Commit
·
6ab019f
1
Parent(s):
1593c29
End of training
Browse files- README.md +52 -12
- model.safetensors +1 -1
- runs/Jan05_07-56-15_414819e23027/events.out.tfevents.1704441386.414819e23027.9579.12 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- trainer_state.json +632 -72
- training_args.bin +1 -1
- vocab.txt +0 -0
README.md
CHANGED
|
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 4.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -40,22 +40,62 @@ The following hyperparameters were used during training:
|
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
-
- num_epochs:
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
-
| 4.
|
| 50 |
-
| 4.
|
| 51 |
-
| 3.
|
| 52 |
-
| 3.
|
| 53 |
-
| 3.
|
| 54 |
-
| 3.
|
| 55 |
-
| 3.
|
| 56 |
-
|
|
| 57 |
-
|
|
| 58 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 4.5134
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 50
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| 4.3188 | 1.0 | 1 | 4.3048 |
|
| 50 |
+
| 4.0523 | 2.0 | 2 | 4.3228 |
|
| 51 |
+
| 3.7875 | 3.0 | 3 | 4.3474 |
|
| 52 |
+
| 3.621 | 4.0 | 4 | 4.3642 |
|
| 53 |
+
| 3.463 | 5.0 | 5 | 4.3595 |
|
| 54 |
+
| 3.2716 | 6.0 | 6 | 4.3646 |
|
| 55 |
+
| 3.1239 | 7.0 | 7 | 4.3788 |
|
| 56 |
+
| 2.95 | 8.0 | 8 | 4.3982 |
|
| 57 |
+
| 2.7756 | 9.0 | 9 | 4.4180 |
|
| 58 |
+
| 2.6549 | 10.0 | 10 | 4.4303 |
|
| 59 |
+
| 2.5244 | 11.0 | 11 | 4.4385 |
|
| 60 |
+
| 2.3896 | 12.0 | 12 | 4.4430 |
|
| 61 |
+
| 2.2981 | 13.0 | 13 | 4.4451 |
|
| 62 |
+
| 2.2074 | 14.0 | 14 | 4.4551 |
|
| 63 |
+
| 2.1064 | 15.0 | 15 | 4.4691 |
|
| 64 |
+
| 1.9709 | 16.0 | 16 | 4.4816 |
|
| 65 |
+
| 1.8962 | 17.0 | 17 | 4.4862 |
|
| 66 |
+
| 1.8365 | 18.0 | 18 | 4.4862 |
|
| 67 |
+
| 1.7521 | 19.0 | 19 | 4.4818 |
|
| 68 |
+
| 1.6779 | 20.0 | 20 | 4.4766 |
|
| 69 |
+
| 1.5921 | 21.0 | 21 | 4.4748 |
|
| 70 |
+
| 1.4871 | 22.0 | 22 | 4.4769 |
|
| 71 |
+
| 1.4557 | 23.0 | 23 | 4.4795 |
|
| 72 |
+
| 1.3541 | 24.0 | 24 | 4.4829 |
|
| 73 |
+
| 1.3201 | 25.0 | 25 | 4.4822 |
|
| 74 |
+
| 1.2871 | 26.0 | 26 | 4.4803 |
|
| 75 |
+
| 1.1979 | 27.0 | 27 | 4.4797 |
|
| 76 |
+
| 1.1499 | 28.0 | 28 | 4.4822 |
|
| 77 |
+
| 1.114 | 29.0 | 29 | 4.4855 |
|
| 78 |
+
| 1.0698 | 30.0 | 30 | 4.4885 |
|
| 79 |
+
| 1.0635 | 31.0 | 31 | 4.4903 |
|
| 80 |
+
| 1.0178 | 32.0 | 32 | 4.4908 |
|
| 81 |
+
| 0.976 | 33.0 | 33 | 4.4920 |
|
| 82 |
+
| 0.9467 | 34.0 | 34 | 4.4933 |
|
| 83 |
+
| 0.9269 | 35.0 | 35 | 4.4953 |
|
| 84 |
+
| 0.8948 | 36.0 | 36 | 4.4968 |
|
| 85 |
+
| 0.8524 | 37.0 | 37 | 4.4994 |
|
| 86 |
+
| 0.8592 | 38.0 | 38 | 4.5028 |
|
| 87 |
+
| 0.8301 | 39.0 | 39 | 4.5061 |
|
| 88 |
+
| 0.799 | 40.0 | 40 | 4.5076 |
|
| 89 |
+
| 0.7772 | 41.0 | 41 | 4.5092 |
|
| 90 |
+
| 0.7611 | 42.0 | 42 | 4.5109 |
|
| 91 |
+
| 0.7345 | 43.0 | 43 | 4.5127 |
|
| 92 |
+
| 0.8036 | 44.0 | 44 | 4.5138 |
|
| 93 |
+
| 0.7261 | 45.0 | 45 | 4.5143 |
|
| 94 |
+
| 0.7305 | 46.0 | 46 | 4.5140 |
|
| 95 |
+
| 0.6898 | 47.0 | 47 | 4.5136 |
|
| 96 |
+
| 0.6926 | 48.0 | 48 | 4.5134 |
|
| 97 |
+
| 0.7093 | 49.0 | 49 | 4.5134 |
|
| 98 |
+
| 0.7009 | 50.0 | 50 | 4.5134 |
|
| 99 |
|
| 100 |
|
