Upload 7 files
Browse files- config.json +37 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +396 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"LABEL_0": 0,
|
| 21 |
+
"LABEL_1": 1,
|
| 22 |
+
"LABEL_2": 2
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"output_past": true,
|
| 30 |
+
"pad_token_id": 1,
|
| 31 |
+
"position_embedding_type": "absolute",
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.41.1",
|
| 34 |
+
"type_vocab_size": 2,
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 31002
|
| 37 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:087c85bdc6aa52c53fddd6665f3aa602fd02694bbf12a6e4bee3bc992d68d87d
|
| 3 |
+
size 437073724
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:372795f8f93e87b2eb9ff982ca417343df476e9dd09b812bf744a6e0ff2f4fe1
|
| 3 |
+
size 874267194
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65698df047fd69f0b32517edff3badac303620c8b1c5094816649334ac277ab0
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d12c31799628bb96494709d75be9daa503a77c472bf96805b97b6510cfee6e19
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,396 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.04531409963965416,
|
| 3 |
+
"best_model_checkpoint": "results_bert-base-spanish-wwm-cased/epoch20_bs64/checkpoint-48",
|
| 4 |
+
"epoch": 11.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 176,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 0.9667894840240479,
|
| 14 |
+
"learning_rate": 4.75e-05,
|
| 15 |
+
"loss": 0.3262,
|
| 16 |
+
"step": 16
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accurracy": {
|
| 21 |
+
"accuracy": 0.9767987486965589
|
| 22 |
+
},
|
| 23 |
+
"eval_f1": [
|
| 24 |
+
0.9801708132194579,
|
| 25 |
+
0.8147120055517002,
|
| 26 |
+
1.0
|
| 27 |
+
],
|
| 28 |
+
"eval_loss": 0.06416129320859909,
|
| 29 |
+
"eval_precision": [
|
| 30 |
+
0.9833109819699002,
|
| 31 |
+
0.7911051212938005,
|
| 32 |
+
1.0
|
| 33 |
+
],
|
| 34 |
+
"eval_recall": [
|
| 35 |
+
0.9770506366597572,
|
| 36 |
+
0.8397711015736766,
|
| 37 |
+
1.0
|
| 38 |
+
],
|
| 39 |
+
"eval_runtime": 3.1156,
|
| 40 |
+
"eval_samples_per_second": 43.972,
|
| 41 |
+
"eval_steps_per_second": 0.963,
|
| 42 |
+
"step": 16
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 2.0,
|
| 46 |
+
"grad_norm": 0.47570934891700745,
|
| 47 |
+
"learning_rate": 4.5e-05,
|
| 48 |
+
"loss": 0.0561,
|
| 49 |
+
"step": 32
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 2.0,
|
| 53 |
+
"eval_accurracy": {
|
| 54 |
+
"accuracy": 0.9820994091067083
|
| 55 |
+
},
|
| 56 |
+
"eval_f1": [
|
| 57 |
+
0.9846999405822935,
|
| 58 |
+
0.8571428571428571,
|
| 59 |
+
1.0
|
| 60 |
+
],
|
| 61 |
+
"eval_loss": 0.04880336672067642,
|
| 62 |
+
"eval_precision": [
|
| 63 |
+
0.9879284649776453,
|
| 64 |
+
0.8317631224764468,
|
| 65 |
+
1.0
|
| 66 |
+
],
|
| 67 |
+
"eval_recall": [
|
| 68 |
+
0.981492448919159,
|
| 69 |
+
0.8841201716738197,
|
| 70 |
+
1.0
|
| 71 |
+
],
|
| 72 |
+
"eval_runtime": 3.673,
|
| 73 |
+
"eval_samples_per_second": 37.299,
|
| 74 |
+
