update base model
Browse files- config.json +44 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +368 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"finetuning_task": "deft_task3",
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "LABEL_0",
|
| 16 |
+
"1": "LABEL_1",
|
| 17 |
+
"2": "LABEL_2",
|
| 18 |
+
"3": "LABEL_3",
|
| 19 |
+
"4": "LABEL_4",
|
| 20 |
+
"5": "LABEL_5"
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 3072,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"LABEL_0": 0,
|
| 26 |
+
"LABEL_1": 1,
|
| 27 |
+
"LABEL_2": 2,
|
| 28 |
+
"LABEL_3": 3,
|
| 29 |
+
"LABEL_4": 4,
|
| 30 |
+
"LABEL_5": 5
|
| 31 |
+
},
|
| 32 |
+
"layer_norm_eps": 1e-05,
|
| 33 |
+
"max_position_embeddings": 514,
|
| 34 |
+
"model_type": "roberta",
|
| 35 |
+
"num_attention_heads": 12,
|
| 36 |
+
"num_hidden_layers": 12,
|
| 37 |
+
"pad_token_id": 1,
|
| 38 |
+
"position_embedding_type": "absolute",
|
| 39 |
+
"problem_type": "single_label_classification",
|
| 40 |
+
"transformers_version": "4.6.1",
|
| 41 |
+
"type_vocab_size": 1,
|
| 42 |
+
"use_cache": true,
|
| 43 |
+
"vocab_size": 50265
|
| 44 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcf6e456500a44d0dd51150c194534ac91da8e788fe6094aee5dc3ab8bfb6f29
|
| 3 |
+
size 498691529
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,368 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7991586011098205,
|
| 3 |
+
"best_model_checkpoint": "results/roberta-base-2e-5-16-256/checkpoint-1000",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 2300,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.22,
|
| 12 |
+
"learning_rate": 8.695652173913044e-06,
|
| 13 |
+
"loss": 1.3164,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.22,
|
| 18 |
+
"eval_accuracy": 0.8347826086956521,
|
| 19 |
+
"eval_f1": 0.15165876777251183,
|
| 20 |
+
"eval_loss": 0.659010648727417,
|
| 21 |
+
"eval_runtime": 1.8554,
|
| 22 |
+
"eval_samples_per_second": 185.947,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.43,
|
| 27 |
+
"learning_rate": 1.730434782608696e-05,
|
| 28 |
+
"loss": 0.7929,
|
| 29 |
+
"step": 200
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.43,
|
| 33 |
+
"eval_accuracy": 0.8956521739130435,
|
| 34 |
+
"eval_f1": 0.3681933057098357,
|
| 35 |
+
"eval_loss": 0.4090113639831543,
|
| 36 |
+
"eval_runtime": 1.8693,
|
| 37 |
+
"eval_samples_per_second": 184.559,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.65,
|
| 42 |
+
"learning_rate": 1.934299516908213e-05,
|
| 43 |
+
"loss": 0.4876,
|
| 44 |
+
"step": 300
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.65,
|
| 48 |
+
"eval_accuracy": 0.9101449275362319,
|
| 49 |
+
"eval_f1": 0.45359927879197653,
|
| 50 |
+
"eval_loss": 0.2804220914840698,
|
| 51 |
+
"eval_runtime": 1.8812,
|
| 52 |
+
"eval_samples_per_second": 183.389,
|
| 53 |
+
"step": 300
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.87,
|
| 57 |
+
"learning_rate": 1.83768115942029e-05,
|
| 58 |
+
"loss": 0.3733,
|
| 59 |
+
"step": 400
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.87,
|
| 63 |
+
"eval_accuracy": 0.9565217391304348,
|
| 64 |
+
"eval_f1": 0.6091620621342052,
