Upload 8 files
Browse files- model.safetensors +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- trainer_state.json +330 -0
- training_args.bin +3 -0
- vocab.json +0 -0
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3d11797f87aec3971efcdc317b15502c3fea335d7312da3feef87a2c298cbc5
|
| 3 |
+
size 1421495416
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3110,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.3215434083601286,
|
| 13 |
+
"grad_norm": 2206121.5,
|
| 14 |
+
"learning_rate": 5.807073954983923e-06,
|
| 15 |
+
"loss": 0.7552,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.6430868167202572,
|
| 20 |
+
"grad_norm": 2082399.375,
|
| 21 |
+
"learning_rate": 5.6141479099678455e-06,
|
| 22 |
+
"loss": 0.6123,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.9646302250803859,
|
| 27 |
+
"grad_norm": 2188612.25,
|
| 28 |
+
"learning_rate": 5.421221864951768e-06,
|
| 29 |
+
"loss": 0.5863,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.0,
|
| 34 |
+
"eval_loss": 0.8456913828849792,
|
| 35 |
+
"eval_runtime": 119.4823,
|
| 36 |
+
"eval_samples_per_second": 25.811,
|
| 37 |
+
"eval_steps_per_second": 3.231,
|
| 38 |
+
"step": 311
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.2861736334405145,
|
| 42 |
+
"grad_norm": 2229254.75,
|
| 43 |
+
"learning_rate": 5.228295819935691e-06,
|
| 44 |
+
"loss": 0.5724,
|
| 45 |
+
"step": 400
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.607717041800643,
|
| 49 |
+
"grad_norm": 1792601.625,
|
| 50 |
+
"learning_rate": 5.035369774919614e-06,
|
| 51 |
+
"loss": 0.5073,
|
| 52 |
+
"step": 500
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.9292604501607717,
|
| 56 |
+
"grad_norm": 1635809.75,
|
| 57 |
+
"learning_rate": 4.842443729903537e-06,
|
| 58 |
+
"loss": 0.546,
|
| 59 |
+
"step": 600
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.0,
|
| 63 |
+
"eval_loss": 0.840407133102417,
|
| 64 |
+
"eval_runtime": 119.5409,
|
| 65 |
+
"eval_samples_per_second": 25.799,
|
| 66 |
+
"eval_steps_per_second": 3.229,
|
| 67 |
+
"step": 622
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 2.2508038585209005,
|
| 71 |
+
"grad_norm": 2690947.75,
|
| 72 |
+
"learning_rate": 4.6495176848874605e-06,
|
| 73 |
+
"loss": 0.4998,
|
| 74 |
+
"step": 700
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.572347266881029,
|
| 78 |
+
"grad_norm": 2749350.25,
|
| 79 |
+
"learning_rate": 4.456591639871383e-06,
|
| 80 |
+
"loss": 0.4927,
|
| 81 |
+
"step": 800
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.8938906752411575,
|
| 85 |
+
"grad_norm": 3980070.25,
|
| 86 |
+
"learning_rate": 4.263665594855306e-06,
|
| 87 |
+
"loss": 0.486,
|
| 88 |
+
"step": 900
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 3.0,
|
| 92 |
+
"eval_loss": 0.9221391081809998,
|
| 93 |
+
"eval_runtime": 119.2209,
|
| 94 |
+
"eval_samples_per_second": 25.868,
|
| 95 |
+
"eval_steps_per_second": 3.238,
|
| 96 |
+
"step": 933
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 3.215434083601286,
|
| 100 |
+
"grad_norm": 2559816.5,
|
| 101 |
+
"learning_rate": 4.0707395498392284e-06,
|
| 102 |
+
"loss": 0.4714,
|
| 103 |
+
"step": 1000
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 3.536977491961415,
|
| 107 |
+
"grad_norm": 1433354.625,
|
| 108 |
+
"learning_rate": 3.877813504823151e-06,
|
| 109 |
+
"loss": 0.4734,
|
| 110 |
+
"step": 1100
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.8585209003215435,
|
| 114 |
+
