Delete checkpoint-17666
Browse files- checkpoint-17666/config.json +0 -58
- checkpoint-17666/generation_config.json +0 -8
- checkpoint-17666/model.safetensors +0 -3
- checkpoint-17666/optimizer.pt +0 -3
- checkpoint-17666/rng_state.pth +0 -3
- checkpoint-17666/scaler.pt +0 -3
- checkpoint-17666/scheduler.pt +0 -3
- checkpoint-17666/special_tokens_map.json +0 -9
- checkpoint-17666/tokenizer.json +0 -0
- checkpoint-17666/tokenizer_config.json +0 -25
- checkpoint-17666/trainer_state.json +0 -411
- checkpoint-17666/training_args.bin +0 -3
checkpoint-17666/config.json
DELETED
|
@@ -1,58 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"activation_dropout": 0.1,
|
| 3 |
-
"activation_function": "gelu",
|
| 4 |
-
"add_bias_logits": false,
|
| 5 |
-
"add_final_layer_norm": true,
|
| 6 |
-
"architectures": [
|
| 7 |
-
"MBartForConditionalGeneration"
|
| 8 |
-
],
|
| 9 |
-
"attention_dropout": 0.1,
|
| 10 |
-
"bos_token_id": 0,
|
| 11 |
-
"classif_dropout": 0.1,
|
| 12 |
-
"classifier_dropout": 0.0,
|
| 13 |
-
"d_model": 768,
|
| 14 |
-
"decoder_attention_heads": 12,
|
| 15 |
-
"decoder_ffn_dim": 3072,
|
| 16 |
-
"decoder_layerdrop": 0.0,
|
| 17 |
-
"decoder_layers": 6,
|
| 18 |
-
"decoder_start_token_id": 2,
|
| 19 |
-
"do_blenderbot_90_layernorm": false,
|
| 20 |
-
"dropout": 0.1,
|
| 21 |
-
"early_stopping": null,
|
| 22 |
-
"encoder_attention_heads": 12,
|
| 23 |
-
"encoder_ffn_dim": 3072,
|
| 24 |
-
"encoder_layerdrop": 0.0,
|
| 25 |
-
"encoder_layers": 6,
|
| 26 |
-
"eos_token_id": 2,
|
| 27 |
-
"extra_pos_embeddings": 2,
|
| 28 |
-
"force_bos_token_to_be_generated": false,
|
| 29 |
-
"forced_eos_token_id": 2,
|
| 30 |
-
"gradient_checkpointing": false,
|
| 31 |
-
"id2label": {
|
| 32 |
-
"0": "LABEL_0",
|
| 33 |
-
"1": "LABEL_1",
|
| 34 |
-
"2": "LABEL_2"
|
| 35 |
-
},
|
| 36 |
-
"init_std": 0.02,
|
| 37 |
-
"is_encoder_decoder": true,
|
| 38 |
-
"label2id": {
|
| 39 |
-
"LABEL_0": 0,
|
| 40 |
-
"LABEL_1": 1,
|
| 41 |
-
"LABEL_2": 2
|
| 42 |
-
},
|
| 43 |
-
"max_position_embeddings": 1024,
|
| 44 |
-
"model_type": "mbart",
|
| 45 |
-
"no_repeat_ngram_size": null,
|
| 46 |
-
"normalize_before": true,
|
| 47 |
-
"normalize_embedding": true,
|
| 48 |
-
"num_beams": null,
|
| 49 |
-
"num_hidden_layers": 6,
|
| 50 |
-
"pad_token_id": 1,
|
| 51 |
-
"scale_embedding": false,
|
| 52 |
-
"static_position_embeddings": false,
|
| 53 |
-
"tokenizer_class": "BarthezTokenizer",
|
| 54 |
-
"torch_dtype": "float32",
|
| 55 |
-
"transformers_version": "4.51.3",
|
| 56 |
-
"use_cache": true,
|
| 57 |
-
"vocab_size": 86001
|
| 58 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-17666/generation_config.json
DELETED
|
@@ -1,8 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token_id": 0,
