Commit
•
86ac4b4
1
Parent(s):
beb58cb
huggingartists
Browse files- README.md +3 -3
- config.json +2 -2
- evaluation.txt +1 -1
- flax_model.msgpack +1 -1
- optimizer.pt +2 -2
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- tokenizer_config.json +1 -1
- trainer_state.json +459 -7
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
| 45 |
dataset = load_dataset("huggingartists/coldplay")
|
| 46 |
```
|
| 47 |
|
| 48 |
-
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 49 |
|
| 50 |
## Training procedure
|
| 51 |
|
| 52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Coldplay's lyrics.
|
| 53 |
|
| 54 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 55 |
|
| 56 |
-
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
|
|
|
| 45 |
dataset = load_dataset("huggingartists/coldplay")
|
| 46 |
```
|
| 47 |
|
| 48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/34iy5awi/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
|
| 49 |
|
| 50 |
## Training procedure
|
| 51 |
|
| 52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Coldplay's lyrics.
|
| 53 |
|
| 54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/p1oxwu42) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/p1oxwu42/artifacts) is logged and versioned.
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
@@ -35,7 +35,7 @@
|
|
| 35 |
}
|
| 36 |
},
|
| 37 |
"torch_dtype": "float32",
|
| 38 |
-
"transformers_version": "4.
|
| 39 |
"use_cache": true,
|
| 40 |
"vocab_size": 50257
|
| 41 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "huggingartists/coldplay",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 35 |
}
|
| 36 |
},
|
| 37 |
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.11.3",
|
| 39 |
"use_cache": true,
|
| 40 |
"vocab_size": 50257
|
| 41 |
}
|
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss": 2.
|
|
|
|
| 1 |
+
{"eval_loss": 2.3194692134857178, "eval_runtime": 1.0619, "eval_samples_per_second": 76.28, "eval_steps_per_second": 10.359, "epoch": 61.0}
|
flax_model.msgpack
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497764120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b47c6d38b14cb8948342f6984a6c1085465ea6d66dc0b0e263b9efdcf12dd4d
|
| 3 |
size 497764120
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da8b48aba8a2ac3780274dff233d2f46b80384823383f633919cb3fff88e3a1a
|
| 3 |
+
size 995604017
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 510403817
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d268187c04aaef8b37af7894fd8c042ea497315e5c23e7d7d5f5175e3c43fc91
|
| 3 |
size 510403817
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8173196c210c0874e6edb77639fe67968b8a0f875123e25b7002bd9aa763efc
|
| 3 |
size 14503
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea923f2e0b275d809c555b520c2a11f0ea9d5d9892df660f643bda82951dfca7
|
| 3 |
size 623
|
tokenizer_config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "
|
|
|
|
| 1 |
+
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "huggingartists/coldplay", "tokenizer_class": "GPT2Tokenizer"}
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 2.
|
| 3 |
-
"best_model_checkpoint": "output/coldplay/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -68,11 +68,463 @@
|
|
| 68 |
"eval_samples_per_second": 21.405,
|
| 69 |
"eval_steps_per_second": 2.932,
|
| 70 |
"step": 48
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
}
|
| 72 |
],
|
| 73 |
-
"max_steps":
|
| 74 |
-
"num_train_epochs":
|
| 75 |
-
"total_flos":
|
| 76 |
"trial_name": null,
|
| 77 |
"trial_params": null
|
| 78 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.3194692134857178,
|
| 3 |
+
"best_model_checkpoint": "output/coldplay/checkpoint-376",
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
+
"global_step": 376,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 68 |
"eval_samples_per_second": 21.405,
|
| 69 |
"eval_steps_per_second": 2.932,
|
| 70 |
"step": 48
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.06,
|
| 74 |
+
"learning_rate": 1.3746270344901413e-06,
|
| 75 |
+
"loss": 2.7251,
|
| 76 |
+
"step": 50
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.17,
|
| 80 |
+
"learning_rate": 9.576451662754438e-06,
|
| 81 |
+