| 101 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 435820636
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4a2d4374956c155ac9bee48ebb63b4df3368b7b92fd6771dd3c084b393a111f
|
| 3 |
size 435820636
|
runs/Jan05_07-56-15_414819e23027/events.out.tfevents.1704441386.414819e23027.9579.12
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1c82d8815f8bf3674f1cf72721f1df697fe10d27e73cc771775941b1f31d805
|
| 3 |
+
size 28725
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
trainer_state.json
CHANGED
|
@@ -1,168 +1,728 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 1,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
-
"learning_rate": 4.
|
| 14 |
-
"loss": 4.
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 1.0,
|
| 19 |
-
"eval_loss": 4.
|
| 20 |
-
"eval_runtime": 0.
|
| 21 |
-
"eval_samples_per_second":
|
| 22 |
-
"eval_steps_per_second":
|
| 23 |
"step": 1
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 2.0,
|
| 27 |
-
"learning_rate":
|
| 28 |
-
"loss": 4.
|
| 29 |
"step": 2
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"epoch": 2.0,
|
| 33 |
-
"eval_loss": 4.
|
| 34 |
-
"eval_runtime": 0.
|
| 35 |
-
"eval_samples_per_second":
|
| 36 |
-
"eval_steps_per_second":
|
| 37 |
"step": 2
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 3.0,
|
| 41 |
-
"learning_rate":
|
| 42 |
-
"loss": 3.
|
| 43 |
"step": 3
|
| 44 |
},
|
| 45 |
{
|
| 46 |
"epoch": 3.0,
|
| 47 |
-
"eval_loss": 4.
|
| 48 |
-
"eval_runtime": 0.
|
| 49 |
-
"eval_samples_per_second":
|
| 50 |
-
"eval_steps_per_second":
|
| 51 |
"step": 3
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 4.0,
|
| 55 |
-
"learning_rate":
|
| 56 |
-
"loss": 3.
|
| 57 |
"step": 4
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 4.0,
|
| 61 |
-
"eval_loss": 4.
|
| 62 |
-
"eval_runtime": 0.
|
| 63 |
-
"eval_samples_per_second":
|
| 64 |
-
"eval_steps_per_second":
|
| 65 |
"step": 4
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 5.0,
|
| 69 |
-
"learning_rate":
|
| 70 |
-
"loss": 3.
|
| 71 |
"step": 5
|
| 72 |
},
|
| 73 |
{
|
| 74 |
"epoch": 5.0,
|
| 75 |
-
"eval_loss": 4.
|
| 76 |
-
"eval_runtime": 0.
|
| 77 |
-
"eval_samples_per_second":
|
| 78 |
-
"eval_steps_per_second":
|
| 79 |
"step": 5
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 6.0,
|
| 83 |
-
"learning_rate":
|
| 84 |
-
"loss": 3.
|
| 85 |
"step": 6
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"epoch": 6.0,
|
| 89 |
-
"eval_loss": 4.
|
| 90 |
-
"eval_runtime": 0.
|
| 91 |
-
"eval_samples_per_second":
|
| 92 |
-
"eval_steps_per_second":
|
| 93 |
"step": 6
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 7.0,
|
| 97 |
-
"learning_rate":
|
| 98 |
-
"loss": 3.
|
| 99 |
"step": 7
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 7.0,
|
| 103 |
-
"eval_loss": 4.
|
| 104 |
-
"eval_runtime": 0.
|
| 105 |
-
"eval_samples_per_second":
|
| 106 |
-
"eval_steps_per_second":
|
| 107 |
"step": 7
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 8.0,
|
| 111 |
-
"learning_rate":
|
| 112 |
-
"loss":
|
| 113 |
"step": 8
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"epoch": 8.0,
|
| 117 |
-
"eval_loss": 4.
