Upload folder using huggingface_hub
Browse files- config.json +27 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +44 -0
- trainer_state.json +317 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 512,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 2048,
|
| 15 |
+
"layer_norm_eps": 1e-12,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"model_type": "bert",
|
| 18 |
+
"num_attention_heads": 8,
|
| 19 |
+
"num_hidden_layers": 6,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"problem_type": "single_label_classification",
|
| 23 |
+
"transformers_version": "4.57.1",
|
| 24 |
+
"type_vocab_size": 2,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 50000
|
| 27 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf6bac3ed8ab13a04a58e3c3771bf8618783ca89cd3fa3a0b334a2652e4525ec
|
| 3 |
+
size 180180928
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d52e77d86d8a3374a90a8639ba3e028c2aa0f5af893f663cdbea531b8a2eca5c
|
| 3 |
+
size 360427403
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2d8f17dbce2c1ba7b05953933032e3f312f06107888bdafc970bda4de84ee35
|
| 3 |
+
size 14709
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5da3e3f1943486073868b2c53a3c36ae7ff342ba9c42bdf7baaa7e2bf91bba4
|
| 3 |
+
size 1383
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6577149420304ede87aa59bf995d3982b1e1dce8c799a97d829347f2ac691371
|
| 3 |
+
size 1465
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<pad>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 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 |
+
},
|
| 36 |
+
"bos_token": "<s>",
|
| 37 |
+
"clean_up_tokenization_spaces": true,
|
| 38 |
+
"eos_token": "</s>",
|
| 39 |
+
"extra_special_tokens": {},
|
| 40 |
+
"model_max_length": 512,
|
| 41 |
+
"pad_token": "<pad>",
|
| 42 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 43 |
+
"unk_token": "<unk>"
|
| 44 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,317 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2049,
|
| 3 |
+
"best_metric": 0.6427525622254758,
|
| 4 |
+
"best_model_checkpoint": "./saved_models/cbert/checkpoint-2049",
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3415,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.14641288433382138,
|
| 14 |
+
"grad_norm": 3.022106647491455,
|
| 15 |
+
"learning_rate": 1.942020497803807e-05,
|
| 16 |
+
"loss": 0.6936,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.29282576866764276,
|
| 21 |
+
"grad_norm": 1.8588309288024902,
|
| 22 |
+
"learning_rate": 1.8834553440702785e-05,
|
| 23 |
+
"loss": 0.6835,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.43923865300146414,
|
| 28 |
+
"grad_norm": 3.637296438217163,
|
| 29 |
+
"learning_rate": 1.8248901903367496e-05,
|
| 30 |
+
"loss": 0.6754,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.5856515373352855,
|
| 35 |
+
"grad_norm": 1.5142912864685059,
|
| 36 |
+
"learning_rate": 1.766325036603221e-05,
|
| 37 |
+
"loss": 0.6739,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.7320644216691069,
|
| 42 |
+
"grad_norm": 4.135972023010254,
|
| 43 |
+
"learning_rate": 1.7077598828696925e-05,
|
| 44 |
+
"loss": 0.6699,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.8784773060029283,
|
| 49 |
+
"grad_norm": 2.758687734603882,
|
| 50 |
+
"learning_rate": 1.649194729136164e-05,
|
| 51 |
+
"loss": 0.6775,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.0,
|
| 56 |
+
"eval_accuracy": 0.5995607613469985,
|
| 57 |
+
"eval_loss": 0.6492753028869629,
|
| 58 |
+
"eval_runtime": 1.5709,
|
| 59 |
+
"eval_samples_per_second": 1739.163,
|
| 60 |
+
"eval_steps_per_second": 54.747,
|
| 61 |
+
"step": 683
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.0248901903367496,
|
| 65 |
+
"grad_norm": 4.188994407653809,
|
| 66 |
+
"learning_rate": 1.5906295754026355e-05,
|
| 67 |
+
"loss": 0.6622,
|
| 68 |
+
"step": 700
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.171303074670571,
|
| 72 |
+
"grad_norm": 2.755507230758667,