|
| 3 |
-
"decoder_start_token_id": 2,
|
| 4 |
-
"eos_token_id": 2,
|
| 5 |
-
"forced_eos_token_id": 2,
|
| 6 |
-
"pad_token_id": 1,
|
| 7 |
-
"transformers_version": "4.51.3"
|
| 8 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-17666/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:dc3dbc93a147703d7016436477b309809daf6cf7dfd5459380d02ef6d6acd536
|
| 3 |
-
size 667849236
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-17666/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e1058b784b49d0e21781e102d0b13cd3bd8b23abbef48c240656d881fd21d466
|
| 3 |
-
size 1964811
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-17666/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:1443da10428be3da89ea4d5f4a48ef57f11bddd9126a53d8fab7939e5b5c2fbf
|
| 3 |
-
size 14645
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-17666/scaler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:3ba978f0695d12a2d6df591e5f03e6a35948da3a5f9f69b750a6cd6494690db9
|
| 3 |
-
size 1383
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-17666/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:6ea73958def745c86f18703159f2a1547b17704a7f9e406e1762cedf51dc3906
|
| 3 |
-
size 1465
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-17666/special_tokens_map.json
DELETED
|
@@ -1,9 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"pad_token": {
|
| 3 |
-
"content": "[PAD]",
|
| 4 |
-
"lstrip": false,
|
| 5 |
-
"normalized": false,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
}
|
| 9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-17666/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-17666/tokenizer_config.json
DELETED
|
@@ -1,25 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"added_tokens_decoder": {
|
| 3 |
-
"0": {
|
| 4 |
-
"content": "<unk>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"86000": {
|
| 12 |
-
"content": "[PAD]",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
}
|
| 19 |
-
},
|
| 20 |
-
"clean_up_tokenization_spaces": true,
|
| 21 |
-
"extra_special_tokens": {},
|
| 22 |
-
"model_max_length": 128,
|
| 23 |
-
"pad_token": "[PAD]",
|
| 24 |
-
"tokenizer_class": "PreTrainedTokenizer"
|
| 25 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-17666/trainer_state.json
DELETED
|
@@ -1,411 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": 17666,
|
| 3 |
-
"best_metric": 0.706001258948505,
|
| 4 |
-
"best_model_checkpoint": "checkpoints/checkpoint-17666",
|
| 5 |
-
"epoch": 2.749970813713663,
|
| 6 |
-
"eval_steps": 1606,
|
| 7 |
-
"global_step": 17666,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 0.07783009689847063,
|
| 14 |
-
"grad_norm": 0.2925865948200226,