"grad_norm": 2509238.5,
|
| 115 |
+
"learning_rate": 3.6848874598070737e-06,
|
| 116 |
+
"loss": 0.4622,
|
| 117 |
+
"step": 1200
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.0,
|
| 121 |
+
"eval_loss": 0.9068471193313599,
|
| 122 |
+
"eval_runtime": 119.3472,
|
| 123 |
+
"eval_samples_per_second": 25.841,
|
| 124 |
+
"eval_steps_per_second": 3.234,
|
| 125 |
+
"step": 1244
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 4.180064308681672,
|
| 129 |
+
"grad_norm": 1468095.75,
|
| 130 |
+
"learning_rate": 3.491961414790997e-06,
|
| 131 |
+
"loss": 0.4211,
|
| 132 |
+
"step": 1300
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 4.501607717041801,
|
| 136 |
+
"grad_norm": 3453460.25,
|
| 137 |
+
"learning_rate": 3.2990353697749195e-06,
|
| 138 |
+
"loss": 0.4318,
|
| 139 |
+
"step": 1400
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 4.823151125401929,
|
| 143 |
+
"grad_norm": 2839102.25,
|
| 144 |
+
"learning_rate": 3.106109324758843e-06,
|
| 145 |
+
"loss": 0.403,
|
| 146 |
+
"step": 1500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 5.0,
|
| 150 |
+
"eval_loss": 0.9916093945503235,
|
| 151 |
+
"eval_runtime": 118.6886,
|
| 152 |
+
"eval_samples_per_second": 25.984,
|
| 153 |
+
"eval_steps_per_second": 3.252,
|
| 154 |
+
"step": 1555
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 5.144694533762058,
|
| 158 |
+
"grad_norm": 1706044.25,
|
| 159 |
+
"learning_rate": 2.9131832797427652e-06,
|
| 160 |
+
"loss": 0.4149,
|
| 161 |
+
"step": 1600
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 5.466237942122186,
|
| 165 |
+
"grad_norm": 1450221.875,
|
| 166 |
+
"learning_rate": 2.7202572347266883e-06,
|
| 167 |
+
"loss": 0.4114,
|
| 168 |
+
"step": 1700
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 5.787781350482315,
|
| 172 |
+
"grad_norm": 2638404.25,
|
| 173 |
+
"learning_rate": 2.527331189710611e-06,
|
| 174 |
+
"loss": 0.4016,
|
| 175 |
+
"step": 1800
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 6.0,
|
| 179 |
+
"eval_loss": 0.991452693939209,
|
| 180 |
+
"eval_runtime": 119.0397,
|
| 181 |
+
"eval_samples_per_second": 25.907,
|
| 182 |
+
"eval_steps_per_second": 3.243,
|
| 183 |
+
"step": 1866
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 6.109324758842444,
|
| 187 |
+
"grad_norm": 2121613.25,
|
| 188 |
+
"learning_rate": 2.3344051446945336e-06,
|
| 189 |
+
"loss": 0.3984,
|
| 190 |
+
"step": 1900
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 6.430868167202572,
|
| 194 |
+
"grad_norm": 6534975.0,
|
| 195 |
+
"learning_rate": 2.1414790996784567e-06,
|
| 196 |
+
"loss": 0.3788,
|
| 197 |
+
"step": 2000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 6.752411575562701,
|
| 201 |
+
"grad_norm": 2598338.5,
|
| 202 |
+
"learning_rate": 1.9485530546623794e-06,
|
| 203 |
+
"loss": 0.3718,
|
| 204 |
+
"step": 2100
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 7.0,
|
| 208 |
+
"eval_loss": 0.9927557110786438,
|
| 209 |
+
"eval_runtime": 118.6036,
|
| 210 |
+
"eval_samples_per_second": 26.003,
|
| 211 |
+
"eval_steps_per_second": 3.255,
|
| 212 |
+
"step": 2177
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 7.07395498392283,
|
| 216 |
+
"grad_norm": 1306477.625,
|
| 217 |
+
"learning_rate": 1.7556270096463025e-06,
|
| 218 |
+
"loss": 0.3777,
|
| 219 |
+
"step": 2200
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.395498392282958,
|
| 223 |
+
"grad_norm": 4472440.0,
|
| 224 |
+
"learning_rate": 1.5627009646302251e-06,
