543e-05,
|
| 282 |
+
"loss": 0.0008,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.3175675675675675,
|
| 287 |
+
"grad_norm": 0.004564313683658838,
|
| 288 |
+
"learning_rate": 2.0991300605707474e-05,
|
| 289 |
+
"loss": 0.0016,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.3513513513513513,
|
| 294 |
+
"grad_norm": 0.012726039625704288,
|
| 295 |
+
"learning_rate": 2.0446112450232316e-05,
|
| 296 |
+
"loss": 0.0001,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.385135135135135,
|
| 301 |
+
"grad_norm": 0.0028580036014318466,
|
| 302 |
+
"learning_rate": 1.9892505753605152e-05,
|
| 303 |
+
"loss": 0.0002,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.4189189189189189,
|
| 308 |
+
"grad_norm": 0.0011500768596306443,
|
| 309 |
+
"learning_rate": 1.9331336275012043e-05,
|
| 310 |
+
"loss": 0.0,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.4527027027027026,
|
| 315 |
+
"grad_norm": 0.0012311682803556323,
|
| 316 |
+
"learning_rate": 1.8763471464104813e-05,
|
| 317 |
+
"loss": 0.0,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.4864864864864864,
|
| 322 |
+
"grad_norm": 0.0042627062648534775,
|
| 323 |
+
"learning_rate": 1.8189789120106866e-05,
|
| 324 |
+
"loss": 0.0058,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.5202702702702702,
|
| 329 |
+
"grad_norm": 0.0009136000298894942,
|
| 330 |
+
"learning_rate": 1.7611176034920735e-05,
|
| 331 |
+
"loss": 0.0,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.554054054054054,
|
| 336 |
+
"grad_norm": 0.0008129957714118063,
|
| 337 |
+
"learning_rate": 1.7028526622334838e-05,
|
| 338 |
+
"loss": 0.0,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.5878378378378377,
|
| 343 |
+
"grad_norm": 0.001546179410070181,
|
| 344 |
+
"learning_rate": 1.644274153544839e-05,
|
| 345 |
+
"loss": 0.0,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.6216216216216215,
|
| 350 |
+
"grad_norm": 0.0011343436781316996,
|
| 351 |
+
"learning_rate": 1.5854726274451723e-05,
|
| 352 |
+
"loss": 0.0,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.6554054054054053,
|
| 357 |
+
"grad_norm": 0.0004109444562345743,
|
| 358 |
+
"learning_rate": 1.5265389786913935e-05,
|
| 359 |
+
"loss": 0.0,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.689189189189189,
|
| 364 |
+
"grad_norm": 0.008421291597187519,
|
| 365 |
+
"learning_rate": 1.4675643062741682e-05,
|
| 366 |
+
"loss": 0.0,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.722972972972973,
|
| 371 |
+
"grad_norm": 0.005281887948513031,
|
| 372 |
+
"learning_rate": 1.4086397725980956e-05,
|
| 373 |
+
"loss": 0.0,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.7567567567567568,
|
| 378 |
+
"grad_norm": 0.0006799366092309356,
|
| 379 |
+
"learning_rate": 1.3498564625638524e-05,
|
| 380 |
+
"loss": 0.0,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.7905405405405406,
|
| 385 |
+
"grad_norm": 0.0005692480481229722,
|
| 386 |
+
"learning_rate": 1.2913052427701557e-05,
|
| 387 |
+
"loss": 0.0,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.8243243243243243,
|
| 392 |
+
"grad_norm": 0.0005203319014981389,
|
| 393 |
+
"learning_rate": 1.2330766210531605e-05,
|
| 394 |
+
"loss": 0.0001,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.8581081081081081,
|
| 399 |
+
"grad_norm": 0.0005495847435668111,
|
| 400 |
+
"learning_rate": 1.1752606065804399e-05,
|
| 401 |
+
"loss": 0.0,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.8918918918918919,
|