"loss": 2.4207,
|
| 82 |
+
"step": 55
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.28,
|
| 86 |
+
"learning_rate": 2.4309929383066146e-05,
|
| 87 |
+
"loss": 2.7058,
|
| 88 |
+
"step": 60
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.38,
|
| 92 |
+
"learning_rate": 4.3944626783346644e-05,
|
| 93 |
+
"loss": 2.6908,
|
| 94 |
+
"step": 65
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.49,
|
| 98 |
+
"learning_rate": 6.630773257727353e-05,
|
| 99 |
+
"loss": 2.7345,
|
| 100 |
+
"step": 70
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.6,
|
| 104 |
+
"learning_rate": 8.892450484875447e-05,
|
| 105 |
+
"loss": 2.4105,
|
| 106 |
+
"step": 75
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.7,
|
| 110 |
+
"learning_rate": 0.00010929213048843373,
|
| 111 |
+
"loss": 2.5926,
|
| 112 |
+
"step": 80
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.81,
|
| 116 |
+
"learning_rate": 0.00012515669103944476,
|
| 117 |
+
"loss": 2.4909,
|
| 118 |
+
"step": 85
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.91,
|
| 122 |
+
"learning_rate": 0.00013476258540873022,
|
| 123 |
+
"loss": 2.5389,
|
| 124 |
+
"step": 90
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 2.0,
|
| 128 |
+
"eval_loss": 2.446333646774292,
|
| 129 |
+
"eval_runtime": 1.0636,
|
| 130 |
+
"eval_samples_per_second": 76.156,
|
| 131 |
+
"eval_steps_per_second": 10.342,
|
| 132 |
+
"step": 94
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.02,
|
| 136 |
+
"learning_rate": 0.00013704680787354832,
|
| 137 |
+
"loss": 2.3598,
|
| 138 |
+
"step": 95
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 2.13,
|
| 142 |
+
"learning_rate": 0.00013175658222600302,
|
| 143 |
+
"loss": 2.2124,
|
| 144 |
+
"step": 100
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 2.23,
|
| 148 |
+
"learning_rate": 0.00011947733444744994,
|
| 149 |
+
"loss": 2.1658,
|
| 150 |
+
"step": 105
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.34,
|
| 154 |
+
"learning_rate": 0.0001015679084058065,
|
| 155 |
+
"loss": 2.1519,
|
| 156 |
+
"step": 110
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.45,
|
| 160 |
+
"learning_rate": 8.001019372440279e-05,
|
| 161 |
+
"loss": 2.243,
|
| 162 |
+
"step": 115
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.55,
|
| 166 |
+
"learning_rate": 5.718980627559731e-05,
|
| 167 |
+
"loss": 2.2952,
|
| 168 |
+
"step": 120
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.66,
|
| 172 |
+
"learning_rate": 3.563209159419354e-05,
|
| 173 |
+
"loss": 2.2394,
|
| 174 |
+
"step": 125
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.77,
|
| 178 |
+
"learning_rate": 1.772266555255008e-05,
|
| 179 |
+
"loss": 2.2106,
|
| 180 |
+
"step": 130
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.87,
|
| 184 |
+
"learning_rate": 5.443417773996978e-06,
|
| 185 |
+
"loss": 2.2222,
|
| 186 |
+
"step": 135
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.98,
|
| 190 |
+
"learning_rate": 1.5319212645169297e-07,
|
| 191 |
+
"loss": 2.1897,
|
| 192 |
+
"step": 140
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 3.0,
|
| 196 |
+
"eval_loss": 2.3795111179351807,
|
| 197 |
+
"eval_runtime": 1.0634,
|
| 198 |
+
"eval_samples_per_second": 76.169,
|
| 199 |
+
"eval_steps_per_second": 10.344,
|
| 200 |
+
"step": 141
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.09,
|
| 204 |
+
"learning_rate": 2.4374145912697595e-06,
|
| 205 |
+
"loss": 2.0277,
|
| 206 |
+
"step": 145
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.19,
|
| 210 |
+
"learning_rate": 1.204330896055522e-05,
|
| 211 |
+
"loss": 2.0337,
|
| 212 |
+
"step": 150
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.3,
|
| 216 |
+
"learning_rate": 2.790786951156628e-05,
|
| 217 |
+
"loss": 2.0818,
|
| 218 |
+
"step": 155
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.4,
|
| 222 |
+
"learning_rate": 4.8275495151245426e-05,
|
| 223 |
+
"loss": 2.1041,
|
| 224 |
+
"step": 160
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.51,
|
| 228 |
+
"learning_rate": 7.089226742272638e-05,
|
| 229 |
+
"loss": 2.1708,
|
| 230 |
+
"step": 165
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.62,
|
| 234 |
+
"learning_rate": 9.325537321665337e-05,