|
| 118 |
-
"eval_runtime": 0.
|
| 119 |
-
"eval_samples_per_second":
|
| 120 |
-
"eval_steps_per_second":
|
| 121 |
"step": 8
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 9.0,
|
| 125 |
-
"learning_rate":
|
| 126 |
-
"loss":
|
| 127 |
"step": 9
|
| 128 |
},
|
| 129 |
{
|
| 130 |
"epoch": 9.0,
|
| 131 |
-
"eval_loss": 4.
|
| 132 |
-
"eval_runtime": 0.
|
| 133 |
-
"eval_samples_per_second":
|
| 134 |
-
"eval_steps_per_second":
|
| 135 |
"step": 9
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 10.0,
|
| 139 |
-
"learning_rate":
|
| 140 |
-
"loss":
|
| 141 |
"step": 10
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 10.0,
|
| 145 |
-
"eval_loss": 4.
|
| 146 |
-
"eval_runtime": 0.
|
| 147 |
-
"eval_samples_per_second":
|
| 148 |
-
"eval_steps_per_second":
|
| 149 |
"step": 10
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch":
|
| 153 |
-
"
|
| 154 |
-
"
|
| 155 |
-
"
|
| 156 |
-
|
| 157 |
-
|
| 158 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 159 |
}
|
| 160 |
],
|
| 161 |
"logging_steps": 1,
|
| 162 |
-
"max_steps":
|
| 163 |
-
"num_train_epochs":
|
| 164 |
"save_steps": 500,
|
| 165 |
-
"total_flos":
|
| 166 |
"trial_name": null,
|
| 167 |
"trial_params": null
|
| 168 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
"eval_steps": 1,
|
| 6 |
+
"global_step": 50,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
+
"learning_rate": 4.9e-05,
|
| 14 |
+
"loss": 4.3188,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 1.0,
|
| 19 |
+
"eval_loss": 4.304834842681885,
|
| 20 |
+
"eval_runtime": 0.0403,
|
| 21 |
+
"eval_samples_per_second": 49.662,
|
| 22 |
+
"eval_steps_per_second": 24.831,
|
| 23 |
"step": 1
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 2.0,
|
| 27 |
+
"learning_rate": 4.8e-05,
|
| 28 |
+
"loss": 4.0523,
|
| 29 |
"step": 2
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"epoch": 2.0,
|
| 33 |
+
"eval_loss": 4.322819709777832,
|
| 34 |
+
"eval_runtime": 0.0337,
|
| 35 |
+
"eval_samples_per_second": 59.353,
|
| 36 |
+
"eval_steps_per_second": 29.677,
|
| 37 |
"step": 2
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 3.0,
|
| 41 |
+
"learning_rate": 4.7e-05,
|
| 42 |
+
"loss": 3.7875,
|
| 43 |
"step": 3
|
| 44 |
},
|
| 45 |
{
|
| 46 |
"epoch": 3.0,
|
| 47 |
+
"eval_loss": 4.347378730773926,
|
| 48 |
+
"eval_runtime": 0.0393,
|
| 49 |
+
"eval_samples_per_second": 50.859,
|
| 50 |
+
"eval_steps_per_second": 25.429,
|
| 51 |
"step": 3
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 4.0,
|
| 55 |
+
"learning_rate": 4.600000000000001e-05,
|
| 56 |
+
"loss": 3.621,
|
| 57 |
"step": 4
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 4.0,
|
| 61 |
+
"eval_loss": 4.364194869995117,
|
| 62 |
+
"eval_runtime": 0.0329,
|
| 63 |
+
"eval_samples_per_second": 60.728,
|
| 64 |
+
"eval_steps_per_second": 30.364,
|
| 65 |
"step": 4
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 5.0,
|
| 69 |
+
"learning_rate": 4.5e-05,
|
| 70 |
+
"loss": 3.463,
|
| 71 |
"step": 5
|
| 72 |
},
|
| 73 |
{
|
| 74 |
"epoch": 5.0,
|
| 75 |
+
"eval_loss": 4.35947847366333,
|
| 76 |
+
"eval_runtime": 0.0331,
|
| 77 |
+
"eval_samples_per_second": 60.333,
|
| 78 |
+
"eval_steps_per_second": 30.167,
|
| 79 |
"step": 5
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 6.0,
|
| 83 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 84 |
+
"loss": 3.2716,
|
| 85 |
"step": 6
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"epoch": 6.0,
|
| 89 |
+
"eval_loss": 4.364583492279053,
|
| 90 |
+
"eval_runtime": 0.0348,
|
| 91 |
+
"eval_samples_per_second": 57.43,
|
| 92 |
+
"eval_steps_per_second": 28.715,
|
| 93 |
"step": 6
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 7.0,
|
| 97 |
+
"learning_rate": 4.3e-05,
|
| 98 |
+
