Upload 12 files
Browse files- config.json +28 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +19 -0
- tokenizer.json +0 -0
- tokenizer_config.json +23 -0
- trainer_state.json +296 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "camembert-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CamembertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 5,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 6,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "camembert",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"output_past": true,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.27.2",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 32005
|
| 28 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3b7326726853cda345d081ed3bbb567a16094d50f5aa17307584426bbb2979a
|
| 3 |
+
size 885360985
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40bc97814d5a6aaa9ed58b7cd056a617ba4c4186d4cbd101cd113d587ea6e782
|
| 3 |
+
size 442693931
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6230dd67d61eba8089f991137da14d61309fd375262d875935009755f659f48
|
| 3 |
+
size 15523
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d9ab43e8261535c82a8e42e45aea71abf334ebfc5f0a3232d48bbc4a4d350cf
|
| 3 |
+
size 559
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:173637140ceedff2e9288a61810f8f55f59f66e3ab40aaab3b1eaa946d880dac
|
| 3 |
+
size 623
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
|
| 3 |
+
size 810912
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<s>NOTUSED",
|
| 4 |
+
"</s>NOTUSED"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": "<s>",
|
| 7 |
+
"cls_token": "<s>",
|
| 8 |
+
"eos_token": "</s>",
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "<mask>",
|
| 11 |
+
"lstrip": true,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<pad>",
|
| 17 |
+
"sep_token": "</s>",
|
| 18 |
+
"unk_token": "<unk>"
|
| 19 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<s>NOTUSED",
|
| 4 |
+
"</s>NOTUSED"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": "<s>",
|
| 7 |
+
"cls_token": "<s>",
|
| 8 |
+
"eos_token": "</s>",
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"__type": "AddedToken",
|
| 11 |
+
"content": "<mask>",
|
| 12 |
+
"lstrip": true,
|
| 13 |
+
"normalized": true,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
"model_max_length": 512,
|
| 18 |
+
"pad_token": "<pad>",
|
| 19 |
+
"sep_token": "</s>",
|
| 20 |
+
"special_tokens_map_file": null,
|
| 21 |
+
"tokenizer_class": "CamembertTokenizer",
|
| 22 |
+
"unk_token": "<unk>"
|
| 23 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,296 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"global_step": 18160,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 1.9003303964757713e-05,
|
| 13 |
+
"loss": 1.3504,
|
| 14 |
+
"step": 908
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_loss": 0.9396927356719971,
|
| 19 |
+
"eval_runtime": 40.3444,
|
| 20 |
+
"eval_samples_per_second": 80.011,
|
| 21 |
+
"eval_steps_per_second": 2.503,
|
| 22 |
+
"step": 908
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 2.0,
|
| 26 |
+
"learning_rate": 1.800330396475771e-05,
|
| 27 |
+
"loss": 0.952,
|
| 28 |
+
"step": 1816
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"eval_loss": 0.7900779247283936,
|
| 33 |
+
"eval_runtime": 40.474,
|
| 34 |
+
"eval_samples_per_second": 79.755,
|
| 35 |
+
"eval_steps_per_second": 2.495,
|
| 36 |
+
"step": 1816
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 3.0,
|
| 40 |
+
"learning_rate": 1.700330396475771e-05,
|
| 41 |
+
"loss": 0.8225,
|
| 42 |
+
"step": 2724
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"eval_loss": 0.7042744755744934,
|
| 47 |
+
"eval_runtime": 40.4219,
|
| 48 |
+
"eval_samples_per_second": 79.858,
|
| 49 |
+