|
| 65 |
+
"eval_loss": 0.20709100365638733,
|
| 66 |
+
"eval_runtime": 1.8861,
|
| 67 |
+
"eval_samples_per_second": 182.913,
|
| 68 |
+
"step": 400
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.09,
|
| 72 |
+
"learning_rate": 1.7410628019323673e-05,
|
| 73 |
+
"loss": 0.2586,
|
| 74 |
+
"step": 500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.09,
|
| 78 |
+
"eval_accuracy": 0.9710144927536232,
|
| 79 |
+
"eval_f1": 0.7547141566653762,
|
| 80 |
+
"eval_loss": 0.14703336358070374,
|
| 81 |
+
"eval_runtime": 1.8842,
|
| 82 |
+
"eval_samples_per_second": 183.1,
|
| 83 |
+
"step": 500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.3,
|
| 87 |
+
"learning_rate": 1.6444444444444444e-05,
|
| 88 |
+
"loss": 0.1932,
|
| 89 |
+
"step": 600
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.3,
|
| 93 |
+
"eval_accuracy": 0.9652173913043478,
|
| 94 |
+
"eval_f1": 0.7599251142269877,
|
| 95 |
+
"eval_loss": 0.14065894484519958,
|
| 96 |
+
"eval_runtime": 1.8891,
|
| 97 |
+
"eval_samples_per_second": 182.625,
|
| 98 |
+
"step": 600
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.52,
|
| 102 |
+
"learning_rate": 1.5478260869565217e-05,
|
| 103 |
+
"loss": 0.1952,
|
| 104 |
+
"step": 700
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.52,
|
| 108 |
+
"eval_accuracy": 0.9739130434782609,
|
| 109 |
+
"eval_f1": 0.7965866610767565,
|
| 110 |
+
"eval_loss": 0.15803956985473633,
|
| 111 |
+
"eval_runtime": 1.8925,
|
| 112 |
+
"eval_samples_per_second": 182.3,
|
| 113 |
+
"step": 700
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.74,
|
| 117 |
+
"learning_rate": 1.4521739130434785e-05,
|
| 118 |
+
"loss": 0.1734,
|
| 119 |
+
"step": 800
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.74,
|
| 123 |
+
"eval_accuracy": 0.9623188405797102,
|
| 124 |
+
"eval_f1": 0.7857069143446852,
|
| 125 |
+
"eval_loss": 0.1854896992444992,
|
| 126 |
+
"eval_runtime": 1.8925,
|
| 127 |
+
"eval_samples_per_second": 182.299,
|
| 128 |
+
"step": 800
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.96,
|
| 132 |
+
"learning_rate": 1.3555555555555557e-05,
|
| 133 |
+
"loss": 0.1515,
|
| 134 |
+
"step": 900
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.96,
|
| 138 |
+
"eval_accuracy": 0.9681159420289855,
|
| 139 |
+
"eval_f1": 0.7569010619010618,
|
| 140 |
+
"eval_loss": 0.1608872264623642,
|
| 141 |
+
"eval_runtime": 1.8927,
|
| 142 |
+
"eval_samples_per_second": 182.276,
|
| 143 |
+
"step": 900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 2.17,
|
| 147 |
+
"learning_rate": 1.2589371980676331e-05,
|
| 148 |
+
"loss": 0.1214,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.17,
|
| 153 |
+
"eval_accuracy": 0.9739130434782609,
|
| 154 |
+
"eval_f1": 0.7991586011098205,
|
| 155 |
+
"eval_loss": 0.14474469423294067,
|
| 156 |
+
"eval_runtime": 1.8926,
|
| 157 |
+
"eval_samples_per_second": 182.29,
|
| 158 |
+
"step": 1000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.39,
|
| 162 |
+
"learning_rate": 1.1623188405797103e-05,
|
| 163 |
+
"loss": 0.1145,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.39,
|
| 168 |
+
"eval_accuracy": 0.9710144927536232,