|
| 235 |
+
"loss": 2.0552,
|
| 236 |
+
"step": 170
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.72,
|
| 240 |
+
"learning_rate": 0.00011289007061693382,
|
| 241 |
+
"loss": 2.1205,
|
| 242 |
+
"step": 175
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.83,
|
| 246 |
+
"learning_rate": 0.00012762354833724553,
|
| 247 |
+
"loss": 1.9704,
|
| 248 |
+
"step": 180
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.94,
|
| 252 |
+
"learning_rate": 0.00013582537296550986,
|
| 253 |
+
"loss": 1.9882,
|
| 254 |
+
"step": 185
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 4.0,
|
| 258 |
+
"eval_loss": 2.3495991230010986,
|
| 259 |
+
"eval_runtime": 1.0619,
|
| 260 |
+
"eval_samples_per_second": 76.281,
|
| 261 |
+
"eval_steps_per_second": 10.359,
|
| 262 |
+
"step": 188
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 4.04,
|
| 266 |
+
"learning_rate": 0.0001365879156874179,
|
| 267 |
+
"loss": 2.1933,
|
| 268 |
+
"step": 190
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 4.15,
|
| 272 |
+
"learning_rate": 0.00012982679213998792,
|
| 273 |
+
"loss": 1.8172,
|
| 274 |
+
"step": 195
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 4.26,
|
| 278 |
+
"learning_rate": 0.00011629020053848047,
|
| 279 |
+
"loss": 1.6238,
|
| 280 |
+
"step": 200
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 4.36,
|
| 284 |
+
"learning_rate": 9.747612470258382e-05,
|
| 285 |
+
"loss": 1.8408,
|
| 286 |
+
"step": 205
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 4.47,
|
| 290 |
+
"learning_rate": 7.546656444541333e-05,
|
| 291 |
+
"loss": 1.8867,
|
| 292 |
+
"step": 210
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 4.57,
|
| 296 |
+
"learning_rate": 5.2697137691647635e-05,
|
| 297 |
+
"loss": 2.0636,
|
| 298 |
+
"step": 215
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 4.68,
|
| 302 |
+
"learning_rate": 3.1687550572992616e-05,
|
| 303 |
+
"loss": 1.8887,
|
| 304 |
+
"step": 220
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 4.79,
|
| 308 |
+
"learning_rate": 1.4762762169883855e-05,
|
| 309 |
+
"loss": 1.9152,
|
| 310 |
+
"step": 225
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 4.89,
|
| 314 |
+
"learning_rate": 3.795700315696817e-06,
|
| 315 |
+
"loss": 1.8236,
|
| 316 |
+
"step": 230
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 5.0,
|
| 320 |
+
"learning_rate": 0.0,
|
| 321 |
+
"loss": 1.6923,
|
| 322 |
+
"step": 235
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 5.0,
|
| 326 |
+
"eval_loss": 2.332808017730713,
|
| 327 |
+
"eval_runtime": 1.0629,
|
| 328 |
+
"eval_samples_per_second": 76.208,
|
| 329 |
+
"eval_steps_per_second": 10.349,
|
| 330 |
+
"step": 235
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 5.11,
|
| 334 |
+
"learning_rate": 3.7957003156967485e-06,
|
| 335 |
+
"loss": 1.6147,
|
| 336 |
+
"step": 240
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 5.21,
|
| 340 |
+
"learning_rate": 1.4762762169883802e-05,
|
| 341 |
+
"loss": 1.7048,
|
| 342 |
+
"step": 245
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 5.32,
|
| 346 |
+
"learning_rate": 3.168755057299255e-05,
|
| 347 |
+
"loss": 1.5544,
|
| 348 |
+
"step": 250
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 5.43,
|
| 352 |
+
"learning_rate": 5.269713769164743e-05,
|
| 353 |
+
"loss": 1.5129,
|
| 354 |
+
"step": 255
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 5.53,
|
| 358 |
+
"learning_rate": 7.546656444541325e-05,
|
| 359 |
+
"loss": 1.7164,
|
| 360 |
+
"step": 260
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 5.64,
|
| 364 |
+
"learning_rate": 9.747612470258363e-05,
|
| 365 |
+
"loss": 1.6792,
|
| 366 |
+
"step": 265
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 5.74,
|
| 370 |
+
"learning_rate": 0.0001162902005384805,
|
| 371 |
+
"loss": 1.7173,
|
| 372 |
+
"step": 270
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 5.85,
|
| 376 |
+
"learning_rate": 0.00012982679213998787,
|
| 377 |
+
"loss": 1.7795,
|
| 378 |
+
"step": 275
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 5.96,
|
| 382 |
+
"learning_rate": 0.00013658791568741792,
|
| 383 |
+
"loss": 1.9717,
|
| 384 |
+
"step": 280
