Commit
·
0a238b6
1
Parent(s):
204fd78
huggingartists
Browse files- README.md +3 -3
- evaluation.txt +1 -1
- flax_model.msgpack +1 -1
- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +539 -7
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
| 45 |
dataset = load_dataset("huggingartists/oxxxymiron")
|
| 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 Oxxxymiron'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/oxxxymiron")
|
| 46 |
```
|
| 47 |
|
| 48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/if83r8sb/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 Oxxxymiron's lyrics.
|
| 53 |
|
| 54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/s58wdkfz) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/s58wdkfz/artifacts) is logged and versioned.
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss": 1.
|
|
|
|
| 1 |
+
{"eval_loss": 1.3110859394073486, "eval_runtime": 18.5351, "eval_samples_per_second": 20.825, "eval_steps_per_second": 2.644, "epoch": 26.0}
|
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:bf04b5cb92f0bb037efcff6106efd6559eadeb2c169561274b38adf7974d3cbd
|
| 3 |
size 497764120
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 995604017
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89bd3fcc9080941291eb43d62d53800524426bd1841ce2e59ad94d37b402ee47
|
| 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 sha256:8b078eadcf9ca889f51cd804d94e22e90d64d6befb42b2adc89663598895f61d
|
| 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 14439
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c93f956bb61c562ef5de6ecf68f0acb1e428bb13e97ddfd9eb68fef96714fcef
|
| 3 |
size 14439
|
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 sha256:40aa28790758cc10852db2e41872a7c552d32089589ee1f68283d1cfcd6cf1da
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "output/oxxxymiron/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -4982,11 +4982,543 @@
|
|
| 4982 |
"eval_samples_per_second": 20.897,
|
| 4983 |
"eval_steps_per_second": 2.629,
|
| 4984 |
"step": 4144
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4985 |
}
|
| 4986 |
],
|
| 4987 |
-
"max_steps":
|
| 4988 |
-
"num_train_epochs":
|
| 4989 |
-
"total_flos":
|
| 4990 |
"trial_name": null,
|
| 4991 |
"trial_params": null
|
| 4992 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.3110859394073486,
|
| 3 |
+
"best_model_checkpoint": "output/oxxxymiron/checkpoint-4573",
|
| 4 |
+
"epoch": 17.0,
|
| 5 |
+
"global_step": 4573,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 4982 |
"eval_samples_per_second": 20.897,