|
| 169 |
+
"eval_f1": 0.7922399586487883,
|
| 170 |
+
"eval_loss": 0.14988109469413757,
|
| 171 |
+
"eval_runtime": 1.8948,
|
| 172 |
+
"eval_samples_per_second": 182.077,
|
| 173 |
+
"step": 1100
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 2.61,
|
| 177 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 178 |
+
"loss": 0.0978,
|
| 179 |
+
"step": 1200
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.61,
|
| 183 |
+
"eval_accuracy": 0.9478260869565217,
|
| 184 |
+
"eval_f1": 0.7102037440793926,
|
| 185 |
+
"eval_loss": 0.21022763848304749,
|
| 186 |
+
"eval_runtime": 1.8939,
|
| 187 |
+
"eval_samples_per_second": 182.162,
|
| 188 |
+
"step": 1200
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.83,
|
| 192 |
+
"learning_rate": 9.700483091787441e-06,
|
| 193 |
+
"loss": 0.112,
|
| 194 |
+
"step": 1300
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.83,
|
| 198 |
+
"eval_accuracy": 0.9681159420289855,
|
| 199 |
+
"eval_f1": 0.7895157299399082,
|
| 200 |
+
"eval_loss": 0.15368108451366425,
|
| 201 |
+
"eval_runtime": 1.8983,
|
| 202 |
+
"eval_samples_per_second": 181.738,
|
| 203 |
+
"step": 1300
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 3.04,
|
| 207 |
+
"learning_rate": 8.734299516908213e-06,
|
| 208 |
+
"loss": 0.0879,
|
| 209 |
+
"step": 1400
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 3.04,
|
| 213 |
+
"eval_accuracy": 0.9681159420289855,
|
| 214 |
+
"eval_f1": 0.7895157299399082,
|
| 215 |
+
"eval_loss": 0.160787895321846,
|
| 216 |
+
"eval_runtime": 1.8947,
|
| 217 |
+
"eval_samples_per_second": 182.086,
|
| 218 |
+
"step": 1400
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.26,
|
| 222 |
+
"learning_rate": 7.768115942028987e-06,
|
| 223 |
+
"loss": 0.0721,
|
| 224 |
+
"step": 1500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.26,
|
| 228 |
+
"eval_accuracy": 0.9710144927536232,
|
| 229 |
+
"eval_f1": 0.7932638888888889,
|
| 230 |
+
"eval_loss": 0.1662783920764923,
|
| 231 |
+
"eval_runtime": 1.895,
|
| 232 |
+
"eval_samples_per_second": 182.054,
|
| 233 |
+
"step": 1500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.48,
|
| 237 |
+
"learning_rate": 6.801932367149759e-06,
|
| 238 |
+
"loss": 0.0744,
|
| 239 |
+
"step": 1600
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.48,
|
| 243 |
+
"eval_accuracy": 0.9710144927536232,
|
| 244 |
+
"eval_f1": 0.7932638888888889,
|
| 245 |
+
"eval_loss": 0.17374691367149353,
|
| 246 |
+
"eval_runtime": 1.8929,
|
| 247 |
+
"eval_samples_per_second": 182.259,
|
| 248 |
+
"step": 1600
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.7,
|
| 252 |
+
"learning_rate": 5.835748792270531e-06,
|
| 253 |
+
"loss": 0.0614,
|
| 254 |
+
"step": 1700
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.7,
|
| 258 |
+
"eval_accuracy": 0.9710144927536232,
|
| 259 |
+
"eval_f1": 0.7929378560367236,
|
| 260 |
+
"eval_loss": 0.15358248353004456,
|
| 261 |
+
"eval_runtime": 1.8971,
|
| 262 |
+
"eval_samples_per_second": 181.86,
|
| 263 |
+
"step": 1700
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.91,
|
| 267 |
+
"learning_rate": 4.869565217391305e-06,
|
| 268 |
+