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 6.0,
|
| 388 |
+
"eval_loss": 2.336082935333252,
|
| 389 |
+
"eval_runtime": 1.0719,
|
| 390 |
+
"eval_samples_per_second": 75.567,
|
| 391 |
+
"eval_steps_per_second": 10.262,
|
| 392 |
+
"step": 282
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 6.06,
|
| 396 |
+
"learning_rate": 0.00013582537296550986,
|
| 397 |
+
"loss": 1.6967,
|
| 398 |
+
"step": 285
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 6.17,
|
| 402 |
+
"learning_rate": 0.00012762354833724559,
|
| 403 |
+
"loss": 1.4993,
|
| 404 |
+
"step": 290
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 6.28,
|
| 408 |
+
"learning_rate": 0.0001128900706169339,
|
| 409 |
+
"loss": 1.3665,
|
| 410 |
+
"step": 295
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 6.38,
|
| 414 |
+
"learning_rate": 9.325537321665346e-05,
|
| 415 |
+
"loss": 1.5098,
|
| 416 |
+
"step": 300
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 6.49,
|
| 420 |
+
"learning_rate": 7.089226742272658e-05,
|
| 421 |
+
"loss": 1.6949,
|
| 422 |
+
"step": 305
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 6.6,
|
| 426 |
+
"learning_rate": 4.827549515124539e-05,
|
| 427 |
+
"loss": 1.5465,
|
| 428 |
+
"step": 310
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 6.7,
|
| 432 |
+
"learning_rate": 2.7907869511566348e-05,
|
| 433 |
+
"loss": 1.506,
|
| 434 |
+
"step": 315
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 6.81,
|
| 438 |
+
"learning_rate": 1.2043308960555334e-05,
|
| 439 |
+
"loss": 1.6257,
|
| 440 |
+
"step": 320
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 6.91,
|
| 444 |
+
"learning_rate": 2.437414591269752e-06,
|
| 445 |
+
"loss": 1.3859,
|
| 446 |
+
"step": 325
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 7.0,
|
| 450 |
+
"eval_loss": 2.334944009780884,
|
| 451 |
+
"eval_runtime": 1.0709,
|
| 452 |
+
"eval_samples_per_second": 75.638,
|
| 453 |
+
"eval_steps_per_second": 10.272,
|
| 454 |
+
"step": 329
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 7.02,
|
| 458 |
+
"learning_rate": 1.5319212645167772e-07,
|
| 459 |
+
"loss": 1.5912,
|
| 460 |
+
"step": 330
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 7.13,
|
| 464 |
+
"learning_rate": 5.443417773996994e-06,
|
| 465 |
+
"loss": 1.4726,
|
| 466 |
+
"step": 335
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 7.23,
|
| 470 |
+
"learning_rate": 1.772266555255011e-05,
|
| 471 |
+
"loss": 1.2431,
|
| 472 |
+
"step": 340
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 7.34,
|
| 476 |
+
"learning_rate": 3.563209159419346e-05,
|
| 477 |
+
"loss": 1.3668,
|
| 478 |
+
"step": 345
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 7.45,
|
| 482 |
+
"learning_rate": 5.718980627559723e-05,
|
| 483 |
+
"loss": 1.3476,
|
| 484 |
+
"step": 350
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 7.55,
|
| 488 |
+
"learning_rate": 8.001019372440265e-05,
|
| 489 |
+
"loss": 1.2561,
|
| 490 |
+
"step": 355
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 7.66,
|
| 494 |
+
"learning_rate": 0.00010156790840580641,
|
| 495 |
+
"loss": 1.6616,
|
| 496 |
+
"step": 360
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 7.77,
|
| 500 |
+
"learning_rate": 0.0001194773344474498,
|
| 501 |
+
"loss": 1.4607,
|
| 502 |
+
"step": 365
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 7.87,
|
| 506 |
+
"learning_rate": 0.00013175658222600294,
|
| 507 |
+
"loss": 1.3461,
|
| 508 |
+
"step": 370
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 7.98,
|
| 512 |
+
"learning_rate": 0.00013704680787354832,
|
| 513 |
+
"loss": 1.3842,
|
| 514 |
+
"step": 375
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 8.0,
|
| 518 |
+
"eval_loss": 2.3194692134857178,
|
| 519 |
+
"eval_runtime": 1.0661,
|
| 520 |
+
"eval_samples_per_second": 75.98,
|
| 521 |
+
"eval_steps_per_second": 10.318,
|
| 522 |
+
"step": 376
|
| 523 |
}
|
| 524 |
],
|
| 525 |
+
"max_steps": 2867,
|
| 526 |
+
"num_train_epochs": 61,
|
| 527 |
+
"total_flos": 391938048000000.0,
|
| 528 |
"trial_name": null,
|
| 529 |
"trial_params": null
|
| 530 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7042b00f38d89f1720e38aa30d3c0f04599b070773bf507b3a660f4d7684fea2
|
| 3 |
+
size 2863
|