Upload folder using huggingface_hub
Browse files- pytorch_model.bin +1 -1
- trainer_state.json +7 -55
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 307910149
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed5fa3e7c123bbdba3ea62ac220a5d6157847d2b375afd7e509f7066e6f69358
|
| 3 |
size 307910149
|
trainer_state.json
CHANGED
|
@@ -1,73 +1,25 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 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": 0.
|
| 13 |
-
"learning_rate":
|
| 14 |
-
"loss":
|
| 15 |
"step": 500
|
| 16 |
-
},
|
| 17 |
-
{
|
| 18 |
-
"epoch": 0.22,
|
| 19 |
-
"learning_rate": 3.111111111111112e-05,
|
| 20 |
-
"loss": 2.4022,
|
| 21 |
-
"step": 1000
|
| 22 |
-
},
|
| 23 |
-
{
|
| 24 |
-
"epoch": 0.33,
|
| 25 |
-
"learning_rate": 2.6666666666666667e-05,
|
| 26 |
-
"loss": 2.189,
|
| 27 |
-
"step": 1500
|
| 28 |
-
},
|
| 29 |
-
{
|
| 30 |
-
"epoch": 0.44,
|
| 31 |
-
"learning_rate": 2.2222222222222227e-05,
|
| 32 |
-
"loss": 2.0362,
|
| 33 |
-
"step": 2000
|
| 34 |
-
},
|
| 35 |
-
{
|
| 36 |
-
"epoch": 0.56,
|
| 37 |
-
"learning_rate": 1.7777777777777777e-05,
|
| 38 |
-
"loss": 1.8886,
|
| 39 |
-
"step": 2500
|
| 40 |
-
},
|
| 41 |
-
{
|
| 42 |
-
"epoch": 0.67,
|
| 43 |
-
"learning_rate": 1.3333333333333333e-05,
|
| 44 |
-
"loss": 1.8523,
|
| 45 |
-
"step": 3000
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.78,
|
| 49 |
-
"learning_rate": 8.888888888888888e-06,
|
| 50 |
-
"loss": 1.8176,
|
| 51 |
-
"step": 3500
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.89,
|
| 55 |
-
"learning_rate": 4.444444444444444e-06,
|
| 56 |
-
"loss": 1.7479,
|
| 57 |
-
"step": 4000
|
| 58 |
-
},
|
| 59 |
-
{
|
| 60 |
-
"epoch": 1.0,
|
| 61 |
-
"learning_rate": 0.0,
|
| 62 |
-
"loss": 1.82,
|
| 63 |
-
"step": 4500
|
| 64 |
}
|
| 65 |
],
|
| 66 |
"logging_steps": 500,
|
| 67 |
-
"max_steps":
|
| 68 |
"num_train_epochs": 1,
|
| 69 |
"save_steps": 300,
|
| 70 |
-
"total_flos":
|
| 71 |
"trial_name": null,
|
| 72 |
"trial_params": null
|
| 73 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.7109004739336493,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 600,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.59,
|
| 13 |
+
"learning_rate": 1.2227488151658767e-05,
|
| 14 |
+
"loss": 2.8753,
|
| 15 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
}
|
| 17 |
],
|
| 18 |
"logging_steps": 500,
|
| 19 |
+
"max_steps": 844,
|
| 20 |
"num_train_epochs": 1,
|
| 21 |
"save_steps": 300,
|
| 22 |
+
"total_flos": 3495926540402688.0,
|
| 23 |
"trial_name": null,
|
| 24 |
"trial_params": null
|
| 25 |
}
|