"loss": 3.1239,
|
| 99 |
"step": 7
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 7.0,
|
| 103 |
+
"eval_loss": 4.3788161277771,
|
| 104 |
+
"eval_runtime": 0.0323,
|
| 105 |
+
"eval_samples_per_second": 61.86,
|
| 106 |
+
"eval_steps_per_second": 30.93,
|
| 107 |
"step": 7
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 8.0,
|
| 111 |
+
"learning_rate": 4.2e-05,
|
| 112 |
+
"loss": 2.95,
|
| 113 |
"step": 8
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"epoch": 8.0,
|
| 117 |
+
"eval_loss": 4.398151874542236,
|
| 118 |
+
"eval_runtime": 0.04,
|
| 119 |
+
"eval_samples_per_second": 49.976,
|
| 120 |
+
"eval_steps_per_second": 24.988,
|
| 121 |
"step": 8
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 9.0,
|
| 125 |
+
"learning_rate": 4.1e-05,
|
| 126 |
+
"loss": 2.7756,
|
| 127 |
"step": 9
|
| 128 |
},
|
| 129 |
{
|
| 130 |
"epoch": 9.0,
|
| 131 |
+
"eval_loss": 4.418046951293945,
|
| 132 |
+
"eval_runtime": 0.0418,
|
| 133 |
+
"eval_samples_per_second": 47.897,
|
| 134 |
+
"eval_steps_per_second": 23.949,
|
| 135 |
"step": 9
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 10.0,
|
| 139 |
+
"learning_rate": 4e-05,
|
| 140 |
+
"loss": 2.6549,
|
| 141 |
"step": 10
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 10.0,
|
| 145 |
+
"eval_loss": 4.430344581604004,
|
| 146 |
+
"eval_runtime": 0.0286,
|
| 147 |
+
"eval_samples_per_second": 69.986,
|
| 148 |
+
"eval_steps_per_second": 34.993,
|
| 149 |
"step": 10
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 11.0,
|
| 153 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 154 |
+
"loss": 2.5244,
|
| 155 |
+
"step": 11
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 11.0,
|
| 159 |
+
"eval_loss": 4.438453197479248,
|
| 160 |
+
"eval_runtime": 0.0276,
|
| 161 |
+
"eval_samples_per_second": 72.47,
|
| 162 |
+
"eval_steps_per_second": 36.235,
|
| 163 |
+
"step": 11
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 12.0,
|
| 167 |
+
"learning_rate": 3.8e-05,
|
| 168 |
+
"loss": 2.3896,
|
| 169 |
+
"step": 12
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 12.0,
|
| 173 |
+
"eval_loss": 4.4430317878723145,
|
| 174 |
+
"eval_runtime": 0.0287,
|
| 175 |
+
"eval_samples_per_second": 69.577,
|
| 176 |
+
"eval_steps_per_second": 34.788,
|
| 177 |
+
"step": 12
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 13.0,
|
| 181 |
+
"learning_rate": 3.7e-05,
|
| 182 |
+
"loss": 2.2981,
|
| 183 |
+
"step": 13
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 13.0,
|
| 187 |
+
"eval_loss": 4.445078372955322,
|
| 188 |
+
"eval_runtime": 0.0283,
|
| 189 |
+
"eval_samples_per_second": 70.789,
|
| 190 |
+
"eval_steps_per_second": 35.394,
|
| 191 |
+
"step": 13
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 14.0,
|
| 195 |
+
"learning_rate": 3.6e-05,
|
| 196 |
+
"loss": 2.2074,
|
| 197 |
+
"step": 14
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 14.0,
|
| 201 |
+
"eval_loss": 4.455099105834961,
|
| 202 |
+
"eval_runtime": 0.0298,
|
| 203 |
+
"eval_samples_per_second": 67.215,
|
| 204 |
+
"eval_steps_per_second": 33.608,
|
| 205 |
+
"step": 14
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 15.0,
|
| 209 |
+
"learning_rate": 3.5e-05,
|
| 210 |
+
"loss": 2.1064,
|
| 211 |
+
"step": 15
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 15.0,
|
| 215 |
+
"eval_loss": 4.469105243682861,
|
| 216 |
+
"eval_runtime": 0.0268,
|
| 217 |
+
"eval_samples_per_second": 74.497,
|
| 218 |
+
"eval_steps_per_second": 37.248,
|
| 219 |
+
"step": 15
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 16.0,
|
| 223 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 224 |
+
"loss": 1.9709,
|
| 225 |
+
"step": 16
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 16.0,
|
| 229 |
+
