Training in progress, step 4120, 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 sha256:35fda0f1844b0460d6eae9750fa3ad261fe789cc6e12814c73233b0d05c8bf82
|
| 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 sha256:65974f1615049dff11abc0e418414d7b14d50469d92827499196ed5f9624f536
|
| 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:b94150969cfeebbe95bb20c05a897983559e93d7ca0aceec6b7290fe043974ac
|
| 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": 31.
|
| 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,
|
|
@@ -7406,6 +7406,24 @@
|
|
| 7406 |
"mean_token_accuracy": 0.6461383640766144,
|
| 7407 |
"num_tokens": 14989504.0,
|
| 7408 |
"step": 4110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7409 |
}
|
| 7410 |
],
|
| 7411 |
"logging_steps": 5,
|
|
@@ -7425,7 +7443,7 @@
|
|
| 7425 |
"attributes": {}
|
| 7426 |
}
|
| 7427 |
},
|
| 7428 |
-
"total_flos": 7.
|
| 7429 |
"train_batch_size": 4,
|
| 7430 |
"trial_name": null,
|
| 7431 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 31.692307692307693,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4120,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7406 |
"mean_token_accuracy": 0.6461383640766144,
|
| 7407 |
"num_tokens": 14989504.0,
|
| 7408 |
"step": 4110
|
| 7409 |
+
},
|
| 7410 |
+
{
|
| 7411 |
+
"epoch": 31.653846153846153,
|
| 7412 |
+
"grad_norm": 0.0,
|
| 7413 |
+
"learning_rate": 2.943e-05,
|
| 7414 |
+
"loss": 1.83,
|
| 7415 |
+
"mean_token_accuracy": 0.6284946590662003,
|
| 7416 |
+
"num_tokens": 15006774.0,
|
| 7417 |
+
"step": 4115
|
| 7418 |
+
},
|
| 7419 |
+
{
|
| 7420 |
+
"epoch": 31.692307692307693,
|
| 7421 |
+
"grad_norm": 0.0,
|
| 7422 |
+
"learning_rate": 2.9405e-05,
|
| 7423 |
+
"loss": 1.7556,
|
| 7424 |
+
"mean_token_accuracy": 0.646930256485939,
|
| 7425 |
+
"num_tokens": 15025098.0,
|
| 7426 |
+
"step": 4120
|
| 7427 |
}
|
| 7428 |
],
|
| 7429 |
"logging_steps": 5,
|
|
|
|
| 7443 |
"attributes": {}
|
| 7444 |
}
|
| 7445 |
},
|
| 7446 |
+
"total_flos": 7.614897013481472e+17,
|
| 7447 |
"train_batch_size": 4,
|
| 7448 |
"trial_name": null,
|
| 7449 |
"trial_params": null
|