|
| 4983 |
"eval_steps_per_second": 2.629,
|
| 4984 |
"step": 4144
|
| 4985 |
+
},
|
| 4986 |
+
{
|
| 4987 |
+
"epoch": 15.41,
|
| 4988 |
+
"learning_rate": 4.923820788333643e-05,
|
| 4989 |
+
"loss": 1.4417,
|
| 4990 |
+
"step": 4145
|
| 4991 |
+
},
|
| 4992 |
+
{
|
| 4993 |
+
"epoch": 15.43,
|
| 4994 |
+
"learning_rate": 5.311198428226757e-05,
|
| 4995 |
+
"loss": 1.5224,
|
| 4996 |
+
"step": 4150
|
| 4997 |
+
},
|
| 4998 |
+
{
|
| 4999 |
+
"epoch": 15.45,
|
| 5000 |
+
"learning_rate": 5.7038557476801184e-05,
|
| 5001 |
+
"loss": 1.4984,
|
| 5002 |
+
"step": 4155
|
| 5003 |
+
},
|
| 5004 |
+
{
|
| 5005 |
+
"epoch": 15.46,
|
| 5006 |
+
"learning_rate": 6.100454224793001e-05,
|
| 5007 |
+
"loss": 1.4427,
|
| 5008 |
+
"step": 4160
|
| 5009 |
+
},
|
| 5010 |
+
{
|
| 5011 |
+
"epoch": 15.48,
|
| 5012 |
+
"learning_rate": 6.49964190272892e-05,
|
| 5013 |
+
"loss": 1.4789,
|
| 5014 |
+
"step": 4165
|
| 5015 |
+
},
|
| 5016 |
+
{
|
| 5017 |
+
"epoch": 15.5,
|
| 5018 |
+
"learning_rate": 6.900057998375254e-05,
|
| 5019 |
+
"loss": 1.5665,
|
| 5020 |
+
"step": 4170
|
| 5021 |
+
},
|
| 5022 |
+
{
|
| 5023 |
+
"epoch": 15.52,
|
| 5024 |
+
"learning_rate": 7.300337541089789e-05,
|
| 5025 |
+
"loss": 1.5002,
|
| 5026 |
+
"step": 4175
|
| 5027 |
+
},
|
| 5028 |
+
{
|
| 5029 |
+
"epoch": 15.54,
|
| 5030 |
+
"learning_rate": 7.699116025723293e-05,
|
| 5031 |
+
"loss": 1.4668,
|
| 5032 |
+
"step": 4180
|
| 5033 |
+
},
|
| 5034 |
+
{
|
| 5035 |
+
"epoch": 15.56,
|
| 5036 |
+
"learning_rate": 8.09503406405399e-05,
|
| 5037 |
+
"loss": 1.3757,
|
| 5038 |
+
"step": 4185
|
| 5039 |
+
},
|
| 5040 |
+
{
|
| 5041 |
+
"epoch": 15.58,
|
| 5042 |
+
"learning_rate": 8.48674201878012e-05,
|
| 5043 |
+
"loss": 1.4722,
|
| 5044 |
+
"step": 4190
|
| 5045 |
+
},
|
| 5046 |
+
{
|
| 5047 |
+
"epoch": 15.59,
|
| 5048 |
+
"learning_rate": 8.872904604271726e-05,
|
| 5049 |
+
"loss": 1.4961,
|
| 5050 |
+
"step": 4195
|
| 5051 |
+
},
|
| 5052 |
+
{
|
| 5053 |
+
"epoch": 15.61,
|
| 5054 |
+
"learning_rate": 9.252205438400528e-05,
|
| 5055 |
+
"loss": 1.4798,
|
| 5056 |
+
"step": 4200
|
| 5057 |
+
},
|
| 5058 |
+
{
|
| 5059 |
+
"epoch": 15.63,
|
| 5060 |
+
"learning_rate": 9.623351529928802e-05,
|
| 5061 |
+
"loss": 1.5392,
|
| 5062 |
+
"step": 4205
|
| 5063 |
+
},
|
| 5064 |
+
{
|
| 5065 |
+
"epoch": 15.65,
|
| 5066 |
+
"learning_rate": 9.985077686162523e-05,
|
| 5067 |
+
"loss": 1.5653,
|
| 5068 |
+
"step": 4210
|
| 5069 |
+
},
|
| 5070 |
+
{
|
| 5071 |
+
"epoch": 15.67,
|
| 5072 |
+
"learning_rate": 0.00010336150825841603,
|
| 5073 |
+
"loss": 1.4743,
|
| 5074 |
+