"eval_loss": 4.4815754890441895,
|
| 230 |
+
"eval_runtime": 0.0324,
|
| 231 |
+
"eval_samples_per_second": 61.699,
|
| 232 |
+
"eval_steps_per_second": 30.85,
|
| 233 |
+
"step": 16
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 17.0,
|
| 237 |
+
"learning_rate": 3.3e-05,
|
| 238 |
+
"loss": 1.8962,
|
| 239 |
+
"step": 17
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 17.0,
|
| 243 |
+
"eval_loss": 4.486156940460205,
|
| 244 |
+
"eval_runtime": 0.028,
|
| 245 |
+
"eval_samples_per_second": 71.398,
|
| 246 |
+
"eval_steps_per_second": 35.699,
|
| 247 |
+
"step": 17
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 18.0,
|
| 251 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 252 |
+
"loss": 1.8365,
|
| 253 |
+
"step": 18
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 18.0,
|
| 257 |
+
"eval_loss": 4.486203670501709,
|
| 258 |
+
"eval_runtime": 0.0375,
|
| 259 |
+
"eval_samples_per_second": 53.347,
|
| 260 |
+
"eval_steps_per_second": 26.674,
|
| 261 |
+
"step": 18
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 19.0,
|
| 265 |
+
"learning_rate": 3.1e-05,
|
| 266 |
+
"loss": 1.7521,
|
| 267 |
+
"step": 19
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 19.0,
|
| 271 |
+
"eval_loss": 4.481803894042969,
|
| 272 |
+
"eval_runtime": 0.0261,
|
| 273 |
+
"eval_samples_per_second": 76.657,
|
| 274 |
+
"eval_steps_per_second": 38.329,
|
| 275 |
+
"step": 19
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 20.0,
|
| 279 |
+
"learning_rate": 3e-05,
|
| 280 |
+
"loss": 1.6779,
|
| 281 |
+
"step": 20
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 20.0,
|
| 285 |
+
"eval_loss": 4.476602077484131,
|
| 286 |
+
"eval_runtime": 0.0289,
|
| 287 |
+
"eval_samples_per_second": 69.157,
|
| 288 |
+
"eval_steps_per_second": 34.579,
|
| 289 |
+
"step": 20
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 21.0,
|
| 293 |
+
"learning_rate": 2.9e-05,
|
| 294 |
+
"loss": 1.5921,
|
| 295 |
+
"step": 21
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 21.0,
|
| 299 |
+
"eval_loss": 4.474806785583496,
|
| 300 |
+
"eval_runtime": 0.0306,
|
| 301 |
+
"eval_samples_per_second": 65.323,
|
| 302 |
+
"eval_steps_per_second": 32.661,
|
| 303 |
+
"step": 21
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 22.0,
|
| 307 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 308 |
+
"loss": 1.4871,
|
| 309 |
+
"step": 22
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 22.0,
|
| 313 |
+
"eval_loss": 4.4769287109375,
|
| 314 |
+
"eval_runtime": 0.0275,
|
| 315 |
+
"eval_samples_per_second": 72.678,
|
| 316 |
+
"eval_steps_per_second": 36.339,
|
| 317 |
+
"step": 22
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 23.0,
|
| 321 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 322 |
+
"loss": 1.4557,
|
| 323 |
+
"step": 23
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 23.0,
|
| 327 |
+
"eval_loss": 4.479461193084717,
|
| 328 |
+
"eval_runtime": 0.0288,
|
| 329 |
+
"eval_samples_per_second": 69.4,
|
| 330 |
+
"eval_steps_per_second": 34.7,
|
| 331 |
+
"step": 23
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 24.0,
|
| 335 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 336 |
+
"loss": 1.3541,
|
| 337 |
+
"step": 24
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 24.0,
|
| 341 |
+
"eval_loss": 4.482919216156006,
|
| 342 |
+
"eval_runtime": 0.0299,
|
| 343 |
+
"eval_samples_per_second": 66.98,
|
| 344 |
+
"eval_steps_per_second": 33.49,
|
| 345 |
+
"step": 24
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 25.0,
|
| 349 |
+
"learning_rate": 2.5e-05,
|
| 350 |
+
"loss": 1.3201,
|
| 351 |
+
"step": 25
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 25.0,
|
| 355 |
+
"eval_loss": 4.482161998748779,
|
| 356 |
+