"loss": 0.0702,
|
| 269 |
+
"step": 1800
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.91,
|
| 273 |
+
"eval_accuracy": 0.9710144927536232,
|
| 274 |
+
"eval_f1": 0.7929378560367236,
|
| 275 |
+
"eval_loss": 0.1646239012479782,
|
| 276 |
+
"eval_runtime": 1.8948,
|
| 277 |
+
"eval_samples_per_second": 182.073,
|
| 278 |
+
"step": 1800
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 4.13,
|
| 282 |
+
"learning_rate": 3.903381642512077e-06,
|
| 283 |
+
"loss": 0.0536,
|
| 284 |
+
"step": 1900
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 4.13,
|
| 288 |
+
"eval_accuracy": 0.9739130434782609,
|
| 289 |
+
"eval_f1": 0.7966849998231528,
|
| 290 |
+
"eval_loss": 0.1578085571527481,
|
| 291 |
+
"eval_runtime": 1.8964,
|
| 292 |
+
"eval_samples_per_second": 181.922,
|
| 293 |
+
"step": 1900
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 4.35,
|
| 297 |
+
"learning_rate": 2.9371980676328504e-06,
|
| 298 |
+
"loss": 0.0489,
|
| 299 |
+
"step": 2000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 4.35,
|
| 303 |
+
"eval_accuracy": 0.9710144927536232,
|
| 304 |
+
"eval_f1": 0.7932638888888889,
|
| 305 |
+
"eval_loss": 0.16712208092212677,
|
| 306 |
+
"eval_runtime": 1.9014,
|
| 307 |
+
"eval_samples_per_second": 181.448,
|
| 308 |
+
"step": 2000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.57,
|
| 312 |
+
"learning_rate": 1.9710144927536233e-06,
|
| 313 |
+
"loss": 0.0267,
|
| 314 |
+
"step": 2100
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 4.57,
|
| 318 |
+
"eval_accuracy": 0.9739130434782609,
|
| 319 |
+
"eval_f1": 0.7982255213856485,
|
| 320 |
+
"eval_loss": 0.1600024402141571,
|
| 321 |
+
"eval_runtime": 1.8949,
|
| 322 |
+
"eval_samples_per_second": 182.068,
|
| 323 |
+
"step": 2100
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 4.78,
|
| 327 |
+
"learning_rate": 1.0048309178743963e-06,
|
| 328 |
+
"loss": 0.0511,
|
| 329 |
+
"step": 2200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 4.78,
|
| 333 |
+
"eval_accuracy": 0.9710144927536232,
|
| 334 |
+
"eval_f1": 0.7932638888888889,
|
| 335 |
+
"eval_loss": 0.17408017814159393,
|
| 336 |
+
"eval_runtime": 1.8946,
|
| 337 |
+
"eval_samples_per_second": 182.094,
|
| 338 |
+
"step": 2200
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 5.0,
|
| 342 |
+
"learning_rate": 3.864734299516908e-08,
|
| 343 |
+
"loss": 0.0291,
|
| 344 |
+
"step": 2300
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 5.0,
|
| 348 |
+
"eval_accuracy": 0.9710144927536232,
|
| 349 |
+
"eval_f1": 0.7932638888888889,
|
| 350 |
+
"eval_loss": 0.180899977684021,
|
| 351 |
+
"eval_runtime": 1.8959,
|
| 352 |
+
"eval_samples_per_second": 181.972,
|
| 353 |
+
"step": 2300
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 5.0,
|
| 357 |
+
"step": 2300,
|
| 358 |
+
"total_flos": 0,
|
| 359 |
+
"train_runtime": 487.2382,
|
| 360 |
+
"train_samples_per_second": 4.72
|
| 361 |
+
}
|
| 362 |
+
],
|
| 363 |
+
"max_steps": 2300,
|
| 364 |
+
"num_train_epochs": 5,
|
| 365 |
+
"total_flos": 0,
|
| 366 |
+
"trial_name": null,
|
| 367 |
+
"trial_params": null
|
| 368 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|