|
| 15 |
-
"learning_rate": 4.991766654390158e-05,
|
| 16 |
-
"loss": 2.2108,
|
| 17 |
-
"step": 500
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 0.15566019379694127,
|
| 21 |
-
"grad_norm": 0.11884481459856033,
|
| 22 |
-
"learning_rate": 4.966988962239142e-05,
|
| 23 |
-
"loss": 0.3886,
|
| 24 |
-
"step": 1000
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 0.2334902906954119,
|
| 28 |
-
"grad_norm": 0.09392867982387543,
|
| 29 |
-
"learning_rate": 4.925831306092169e-05,
|
| 30 |
-
"loss": 0.2271,
|
| 31 |
-
"step": 1500
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 0.2499902712378877,
|
| 35 |
-
"eval_avg": 26.749637281629344,
|
| 36 |
-
"eval_cer": 0.6640905490705347,
|
| 37 |
-
"eval_der": 78.87487905513909,
|
| 38 |
-
"eval_loss": 0.13775022327899933,
|
| 39 |
-
"eval_runtime": 1439.866,
|
| 40 |
-
"eval_samples_per_second": 94.261,
|
| 41 |
-
"eval_steps_per_second": 0.369,
|
| 42 |
-
"eval_wer": 0.7099422406784007,
|
| 43 |
-
"step": 1606
|
| 44 |
-
},
|
| 45 |
-
{
|
| 46 |
-
"epoch": 0.31132038759388253,
|
| 47 |
-
"grad_norm": 0.0717502012848854,
|
| 48 |
-
"learning_rate": 4.8685669587267704e-05,
|
| 49 |
-
"loss": 0.1657,
|
| 50 |
-
"step": 2000
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"epoch": 0.3891504844923532,
|
| 54 |
-
"grad_norm": 0.0638226792216301,
|
| 55 |
-
"learning_rate": 4.795576135848184e-05,
|
| 56 |
-
"loss": 0.1334,
|
| 57 |
-
"step": 2500
|
| 58 |
-
},
|
| 59 |
-
{
|
| 60 |
-
"epoch": 0.4669805813908238,
|
| 61 |
-
"grad_norm": 0.05441045016050339,
|
| 62 |
-
"learning_rate": 4.707343471586959e-05,
|
| 63 |
-
"loss": 0.1135,
|
| 64 |
-
"step": 3000
|
| 65 |
-
},
|
| 66 |
-
{
|
| 67 |
-
"epoch": 0.4999805424757754,
|
| 68 |
-
"eval_avg": 26.867260983703588,
|
| 69 |
-
"eval_cer": 0.6597599235984197,
|
| 70 |
-
"eval_der": 79.24906581788363,
|
| 71 |
-
"eval_loss": 0.07722582668066025,
|
| 72 |
-
"eval_runtime": 1442.4649,
|
| 73 |
-
"eval_samples_per_second": 94.091,
|
| 74 |
-
"eval_steps_per_second": 0.368,
|
| 75 |
-
"eval_wer": 0.6929572096287142,
|
| 76 |
-
"step": 3212
|
| 77 |
-
},
|
| 78 |
-
{
|
| 79 |
-
"epoch": 0.5448106782892945,
|
| 80 |
-
"grad_norm": 0.050636373460292816,
|
| 81 |
-
"learning_rate": 4.604454800693874e-05,
|
| 82 |
-
"loss": 0.1002,
|
| 83 |
-
"step": 3500
|
| 84 |
-
},
|
| 85 |
-
{
|
| 86 |
-
"epoch": 0.6226407751877651,
|
| 87 |
-
"grad_norm": 0.0581156350672245,
|
| 88 |
-
"learning_rate": 4.48759326879731e-05,
|
| 89 |
-
"loss": 0.0906,
|
| 90 |
-
"step": 4000
|
| 91 |
-
},
|
| 92 |
-
{
|
| 93 |
-
"epoch": 0.7004708720862357,
|
| 94 |
-
"grad_norm": 0.050500743091106415,
|
| 95 |
-
"learning_rate": 4.3575347965496405e-05,
|
| 96 |
-
"loss": 0.0828,