| 406 |
+
"grad_norm": 0.002254391787573695,
|
| 407 |
+
"learning_rate": 1.1179465707157924e-05,
|
| 408 |
+
"loss": 0.0,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.9256756756756757,
|
| 413 |
+
"grad_norm": 0.0006869367207400501,
|
| 414 |
+
"learning_rate": 1.061223108869968e-05,
|
| 415 |
+
"loss": 0.0,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.9594594594594594,
|
| 420 |
+
"grad_norm": 0.0006207679980434477,
|
| 421 |
+
"learning_rate": 1.0051779035508465e-05,
|
| 422 |
+
"loss": 0.0001,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.9932432432432432,
|
| 427 |
+
"grad_norm": 0.0012077532010152936,
|
| 428 |
+
"learning_rate": 9.498975888247754e-06,
|
| 429 |
+
"loss": 0.0,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.0,
|
| 434 |
+
"eval_loss": 2.5043016194103984e-06,
|
| 435 |
+
"eval_runtime": 2.3685,
|
| 436 |
+
"eval_samples_per_second": 111.039,
|
| 437 |
+
"eval_steps_per_second": 27.865,
|
| 438 |
+
"step": 592
|
| 439 |
+
}
|
| 440 |
+
],
|
| 441 |
+
"logging_steps": 10,
|
| 442 |
+
"max_steps": 888,
|
| 443 |
+
"num_input_tokens_seen": 0,
|
| 444 |
+
"num_train_epochs": 3,
|
| 445 |
+
"save_steps": 500,
|
| 446 |
+
"stateful_callbacks": {
|
| 447 |
+
"TrainerControl": {
|
| 448 |
+
"args": {
|
| 449 |
+
"should_epoch_stop": false,
|
| 450 |
+
"should_evaluate": false,
|
| 451 |
+
"should_log": false,
|
| 452 |
+
"should_save": true,
|
| 453 |
+
"should_training_stop": false
|
| 454 |
+
},
|
| 455 |
+
"attributes": {}
|
| 456 |
+
}
|
| 457 |
+
},
|
| 458 |
+
"total_flos": 926950244520960.0,
|
| 459 |
+
"train_batch_size": 4,
|
| 460 |
+
"trial_name": null,
|
| 461 |
+
"trial_params": null
|
| 462 |
+
}
|
finetuned_xlm-roberta/checkpoint-592/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8369906ea6653c33f21f912c813f8bd76e66bb2c941c41c44ab07ead5ecf8f7
|
| 3 |
+
size 5649
|
finetuned_xlm-roberta/checkpoint-888/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "deepset/xlm-roberta-base-squad2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"language": "english",
|
| 17 |
+
"layer_norm_eps": 1e-05,
|
| 18 |
+
"max_position_embeddings": 514,
|
| 19 |
+
"model_type": "xlm-roberta",
|
| 20 |
+
"name": "XLMRoberta",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 1,
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.44.2",
|
| 28 |
+
"type_vocab_size": 1,
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 250002
|
| 31 |
+
}
|
finetuned_xlm-roberta/checkpoint-888/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48a9bc16f34efeb7931bd9e52e7f54133892e90c8deb4cbe248113dc2dcb6ed5
|
| 3 |
+
size 14645
|
finetuned_xlm-roberta/checkpoint-888/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f46c25608883cb938a693afe01aa9c1e4d97207dbfc8278a78ac414c389f4dbb
|
| 3 |
+
size 1465
|
finetuned_xlm-roberta/checkpoint-888/trainer_state.json
ADDED
|
@@ -0,0 +1,673 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.4904770725697745e-06,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/My Drive/BonsAI/RAG/finetuned_xlm-roberta/checkpoint-888",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 888,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.033783783783783786,
|
| 13 |
+
"grad_norm": Infinity,
|
| 14 |
+
"learning_rate": 1.6853932584269663e-06,
|
| 15 |
+
"loss": 2.6886,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06756756756756757,
|
| 20 |
+
"grad_norm": 29.947162628173828,
|
| 21 |
+
"learning_rate": 5.056179775280899e-06,
