Training in progress, step 5220, 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:e6b22a8a53931370ef1a6ee5469b2c6ca646e287d05c0b668dddb2a1da21a60d
|
| 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:fa5ef09a91348f458d10817013cb7a6821374acbd0e40fd0c6efb1cd5dac57d8
|
| 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 sha256:0f47048e24bfd6e1809e1a1b39af7cfc34a36c2a58cae77daa8f6bca57bb575b
|
| 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": 40.
|
| 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,
|
|
@@ -9386,6 +9386,24 @@
|
|
| 9386 |
"mean_token_accuracy": 0.6510910272598267,
|
| 9387 |
"num_tokens": 19000451.0,
|
| 9388 |
"step": 5210
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9389 |
}
|
| 9390 |
],
|
| 9391 |
"logging_steps": 5,
|
|
@@ -9405,7 +9423,7 @@
|
|
| 9405 |
"attributes": {}
|
| 9406 |
}
|
| 9407 |
},
|
| 9408 |
-
"total_flos": 9.
|
| 9409 |
"train_batch_size": 4,
|
| 9410 |
"trial_name": null,
|
| 9411 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 40.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5220,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9386 |
"mean_token_accuracy": 0.6510910272598267,
|
| 9387 |
"num_tokens": 19000451.0,
|
| 9388 |
"step": 5210
|
| 9389 |
+
},
|
| 9390 |
+
{
|
| 9391 |
+
"epoch": 40.11538461538461,
|
| 9392 |
+
"grad_norm": 0.0,
|
| 9393 |
+
"learning_rate": 2.3930000000000003e-05,
|
| 9394 |
+
"loss": 1.7149,
|
| 9395 |
+
"mean_token_accuracy": 0.6571291297674179,
|
| 9396 |
+
"num_tokens": 19018812.0,
|
| 9397 |
+
"step": 5215
|
| 9398 |
+
},
|
| 9399 |
+
{
|
| 9400 |
+
"epoch": 40.15384615384615,
|
| 9401 |
+
"grad_norm": 0.0,
|
| 9402 |
+
"learning_rate": 2.3905000000000002e-05,
|
| 9403 |
+
"loss": 1.7426,
|
| 9404 |
+
"mean_token_accuracy": 0.6531620174646378,
|
| 9405 |
+
"num_tokens": 19036736.0,
|
| 9406 |
+
"step": 5220
|
| 9407 |
}
|
| 9408 |
],
|
| 9409 |
"logging_steps": 5,
|
|
|
|
| 9423 |
"attributes": {}
|
| 9424 |
}
|
| 9425 |
},
|
| 9426 |
+
"total_flos": 9.64630947151872e+17,
|
| 9427 |
"train_batch_size": 4,
|
| 9428 |
"trial_name": null,
|
| 9429 |
"trial_params": null
|