"step": 4215
|
| 5075 |
+
},
|
| 5076 |
+
{
|
| 5077 |
+
"epoch": 15.69,
|
| 5078 |
+
"learning_rate": 0.00010675374182567242,
|
| 5079 |
+
"loss": 1.4201,
|
| 5080 |
+
"step": 4220
|
| 5081 |
+
},
|
| 5082 |
+
{
|
| 5083 |
+
"epoch": 15.71,
|
| 5084 |
+
"learning_rate": 0.00011001591384435138,
|
| 5085 |
+
"loss": 1.3889,
|
| 5086 |
+
"step": 4225
|
| 5087 |
+
},
|
| 5088 |
+
{
|
| 5089 |
+
"epoch": 15.72,
|
| 5090 |
+
"learning_rate": 0.00011313690395969416,
|
| 5091 |
+
"loss": 1.4913,
|
| 5092 |
+
"step": 4230
|
| 5093 |
+
},
|
| 5094 |
+
{
|
| 5095 |
+
"epoch": 15.74,
|
| 5096 |
+
"learning_rate": 0.00011610607308918656,
|
| 5097 |
+
"loss": 1.3722,
|
| 5098 |
+
"step": 4235
|
| 5099 |
+
},
|
| 5100 |
+
{
|
| 5101 |
+
"epoch": 15.76,
|
| 5102 |
+
"learning_rate": 0.00011891329968992182,
|
| 5103 |
+
"loss": 1.4133,
|
| 5104 |
+
"step": 4240
|
| 5105 |
+
},
|
| 5106 |
+
{
|
| 5107 |
+
"epoch": 15.78,
|
| 5108 |
+
"learning_rate": 0.0001215490142617292,
|
| 5109 |
+
"loss": 1.36,
|
| 5110 |
+
"step": 4245
|
| 5111 |
+
},
|
| 5112 |
+
{
|
| 5113 |
+
"epoch": 15.8,
|
| 5114 |
+
"learning_rate": 0.00012400423196845864,
|
| 5115 |
+
"loss": 1.361,
|
| 5116 |
+
"step": 4250
|
| 5117 |
+
},
|
| 5118 |
+
{
|
| 5119 |
+
"epoch": 15.82,
|
| 5120 |
+
"learning_rate": 0.00012627058326621316,
|
| 5121 |
+
"loss": 1.542,
|
| 5122 |
+
"step": 4255
|
| 5123 |
+
},
|
| 5124 |
+
{
|
| 5125 |
+
"epoch": 15.84,
|
| 5126 |
+
"learning_rate": 0.0001283403424341258,
|
| 5127 |
+
"loss": 1.4983,
|
| 5128 |
+
"step": 4260
|
| 5129 |
+
},
|
| 5130 |
+
{
|
| 5131 |
+
"epoch": 15.86,
|
| 5132 |
+
"learning_rate": 0.00013020645391041629,
|
| 5133 |
+
"loss": 1.4985,
|
| 5134 |
+
"step": 4265
|
| 5135 |
+
},
|
| 5136 |
+
{
|
| 5137 |
+
"epoch": 15.87,
|
| 5138 |
+
"learning_rate": 0.00013186255634396195,
|
| 5139 |
+
"loss": 1.4767,
|
| 5140 |
+
"step": 4270
|
| 5141 |
+
},
|
| 5142 |
+
{
|
| 5143 |
+
"epoch": 15.89,
|
| 5144 |
+
"learning_rate": 0.00013330300427938103,
|
| 5145 |
+
"loss": 1.4258,
|
| 5146 |
+
"step": 4275
|
| 5147 |
+
},
|
| 5148 |
+
{
|
| 5149 |
+
"epoch": 15.91,
|
| 5150 |
+
"learning_rate": 0.00013452288740171763,
|
| 5151 |
+
"loss": 1.4773,
|
| 5152 |
+
"step": 4280
|
| 5153 |
+
},
|
| 5154 |
+
{
|
| 5155 |
+
"epoch": 15.93,
|
| 5156 |
+
"learning_rate": 0.00013551804727511717,
|
| 5157 |
+
"loss": 1.462,
|
| 5158 |
+
"step": 4285
|
| 5159 |
+
},
|
| 5160 |
+
{
|
| 5161 |
+
"epoch": 15.95,
|
| 5162 |
+
"learning_rate": 0.0001362850915184393,
|
| 5163 |
+
"loss": 1.4688,
|
| 5164 |
+
"step": 4290
|
| 5165 |
+
},
|
| 5166 |
+
{
|
| 5167 |
