Training in progress, step 39, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 43122580
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7f31bd243a6ffcf6a5082ed62d1e8baa98f7a561e7dcf10fd8ad53ccccea549
|
| 3 |
size 43122580
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5b646d94c8ce9e19d2d7de66c5cb6b11a12f9387acbdc702e8c6219ac517632
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 13,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -45,6 +45,21 @@
|
|
| 45 |
"eval_samples_per_second": 27.453,
|
| 46 |
"eval_steps_per_second": 13.726,
|
| 47 |
"step": 26
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
}
|
| 49 |
],
|
| 50 |
"logging_steps": 10,
|
|
@@ -64,7 +79,7 @@
|
|
| 64 |
"attributes": {}
|
| 65 |
}
|
| 66 |
},
|
| 67 |
-
"total_flos":
|
| 68 |
"train_batch_size": 2,
|
| 69 |
"trial_name": null,
|
| 70 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.014535967200894522,
|
| 5 |
"eval_steps": 13,
|
| 6 |
+
"global_step": 39,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 45 |
"eval_samples_per_second": 27.453,
|
| 46 |
"eval_steps_per_second": 13.726,
|
| 47 |
"step": 26
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.011181513231457324,
|
| 51 |
+
"grad_norm": NaN,
|
| 52 |
+
"learning_rate": 8.263518223330697e-05,
|
| 53 |
+
"loss": 0.2226,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.014535967200894522,
|
| 58 |
+
"eval_loss": NaN,
|
| 59 |
+
"eval_runtime": 41.1646,
|
| 60 |
+
"eval_samples_per_second": 27.451,
|
| 61 |
+
"eval_steps_per_second": 13.725,
|
| 62 |
+
"step": 39
|
| 63 |
}
|
| 64 |
],
|
| 65 |
"logging_steps": 10,
|
|
|
|
| 79 |
"attributes": {}
|
| 80 |
}
|
| 81 |
},
|
| 82 |
+
"total_flos": 8106097760010240.0,
|
| 83 |
"train_batch_size": 2,
|
| 84 |
"trial_name": null,
|
| 85 |
"trial_params": null
|