"eval_runtime": 0.0318,
|
| 357 |
+
"eval_samples_per_second": 62.819,
|
| 358 |
+
"eval_steps_per_second": 31.409,
|
| 359 |
+
"step": 25
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 26.0,
|
| 363 |
+
"learning_rate": 2.4e-05,
|
| 364 |
+
"loss": 1.2871,
|
| 365 |
+
"step": 26
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 26.0,
|
| 369 |
+
"eval_loss": 4.480334281921387,
|
| 370 |
+
"eval_runtime": 0.028,
|
| 371 |
+
"eval_samples_per_second": 71.489,
|
| 372 |
+
"eval_steps_per_second": 35.745,
|
| 373 |
+
"step": 26
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 27.0,
|
| 377 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 378 |
+
"loss": 1.1979,
|
| 379 |
+
"step": 27
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 27.0,
|
| 383 |
+
"eval_loss": 4.479716777801514,
|
| 384 |
+
"eval_runtime": 0.0295,
|
| 385 |
+
"eval_samples_per_second": 67.699,
|
| 386 |
+
"eval_steps_per_second": 33.849,
|
| 387 |
+
"step": 27
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 28.0,
|
| 391 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 392 |
+
"loss": 1.1499,
|
| 393 |
+
"step": 28
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 28.0,
|
| 397 |
+
"eval_loss": 4.4821858406066895,
|
| 398 |
+
"eval_runtime": 0.0339,
|
| 399 |
+
"eval_samples_per_second": 59.02,
|
| 400 |
+
"eval_steps_per_second": 29.51,
|
| 401 |
+
"step": 28
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 29.0,
|
| 405 |
+
"learning_rate": 2.1e-05,
|
| 406 |
+
"loss": 1.114,
|
| 407 |
+
"step": 29
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 29.0,
|
| 411 |
+
"eval_loss": 4.485532283782959,
|
| 412 |
+
"eval_runtime": 0.0295,
|
| 413 |
+
"eval_samples_per_second": 67.701,
|
| 414 |
+
"eval_steps_per_second": 33.851,
|
| 415 |
+
"step": 29
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 30.0,
|
| 419 |
+
"learning_rate": 2e-05,
|
| 420 |
+
"loss": 1.0698,
|
| 421 |
+
"step": 30
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 30.0,
|
| 425 |
+
"eval_loss": 4.4885077476501465,
|
| 426 |
+
"eval_runtime": 0.0292,
|
| 427 |
+
"eval_samples_per_second": 68.609,
|
| 428 |
+
"eval_steps_per_second": 34.305,
|
| 429 |
+
"step": 30
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 31.0,
|
| 433 |
+
"learning_rate": 1.9e-05,
|
| 434 |
+
"loss": 1.0635,
|
| 435 |
+
"step": 31
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 31.0,
|
| 439 |
+
"eval_loss": 4.490349769592285,
|
| 440 |
+
"eval_runtime": 0.0278,
|
| 441 |
+
"eval_samples_per_second": 71.898,
|
| 442 |
+
"eval_steps_per_second": 35.949,
|
| 443 |
+
"step": 31
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 32.0,
|
| 447 |
+
"learning_rate": 1.8e-05,
|
| 448 |
+
"loss": 1.0178,
|
| 449 |
+
"step": 32
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 32.0,
|
| 453 |
+
"eval_loss": 4.4907612800598145,
|
| 454 |
+
"eval_runtime": 0.0278,
|
| 455 |
+
"eval_samples_per_second": 71.828,
|
| 456 |
+
"eval_steps_per_second": 35.914,
|
| 457 |
+
"step": 32
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 33.0,
|
| 461 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 462 |
+
"loss": 0.976,
|
| 463 |
+
"step": 33
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 33.0,
|
| 467 |
+
"eval_loss": 4.491974830627441,
|
| 468 |
+
"eval_runtime": 0.0282,
|
| 469 |
+
"eval_samples_per_second": 71.029,
|
| 470 |
+
"eval_steps_per_second": 35.515,
|
| 471 |
+
"step": 33
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 34.0,
|
| 475 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 476 |
+
"loss": 0.9467,
|
| 477 |
+
"step": 34
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 34.0,
|
| 481 |
+
"eval_loss": 4.493342876434326,
|
| 482 |
+
"eval_runtime": 0.0333,
|
| 483 |
+