+
"epoch": 15.97,
|
| 5168 |
+
"learning_rate": 0.00013682140536947865,
|
| 5169 |
+
"loss": 1.5146,
|
| 5170 |
+
"step": 4295
|
| 5171 |
+
},
|
| 5172 |
+
{
|
| 5173 |
+
"epoch": 15.99,
|
| 5174 |
+
"learning_rate": 0.00013712516059837763,
|
| 5175 |
+
"loss": 1.5462,
|
| 5176 |
+
"step": 4300
|
| 5177 |
+
},
|
| 5178 |
+
{
|
| 5179 |
+
"epoch": 16.0,
|
| 5180 |
+
"eval_loss": 1.3411859273910522,
|
| 5181 |
+
"eval_runtime": 18.5136,
|
| 5182 |
+
"eval_samples_per_second": 20.85,
|
| 5183 |
+
"eval_steps_per_second": 2.647,
|
| 5184 |
+
"step": 4304
|
| 5185 |
+
},
|
| 5186 |
+
{
|
| 5187 |
+
"epoch": 16.0,
|
| 5188 |
+
"learning_rate": 0.00013719532173984305,
|
| 5189 |
+
"loss": 1.3395,
|
| 5190 |
+
"step": 4305
|
| 5191 |
+
},
|
| 5192 |
+
{
|
| 5193 |
+
"epoch": 16.02,
|
| 5194 |
+
"learning_rate": 0.00013703164962292424,
|
| 5195 |
+
"loss": 1.3995,
|
| 5196 |
+
"step": 4310
|
| 5197 |
+
},
|
| 5198 |
+
{
|
| 5199 |
+
"epoch": 16.04,
|
| 5200 |
+
"learning_rate": 0.00013663470218631772,
|
| 5201 |
+
"loss": 1.4118,
|
| 5202 |
+
"step": 4315
|
| 5203 |
+
},
|
| 5204 |
+
{
|
| 5205 |
+
"epoch": 16.06,
|
| 5206 |
+
"learning_rate": 0.00013600583257642132,
|
| 5207 |
+
"loss": 1.3778,
|
| 5208 |
+
"step": 4320
|
| 5209 |
+
},
|
| 5210 |
+
{
|
| 5211 |
+
"epoch": 16.08,
|
| 5212 |
+
"learning_rate": 0.00013514718453461912,
|
| 5213 |
+
"loss": 1.4416,
|
| 5214 |
+
"step": 4325
|
| 5215 |
+
},
|
| 5216 |
+
{
|
| 5217 |
+
"epoch": 16.1,
|
| 5218 |
+
"learning_rate": 0.0001340616850895236,
|
| 5219 |
+
"loss": 1.4926,
|
| 5220 |
+
"step": 4330
|
| 5221 |
+
},
|
| 5222 |
+
{
|
| 5223 |
+
"epoch": 16.12,
|
| 5224 |
+
"learning_rate": 0.00013275303457908525,
|
| 5225 |
+
"loss": 1.4668,
|
| 5226 |
+
"step": 4335
|
| 5227 |
+
},
|
| 5228 |
+
{
|
| 5229 |
+
"epoch": 16.13,
|
| 5230 |
+
"learning_rate": 0.00013122569403658038,
|
| 5231 |
+
"loss": 1.3931,
|
| 5232 |
+
"step": 4340
|
| 5233 |
+
},
|
| 5234 |
+
{
|
| 5235 |
+
"epoch": 16.15,
|
| 5236 |
+
"learning_rate": 0.00012948486998348453,
|
| 5237 |
+
"loss": 1.403,
|
| 5238 |
+
"step": 4345
|
| 5239 |
+
},
|
| 5240 |
+
{
|
| 5241 |
+
"epoch": 16.17,
|
| 5242 |
+
"learning_rate": 0.0001275364966810606,
|
| 5243 |
+
"loss": 1.3802,
|
| 5244 |
+
"step": 4350
|
| 5245 |
+
},
|
| 5246 |
+
{
|
| 5247 |
+
"epoch": 16.19,
|
| 5248 |
+
"learning_rate": 0.00012538721590117088,
|
| 5249 |
+
"loss": 1.429,
|
| 5250 |
+
"step": 4355
|
| 5251 |
+
},
|
| 5252 |
+
{
|
| 5253 |
+
"epoch": 16.21,
|
| 5254 |
+
"learning_rate": 0.00012304435428527134,
|
| 5255 |
+
"loss": 1.4773,
|
| 5256 |
+
"step": 4360