|
| 225 |
+
"loss": 0.3696,
|
| 226 |
+
"step": 2300
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 7.717041800643087,
|
| 230 |
+
"grad_norm": 2177569.75,
|
| 231 |
+
"learning_rate": 1.369774919614148e-06,
|
| 232 |
+
"loss": 0.3683,
|
| 233 |
+
"step": 2400
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 8.0,
|
| 237 |
+
"eval_loss": 0.9982658624649048,
|
| 238 |
+
"eval_runtime": 119.853,
|
| 239 |
+
"eval_samples_per_second": 25.732,
|
| 240 |
+
"eval_steps_per_second": 3.221,
|
| 241 |
+
"step": 2488
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 8.038585209003216,
|
| 245 |
+
"grad_norm": 2502705.75,
|
| 246 |
+
"learning_rate": 1.1768488745980709e-06,
|
| 247 |
+
"loss": 0.3577,
|
| 248 |
+
"step": 2500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 8.360128617363344,
|
| 252 |
+
"grad_norm": 1114851.875,
|
| 253 |
+
"learning_rate": 9.839228295819935e-07,
|
| 254 |
+
"loss": 0.357,
|
| 255 |
+
"step": 2600
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 8.681672025723472,
|
| 259 |
+
"grad_norm": 1848325.0,
|
| 260 |
+
"learning_rate": 7.909967845659164e-07,
|
| 261 |
+
"loss": 0.3572,
|
| 262 |
+
"step": 2700
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 9.0,
|
| 266 |
+
"eval_loss": 1.01869797706604,
|
| 267 |
+
"eval_runtime": 119.1193,
|
| 268 |
+
"eval_samples_per_second": 25.89,
|
| 269 |
+
"eval_steps_per_second": 3.24,
|
| 270 |
+
"step": 2799
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 9.003215434083602,
|
| 274 |
+
"grad_norm": 2616566.5,
|
| 275 |
+
"learning_rate": 5.980707395498393e-07,
|
| 276 |
+
"loss": 0.3513,
|
| 277 |
+
"step": 2800
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 9.32475884244373,
|
| 281 |
+
"grad_norm": 1535270.375,
|
| 282 |
+
"learning_rate": 4.051446945337621e-07,
|
| 283 |
+
"loss": 0.3412,
|
| 284 |
+
"step": 2900
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 9.646302250803858,
|
| 288 |
+
"grad_norm": 1695442.875,
|
| 289 |
+
"learning_rate": 2.1221864951768489e-07,
|
| 290 |
+
"loss": 0.365,
|
| 291 |
+
"step": 3000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 9.967845659163988,
|
| 295 |
+
"grad_norm": 2609392.5,
|
| 296 |
+
"learning_rate": 1.929260450160772e-08,
|
| 297 |
+
"loss": 0.3473,
|
| 298 |
+
"step": 3100
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 10.0,
|
| 302 |
+
"eval_loss": 1.024717092514038,
|
| 303 |
+
"eval_runtime": 119.192,
|
| 304 |
+
"eval_samples_per_second": 25.874,
|
| 305 |
+
"eval_steps_per_second": 3.238,
|
| 306 |
+
"step": 3110
|
| 307 |
+
}
|
| 308 |
+
],
|
| 309 |
+
"logging_steps": 100,
|
| 310 |
+
"max_steps": 3110,
|
| 311 |
+
"num_input_tokens_seen": 0,
|
| 312 |
+
"num_train_epochs": 10,
|
| 313 |
+
"save_steps": 500,
|
| 314 |
+
"stateful_callbacks": {
|
| 315 |
+
"TrainerControl": {
|
| 316 |
+
"args": {
|
| 317 |
+
"should_epoch_stop": false,
|
| 318 |
+
"should_evaluate": false,
|
| 319 |
+
"should_log": false,
|
| 320 |
+
"should_save": true,
|
| 321 |
+
"should_training_stop": true
|
| 322 |
+
},
|
| 323 |
+
"attributes": {}
|
| 324 |
+
}
|
| 325 |
+
},
|
| 326 |
+
"total_flos": 9.25876937799168e+16,
|
| 327 |
+
"train_batch_size": 32,
|
| 328 |
+
"trial_name": null,
|
| 329 |
+
"trial_params": null
|
| 330 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1edc61847b8051697a0c1e5451ee8cc36753ad537711293c670074f0129bfb7d
|
| 3 |
+
size 5240
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|