"eval_steps_per_second": 2.499,
|
| 50 |
+
"step": 2724
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"learning_rate": 1.600330396475771e-05,
|
| 55 |
+
"loss": 0.7475,
|
| 56 |
+
"step": 3632
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.0,
|
| 60 |
+
"eval_loss": 0.6635274291038513,
|
| 61 |
+
"eval_runtime": 40.4218,
|
| 62 |
+
"eval_samples_per_second": 79.858,
|
| 63 |
+
"eval_steps_per_second": 2.499,
|
| 64 |
+
"step": 3632
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 5.0,
|
| 68 |
+
"learning_rate": 1.5003303964757709e-05,
|
| 69 |
+
"loss": 0.6945,
|
| 70 |
+
"step": 4540
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 5.0,
|
| 74 |
+
"eval_loss": 0.6002705693244934,
|
| 75 |
+
"eval_runtime": 40.5407,
|
| 76 |
+
"eval_samples_per_second": 79.624,
|
| 77 |
+
"eval_steps_per_second": 2.491,
|
| 78 |
+
"step": 4540
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 6.0,
|
| 82 |
+
"learning_rate": 1.4003303964757711e-05,
|
| 83 |
+
"loss": 0.6558,
|
| 84 |
+
"step": 5448
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 6.0,
|
| 88 |
+
"eval_loss": 0.5814478993415833,
|
| 89 |
+
"eval_runtime": 40.4802,
|
| 90 |
+
"eval_samples_per_second": 79.743,
|
| 91 |
+
"eval_steps_per_second": 2.495,
|
| 92 |
+
"step": 5448
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.0,
|
| 96 |
+
"learning_rate": 1.3003303964757709e-05,
|
| 97 |
+
"loss": 0.6179,
|
| 98 |
+
"step": 6356
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 7.0,
|
| 102 |
+
"eval_loss": 0.530373215675354,
|
| 103 |
+
"eval_runtime": 40.4721,
|
| 104 |
+
"eval_samples_per_second": 79.759,
|
| 105 |
+
"eval_steps_per_second": 2.496,
|
| 106 |
+
"step": 6356
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 8.0,
|
| 110 |
+
"learning_rate": 1.2004405286343613e-05,
|
| 111 |
+
"loss": 0.5939,
|
| 112 |
+
"step": 7264
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 8.0,
|
| 116 |
+
"eval_loss": 0.5254124402999878,
|
| 117 |
+
"eval_runtime": 40.4437,
|
| 118 |
+
"eval_samples_per_second": 79.815,
|
| 119 |
+
"eval_steps_per_second": 2.497,
|
| 120 |
+
"step": 7264
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 9.0,
|
| 124 |
+
"learning_rate": 1.1004405286343614e-05,
|
| 125 |
+
"loss": 0.5724,
|
| 126 |
+
"step": 8172
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 9.0,
|
| 130 |
+
"eval_loss": 0.5123583078384399,
|
| 131 |
+
"eval_runtime": 40.4461,
|
| 132 |
+
"eval_samples_per_second": 79.81,
|
| 133 |
+
"eval_steps_per_second": 2.497,
|
| 134 |
+
"step": 8172
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 10.0,
|
| 138 |
+
"learning_rate": 1.0005506607929516e-05,
|
| 139 |
+
"loss": 0.5518,
|
| 140 |
+
"step": 9080
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 10.0,
|
| 144 |
+
"eval_loss": 0.5051878094673157,
|
| 145 |
+
"eval_runtime": 40.5153,
|
| 146 |
+
"eval_samples_per_second": 79.674,
|
| 147 |
+
"eval_steps_per_second": 2.493,
|
| 148 |
+
"step": 9080
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 11.0,
|
| 152 |
+
"learning_rate": 9.005506607929516e-06,
|
| 153 |
+
"loss": 0.5374,
|
| 154 |
+
"step": 9988
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 11.0,
|
| 158 |
+
"eval_loss": 0.48619189858436584,
|
| 159 |
+
"eval_runtime": 40.4854,
|
| 160 |
+
"eval_samples_per_second": 79.732,
|
| 161 |
+
"eval_steps_per_second": 2.495,
|
| 162 |
+
"step": 9988
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 12.0,
|
| 166 |
+
"learning_rate": 8.006607929515418e-06,
|
| 167 |
+
"loss": 0.5257,
|
| 168 |
+
"step": 10896
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 12.0,
|
| 172 |
+
"eval_loss": 0.4822216033935547,
|
| 173 |
+
"eval_runtime": 40.4555,
|
| 174 |
+
"eval_samples_per_second": 79.791,
|
| 175 |
+
"eval_steps_per_second": 2.497,
|
