Training in progress, step 3080, 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 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4687ee92319fcb7b22cc04cabdab73e214971d07d646fe8699e5d5a78cd5db9
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25cdea20690c9d3c7747b6405fb7702014d2373d0cf64a030ce8b9a6c89b94ae
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3dd6d049158f43f33718b365820c014eb43d6e5f6acd61538779cf43524a766c
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 23.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -5534,6 +5534,24 @@
|
|
| 5534 |
"mean_token_accuracy": 0.650464779138565,
|
| 5535 |
"num_tokens": 11196788.0,
|
| 5536 |
"step": 3070
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5537 |
}
|
| 5538 |
],
|
| 5539 |
"logging_steps": 5,
|
|
@@ -5553,7 +5571,7 @@
|
|
| 5553 |
"attributes": {}
|
| 5554 |
}
|
| 5555 |
},
|
| 5556 |
-
"total_flos": 5.
|
| 5557 |
"train_batch_size": 4,
|
| 5558 |
"trial_name": null,
|
| 5559 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 23.692307692307693,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3080,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5534 |
"mean_token_accuracy": 0.650464779138565,
|
| 5535 |
"num_tokens": 11196788.0,
|
| 5536 |
"step": 3070
|
| 5537 |
+
},
|
| 5538 |
+
{
|
| 5539 |
+
"epoch": 23.653846153846153,
|
| 5540 |
+
"grad_norm": 0.0,
|
| 5541 |
+
"learning_rate": 3.463e-05,
|
| 5542 |
+
"loss": 1.7563,
|
| 5543 |
+
"mean_token_accuracy": 0.6483624398708343,
|
| 5544 |
+
"num_tokens": 11214549.0,
|
| 5545 |
+
"step": 3075
|
| 5546 |
+
},
|
| 5547 |
+
{
|
| 5548 |
+
"epoch": 23.692307692307693,
|
| 5549 |
+
"grad_norm": 0.0,
|
| 5550 |
+
"learning_rate": 3.4605000000000005e-05,
|
| 5551 |
+
"loss": 1.6635,
|
| 5552 |
+
"mean_token_accuracy": 0.6658029884099961,
|
| 5553 |
+
"num_tokens": 11233473.0,
|
| 5554 |
+
"step": 3080
|
| 5555 |
}
|
| 5556 |
],
|
| 5557 |
"logging_steps": 5,
|
|
|
|
| 5571 |
"attributes": {}
|
| 5572 |
}
|
| 5573 |
},
|
| 5574 |
+
"total_flos": 5.692232392704e+17,
|
| 5575 |
"train_batch_size": 4,
|
| 5576 |
"trial_name": null,
|
| 5577 |
"trial_params": null
|