"eval_steps_per_second": 0.817,
|
| 75 |
+
"step": 32
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 3.0,
|
| 79 |
+
"grad_norm": 0.4510585069656372,
|
| 80 |
+
"learning_rate": 4.25e-05,
|
| 81 |
+
"loss": 0.041,
|
| 82 |
+
"step": 48
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 3.0,
|
| 86 |
+
"eval_accurracy": {
|
| 87 |
+
"accuracy": 0.9831421619742787
|
| 88 |
+
},
|
| 89 |
+
"eval_f1": [
|
| 90 |
+
0.9856040368061739,
|
| 91 |
+
0.8643356643356643,
|
| 92 |
+
1.0
|
| 93 |
+
],
|
| 94 |
+
"eval_loss": 0.04531409963965416,
|
| 95 |
+
"eval_precision": [
|
| 96 |
+
0.9879500148765249,
|
| 97 |
+
0.8454172366621067,
|
| 98 |
+
1.0
|
| 99 |
+
],
|
| 100 |
+
"eval_recall": [
|
| 101 |
+
0.9832691738229198,
|
| 102 |
+
0.8841201716738197,
|
| 103 |
+
1.0
|
| 104 |
+
],
|
| 105 |
+
"eval_runtime": 3.2836,
|
| 106 |
+
"eval_samples_per_second": 41.722,
|
| 107 |
+
"eval_steps_per_second": 0.914,
|
| 108 |
+
"step": 48
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 4.0,
|
| 112 |
+
"grad_norm": 0.5891135334968567,
|
| 113 |
+
"learning_rate": 4e-05,
|
| 114 |
+
"loss": 0.0305,
|
| 115 |
+
"step": 64
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 4.0,
|
| 119 |
+
"eval_accurracy": {
|
| 120 |
+
"accuracy": 0.9830552659019812
|
| 121 |
+
},
|
| 122 |
+
"eval_f1": [
|
| 123 |
+
0.9855544855174457,
|
| 124 |
+
0.8614072494669509,
|
| 125 |
+
1.0
|
| 126 |
+
],
|
| 127 |
+
"eval_loss": 0.04799243062734604,
|
| 128 |
+
"eval_precision": [
|
| 129 |
+
0.9862120088954781,
|
| 130 |
+
0.8559322033898306,
|
| 131 |
+
1.0
|
| 132 |
+
],
|
| 133 |
+
"eval_recall": [
|
| 134 |
+
0.9848978383180338,
|
| 135 |
+
0.8669527896995708,
|
| 136 |
+
1.0
|
| 137 |
+
],
|
| 138 |
+
"eval_runtime": 3.6636,
|
| 139 |
+
"eval_samples_per_second": 37.395,
|
| 140 |
+
"eval_steps_per_second": 0.819,
|
| 141 |
+
"step": 64
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 5.0,
|
| 145 |
+
"grad_norm": 0.9005504250526428,
|
| 146 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 147 |
+
"loss": 0.023,
|
| 148 |
+
"step": 80
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 5.0,
|
| 152 |
+
"eval_accurracy": {
|
| 153 |
+
"accuracy": 0.982186305179006
|
| 154 |
+
},
|
| 155 |
+
"eval_f1": [
|
| 156 |
+
0.9847843835819787,
|
| 157 |
+
0.8569434752267969,
|
| 158 |
+
1.0
|
| 159 |
+
],
|
| 160 |
+
"eval_loss": 0.055779680609703064,
|
| 161 |
+
"eval_precision": [
|
| 162 |
+
0.9873493079327281,
|
| 163 |
+
0.8365122615803815,
|
| 164 |
+
1.0
|
| 165 |
+
],
|
| 166 |
+
"eval_recall": [
|
| 167 |
+
0.9822327509623927,
|
| 168 |
+
0.8783977110157367,
|
| 169 |
+
1.0
|
| 170 |
+
],
|
| 171 |
+
"eval_runtime": 3.8421,
|
| 172 |
+
"eval_samples_per_second": 35.657,
|
| 173 |
+
"eval_steps_per_second": 0.781,
|
| 174 |
+
"step": 80
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 6.0,
|
| 178 |
+
"grad_norm": 0.5966660976409912,
|
| 179 |
+
"learning_rate": 3.5e-05,
|
| 180 |
+
"loss": 0.0181,
|
| 181 |
+
"step": 96
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 6.0,
|
| 185 |
+
