Training in progress, step 300, checkpoint
Browse files- checkpoint-300/config.json +36 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/pytorch_model.bin +3 -0
- checkpoint-300/rng_state.pth +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/special_tokens_map.json +11 -0
- checkpoint-300/tokenizer.json +0 -0
- checkpoint-300/tokenizer_config.json +72 -0
- checkpoint-300/trainer_state.json +226 -0
- checkpoint-300/training_args.bin +3 -0
checkpoint-300/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "EleutherAI/polyglot-ko-1.3b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTNeoXForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": 0.1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout": 0.0,
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 8192,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-05,
|
| 22 |
+
"max_position_embeddings": 2048,
|
| 23 |
+
"model_type": "gpt_neox",
|
| 24 |
+
"num_attention_heads": 16,
|
| 25 |
+
"num_hidden_layers": 24,
|
| 26 |
+
"pad_token_id": 2,
|
| 27 |
+
"rope_scaling": null,
|
| 28 |
+
"rotary_emb_base": 10000,
|
| 29 |
+
"rotary_pct": 0.5,
|
| 30 |
+
"tie_word_embeddings": false,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.34.1",
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"use_parallel_residual": true,
|
| 35 |
+
"vocab_size": 30080
|
| 36 |
+
}
|
checkpoint-300/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba1c2998331a8d59c9e4fd0e95ca45b9e7307dbe5662c1fa52581a901dc63590
|
| 3 |
+
size 10161845830
|
checkpoint-300/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c94c5e1ded3e3eb3775e169b4b2921545c157a5fa927d7b4ba16f2ec3497954
|
| 3 |
+
size 5080945162
|
checkpoint-300/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1dbca245f4c6603645dbab7224b3a520ea557088259edf5fb8205675ece2a192
|
| 3 |
+
size 14308
|
checkpoint-300/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:153655dd49971685f6e46e64b8fe8ae819c331baf597a84fccbaf9b90e0354b0
|
| 3 |
+
size 1064
|
checkpoint-300/special_tokens_map.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<|sep|>",
|
| 5 |
+
"<|acc|>",
|
| 6 |
+
"<|tel|>",
|
| 7 |
+
"<|rrn|>"
|
| 8 |
+
],
|
| 9 |
+
"eos_token": "<|endoftext|>",
|
| 10 |
+
"pad_token": "<|endoftext|>"
|
| 11 |
+
}
|
checkpoint-300/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-300/tokenizer_config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<|unused0|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<|unused1|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<|endoftext|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<|sep|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"30000": {
|
| 36 |
+
"content": "<|acc|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"30001": {
|
| 44 |
+
"content": "<|tel|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"30002": {
|
| 52 |
+
"content": "<|rrn|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"additional_special_tokens": [
|
| 61 |
+
"<|endoftext|>",
|
| 62 |
+
"<|sep|>",
|
| 63 |
+
"<|acc|>",
|
| 64 |
+
"<|tel|>",
|
| 65 |
+
"<|rrn|>"
|
| 66 |
+
],
|
| 67 |
+
"clean_up_tokenization_spaces": true,
|
| 68 |
+
"eos_token": "<|endoftext|>",
|
| 69 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 70 |
+
"pad_token": "<|endoftext|>",
|
| 71 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 72 |
+
}
|
checkpoint-300/trainer_state.json
ADDED
|
@@ -0,0 +1,226 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.4877057508636456,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 300,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 8.994130006901536e-06,
|
| 14 |
+
"loss": 0.3053,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.03,
|
| 19 |
+
"learning_rate": 8.976535341747906e-06,
|
| 20 |
+
"loss": 0.1363,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.05,
|
| 25 |
+
"learning_rate": 8.947261907011569e-06,
|
| 26 |
+
"loss": 0.1087,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.07,
|
| 31 |
+
"learning_rate": 8.906386073741352e-06,
|
| 32 |
+
"loss": 0.106,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.08,
|
| 37 |
+
"learning_rate": 8.85401448231912e-06,
|
| 38 |
+
"loss": 0.0791,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.1,
|
| 43 |
+
"learning_rate": 8.790283764247187e-06,
|
| 44 |
+
"loss": 0.0702,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11,
|
| 49 |
+
"learning_rate": 8.715360185692326e-06,
|
| 50 |
+
"loss": 0.0773,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.13,
|
| 55 |
+
"learning_rate": 8.629439213716327e-06,
|
| 56 |
+
"loss": 0.0583,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.15,
|
| 61 |
+
"learning_rate": 8.532745006324751e-06,