| 176 |
+
"step": 10896
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 13.0,
|
| 180 |
+
"learning_rate": 7.006607929515419e-06,
|
| 181 |
+
"loss": 0.5109,
|
| 182 |
+
"step": 11804
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 13.0,
|
| 186 |
+
"eval_loss": 0.4707971215248108,
|
| 187 |
+
"eval_runtime": 40.4351,
|
| 188 |
+
"eval_samples_per_second": 79.832,
|
| 189 |
+
"eval_steps_per_second": 2.498,
|
| 190 |
+
"step": 11804
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 14.0,
|
| 194 |
+
"learning_rate": 6.006607929515419e-06,
|
| 195 |
+
"loss": 0.4991,
|
| 196 |
+
"step": 12712
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 14.0,
|
| 200 |
+
"eval_loss": 0.4686879813671112,
|
| 201 |
+
"eval_runtime": 40.4561,
|
| 202 |
+
"eval_samples_per_second": 79.79,
|
| 203 |
+
"eval_steps_per_second": 2.497,
|
| 204 |
+
"step": 12712
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 15.0,
|
| 208 |
+
"learning_rate": 5.0066079295154195e-06,
|
| 209 |
+
"loss": 0.4966,
|
| 210 |
+
"step": 13620
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 15.0,
|
| 214 |
+
"eval_loss": 0.4615265130996704,
|
| 215 |
+
"eval_runtime": 40.492,
|
| 216 |
+
"eval_samples_per_second": 79.719,
|
| 217 |
+
"eval_steps_per_second": 2.494,
|
| 218 |
+
"step": 13620
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 16.0,
|
| 222 |
+
"learning_rate": 4.0077092511013225e-06,
|
| 223 |
+
"loss": 0.4877,
|
| 224 |
+
"step": 14528
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 16.0,
|
| 228 |
+
"eval_loss": 0.45428407192230225,
|
| 229 |
+
"eval_runtime": 40.5187,
|
| 230 |
+
"eval_samples_per_second": 79.667,
|
| 231 |
+
"eval_steps_per_second": 2.493,
|
| 232 |
+
"step": 14528
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 17.0,
|
| 236 |
+
"learning_rate": 3.007709251101322e-06,
|
| 237 |
+
"loss": 0.4837,
|
| 238 |
+
"step": 15436
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 17.0,
|
| 242 |
+
"eval_loss": 0.4501075744628906,
|
| 243 |
+
"eval_runtime": 40.541,
|
| 244 |
+
"eval_samples_per_second": 79.623,
|
| 245 |
+
"eval_steps_per_second": 2.491,
|
| 246 |
+
"step": 15436
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 18.0,
|
| 250 |
+
"learning_rate": 2.0077092511013217e-06,
|
| 251 |
+
"loss": 0.4788,
|
| 252 |
+
"step": 16344
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 18.0,
|
| 256 |
+
"eval_loss": 0.44279614090919495,
|
| 257 |
+
"eval_runtime": 40.6464,
|
| 258 |
+
"eval_samples_per_second": 79.417,
|
| 259 |
+
"eval_steps_per_second": 2.485,
|
| 260 |
+
"step": 16344
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 19.0,
|
| 264 |
+
"learning_rate": 1.0088105726872247e-06,
|
| 265 |
+
"loss": 0.4746,
|
| 266 |
+
"step": 17252
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 19.0,
|
| 270 |
+
"eval_loss": 0.4437817931175232,
|
| 271 |
+
"eval_runtime": 40.5435,
|
| 272 |
+
"eval_samples_per_second": 79.618,
|
| 273 |
+
"eval_steps_per_second": 2.491,
|
| 274 |
+
"step": 17252
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 20.0,
|
| 278 |
+
"learning_rate": 8.81057268722467e-09,
|
| 279 |
+
"loss": 0.4758,
|
| 280 |
+
"step": 18160
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 20.0,
|
| 284 |
+
"eval_loss": 0.44726473093032837,
|
| 285 |
+
"eval_runtime": 40.5882,
|
| 286 |
+
"eval_samples_per_second": 79.531,
|
| 287 |
+
"eval_steps_per_second": 2.488,
|
| 288 |
+
"step": 18160
|
| 289 |
+
}
|
| 290 |
+
],
|
| 291 |
+
"max_steps": 18160,
|
| 292 |
+
"num_train_epochs": 20,
|
| 293 |
+
"total_flos": 3.822589659829248e+16,
|
| 294 |
+
"trial_name": null,
|
| 295 |
+
"trial_params": null
|
| 296 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec09ee8c7897e38f915035ec62847e8034816bd6c72b043b8f94454a7e4124b0
|
| 3 |
+
size 3631
|