"eval_accurracy": {
|
| 186 |
+
"accuracy": 0.982186305179006
|
| 187 |
+
},
|
| 188 |
+
"eval_f1": [
|
| 189 |
+
0.9847776045147397,
|
| 190 |
+
0.857539958304378,
|
| 191 |
+
1.0
|
| 192 |
+
],
|
| 193 |
+
"eval_loss": 0.055696263909339905,
|
| 194 |
+
"eval_precision": [
|
| 195 |
+
0.9877848949798897,
|
| 196 |
+
0.8337837837837838,
|
| 197 |
+
1.0
|
| 198 |
+
],
|
| 199 |
+
"eval_recall": [
|
| 200 |
+
0.9817885697364525,
|
| 201 |
+
0.882689556509299,
|
| 202 |
+
1.0
|
| 203 |
+
],
|
| 204 |
+
"eval_runtime": 3.6299,
|
| 205 |
+
"eval_samples_per_second": 37.742,
|
| 206 |
+
"eval_steps_per_second": 0.826,
|
| 207 |
+
"step": 96
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 7.0,
|
| 211 |
+
"grad_norm": 0.6903554797172546,
|
| 212 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 213 |
+
"loss": 0.0142,
|
| 214 |
+
"step": 112
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 7.0,
|
| 218 |
+
"eval_accurracy": {
|
| 219 |
+
"accuracy": 0.9822732012513035
|
| 220 |
+
},
|
| 221 |
+
"eval_f1": [
|
| 222 |
+
0.984870958172649,
|
| 223 |
+
0.8565400843881856,
|
| 224 |
+
1.0
|
| 225 |
+
],
|
| 226 |
+
"eval_loss": 0.06568428128957748,
|
| 227 |
+
"eval_precision": [
|
| 228 |
+
0.986627043090639,
|
| 229 |
+
0.8423236514522822,
|
| 230 |
+
1.0
|
| 231 |
+
],
|
| 232 |
+
"eval_recall": [
|
| 233 |
+
0.983121113414273,
|
| 234 |
+
0.871244635193133,
|
| 235 |
+
1.0
|
| 236 |
+
],
|
| 237 |
+
"eval_runtime": 3.4926,
|
| 238 |
+
"eval_samples_per_second": 39.226,
|
| 239 |
+
"eval_steps_per_second": 0.859,
|
| 240 |
+
"step": 112
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 8.0,
|
| 244 |
+
"grad_norm": 0.4664444923400879,
|
| 245 |
+
"learning_rate": 3e-05,
|
| 246 |
+
"loss": 0.0096,
|
| 247 |
+
"step": 128
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 8.0,
|
| 251 |
+
"eval_accurracy": {
|
| 252 |
+
"accuracy": 0.9815780326729232
|
| 253 |
+
},
|
| 254 |
+
"eval_f1": [
|
| 255 |
+
0.9842613214550854,
|
| 256 |
+
0.8523676880222841,
|
| 257 |
+
1.0
|
| 258 |
+
],
|
| 259 |
+
"eval_loss": 0.07148059457540512,
|
| 260 |
+
"eval_precision": [
|
| 261 |
+
0.9870458606313282,
|
| 262 |
+
0.830393487109905,
|
| 263 |
+
1.0
|
| 264 |
+
],
|
| 265 |
+
"eval_recall": [
|
| 266 |
+
0.981492448919159,
|
| 267 |
+
0.8755364806866953,
|
| 268 |
+
1.0
|
| 269 |
+
],
|
| 270 |
+
"eval_runtime": 3.6227,
|
| 271 |
+
"eval_samples_per_second": 37.817,
|
| 272 |
+
"eval_steps_per_second": 0.828,
|
| 273 |
+
"step": 128
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 9.0,
|
| 277 |
+
"grad_norm": 0.12620803713798523,
|
| 278 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 279 |
+
"loss": 0.0077,
|
| 280 |
+
"step": 144
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 9.0,
|
| 284 |
+
"eval_accurracy": {
|
| 285 |
+
"accuracy": 0.9833159541188738
|
| 286 |
+
},
|
| 287 |
+
"eval_f1": [
|
| 288 |
+
0.9858197932053175,
|
| 289 |
+
0.8594436310395315,
|
| 290 |
+
1.0
|
| 291 |
+
],
|
| 292 |
+
"eval_loss": 0.07231755554676056,
|
| 293 |
+
"eval_precision": [
