Training in progress, step 4710, 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 sha256:503ade52c9b5147e51e3ae774d93787012e04c59278e023540c0239f6a4e2eb5
|
| 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 sha256:8b9eb1aa62c75f9c2adcac8cca9bbd1ae6807430bd195cf87b0e3e9ef6bfcdc6
|
| 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 sha256:477fce552e8e39633381b845fe8309e092b1b111d9d01ec12f96ba1651298302
|
| 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": 36.
|
| 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,
|
|
@@ -8468,6 +8468,24 @@
|
|
| 8468 |
"mean_token_accuracy": 0.6540112674236298,
|
| 8469 |
"num_tokens": 17139263.0,
|
| 8470 |
"step": 4700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8471 |
}
|
| 8472 |
],
|
| 8473 |
"logging_steps": 5,
|
|
@@ -8487,7 +8505,7 @@
|
|
| 8487 |
"attributes": {}
|
| 8488 |
}
|
| 8489 |
},
|
| 8490 |
-
"total_flos": 8.
|
| 8491 |
"train_batch_size": 4,
|
| 8492 |
"trial_name": null,
|
| 8493 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 36.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4710,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8468 |
"mean_token_accuracy": 0.6540112674236298,
|
| 8469 |
"num_tokens": 17139263.0,
|
| 8470 |
"step": 4700
|
| 8471 |
+
},
|
| 8472 |
+
{
|
| 8473 |
+
"epoch": 36.19230769230769,
|
| 8474 |
+
"grad_norm": 0.0,
|
| 8475 |
+
"learning_rate": 2.648e-05,
|
| 8476 |
+
"loss": 1.6614,
|
| 8477 |
+
"mean_token_accuracy": 0.6684265941381454,
|
| 8478 |
+
"num_tokens": 17158319.0,
|
| 8479 |
+
"step": 4705
|
| 8480 |
+
},
|
| 8481 |
+
{
|
| 8482 |
+
"epoch": 36.23076923076923,
|
| 8483 |
+
"grad_norm": 0.0,
|
| 8484 |
+
"learning_rate": 2.6455000000000003e-05,
|
| 8485 |
+
"loss": 1.7377,
|
| 8486 |
+
"mean_token_accuracy": 0.6504531025886535,
|
| 8487 |
+
"num_tokens": 17176907.0,
|
| 8488 |
+
"step": 4710
|
| 8489 |
}
|
| 8490 |
],
|
| 8491 |
"logging_steps": 5,
|
|
|
|
| 8505 |
"attributes": {}
|
| 8506 |
}
|
| 8507 |
},
|
| 8508 |
+
"total_flos": 8.705744679562445e+17,
|
| 8509 |
"train_batch_size": 4,
|
| 8510 |
"trial_name": null,
|
| 8511 |
"trial_params": null
|