|
| 22 |
+
"loss": 1.3345,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.10135135135135136,
|
| 27 |
+
"grad_norm": 19.499181747436523,
|
| 28 |
+
"learning_rate": 8.426966292134832e-06,
|
| 29 |
+
"loss": 0.7008,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.13513513513513514,
|
| 34 |
+
"grad_norm": 6.167481422424316,
|
| 35 |
+
"learning_rate": 1.1797752808988765e-05,
|
| 36 |
+
"loss": 0.2206,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.16891891891891891,
|
| 41 |
+
"grad_norm": 0.40867164731025696,
|
| 42 |
+
"learning_rate": 1.5168539325842698e-05,
|
| 43 |
+
"loss": 0.0447,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.20270270270270271,
|
| 48 |
+
"grad_norm": 9.221413612365723,
|
| 49 |
+
"learning_rate": 1.853932584269663e-05,
|
| 50 |
+
"loss": 0.0051,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.23648648648648649,
|
| 55 |
+
"grad_norm": 0.042814701795578,
|
| 56 |
+
"learning_rate": 2.1910112359550563e-05,
|
| 57 |
+
"loss": 0.0036,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2702702702702703,
|
| 62 |
+
"grad_norm": 0.12612159550189972,
|
| 63 |
+
"learning_rate": 2.5280898876404494e-05,
|
| 64 |
+
"loss": 0.0182,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.30405405405405406,
|
| 69 |
+
"grad_norm": 0.04947296157479286,
|
| 70 |
+
"learning_rate": 2.8314606741573034e-05,
|
| 71 |
+
"loss": 0.0101,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.33783783783783783,
|
| 76 |
+
"grad_norm": 0.18833085894584656,
|
| 77 |
+
"learning_rate": 2.9997101365406277e-05,
|
| 78 |
+
"loss": 0.0907,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3716216216216216,
|
| 83 |
+
"grad_norm": 1.308021903038025,
|
| 84 |
+
"learning_rate": 2.9973919009889526e-05,
|
| 85 |
+
"loss": 0.0533,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.40540540540540543,
|
| 90 |
+
"grad_norm": 0.051874082535505295,
|
| 91 |
+
"learning_rate": 2.9927590133888025e-05,
|
| 92 |
+
"loss": 0.0102,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4391891891891892,
|
| 97 |
+
"grad_norm": 0.06415823101997375,
|
| 98 |
+
"learning_rate": 2.985818635207236e-05,
|
| 99 |
+
"loss": 0.0066,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.47297297297297297,
|
| 104 |
+
"grad_norm": 0.13685275614261627,
|
| 105 |
+
"learning_rate": 2.9765814948050558e-05,
|
| 106 |
+
"loss": 0.0138,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5067567567567568,
|
| 111 |
+
"grad_norm": 0.012585842050611973,
|
| 112 |
+
"learning_rate": 2.9650618708530222e-05,
|
| 113 |
+
"loss": 0.0002,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5405405405405406,
|
| 118 |
+
"grad_norm": 0.007939927279949188,
|
| 119 |
+
"learning_rate": 2.9512775702600414e-05,
|
| 120 |
+
"loss": 0.0002,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5743243243243243,
|
| 125 |
+
"grad_norm": 0.0030424967408180237,
|
| 126 |
+
"learning_rate": 2.93524990064744e-05,
|
| 127 |
+
"loss": 0.0001,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6081081081081081,
|
| 132 |
+
"grad_norm": 0.006802604999393225,
|
| 133 |
+
"learning_rate": 2.917003637411878e-05,
|
| 134 |
+
"loss": 0.0002,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.6418918918918919,
|
| 139 |
+
"grad_norm": 0.004224637057632208,
|
| 140 |
+
"learning_rate": 2.896566985427809e-05,
|
| 141 |
+
"loss": 0.0106,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6756756756756757,
|
| 146 |
+
"grad_norm": 0.47990503907203674,
