smallfiles
Browse files- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +64 -0
- training_args.bin +3 -0
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a2b01e91e2ab47dbf3628c8da7c816bb0898ba0af4e57d7f0694019315e9fd8
|
| 3 |
+
size 14503
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9aa9c819d4d7b55d4864b449e3db356ae0bac99b6bb47a88b5517a98d7f2624b
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 93.61702127659575,
|
| 5 |
+
"global_step": 4400,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 10.64,
|
| 12 |
+
"learning_rate": 4.9444444444444446e-05,
|
| 13 |
+
"loss": 1.6101,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 21.28,
|
| 18 |
+
"learning_rate": 4.666666666666667e-05,
|
| 19 |
+
"loss": 0.2288,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 31.91,
|
| 24 |
+
"learning_rate": 4.388888888888889e-05,
|
| 25 |
+
"loss": 0.1346,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 42.55,
|
| 30 |
+
"learning_rate": 4.111111111111111e-05,
|
| 31 |
+
"loss": 0.1033,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 53.19,
|
| 36 |
+
"learning_rate": 3.8333333333333334e-05,
|
| 37 |
+
"loss": 0.0754,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 63.83,
|
| 42 |
+
"learning_rate": 3.555555555555556e-05,
|
| 43 |
+
"loss": 0.0536,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 74.47,
|
| 48 |
+
"learning_rate": 3.277777777777778e-05,
|
| 49 |
+
"loss": 0.0433,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 85.11,
|
| 54 |
+
"learning_rate": 3e-05,
|
| 55 |
+
"loss": 0.0455,
|
| 56 |
+
"step": 4000
|
| 57 |
+
}
|
| 58 |
+
],
|
| 59 |
+
"max_steps": 9400,
|
| 60 |
+
"num_train_epochs": 200,
|
| 61 |
+
"total_flos": 5549594939136000.0,
|
| 62 |
+
"trial_name": null,
|
| 63 |
+
"trial_params": null
|
| 64 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1dc45817694681223022102177a55ffe1669e9d9bdf750b9ca63d264f2ba248a
|
| 3 |
+
size 3247
|