Training in progress, step 6350, 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:d5f35ef9c5bc09fc65f7b54d1782ee00bbee794825bcefcfe7d06497eba1bf1e
|
| 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:e5bc2fab9408b6589d77db4d0ff290f810c23a45577d3814e91b579fb15232c6
|
| 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 sha256:2bb7c0e738c1068a43ef000348c2f525aeda7f6242075c45ca7cba5da5b1c42a
|
| 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": 48.
|
| 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,
|
|
@@ -11420,6 +11420,24 @@
|
|
| 11420 |
"mean_token_accuracy": 0.6524953216314315,
|
| 11421 |
"num_tokens": 23120020.0,
|
| 11422 |
"step": 6340
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11423 |
}
|
| 11424 |
],
|
| 11425 |
"logging_steps": 5,
|
|
@@ -11439,7 +11457,7 @@
|
|
| 11439 |
"attributes": {}
|
| 11440 |
}
|
| 11441 |
},
|
| 11442 |
-
"total_flos": 1.
|
| 11443 |
"train_batch_size": 4,
|
| 11444 |
"trial_name": null,
|
| 11445 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 48.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6350,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11420 |
"mean_token_accuracy": 0.6524953216314315,
|
| 11421 |
"num_tokens": 23120020.0,
|
| 11422 |
"step": 6340
|
| 11423 |
+
},
|
| 11424 |
+
{
|
| 11425 |
+
"epoch": 48.80769230769231,
|
| 11426 |
+
"grad_norm": 0.0,
|
| 11427 |
+
"learning_rate": 1.828e-05,
|
| 11428 |
+
"loss": 1.6759,
|
| 11429 |
+
"mean_token_accuracy": 0.6643141090869904,
|
| 11430 |
+
"num_tokens": 23139519.0,
|
| 11431 |
+
"step": 6345
|
| 11432 |
+
},
|
| 11433 |
+
{
|
| 11434 |
+
"epoch": 48.84615384615385,
|
| 11435 |
+
"grad_norm": 0.0,
|
| 11436 |
+
"learning_rate": 1.8255e-05,
|
| 11437 |
+
"loss": 1.8242,
|
| 11438 |
+
"mean_token_accuracy": 0.6340841352939606,
|
| 11439 |
+
"num_tokens": 23156832.0,
|
| 11440 |
+
"step": 6350
|
| 11441 |
}
|
| 11442 |
],
|
| 11443 |
"logging_steps": 5,
|
|
|
|
| 11457 |
"attributes": {}
|
| 11458 |
}
|
| 11459 |
},
|
| 11460 |
+
"total_flos": 1.1738910649142477e+18,
|
| 11461 |
"train_batch_size": 4,
|
| 11462 |
"trial_name": null,
|
| 11463 |
"trial_params": null
|