|
| 97 |
-
"step": 4500
|
| 98 |
-
},
|
| 99 |
-
{
|
| 100 |
-
"epoch": 0.749970813713663,
|
| 101 |
-
"eval_avg": 26.888053782081823,
|
| 102 |
-
"eval_cer": 0.6586451367564623,
|
| 103 |
-
"eval_der": 79.3192047037025,
|
| 104 |
-
"eval_loss": 0.05902250111103058,
|
| 105 |
-
"eval_runtime": 1431.2383,
|
| 106 |
-
"eval_samples_per_second": 94.829,
|
| 107 |
-
"eval_steps_per_second": 0.371,
|
| 108 |
-
"eval_wer": 0.6863115057865005,
|
| 109 |
-
"step": 4818
|
| 110 |
-
},
|
| 111 |
-
{
|
| 112 |
-
"epoch": 0.7783009689847064,
|
| 113 |
-
"grad_norm": 0.04594194516539574,
|
| 114 |
-
"learning_rate": 4.9989118673869795e-05,
|
| 115 |
-
"loss": 0.0765,
|
| 116 |
-
"step": 5000
|
| 117 |
-
},
|
| 118 |
-
{
|
| 119 |
-
"epoch": 0.856131065883177,
|
| 120 |
-
"grad_norm": 0.04987065866589546,
|
| 121 |
-
"learning_rate": 4.984611214237347e-05,
|
| 122 |
-
"loss": 0.0724,
|
| 123 |
-
"step": 5500
|
| 124 |
-
},
|
| 125 |
-
{
|
| 126 |
-
"epoch": 0.9339611627816476,
|
| 127 |
-
"grad_norm": 0.04362853616476059,
|
| 128 |
-
"learning_rate": 4.953813591358179e-05,
|
| 129 |
-
"loss": 0.0683,
|
| 130 |
-
"step": 6000
|
| 131 |
-
},
|
| 132 |
-
{
|
| 133 |
-
"epoch": 0.9999610849515508,
|
| 134 |
-
"eval_avg": 0.708712044715695,
|
| 135 |
-
"eval_cer": 0.6546741642910598,
|
| 136 |
-
"eval_der": 0.7934032551594553,
|
| 137 |
-
"eval_loss": 0.049141544848680496,
|
| 138 |
-
"eval_runtime": 305.8639,
|
| 139 |
-
"eval_samples_per_second": 443.737,
|
| 140 |
-
"eval_steps_per_second": 1.736,
|
| 141 |
-
"eval_wer": 0.6780587146965699,
|
| 142 |
-
"step": 6424
|
| 143 |
-
},
|
| 144 |
-
{
|
| 145 |
-
"epoch": 1.0118301747285676,
|
| 146 |
-
"grad_norm": 0.04417261481285095,
|
| 147 |
-
"learning_rate": 4.99981315851881e-05,
|
| 148 |
-
"loss": 0.0626,
|
| 149 |
-
"step": 6500
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 1.0896602716270383,
|
| 153 |
-
"grad_norm": 0.039167486131191254,
|
| 154 |
-
"learning_rate": 4.9890257744619245e-05,
|
| 155 |
-
"loss": 0.061,
|
| 156 |
-
"step": 7000
|
| 157 |
-
},
|
| 158 |
-
{
|
| 159 |
-
"epoch": 1.1674903685255087,
|
| 160 |
-
"grad_norm": 0.035239290446043015,
|
| 161 |
-
"learning_rate": 4.961712109503609e-05,
|
| 162 |
-
"loss": 0.0583,
|
| 163 |
-
"step": 7500
|
| 164 |
-
},
|
| 165 |
-
{
|
| 166 |
-
"epoch": 1.2453204654239793,
|
| 167 |
-
"grad_norm": 0.03707383945584297,
|
| 168 |
-
"learning_rate": 4.918053517048949e-05,
|
| 169 |
-
"loss": 0.056,
|
| 170 |
-
"step": 8000
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 1.2499902712378876,
|
| 174 |
-
"eval_avg": 0.7079419812877328,
|
| 175 |
-
"eval_cer": 0.6543333833811898,
|
| 176 |
-
"eval_der": 0.793713077370868,
|
| 177 |
-