|
| 5257 |
+
},
|
| 5258 |
+
{
|
| 5259 |
+
"epoch": 16.23,
|
| 5260 |
+
"learning_rate": 0.00012051589836876666,
|
| 5261 |
+
"loss": 1.3717,
|
| 5262 |
+
"step": 4365
|
| 5263 |
+
},
|
| 5264 |
+
{
|
| 5265 |
+
"epoch": 16.25,
|
| 5266 |
+
"learning_rate": 0.00011781046735586077,
|
| 5267 |
+
"loss": 1.4166,
|
| 5268 |
+
"step": 4370
|
| 5269 |
+
},
|
| 5270 |
+
{
|
| 5271 |
+
"epoch": 16.26,
|
| 5272 |
+
"learning_rate": 0.00011493728373772612,
|
| 5273 |
+
"loss": 1.432,
|
| 5274 |
+
"step": 4375
|
| 5275 |
+
},
|
| 5276 |
+
{
|
| 5277 |
+
"epoch": 16.28,
|
| 5278 |
+
"learning_rate": 0.00011190614185412497,
|
| 5279 |
+
"loss": 1.4722,
|
| 5280 |
+
"step": 4380
|
| 5281 |
+
},
|
| 5282 |
+
{
|
| 5283 |
+
"epoch": 16.3,
|
| 5284 |
+
"learning_rate": 0.00010872737450568259,
|
| 5285 |
+
"loss": 1.3411,
|
| 5286 |
+
"step": 4385
|
| 5287 |
+
},
|
| 5288 |
+
{
|
| 5289 |
+
"epoch": 16.32,
|
| 5290 |
+
"learning_rate": 0.00010541181773059928,
|
| 5291 |
+
"loss": 1.4268,
|
| 5292 |
+
"step": 4390
|
| 5293 |
+
},
|
| 5294 |
+
{
|
| 5295 |
+
"epoch": 16.34,
|
| 5296 |
+
"learning_rate": 0.00010197077386589103,
|
| 5297 |
+
"loss": 1.4257,
|
| 5298 |
+
"step": 4395
|
| 5299 |
+
},
|
| 5300 |
+
{
|
| 5301 |
+
"epoch": 16.36,
|
| 5302 |
+
"learning_rate": 9.841597301907411e-05,
|
| 5303 |
+
"loss": 1.4367,
|
| 5304 |
+
"step": 4400
|
| 5305 |
+
},
|
| 5306 |
+
{
|
| 5307 |
+
"epoch": 16.38,
|
| 5308 |
+
"learning_rate": 9.475953308163089e-05,
|
| 5309 |
+
"loss": 1.388,
|
| 5310 |
+
"step": 4405
|
| 5311 |
+
},
|
| 5312 |
+
{
|
| 5313 |
+
"epoch": 16.39,
|
| 5314 |
+
"learning_rate": 9.101391842055883e-05,
|
| 5315 |
+
"loss": 1.4486,
|
| 5316 |
+
"step": 4410
|
| 5317 |
+
},
|
| 5318 |
+
{
|
| 5319 |
+
"epoch": 16.41,
|
| 5320 |
+
"learning_rate": 8.719189738884117e-05,
|
| 5321 |
+
"loss": 1.3824,
|
| 5322 |
+
"step": 4415
|
| 5323 |
+
},
|
| 5324 |
+
{
|
| 5325 |
+
"epoch": 16.43,
|
| 5326 |
+
"learning_rate": 8.330649879965051e-05,
|
| 5327 |
+
"loss": 1.4313,
|
| 5328 |
+
"step": 4420
|
| 5329 |
+
},
|
| 5330 |
+
{
|
| 5331 |
+
"epoch": 16.45,
|
| 5332 |
+
"learning_rate": 7.937096751268169e-05,
|
| 5333 |
+
"loss": 1.3933,
|
| 5334 |
+
"step": 4425
|
| 5335 |
+
},
|
| 5336 |
+
{
|
| 5337 |
+
"epoch": 16.47,
|
| 5338 |
+
"learning_rate": 7.539871928400956e-05,
|
| 5339 |
+
"loss": 1.4352,
|
| 5340 |
+
"step": 4430
|
| 5341 |
+
},
|
| 5342 |
+
{
|
| 5343 |
+
"epoch": 16.49,
|
| 5344 |
+
"learning_rate": 7.140329503337758e-05,
|
| 5345 |
+
"loss": 1.4244,
|
| 5346 |
+
"step": 4435
|
| 5347 |
+
},
|
| 5348 |
+
{
|
| 5349 |
+
"epoch": 16.51,