|
| 147 |
+
"learning_rate": 2.8739715354486934e-05,
|
| 148 |
+
"loss": 0.0061,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.7094594594594594,
|
| 153 |
+
"grad_norm": 3.0428385734558105,
|
| 154 |
+
"learning_rate": 2.8492522152743587e-05,
|
| 155 |
+
"loss": 0.0007,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.7432432432432432,
|
| 160 |
+
"grad_norm": 0.28697794675827026,
|
| 161 |
+
"learning_rate": 2.8224472357599862e-05,
|
| 162 |
+
"loss": 0.005,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.777027027027027,
|
| 167 |
+
"grad_norm": 10.434463500976562,
|
| 168 |
+
"learning_rate": 2.793598031750189e-05,
|
| 169 |
+
"loss": 0.0059,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.8108108108108109,
|
| 174 |
+
"grad_norm": 0.16486147046089172,
|
| 175 |
+
"learning_rate": 2.7627491980294813e-05,
|
| 176 |
+
"loss": 0.0048,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.8445945945945946,
|
| 181 |
+
"grad_norm": 0.014305876567959785,
|
| 182 |
+
"learning_rate": 2.7299484203881476e-05,
|
| 183 |
+
"loss": 0.0262,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.8783783783783784,
|
| 188 |
+
"grad_norm": 0.003319332841783762,
|
| 189 |
+
"learning_rate": 2.69524640191007e-05,
|
| 190 |
+
"loss": 0.0313,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.9121621621621622,
|
| 195 |
+
"grad_norm": 0.011635912582278252,
|
| 196 |
+
"learning_rate": 2.6586967845964528e-05,
|
| 197 |
+
"loss": 0.0022,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.9459459459459459,
|
| 202 |
+
"grad_norm": 0.04328622668981552,
|
| 203 |
+
"learning_rate": 2.6203560664466036e-05,
|
| 204 |
+
"loss": 0.0003,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.9797297297297297,
|
| 209 |
+
"grad_norm": 98.71577453613281,
|
| 210 |
+
"learning_rate": 2.580283514123944e-05,
|
| 211 |
+
"loss": 0.0112,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.0,
|
| 216 |
+
"eval_loss": 0.00018429462215863168,
|
| 217 |
+
"eval_runtime": 2.4293,
|
| 218 |
+
"eval_samples_per_second": 108.261,
|
| 219 |
+
"eval_steps_per_second": 27.168,
|
| 220 |
+
"step": 296
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.0135135135135136,
|
| 224 |
+
"grad_norm": 0.0028017598669975996,
|
| 225 |
+
"learning_rate": 2.5385410713422475e-05,
|
| 226 |
+
"loss": 0.0001,
|
| 227 |
+
"step": 300
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.0472972972972974,
|
| 231 |
+
"grad_norm": 0.0028585209511220455,
|
| 232 |
+
"learning_rate": 2.495193263113722e-05,
|
| 233 |
+
"loss": 0.0001,
|
| 234 |
+
"step": 310
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.0810810810810811,
|
| 238 |
+
"grad_norm": 0.0021099066361784935,
|
| 239 |
+
"learning_rate": 2.4503070960069545e-05,
|
| 240 |
+
"loss": 0.0,
|
| 241 |
+
"step": 320
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.114864864864865,
|
| 245 |
+
"grad_norm": 0.0021344744600355625,
|
| 246 |
+
"learning_rate": 2.4039519545688848e-05,
|
| 247 |
+
"loss": 0.0,
|
| 248 |
+
"step": 330
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.1486486486486487,
|
| 252 |
+
"grad_norm": 0.007050791289657354,
|
| 253 |
+
"learning_rate": 2.356199494070932e-05,
|
| 254 |
+
"loss": 0.0009,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.1824324324324325,
|
| 259 |
+
"grad_norm": 0.2592613697052002,
|
| 260 |
+
"learning_rate": 2.307123529745059e-05,
|
| 261 |
+
"loss": 0.0002,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.2162162162162162,