"eval_loss": 0.043703265488147736,
|
| 178 |
-
"eval_runtime": 307.3798,
|
| 179 |
-
"eval_samples_per_second": 441.548,
|
| 180 |
-
"eval_steps_per_second": 1.728,
|
| 181 |
-
"eval_wer": 0.6757794831111406,
|
| 182 |
-
"step": 8030
|
| 183 |
-
},
|
| 184 |
-
{
|
| 185 |
-
"epoch": 1.32315056232245,
|
| 186 |
-
"grad_norm": 0.035194575786590576,
|
| 187 |
-
"learning_rate": 4.8583398752382485e-05,
|
| 188 |
-
"loss": 0.0539,
|
| 189 |
-
"step": 8500
|
| 190 |
-
},
|
| 191 |
-
{
|
| 192 |
-
"epoch": 1.4009806592209206,
|
| 193 |
-
"grad_norm": 0.03347332403063774,
|
| 194 |
-
"learning_rate": 4.782967662255196e-05,
|
| 195 |
-
"loss": 0.0523,
|
| 196 |
-
"step": 9000
|
| 197 |
-
},
|
| 198 |
-
{
|
| 199 |
-
"epoch": 1.4788107561193913,
|
| 200 |
-
"grad_norm": 0.06645191460847855,
|
| 201 |
-
"learning_rate": 4.692437323847159e-05,
|
| 202 |
-
"loss": 0.0507,
|
| 203 |
-
"step": 9500
|
| 204 |
-
},
|
| 205 |
-
{
|
| 206 |
-
"epoch": 1.4999805424757753,
|
| 207 |
-
"eval_avg": 0.7073388677263619,
|
| 208 |
-
"eval_cer": 0.6541002942380697,
|
| 209 |
-
"eval_der": 0.7938397323961762,
|
| 210 |
-
"eval_loss": 0.03928952291607857,
|
| 211 |
-
"eval_runtime": 307.3123,
|
| 212 |
-
"eval_samples_per_second": 441.645,
|
| 213 |
-
"eval_steps_per_second": 1.728,
|
| 214 |
-
"eval_wer": 0.6740765765448399,
|
| 215 |
-
"step": 9636
|
| 216 |
-
},
|
| 217 |
-
{
|
| 218 |
-
"epoch": 1.556640853017862,
|
| 219 |
-
"grad_norm": 0.031485334038734436,
|
| 220 |
-
"learning_rate": 4.587349950536374e-05,
|
| 221 |
-
"loss": 0.0492,
|
| 222 |
-
"step": 10000
|
| 223 |
-
},
|
| 224 |
-
{
|
| 225 |
-
"epoch": 1.6344709499163326,
|
| 226 |
-
"grad_norm": 0.031592607498168945,
|
| 227 |
-
"learning_rate": 4.46840328658421e-05,
|
| 228 |
-
"loss": 0.0481,
|
| 229 |
-
"step": 10500
|
| 230 |
-
},
|
| 231 |
-
{
|
| 232 |
-
"epoch": 1.7123010468148032,
|
| 233 |
-
"grad_norm": 0.031952131539583206,
|
| 234 |
-
"learning_rate": 4.336387097207617e-05,
|
| 235 |
-
"loss": 0.0468,
|
| 236 |
-
"step": 11000
|
| 237 |
-
},
|
| 238 |
-
{
|
| 239 |
-
"epoch": 1.749970813713663,
|
| 240 |
-
"eval_avg": 0.7068964281422255,
|
| 241 |
-
"eval_cer": 0.6539495257646198,
|
| 242 |
-
"eval_der": 0.7937636951733035,
|
| 243 |
-
"eval_loss": 0.036437951028347015,
|
| 244 |
-
"eval_runtime": 308.1694,
|
| 245 |
-
"eval_samples_per_second": 440.417,
|
| 246 |
-
"eval_steps_per_second": 1.723,
|
| 247 |
-
"eval_wer": 0.6729760634887532,
|
| 248 |
-
"step": 11242
|
| 249 |
-
},
|
| 250 |
-
{
|
| 251 |
-
"epoch": 1.7901311437132739,
|
| 252 |
-
"grad_norm": 0.030866818502545357,
|
| 253 |
-
"learning_rate": 4.9978063925651226e-05,
|
| 254 |
-
"loss": 0.0457,
|
| 255 |
-
"step": 11500