|
| 62 |
+
"loss": 0.0637,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.16,
|
| 67 |
+
"learning_rate": 8.425529827664287e-06,
|
| 68 |
+
"loss": 0.0554,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.16,
|
| 73 |
+
"eval_accuracy": 0.5,
|
| 74 |
+
"eval_loss": 7.870811641330633e-11,
|
| 75 |
+
"eval_runtime": 51.3409,
|
| 76 |
+
"eval_samples_per_second": 85.195,
|
| 77 |
+
"eval_steps_per_second": 10.654,
|
| 78 |
+
"step": 100
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.18,
|
| 82 |
+
"learning_rate": 8.308073389894399e-06,
|
| 83 |
+
"loss": 0.0666,
|
| 84 |
+
"step": 110
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.2,
|
| 88 |
+
"learning_rate": 8.18068212345023e-06,
|
| 89 |
+
"loss": 0.0598,
|
| 90 |
+
"step": 120
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.21,
|
| 94 |
+
"learning_rate": 8.043688377600596e-06,
|
| 95 |
+
"loss": 0.0423,
|
| 96 |
+
"step": 130
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.23,
|
| 100 |
+
"learning_rate": 7.897449553386683e-06,
|
| 101 |
+
"loss": 0.0311,
|
| 102 |
+
"step": 140
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.24,
|
| 106 |
+
"learning_rate": 7.742347171203542e-06,
|
| 107 |
+
"loss": 0.0527,
|
| 108 |
+
"step": 150
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.26,
|
| 112 |
+
"learning_rate": 7.578785875456937e-06,
|
| 113 |
+
"loss": 0.0847,
|
| 114 |
+
"step": 160
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.28,
|
| 118 |
+
"learning_rate": 7.407192378892295e-06,
|
| 119 |
+
"loss": 0.0595,
|
| 120 |
+
"step": 170
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.29,
|
| 124 |
+
"learning_rate": 7.2280143493498716e-06,
|
| 125 |
+
"loss": 0.0327,
|
| 126 |
+
"step": 180
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.31,
|
| 130 |
+
"learning_rate": 7.041719241850471e-06,
|
| 131 |
+
"loss": 0.0877,
|
| 132 |
+
"step": 190
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.33,
|
| 136 |
+
"learning_rate": 6.848793079058672e-06,
|
| 137 |
+
"loss": 0.0356,
|
| 138 |
+
"step": 200
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.33,
|
| 142 |
+
"eval_accuracy": 0.5,
|
| 143 |
+
"eval_loss": 9.303278147854144e-08,
|
| 144 |
+
"eval_runtime": 53.2016,
|
| 145 |
+
"eval_samples_per_second": 82.216,
|
| 146 |
+
"eval_steps_per_second": 10.282,
|
| 147 |
+
"step": 200
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.34,
|
| 151 |
+
"learning_rate": 6.649739183305183e-06,
|
| 152 |
+
"loss": 0.0332,
|
| 153 |
+
"step": 210
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.36,
|
| 157 |
+
"learning_rate": 6.445076863476361e-06,
|
| 158 |
+
"loss": 0.0537,
|
| 159 |
+
"step": 220
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.37,
|
| 163 |
+
"learning_rate": 6.235340060196612e-06,
|
| 164 |
+
"loss": 0.0548,
|
| 165 |
+
"step": 230
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.39,
|
| 169 |
+
"learning_rate": 6.021075952838263e-06,
|
| 170 |
+
"loss": 0.0485,
|
| 171 |
+
"step": 240
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.41,
|
| 175 |
+
"learning_rate": 5.802843531993069e-06,
|
| 176 |
+
"loss": 0.041,
|
| 177 |
+
"step": 250
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.42,
|
| 181 |
+
"learning_rate": 5.581212141129573e-06,
|
| 182 |
+
"loss": 0.0266,
|
| 183 |
+
"step": 260
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.44,
|
| 187 |
+
"learning_rate": 5.3567599912410075e-06,
|
| 188 |
+
"loss": 0.0421,
|
| 189 |
+
"step": 270
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.46,
|
| 193 |
+
"learning_rate": 5.130072652358832e-06,
|
| 194 |
+
"loss": 0.0522,
|
| 195 |
+
"step": 280
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.47,
|
| 199 |
+
"learning_rate": 4.901741525867374e-06,
|
| 200 |
+
"loss": 0.0302,
|
| 201 |
+
"step": 290
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.49,
|
| 205 |
+
"learning_rate": 4.67236230160516e-06,
|
| 206 |
+
"loss": 0.0741,
|
| 207 |
+
"step": 300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.49,
|
| 211 |
+
"eval_accuracy": 0.0,
|
| 212 |
+
"eval_loss": 2.2148276457301108e-07,
|
| 213 |
+
"eval_runtime": 51.7845,
|
| 214 |
+
"eval_samples_per_second": 84.465,
|
| 215 |
+
"eval_steps_per_second": 10.563,
|
| 216 |
+
"step": 300
|
| 217 |
+
}
|
| 218 |
+
],
|
| 219 |
+
"logging_steps": 10,
|
| 220 |
+
"max_steps": 615,
|
| 221 |
+
"num_train_epochs": 1,
|
| 222 |
+
"save_steps": 100,
|
| 223 |
+
"total_flos": 0.0,
|
| 224 |
+
"trial_name": null,
|
| 225 |
+
"trial_params": null
|
| 226 |
+
}
|
checkpoint-300/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f83b04586007121ba3ee6bfcd4a06860c6098884f4f89ada67554e532440c28
|
| 3 |
+
size 4600
|