|
| 266 |
+
"grad_norm": 0.004164527636021376,
|
| 267 |
+
"learning_rate": 2.256799922680994e-05,
|
| 268 |
+
"loss": 0.0001,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.25,
|
| 273 |
+
"grad_norm": 0.009292829781770706,
|
| 274 |
+
"learning_rate": 2.2053064625609836e-05,
|
| 275 |
+
"loss": 0.0001,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.2837837837837838,
|
| 280 |
+
"grad_norm": 0.24080495536327362,
|
| 281 |
+
"learning_rate": 2.1527227474133543e-05,
|
| 282 |
+
"loss": 0.0008,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.3175675675675675,
|
| 287 |
+
"grad_norm": 0.004564313683658838,
|
| 288 |
+
"learning_rate": 2.0991300605707474e-05,
|
| 289 |
+
"loss": 0.0016,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.3513513513513513,
|
| 294 |
+
"grad_norm": 0.012726039625704288,
|
| 295 |
+
"learning_rate": 2.0446112450232316e-05,
|
| 296 |
+
"loss": 0.0001,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.385135135135135,
|
| 301 |
+
"grad_norm": 0.0028580036014318466,
|
| 302 |
+
"learning_rate": 1.9892505753605152e-05,
|
| 303 |
+
"loss": 0.0002,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.4189189189189189,
|
| 308 |
+
"grad_norm": 0.0011500768596306443,
|
| 309 |
+
"learning_rate": 1.9331336275012043e-05,
|
| 310 |
+
"loss": 0.0,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.4527027027027026,
|
| 315 |
+
"grad_norm": 0.0012311682803556323,
|
| 316 |
+
"learning_rate": 1.8763471464104813e-05,
|
| 317 |
+
"loss": 0.0,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.4864864864864864,
|
| 322 |
+
"grad_norm": 0.0042627062648534775,
|
| 323 |
+
"learning_rate": 1.8189789120106866e-05,
|
| 324 |
+
"loss": 0.0058,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.5202702702702702,
|
| 329 |
+
"grad_norm": 0.0009136000298894942,
|
| 330 |
+
"learning_rate": 1.7611176034920735e-05,
|
| 331 |
+
"loss": 0.0,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.554054054054054,
|
| 336 |
+
"grad_norm": 0.0008129957714118063,
|
| 337 |
+
"learning_rate": 1.7028526622334838e-05,
|
| 338 |
+
"loss": 0.0,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.5878378378378377,
|
| 343 |
+
"grad_norm": 0.001546179410070181,
|
| 344 |
+
"learning_rate": 1.644274153544839e-05,
|
| 345 |
+
"loss": 0.0,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.6216216216216215,
|
| 350 |
+
"grad_norm": 0.0011343436781316996,
|
| 351 |
+
"learning_rate": 1.5854726274451723e-05,
|
| 352 |
+
"loss": 0.0,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.6554054054054053,
|
| 357 |
+
"grad_norm": 0.0004109444562345743,
|
| 358 |
+
"learning_rate": 1.5265389786913935e-05,
|
| 359 |
+
"loss": 0.0,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.689189189189189,
|
| 364 |
+
"grad_norm": 0.008421291597187519,
|
| 365 |
+
"learning_rate": 1.4675643062741682e-05,
|
| 366 |
+
"loss": 0.0,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.722972972972973,
|
| 371 |
+
"grad_norm": 0.005281887948513031,
|
| 372 |
+
"learning_rate": 1.4086397725980956e-05,
|
| 373 |
+
"loss": 0.0,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.7567567567567568,
|
| 378 |
+
"grad_norm": 0.0006799366092309356,
|
| 379 |
+
"learning_rate": 1.3498564625638524e-05,
|
| 380 |
+
"loss": 0.0,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.7905405405405406,
|
| 385 |
+
"grad_norm": 0.0005692480481229722,
|
| 386 |
+
"learning_rate": 1.2913052427701557e-05,
|