|
| 73 |
+
"learning_rate": 1.532064421669107e-05,
|
| 74 |
+
"loss": 0.6485,
|
| 75 |
+
"step": 800
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.3177159590043923,
|
| 79 |
+
"grad_norm": 4.434422016143799,
|
| 80 |
+
"learning_rate": 1.4734992679355784e-05,
|
| 81 |
+
"loss": 0.6422,
|
| 82 |
+
"step": 900
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.4641288433382138,
|
| 86 |
+
"grad_norm": 3.1107141971588135,
|
| 87 |
+
"learning_rate": 1.4149341142020499e-05,
|
| 88 |
+
"loss": 0.6436,
|
| 89 |
+
"step": 1000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.610541727672035,
|
| 93 |
+
"grad_norm": 4.113313674926758,
|
| 94 |
+
"learning_rate": 1.3563689604685213e-05,
|
| 95 |
+
"loss": 0.6308,
|
| 96 |
+
"step": 1100
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.7569546120058566,
|
| 100 |
+
"grad_norm": 5.160773754119873,
|
| 101 |
+
"learning_rate": 1.2978038067349928e-05,
|
| 102 |
+
"loss": 0.6223,
|
| 103 |
+
"step": 1200
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.903367496339678,
|
| 107 |
+
"grad_norm": 2.9103806018829346,
|
| 108 |
+
"learning_rate": 1.2392386530014641e-05,
|
| 109 |
+
"loss": 0.6312,
|
| 110 |
+
"step": 1300
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.0,
|
| 114 |
+
"eval_accuracy": 0.6317715959004392,
|
| 115 |
+
"eval_loss": 0.6276857256889343,
|
| 116 |
+
"eval_runtime": 1.5723,
|
| 117 |
+
"eval_samples_per_second": 1737.632,
|
| 118 |
+
"eval_steps_per_second": 54.699,
|
| 119 |
+
"step": 1366
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 2.049780380673499,
|
| 123 |
+
"grad_norm": 4.584695339202881,
|
| 124 |
+
"learning_rate": 1.1806734992679356e-05,
|
| 125 |
+
"loss": 0.6105,
|
| 126 |
+
"step": 1400
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 2.1961932650073206,
|
| 130 |
+
"grad_norm": 11.84752368927002,
|
| 131 |
+
"learning_rate": 1.122108345534407e-05,
|
| 132 |
+
"loss": 0.5812,
|
| 133 |
+
"step": 1500
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 2.342606149341142,
|
| 137 |
+
"grad_norm": 4.095500946044922,
|
| 138 |
+
"learning_rate": 1.0635431918008785e-05,
|
| 139 |
+
"loss": 0.589,
|
| 140 |
+
"step": 1600
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.4890190336749636,
|
| 144 |
+
"grad_norm": 4.87593936920166,
|
| 145 |
+
"learning_rate": 1.00497803806735e-05,
|
| 146 |
+
"loss": 0.5835,
|
| 147 |
+
"step": 1700
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 2.6354319180087846,
|
| 151 |
+
"grad_norm": 4.864409446716309,
|
| 152 |
+
"learning_rate": 9.464128843338215e-06,
|
| 153 |
+
"loss": 0.5877,
|
| 154 |
+
"step": 1800
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.781844802342606,
|
| 158 |
+
"grad_norm": 5.729854583740234,
|
| 159 |
+
"learning_rate": 8.87847730600293e-06,
|
| 160 |
+
"loss": 0.5911,
|
| 161 |
+
"step": 1900
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.9282576866764276,
|
| 165 |
+
"grad_norm": 9.67723560333252,
|
| 166 |
+
"learning_rate": 8.292825768667644e-06,
|
| 167 |
+
"loss": 0.5689,
|
| 168 |
+
"step": 2000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 3.0,
|
| 172 |
+
"eval_accuracy": 0.6427525622254758,
|
| 173 |
+
"eval_loss": 0.6189645528793335,
|
| 174 |
+
"eval_runtime": 1.5647,
|
| 175 |
+
"eval_samples_per_second": 1746.065,
|
| 176 |
+
"eval_steps_per_second": 54.964,
|
| 177 |
+
"step": 2049
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.074670571010249,
|
| 181 |
+
"grad_norm": 5.034663677215576,
|
| 182 |
+
"learning_rate": 7.707174231332359e-06,
|
| 183 |
+
"loss": 0.5712,
|
| 184 |
+
"step": 2100
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 3.22108345534407,
|
| 188 |
+
"grad_norm": 4.707498550415039,
|
| 189 |
+
"learning_rate": 7.1215226939970725e-06,
|
| 190 |
+
"loss": 0.5292,
|
| 191 |
+
"step": 2200
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 3.3674963396778916,
|
| 195 |
+
"grad_norm": 4.101770401000977,
|
| 196 |
+
"learning_rate": 6.535871156661787e-06,