|
| 294 |
+
0.9834954317712938,
|
| 295 |
+
0.8800599700149925,
|
| 296 |
+
1.0
|
| 297 |
+
],
|
| 298 |
+
"eval_recall": [
|
| 299 |
+
0.9881551673082618,
|
| 300 |
+
0.8397711015736766,
|
| 301 |
+
1.0
|
| 302 |
+
],
|
| 303 |
+
"eval_runtime": 3.2894,
|
| 304 |
+
"eval_samples_per_second": 41.649,
|
| 305 |
+
"eval_steps_per_second": 0.912,
|
| 306 |
+
"step": 144
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 10.0,
|
| 310 |
+
"grad_norm": 0.5548684597015381,
|
| 311 |
+
"learning_rate": 2.5e-05,
|
| 312 |
+
"loss": 0.0062,
|
| 313 |
+
"step": 160
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 10.0,
|
| 317 |
+
"eval_accurracy": {
|
| 318 |
+
"accuracy": 0.9833159541188738
|
| 319 |
+
},
|
| 320 |
+
"eval_f1": [
|
| 321 |
+
0.9857798844615613,
|
| 322 |
+
0.8632478632478633,
|
| 323 |
+
1.0
|
| 324 |
+
],
|
| 325 |
+
"eval_loss": 0.07776156067848206,
|
| 326 |
+
"eval_precision": [
|
| 327 |
+
0.9862181387077653,
|
| 328 |
+
0.8595744680851064,
|
| 329 |
+
1.0
|
| 330 |
+
],
|
| 331 |
+
"eval_recall": [
|
| 332 |
+
0.9853420195439739,
|
| 333 |
+
0.8669527896995708,
|
| 334 |
+
1.0
|
| 335 |
+
],
|
| 336 |
+
"eval_runtime": 3.5848,
|
| 337 |
+
"eval_samples_per_second": 38.217,
|
| 338 |
+
"eval_steps_per_second": 0.837,
|
| 339 |
+
"step": 160
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 11.0,
|
| 343 |
+
"grad_norm": 0.6255295872688293,
|
| 344 |
+
"learning_rate": 2.25e-05,
|
| 345 |
+
"loss": 0.0049,
|
| 346 |
+
"step": 176
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 11.0,
|
| 350 |
+
"eval_accurracy": {
|
| 351 |
+
"accuracy": 0.9835766423357665
|
| 352 |
+
},
|
| 353 |
+
"eval_f1": [
|
| 354 |
+
0.9859865055238378,
|
| 355 |
+
0.8668076109936576,
|
| 356 |
+
1.0
|
| 357 |
+
],
|
| 358 |
+
"eval_loss": 0.07731029391288757,
|
| 359 |
+
"eval_precision": [
|
| 360 |
+
0.9875241348581613,
|
| 361 |
+
0.8541666666666666,
|
| 362 |
+
1.0
|
| 363 |
+
],
|
| 364 |
+
"eval_recall": [
|
| 365 |
+
0.9844536570920935,
|
| 366 |
+
0.8798283261802575,
|
| 367 |
+
1.0
|
| 368 |
+
],
|
| 369 |
+
"eval_runtime": 3.8542,
|
| 370 |
+
"eval_samples_per_second": 35.545,
|
| 371 |
+
"eval_steps_per_second": 0.778,
|
| 372 |
+
"step": 176
|
| 373 |
+
}
|
| 374 |
+
],
|
| 375 |
+
"logging_steps": 500,
|
| 376 |
+
"max_steps": 320,
|
| 377 |
+
"num_input_tokens_seen": 0,
|
| 378 |
+
"num_train_epochs": 20,
|
| 379 |
+
"save_steps": 500,
|
| 380 |
+
"stateful_callbacks": {
|
| 381 |
+
"TrainerControl": {
|
| 382 |
+
"args": {
|
| 383 |
+
"should_epoch_stop": false,
|
| 384 |
+
"should_evaluate": false,
|
| 385 |
+
"should_log": false,
|
| 386 |
+
"should_save": true,
|
| 387 |
+
"should_training_stop": false
|
| 388 |
+
},
|
| 389 |
+
"attributes": {}
|
| 390 |
+
}
|
| 391 |
+
},
|
| 392 |
+
"total_flos": 491604692303340.0,
|
| 393 |
+
"train_batch_size": 64,
|
| 394 |
+
"trial_name": null,
|
| 395 |
+
"trial_params": null
|
| 396 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f484095468004493b30a97e3c0e5e12e1b6d990724f2109089d216af8d54cae
|
| 3 |
+
size 5112
|