| 387 |
+
"loss": 0.0,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.8243243243243243,
|
| 392 |
+
"grad_norm": 0.0005203319014981389,
|
| 393 |
+
"learning_rate": 1.2330766210531605e-05,
|
| 394 |
+
"loss": 0.0001,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.8581081081081081,
|
| 399 |
+
"grad_norm": 0.0005495847435668111,
|
| 400 |
+
"learning_rate": 1.1752606065804399e-05,
|
| 401 |
+
"loss": 0.0,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.8918918918918919,
|
| 406 |
+
"grad_norm": 0.002254391787573695,
|
| 407 |
+
"learning_rate": 1.1179465707157924e-05,
|
| 408 |
+
"loss": 0.0,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.9256756756756757,
|
| 413 |
+
"grad_norm": 0.0006869367207400501,
|
| 414 |
+
"learning_rate": 1.061223108869968e-05,
|
| 415 |
+
"loss": 0.0,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.9594594594594594,
|
| 420 |
+
"grad_norm": 0.0006207679980434477,
|
| 421 |
+
"learning_rate": 1.0051779035508465e-05,
|
| 422 |
+
"loss": 0.0001,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.9932432432432432,
|
| 427 |
+
"grad_norm": 0.0012077532010152936,
|
| 428 |
+
"learning_rate": 9.498975888247754e-06,
|
| 429 |
+
"loss": 0.0,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.0,
|
| 434 |
+
"eval_loss": 2.5043016194103984e-06,
|
| 435 |
+
"eval_runtime": 2.3685,
|
| 436 |
+
"eval_samples_per_second": 111.039,
|
| 437 |
+
"eval_steps_per_second": 27.865,
|
| 438 |
+
"step": 592
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 2.027027027027027,
|
| 442 |
+
"grad_norm": 0.0005680551403202116,
|
| 443 |
+
"learning_rate": 8.954676163985774e-06,
|
| 444 |
+
"loss": 0.0,
|
| 445 |
+
"step": 600
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 2.060810810810811,
|
| 449 |
+
"grad_norm": 0.001357720117084682,
|
| 450 |
+
"learning_rate": 8.419721235292331e-06,
|
| 451 |
+
"loss": 0.0001,
|
| 452 |
+
"step": 610
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.0945945945945947,
|
| 456 |
+
"grad_norm": 0.0008826570701785386,
|
| 457 |
+
"learning_rate": 7.894938029654297e-06,
|
| 458 |
+
"loss": 0.0,
|
| 459 |
+
"step": 620
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.1283783783783785,
|
| 463 |
+
"grad_norm": 0.0008256045402958989,
|
| 464 |
+
"learning_rate": 7.381137751220117e-06,
|
| 465 |
+
"loss": 0.0,
|
| 466 |
+
"step": 630
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 2.1621621621621623,
|
| 470 |
+
"grad_norm": 0.0006997581222094595,
|
| 471 |
+
"learning_rate": 6.879114626849301e-06,
|
| 472 |
+
"loss": 0.0,
|
| 473 |
+
"step": 640
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.195945945945946,
|
| 477 |
+
"grad_norm": 0.0004744347825180739,
|
| 478 |
+
"learning_rate": 6.38964467840524e-06,
|
| 479 |
+
"loss": 0.0,
|
| 480 |
+
"step": 650
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.22972972972973,
|
| 484 |
+
"grad_norm": 0.0010553617030382156,
|
| 485 |
+
"learning_rate": 5.913484523189031e-06,
|
| 486 |
+
"loss": 0.0,
|
| 487 |
+
"step": 660
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 2.2635135135135136,
|
| 491 |
+
"grad_norm": 0.0008697208249941468,
|
| 492 |
+
"learning_rate": 5.45137020436876e-06,
|
| 493 |
+
"loss": 0.0,
|
| 494 |
+
"step": 670
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.2972972972972974,
|
| 498 |
+
"grad_norm": 0.001438570092432201,
|
| 499 |
+
"learning_rate": 5.004016053212012e-06,
|
| 500 |
+
"loss": 0.0,
|
| 501 |
+
"step": 680