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 1.8679612406117445,
|
| 259 |
-
"grad_norm": 0.029339410364627838,
|
| 260 |
-
"learning_rate": 4.980989359026424e-05,
|
| 261 |
-
"loss": 0.0451,
|
| 262 |
-
"step": 12000
|
| 263 |
-
},
|
| 264 |
-
{
|
| 265 |
-
"epoch": 1.9457913375102152,
|
| 266 |
-
"grad_norm": 0.02953779138624668,
|
| 267 |
-
"learning_rate": 4.94769940363958e-05,
|
| 268 |
-
"loss": 0.0439,
|
| 269 |
-
"step": 12500
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 1.9999610849515508,
|
| 273 |
-
"eval_avg": 0.706664474285978,
|
| 274 |
-
"eval_cer": 0.6538952007882788,
|
| 275 |
-
"eval_der": 0.7938883608526655,
|
| 276 |
-
"eval_loss": 0.0344935841858387,
|
| 277 |
-
"eval_runtime": 304.0677,
|
| 278 |
-
"eval_samples_per_second": 446.358,
|
| 279 |
-
"eval_steps_per_second": 1.746,
|
| 280 |
-
"eval_wer": 0.6722098612169899,
|
| 281 |
-
"step": 12848
|
| 282 |
-
},
|
| 283 |
-
{
|
| 284 |
-
"epoch": 2.0236603494571352,
|
| 285 |
-
"grad_norm": 0.028502434492111206,
|
| 286 |
-
"learning_rate": 4.898157560336646e-05,
|
| 287 |
-
"loss": 0.043,
|
| 288 |
-
"step": 13000
|
| 289 |
-
},
|
| 290 |
-
{
|
| 291 |
-
"epoch": 2.101490446355606,
|
| 292 |
-
"grad_norm": 0.030778545886278152,
|
| 293 |
-
"learning_rate": 4.832692770033863e-05,
|
| 294 |
-
"loss": 0.0417,
|
| 295 |
-
"step": 13500
|
| 296 |
-
},
|
| 297 |
-
{
|
| 298 |
-
"epoch": 2.1793205432540765,
|
| 299 |
-
"grad_norm": 0.0269626472145319,
|
| 300 |
-
"learning_rate": 4.7517396965763394e-05,
|
| 301 |
-
"loss": 0.041,
|
| 302 |
-
"step": 14000
|
| 303 |
-
},
|
| 304 |
-
{
|
| 305 |
-
"epoch": 2.2499902712378876,
|
| 306 |
-
"eval_avg": 0.7064455694431908,
|
| 307 |
-
"eval_cer": 0.6538135050224774,
|
| 308 |
-
"eval_der": 0.7939745658437141,
|
| 309 |
-
"eval_loss": 0.032875534147024155,
|
| 310 |
-
"eval_runtime": 304.6489,
|
| 311 |
-
"eval_samples_per_second": 445.506,
|
| 312 |
-
"eval_steps_per_second": 1.743,
|
| 313 |
-
"eval_wer": 0.6715486374633808,
|
| 314 |
-
"step": 14454
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 2.257150640152547,
|
| 318 |
-
"grad_norm": 0.03818966820836067,
|
| 319 |
-
"learning_rate": 4.6558358407185946e-05,
|
| 320 |
-
"loss": 0.0402,
|
| 321 |
-
"step": 14500
|
| 322 |
-
},
|
| 323 |
-
{
|
| 324 |
-
"epoch": 2.3349807370510174,
|
| 325 |
-
"grad_norm": 0.029628828167915344,
|
| 326 |
-
"learning_rate": 4.5456179713031586e-05,
|
| 327 |
-
"loss": 0.0395,
|
| 328 |
-
"step": 15000
|
| 329 |
-
},
|
| 330 |
-
{
|
| 331 |
-
"epoch": 2.4128108339494885,
|
| 332 |
-
"grad_norm": 0.02792350761592388,
|
| 333 |
-
"learning_rate": 4.4218178973329804e-05,
|
| 334 |
-
"loss": 0.0392,
|
| 335 |
-
"step": 15500
|
| 336 |
-
},
|
| 337 |