"eval_samples_per_second": 60.02,
|
| 484 |
+
"eval_steps_per_second": 30.01,
|
| 485 |
+
"step": 34
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 35.0,
|
| 489 |
+
"learning_rate": 1.5e-05,
|
| 490 |
+
"loss": 0.9269,
|
| 491 |
+
"step": 35
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 35.0,
|
| 495 |
+
"eval_loss": 4.49529504776001,
|
| 496 |
+
"eval_runtime": 0.0269,
|
| 497 |
+
"eval_samples_per_second": 74.297,
|
| 498 |
+
"eval_steps_per_second": 37.149,
|
| 499 |
+
"step": 35
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 36.0,
|
| 503 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 504 |
+
"loss": 0.8948,
|
| 505 |
+
"step": 36
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 36.0,
|
| 509 |
+
"eval_loss": 4.496817588806152,
|
| 510 |
+
"eval_runtime": 0.0305,
|
| 511 |
+
"eval_samples_per_second": 65.479,
|
| 512 |
+
"eval_steps_per_second": 32.74,
|
| 513 |
+
"step": 36
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 37.0,
|
| 517 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 518 |
+
"loss": 0.8524,
|
| 519 |
+
"step": 37
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 37.0,
|
| 523 |
+
"eval_loss": 4.499395847320557,
|
| 524 |
+
"eval_runtime": 0.0281,
|
| 525 |
+
"eval_samples_per_second": 71.264,
|
| 526 |
+
"eval_steps_per_second": 35.632,
|
| 527 |
+
"step": 37
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 38.0,
|
| 531 |
+
"learning_rate": 1.2e-05,
|
| 532 |
+
"loss": 0.8592,
|
| 533 |
+
"step": 38
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 38.0,
|
| 537 |
+
"eval_loss": 4.502837657928467,
|
| 538 |
+
"eval_runtime": 0.0297,
|
| 539 |
+
"eval_samples_per_second": 67.239,
|
| 540 |
+
"eval_steps_per_second": 33.62,
|
| 541 |
+
"step": 38
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 39.0,
|
| 545 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 546 |
+
"loss": 0.8301,
|
| 547 |
+
"step": 39
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 39.0,
|
| 551 |
+
"eval_loss": 4.506129264831543,
|
| 552 |
+
"eval_runtime": 0.0327,
|
| 553 |
+
"eval_samples_per_second": 61.108,
|
| 554 |
+
"eval_steps_per_second": 30.554,
|
| 555 |
+
"step": 39
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 40.0,
|
| 559 |
+
"learning_rate": 1e-05,
|
| 560 |
+
"loss": 0.799,
|
| 561 |
+
"step": 40
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 40.0,
|
| 565 |
+
"eval_loss": 4.507645130157471,
|
| 566 |
+
"eval_runtime": 0.0271,
|
| 567 |
+
"eval_samples_per_second": 73.666,
|
| 568 |
+
"eval_steps_per_second": 36.833,
|
| 569 |
+
"step": 40
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 41.0,
|
| 573 |
+
"learning_rate": 9e-06,
|
| 574 |
+
"loss": 0.7772,
|
| 575 |
+
"step": 41
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 41.0,
|
| 579 |
+
"eval_loss": 4.509157180786133,
|
| 580 |
+
"eval_runtime": 0.0285,
|
| 581 |
+
"eval_samples_per_second": 70.159,
|
| 582 |
+
"eval_steps_per_second": 35.08,
|
| 583 |
+
"step": 41
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 42.0,
|
| 587 |
+
"learning_rate": 8.000000000000001e-06,
|
| 588 |
+
"loss": 0.7611,
|
| 589 |
+
"step": 42
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 42.0,
|
| 593 |
+
"eval_loss": 4.510908603668213,
|
| 594 |
+
"eval_runtime": 0.0285,
|
| 595 |
+
"eval_samples_per_second": 70.164,
|
| 596 |
+
"eval_steps_per_second": 35.082,
|
| 597 |
+
"step": 42
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 43.0,
|
| 601 |
+
"learning_rate": 7.000000000000001e-06,
|
| 602 |
+
"loss": 0.7345,
|
| 603 |
+
"step": 43
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 43.0,
|
| 607 |
+
"eval_loss": 4.512662410736084,
|
| 608 |
+
"eval_runtime": 0.0295,
|
| 609 |
+
"eval_samples_per_second": 67.814,
|