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.331081081081081,
|
| 505 |
+
"grad_norm": 0.0011523235589265823,
|
| 506 |
+
"learning_rate": 4.572113584880366e-06,
|
| 507 |
+
"loss": 0.0001,
|
| 508 |
+
"step": 690
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.364864864864865,
|
| 512 |
+
"grad_norm": 0.0006420955178327858,
|
| 513 |
+
"learning_rate": 4.156330429492835e-06,
|
| 514 |
+
"loss": 0.0,
|
| 515 |
+
"step": 700
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.3986486486486487,
|
| 519 |
+
"grad_norm": 0.0010312465019524097,
|
| 520 |
+
"learning_rate": 3.7573093001105114e-06,
|
| 521 |
+
"loss": 0.0,
|
| 522 |
+
"step": 710
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.4324324324324325,
|
| 526 |
+
"grad_norm": 0.0007165200659073889,
|
| 527 |
+
"learning_rate": 3.375666999237735e-06,
|
| 528 |
+
"loss": 0.0,
|
| 529 |
+
"step": 720
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.4662162162162162,
|
| 533 |
+
"grad_norm": 0.0009894678369164467,
|
| 534 |
+
"learning_rate": 3.0119934653755215e-06,
|
| 535 |
+
"loss": 0.0,
|
| 536 |
+
"step": 730
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.5,
|
| 540 |
+
"grad_norm": 0.000802612688858062,
|
| 541 |
+
"learning_rate": 2.666850861101064e-06,
|
| 542 |
+
"loss": 0.0,
|
| 543 |
+
"step": 740
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.5337837837837838,
|
| 547 |
+
"grad_norm": 0.000768653058912605,
|
| 548 |
+
"learning_rate": 2.3407727040829624e-06,
|
| 549 |
+
"loss": 0.0278,
|
| 550 |
+
"step": 750
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.5675675675675675,
|
| 554 |
+
"grad_norm": 0.0009041289449669421,
|
| 555 |
+
"learning_rate": 2.0342630423754505e-06,
|
| 556 |
+
"loss": 0.0,
|
| 557 |
+
"step": 760
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.6013513513513513,
|
| 561 |
+
"grad_norm": 0.00031831240630708635,
|
| 562 |
+
"learning_rate": 1.7477956752663882e-06,
|
| 563 |
+
"loss": 0.0,
|
| 564 |
+
"step": 770
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.635135135135135,
|
| 568 |
+
"grad_norm": 0.0017055063508450985,
|
| 569 |
+
"learning_rate": 1.4818134208835233e-06,
|
| 570 |
+
"loss": 0.0,
|
| 571 |
+
"step": 780
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.668918918918919,
|
| 575 |
+
"grad_norm": 0.0008075103396549821,
|
| 576 |
+
"learning_rate": 1.2367274316910603e-06,
|
| 577 |
+
"loss": 0.0,
|
| 578 |
+
"step": 790
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.7027027027027026,
|
| 582 |
+
"grad_norm": 0.0003939785819966346,
|
| 583 |
+
"learning_rate": 1.0129165589346644e-06,
|
| 584 |
+
"loss": 0.0,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.7364864864864864,
|
| 589 |
+
"grad_norm": 0.00043582680518738925,
|
| 590 |
+
"learning_rate": 8.10726767017338e-07,
|
| 591 |
+
"loss": 0.0,
|
| 592 |
+
"step": 810
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.77027027027027,
|
| 596 |
+
"grad_norm": 0.0009908125502988696,
|
| 597 |
+
"learning_rate": 6.304705987114467e-07,
|
| 598 |
+
"loss": 0.0,
|
| 599 |
+
"step": 820
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.804054054054054,
|
| 603 |
+
"grad_norm": 0.0004368584486655891,
|
| 604 |
+
"learning_rate": 4.724266920334891e-07,
|
| 605 |
+
"loss": 0.0124,
|
| 606 |
+
"step": 830
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.8378378378378377,
|
| 610 |
+
"grad_norm": 0.0012720432132482529,
|
| 611 |
+
"learning_rate": 3.3683934952851215e-07,
|
| 612 |
+