|
| 5350 |
+
"learning_rate": 6.739831468481779e-05,
|
| 5351 |
+
"loss": 1.4062,
|
| 5352 |
+
"step": 4440
|
| 5353 |
+
},
|
| 5354 |
+
{
|
| 5355 |
+
"epoch": 16.52,
|
| 5356 |
+
"learning_rate": 6.33974307379626e-05,
|
| 5357 |
+
"loss": 1.3753,
|
| 5358 |
+
"step": 4445
|
| 5359 |
+
},
|
| 5360 |
+
{
|
| 5361 |
+
"epoch": 16.54,
|
| 5362 |
+
"learning_rate": 5.94142817282949e-05,
|
| 5363 |
+
"loss": 1.3918,
|
| 5364 |
+
"step": 4450
|
| 5365 |
+
},
|
| 5366 |
+
{
|
| 5367 |
+
"epoch": 16.56,
|
| 5368 |
+
"learning_rate": 5.546244573501996e-05,
|
| 5369 |
+
"loss": 1.423,
|
| 5370 |
+
"step": 4455
|
| 5371 |
+
},
|
| 5372 |
+
{
|
| 5373 |
+
"epoch": 16.58,
|
| 5374 |
+
"learning_rate": 5.155539409500841e-05,
|
| 5375 |
+
"loss": 1.4141,
|
| 5376 |
+
"step": 4460
|
| 5377 |
+
},
|
| 5378 |
+
{
|
| 5379 |
+
"epoch": 16.6,
|
| 5380 |
+
"learning_rate": 4.7706445480618974e-05,
|
| 5381 |
+
"loss": 1.4364,
|
| 5382 |
+
"step": 4465
|
| 5383 |
+
},
|
| 5384 |
+
{
|
| 5385 |
+
"epoch": 16.62,
|
| 5386 |
+
"learning_rate": 4.3928720497937174e-05,
|
| 5387 |
+
"loss": 1.405,
|
| 5388 |
+
"step": 4470
|
| 5389 |
+
},
|
| 5390 |
+
{
|
| 5391 |
+
"epoch": 16.64,
|
| 5392 |
+
"learning_rate": 4.02350969601972e-05,
|
| 5393 |
+
"loss": 1.4752,
|
| 5394 |
+
"step": 4475
|
| 5395 |
+
},
|
| 5396 |
+
{
|
| 5397 |
+
"epoch": 16.65,
|
| 5398 |
+
"learning_rate": 3.663816598884848e-05,
|
| 5399 |
+
"loss": 1.4515,
|
| 5400 |
+
"step": 4480
|
| 5401 |
+
},
|
| 5402 |
+
{
|
| 5403 |
+
"epoch": 16.67,
|
| 5404 |
+
"learning_rate": 3.315018909193563e-05,
|
| 5405 |
+
"loss": 1.4503,
|
| 5406 |
+
"step": 4485
|
| 5407 |
+
},
|
| 5408 |
+
{
|
| 5409 |
+
"epoch": 16.69,
|
| 5410 |
+
"learning_rate": 2.9783056366075814e-05,
|
| 5411 |
+
"loss": 1.3878,
|
| 5412 |
+
"step": 4490
|
| 5413 |
+
},
|
| 5414 |
+
{
|
| 5415 |
+
"epoch": 16.71,
|
| 5416 |
+
"learning_rate": 2.6548245964540616e-05,
|
| 5417 |
+
"loss": 1.3826,
|
| 5418 |
+
"step": 4495
|
| 5419 |
+
},
|
| 5420 |
+
{
|
| 5421 |
+
"epoch": 16.73,
|
| 5422 |
+
"learning_rate": 2.345678496960497e-05,
|
| 5423 |
+
"loss": 1.3709,
|
| 5424 |
+
"step": 4500
|
| 5425 |
+
},
|
| 5426 |
+
{
|
| 5427 |
+
"epoch": 16.75,
|
| 5428 |
+
"learning_rate": 2.051921180253764e-05,
|
| 5429 |
+
"loss": 1.4434,
|
| 5430 |
+
"step": 4505
|
| 5431 |
+
},
|
| 5432 |
+
{
|
| 5433 |
+
"epoch": 16.77,
|
| 5434 |
+
"learning_rate": 1.774554029938429e-05,
|
| 5435 |
+
"loss": 1.4217,
|
| 5436 |
+
"step": 4510
|
| 5437 |
+
},
|
| 5438 |
+
{
|
| 5439 |
+
"epoch": 16.78,
|
| 5440 |
+
"learning_rate": 1.5145225574996895e-05,