| 610 |
+
"eval_steps_per_second": 33.907,
|
| 611 |
+
"step": 43
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 44.0,
|
| 615 |
+
"learning_rate": 6e-06,
|
| 616 |
+
"loss": 0.8036,
|
| 617 |
+
"step": 44
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 44.0,
|
| 621 |
+
"eval_loss": 4.51375150680542,
|
| 622 |
+
"eval_runtime": 0.0295,
|
| 623 |
+
"eval_samples_per_second": 67.686,
|
| 624 |
+
"eval_steps_per_second": 33.843,
|
| 625 |
+
"step": 44
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 45.0,
|
| 629 |
+
"learning_rate": 5e-06,
|
| 630 |
+
"loss": 0.7261,
|
| 631 |
+
"step": 45
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 45.0,
|
| 635 |
+
"eval_loss": 4.514307022094727,
|
| 636 |
+
"eval_runtime": 0.0366,
|
| 637 |
+
"eval_samples_per_second": 54.69,
|
| 638 |
+
"eval_steps_per_second": 27.345,
|
| 639 |
+
"step": 45
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 46.0,
|
| 643 |
+
"learning_rate": 4.000000000000001e-06,
|
| 644 |
+
"loss": 0.7305,
|
| 645 |
+
"step": 46
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 46.0,
|
| 649 |
+
"eval_loss": 4.514035701751709,
|
| 650 |
+
"eval_runtime": 0.0325,
|
| 651 |
+
"eval_samples_per_second": 61.45,
|
| 652 |
+
"eval_steps_per_second": 30.725,
|
| 653 |
+
"step": 46
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 47.0,
|
| 657 |
+
"learning_rate": 3e-06,
|
| 658 |
+
"loss": 0.6898,
|
| 659 |
+
"step": 47
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 47.0,
|
| 663 |
+
"eval_loss": 4.51362419128418,
|
| 664 |
+
"eval_runtime": 0.0279,
|
| 665 |
+
"eval_samples_per_second": 71.677,
|
| 666 |
+
"eval_steps_per_second": 35.838,
|
| 667 |
+
"step": 47
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 48.0,
|
| 671 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 672 |
+
"loss": 0.6926,
|
| 673 |
+
"step": 48
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 48.0,
|
| 677 |
+
"eval_loss": 4.513439178466797,
|
| 678 |
+
"eval_runtime": 0.0286,
|
| 679 |
+
"eval_samples_per_second": 69.881,
|
| 680 |
+
"eval_steps_per_second": 34.94,
|
| 681 |
+
"step": 48
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 49.0,
|
| 685 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 686 |
+
"loss": 0.7093,
|
| 687 |
+
"step": 49
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 49.0,
|
| 691 |
+
"eval_loss": 4.513415813446045,
|
| 692 |
+
"eval_runtime": 0.0336,
|
| 693 |
+
"eval_samples_per_second": 59.457,
|
| 694 |
+
"eval_steps_per_second": 29.728,
|
| 695 |
+
"step": 49
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 50.0,
|
| 699 |
+
"learning_rate": 0.0,
|
| 700 |
+
"loss": 0.7009,
|
| 701 |
+
"step": 50
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 50.0,
|
| 705 |
+
"eval_loss": 4.513373851776123,
|
| 706 |
+
"eval_runtime": 0.0276,
|
| 707 |
+
"eval_samples_per_second": 72.415,
|
| 708 |
+
"eval_steps_per_second": 36.208,
|
| 709 |
+
"step": 50
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 50.0,
|
| 713 |
+
"step": 50,
|
| 714 |
+
"total_flos": 28802467620000.0,
|
| 715 |
+
"train_loss": 1.6839551556110381,
|
| 716 |
+
"train_runtime": 12.3811,
|
| 717 |
+
"train_samples_per_second": 32.307,
|
| 718 |
+
"train_steps_per_second": 4.038
|
| 719 |
}
|
| 720 |
],
|
| 721 |
"logging_steps": 1,
|
| 722 |
+
"max_steps": 50,
|
| 723 |
+
"num_train_epochs": 50,
|
| 724 |
"save_steps": 500,
|
| 725 |
+
"total_flos": 28802467620000.0,
|
| 726 |
"trial_name": null,
|
| 727 |
"trial_params": null
|
| 728 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4600
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:058e290455a7ba56c355ecc012bae0490088b0f15056d1558ffb8bfa78af940f
|
| 3 |
size 4600
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|