|
| 197 |
+
"loss": 0.5367,
|
| 198 |
+
"step": 2300
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 3.513909224011713,
|
| 202 |
+
"grad_norm": 6.7061614990234375,
|
| 203 |
+
"learning_rate": 5.950219619326502e-06,
|
| 204 |
+
"loss": 0.542,
|
| 205 |
+
"step": 2400
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 3.660322108345534,
|
| 209 |
+
"grad_norm": 10.22519588470459,
|
| 210 |
+
"learning_rate": 5.364568081991216e-06,
|
| 211 |
+
"loss": 0.5486,
|
| 212 |
+
"step": 2500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.8067349926793557,
|
| 216 |
+
"grad_norm": 4.292933940887451,
|
| 217 |
+
"learning_rate": 4.77891654465593e-06,
|
| 218 |
+
"loss": 0.5331,
|
| 219 |
+
"step": 2600
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 3.953147877013177,
|
| 223 |
+
"grad_norm": 4.438432216644287,
|
| 224 |
+
"learning_rate": 4.193265007320644e-06,
|
| 225 |
+
"loss": 0.5361,
|
| 226 |
+
"step": 2700
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 4.0,
|
| 230 |
+
"eval_accuracy": 0.6295754026354319,
|
| 231 |
+
"eval_loss": 0.633277177810669,
|
| 232 |
+
"eval_runtime": 1.5589,
|
| 233 |
+
"eval_samples_per_second": 1752.491,
|
| 234 |
+
"eval_steps_per_second": 55.166,
|
| 235 |
+
"step": 2732
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 4.099560761346998,
|
| 239 |
+
"grad_norm": 5.632227420806885,
|
| 240 |
+
"learning_rate": 3.607613469985359e-06,
|
| 241 |
+
"loss": 0.5327,
|
| 242 |
+
"step": 2800
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 4.24597364568082,
|
| 246 |
+
"grad_norm": 8.069804191589355,
|
| 247 |
+
"learning_rate": 3.0219619326500732e-06,
|
| 248 |
+
"loss": 0.5111,
|
| 249 |
+
"step": 2900
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 4.392386530014641,
|
| 253 |
+
"grad_norm": 7.2090840339660645,
|
| 254 |
+
"learning_rate": 2.436310395314788e-06,
|
| 255 |
+
"loss": 0.4965,
|
| 256 |
+
"step": 3000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 4.538799414348462,
|
| 260 |
+
"grad_norm": 10.964486122131348,
|
| 261 |
+
"learning_rate": 1.8506588579795024e-06,
|
| 262 |
+
"loss": 0.5082,
|
| 263 |
+
"step": 3100
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 4.685212298682284,
|
| 267 |
+
"grad_norm": 4.838050365447998,
|
| 268 |
+
"learning_rate": 1.2650073206442169e-06,
|
| 269 |
+
"loss": 0.497,
|
| 270 |
+
"step": 3200
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 4.831625183016105,
|
| 274 |
+
"grad_norm": 6.126997470855713,
|
| 275 |
+
"learning_rate": 6.793557833089313e-07,
|
| 276 |
+
"loss": 0.5137,
|
| 277 |
+
"step": 3300
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 4.978038067349927,
|
| 281 |
+
"grad_norm": 13.103296279907227,
|
| 282 |
+
"learning_rate": 9.370424597364569e-08,
|
| 283 |
+
"loss": 0.5202,
|
| 284 |
+
"step": 3400
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 5.0,
|
| 288 |
+
"eval_accuracy": 0.6372620790629575,
|
| 289 |
+
"eval_loss": 0.6495257019996643,
|
| 290 |
+
"eval_runtime": 1.5569,
|
| 291 |
+
"eval_samples_per_second": 1754.803,
|
| 292 |
+
"eval_steps_per_second": 55.239,
|
| 293 |
+
"step": 3415
|
| 294 |
+
}
|
| 295 |
+
],
|
| 296 |
+
"logging_steps": 100,
|
| 297 |
+
"max_steps": 3415,
|
| 298 |
+
"num_input_tokens_seen": 0,
|
| 299 |
+
"num_train_epochs": 5,
|
| 300 |
+
"save_steps": 500,
|
| 301 |
+
"stateful_callbacks": {
|
| 302 |
+
"TrainerControl": {
|
| 303 |
+
"args": {
|
| 304 |
+
"should_epoch_stop": false,
|
| 305 |
+
"should_evaluate": false,
|
| 306 |
+
"should_log": false,
|
| 307 |
+
"should_save": true,
|
| 308 |
+
"should_training_stop": true
|
| 309 |
+
},
|
| 310 |
+
"attributes": {}
|
| 311 |
+
}
|
| 312 |
+
},
|
| 313 |
+
"total_flos": 3218980489267200.0,
|
| 314 |
+
"train_batch_size": 16,
|
| 315 |
+
"trial_name": null,
|
| 316 |
+
"trial_params": null
|
| 317 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60296b0ac67aa42d8068a139559567ccac3ac42ca392159292ed93f2f8628b44
|
| 3 |
+
size 5777
|