|
| 5441 |
+
"loss": 1.3259,
|
| 5442 |
+
"step": 4515
|
| 5443 |
+
},
|
| 5444 |
+
{
|
| 5445 |
+
"epoch": 16.8,
|
| 5446 |
+
"learning_rate": 1.272713179167218e-05,
|
| 5447 |
+
"loss": 1.3681,
|
| 5448 |
+
"step": 4520
|
| 5449 |
+
},
|
| 5450 |
+
{
|
| 5451 |
+
"epoch": 16.82,
|
| 5452 |
+
"learning_rate": 1.0499501942287456e-05,
|
| 5453 |
+
"loss": 1.3708,
|
| 5454 |
+
"step": 4525
|
| 5455 |
+
},
|
| 5456 |
+
{
|
| 5457 |
+
"epoch": 16.84,
|
| 5458 |
+
"learning_rate": 8.469929750918058e-06,
|
| 5459 |
+
"loss": 1.4352,
|
| 5460 |
+
"step": 4530
|
| 5461 |
+
},
|
| 5462 |
+
{
|
| 5463 |
+
"epoch": 16.86,
|
| 5464 |
+
"learning_rate": 6.6453337867398825e-06,
|
| 5465 |
+
"loss": 1.4355,
|
| 5466 |
+
"step": 4535
|
| 5467 |
+
},
|
| 5468 |
+
{
|
| 5469 |
+
"epoch": 16.88,
|
| 5470 |
+
"learning_rate": 5.031933879454651e-06,
|
| 5471 |
+
"loss": 1.4338,
|
| 5472 |
+
"step": 4540
|
| 5473 |
+
},
|
| 5474 |
+
{
|
| 5475 |
+
"epoch": 16.9,
|
| 5476 |
+
"learning_rate": 3.6352299166325223e-06,
|
| 5477 |
+
"loss": 1.3822,
|
| 5478 |
+
"step": 4545
|
| 5479 |
+
},
|
| 5480 |
+
{
|
| 5481 |
+
"epoch": 16.91,
|
| 5482 |
+
"learning_rate": 2.459983095251791e-06,
|
| 5483 |
+
"loss": 1.3442,
|
| 5484 |
+
"step": 4550
|
| 5485 |
+
},
|
| 5486 |
+
{
|
| 5487 |
+
"epoch": 16.93,
|
| 5488 |
+
"learning_rate": 1.5101996913488535e-06,
|
| 5489 |
+
"loss": 1.356,
|
| 5490 |
+
"step": 4555
|
| 5491 |
+
},
|
| 5492 |
+
{
|
| 5493 |
+
"epoch": 16.95,
|
| 5494 |
+
"learning_rate": 7.891174030992353e-07,
|
| 5495 |
+
"loss": 1.3681,
|
| 5496 |
+
"step": 4560
|
| 5497 |
+
},
|
| 5498 |
+
{
|
| 5499 |
+
"epoch": 16.97,
|
| 5500 |
+
"learning_rate": 2.991943138937121e-07,
|
| 5501 |
+
"loss": 1.3964,
|
| 5502 |
+
"step": 4565
|
| 5503 |
+
},
|
| 5504 |
+
{
|
| 5505 |
+
"epoch": 16.99,
|
| 5506 |
+
"learning_rate": 4.2100513024036057e-08,
|
| 5507 |
+
"loss": 1.4004,
|
| 5508 |
+
"step": 4570
|
| 5509 |
+
},
|
| 5510 |
+
{
|
| 5511 |
+
"epoch": 17.0,
|
| 5512 |
+
"eval_loss": 1.3110859394073486,
|
| 5513 |
+
"eval_runtime": 18.5084,
|
| 5514 |
+
"eval_samples_per_second": 20.855,
|
| 5515 |
+
"eval_steps_per_second": 2.647,
|
| 5516 |
+
"step": 4573
|
| 5517 |
}
|
| 5518 |
],
|
| 5519 |
+
"max_steps": 6994,
|
| 5520 |
+
"num_train_epochs": 26,
|
| 5521 |
+
"total_flos": 4776548990976000.0,
|
| 5522 |
"trial_name": null,
|
| 5523 |
"trial_params": null
|
| 5524 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2991
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c111611d0270c2f70ae5a43dbcc59025e6535cde71a5fbf71689de64f457d265
|
| 3 |
size 2991
|