-
{
|
| 338 |
-
"epoch": 2.4906409308479587,
|
| 339 |
-
"grad_norm": 0.03364017978310585,
|
| 340 |
-
"learning_rate": 4.2852576090096216e-05,
|
| 341 |
-
"loss": 0.0384,
|
| 342 |
-
"step": 16000
|
| 343 |
-
},
|
| 344 |
-
{
|
| 345 |
-
"epoch": 2.4999805424757753,
|
| 346 |
-
"eval_avg": 0.7061941356307186,
|
| 347 |
-
"eval_cer": 0.6537081045699137,
|
| 348 |
-
"eval_der": 0.7939727975362082,
|
| 349 |
-
"eval_loss": 0.031167298555374146,
|
| 350 |
-
"eval_runtime": 303.0246,
|
| 351 |
-
"eval_samples_per_second": 447.894,
|
| 352 |
-
"eval_steps_per_second": 1.752,
|
| 353 |
-
"eval_wer": 0.670901504786034,
|
| 354 |
-
"step": 16060
|
| 355 |
-
},
|
| 356 |
-
{
|
| 357 |
-
"epoch": 2.5684710277464298,
|
| 358 |
-
"grad_norm": 0.032605357468128204,
|
| 359 |
-
"learning_rate": 4.136843819999117e-05,
|
| 360 |
-
"loss": 0.038,
|
| 361 |
-
"step": 16500
|
| 362 |
-
},
|
| 363 |
-
{
|
| 364 |
-
"epoch": 2.6463011246449,
|
| 365 |
-
"grad_norm": 0.027949590235948563,
|
| 366 |
-
"learning_rate": 3.977561947162954e-05,
|
| 367 |
-
"loss": 0.0376,
|
| 368 |
-
"step": 17000
|
| 369 |
-
},
|
| 370 |
-
{
|
| 371 |
-
"epoch": 2.724131221543371,
|
| 372 |
-
"grad_norm": 0.026584528386592865,
|
| 373 |
-
"learning_rate": 3.80846956772673e-05,
|
| 374 |
-
"loss": 0.0372,
|
| 375 |
-
"step": 17500
|
| 376 |
-
},
|
| 377 |
-
{
|
| 378 |
-
"epoch": 2.749970813713663,
|
| 379 |
-
"eval_avg": 0.706001258948505,
|
| 380 |
-
"eval_cer": 0.6536609451579365,
|
| 381 |
-
"eval_der": 0.7939834810607371,
|
| 382 |
-
"eval_loss": 0.030004331842064857,
|
| 383 |
-
"eval_runtime": 304.4012,
|
| 384 |
-
"eval_samples_per_second": 445.869,
|
| 385 |
-
"eval_steps_per_second": 1.744,
|
| 386 |
-
"eval_wer": 0.6703593506268415,
|
| 387 |
-
"step": 17666
|
| 388 |
-
}
|
| 389 |
-
],
|
| 390 |
-
"logging_steps": 500,
|
| 391 |
-
"max_steps": 19272,
|
| 392 |
-
"num_input_tokens_seen": 0,
|
| 393 |
-
"num_train_epochs": 3,
|
| 394 |
-
"save_steps": 1606,
|
| 395 |
-
"stateful_callbacks": {
|
| 396 |
-
"TrainerControl": {
|
| 397 |
-
"args": {
|
| 398 |
-
"should_epoch_stop": false,
|
| 399 |
-
"should_evaluate": false,
|
| 400 |
-
"should_log": false,
|
| 401 |
-
"should_save": true,
|
| 402 |
-
"should_training_stop": false
|
| 403 |
-
},
|
| 404 |
-
"attributes": {}
|
| 405 |
-
}
|
| 406 |
-
},
|
| 407 |
-
"total_flos": 1.3788271574227354e+18,
|
| 408 |
-
"train_batch_size": 256,
|
| 409 |
-
"trial_name": null,
|
| 410 |
-
"trial_params": null
|
| 411 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-17666/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:17c2aac82a2d734eb14ae276b8d6dd7dc2382b632edb33fe02e78d4676bca897
|
| 3 |
-
size 5841
|
|
|
|
|
|
|
|
|
|
|
|