"loss": 0.0,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.8716216216216215,
|
| 617 |
+
"grad_norm": 0.0004999402444809675,
|
| 618 |
+
"learning_rate": 2.2391816062989624e-07,
|
| 619 |
+
"loss": 0.0,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.9054054054054053,
|
| 624 |
+
"grad_norm": 0.0006334020290523767,
|
| 625 |
+
"learning_rate": 1.3383767767829957e-07,
|
| 626 |
+
"loss": 0.0,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.939189189189189,
|
| 631 |
+
"grad_norm": 0.0003505792992655188,
|
| 632 |
+
"learning_rate": 6.673714610055448e-08,
|
| 633 |
+
"loss": 0.0,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.972972972972973,
|
| 638 |
+
"grad_norm": 0.0010267982725054026,
|
| 639 |
+
"learning_rate": 2.2720289165613083e-08,
|
| 640 |
+
"loss": 0.0,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 3.0,
|
| 645 |
+
"eval_loss": 2.4904770725697745e-06,
|
| 646 |
+
"eval_runtime": 2.4326,
|
| 647 |
+
"eval_samples_per_second": 108.114,
|
| 648 |
+
"eval_steps_per_second": 27.131,
|
| 649 |
+
"step": 888
|
| 650 |
+
}
|
| 651 |
+
],
|
| 652 |
+
"logging_steps": 10,
|
| 653 |
+
"max_steps": 888,
|
| 654 |
+
"num_input_tokens_seen": 0,
|
| 655 |
+
"num_train_epochs": 3,
|
| 656 |
+
"save_steps": 500,
|
| 657 |
+
"stateful_callbacks": {
|
| 658 |
+
"TrainerControl": {
|
| 659 |
+
"args": {
|
| 660 |
+
"should_epoch_stop": false,
|
| 661 |
+
"should_evaluate": false,
|
| 662 |
+
"should_log": false,
|
| 663 |
+
"should_save": true,
|
| 664 |
+
"should_training_stop": true
|
| 665 |
+
},
|
| 666 |
+
"attributes": {}
|
| 667 |
+
}
|
| 668 |
+
},
|
| 669 |
+
"total_flos": 1390425366781440.0,
|
| 670 |
+
"train_batch_size": 4,
|
| 671 |
+
"trial_name": null,
|
| 672 |
+
"trial_params": null
|
| 673 |
+
}
|
finetuned_xlm-roberta/checkpoint-888/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8369906ea6653c33f21f912c813f8bd76e66bb2c941c41c44ab07ead5ecf8f7
|
| 3 |
+
size 5649
|
finetuned_xlm-roberta/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "deepset/xlm-roberta-base-squad2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForQuestionAnswering"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"language": "english",
|
| 17 |
+
"layer_norm_eps": 1e-05,
|
| 18 |
+
"max_position_embeddings": 514,
|
| 19 |
+
"model_type": "xlm-roberta",
|
| 20 |
+
"name": "XLMRoberta",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 1,
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.44.2",
|
| 28 |
+
"type_vocab_size": 1,
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 250002
|
| 31 |
+
}
|
finetuned_xlm-roberta/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:267bba456c1a3fa5f7e769a14754038ede3c823a04c94677e4a79a33fb36c98b
|
| 3 |
+
size 1109842416
|
finetuned_xlm-roberta/sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
finetuned_xlm-roberta/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
finetuned_xlm-roberta/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27659330da3a728337a458ae70d3bec0244950f6c9ee267ea68ed6ff17e09df5
|
| 3 |
+
size 17098516
|
finetuned_xlm-roberta/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"full_tokenizer_file": null,
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"sp_model_kwargs": {},
|
| 55 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
finetuned_xlm-roberta/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8369906ea6653c33f21f912c813f8bd76e66bb2c941c41c44ab07ead5ecf8f7
|
| 3 |
+
size 5649
|