Training in progress, step 8570, 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:eed8482f79bb79ecf550d0bd15b8cb4be2963184e84842f0483b00a56d28f661
|
| 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 sha256:6b6608971064f6ca1fca83019b3814f8c437358bbdc23e1de2fd7ed359fca79e
|
| 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 sha256:690b11fc6fabdec8740678f566a57236cc8d88a569849d55361759ea8279311e
|
| 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": 65.
|
| 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,
|
|
@@ -15416,6 +15416,24 @@
|
|
| 15416 |
"mean_token_accuracy": 0.6532280802726745,
|
| 15417 |
"num_tokens": 31219465.0,
|
| 15418 |
"step": 8560
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15419 |
}
|
| 15420 |
],
|
| 15421 |
"logging_steps": 5,
|
|
@@ -15435,7 +15453,7 @@
|
|
| 15435 |
"attributes": {}
|
| 15436 |
}
|
| 15437 |
},
|
| 15438 |
-
"total_flos": 1.
|
| 15439 |
"train_batch_size": 4,
|
| 15440 |
"trial_name": null,
|
| 15441 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 65.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8570,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15416 |
"mean_token_accuracy": 0.6532280802726745,
|
| 15417 |
"num_tokens": 31219465.0,
|
| 15418 |
"step": 8560
|
| 15419 |
+
},
|
| 15420 |
+
{
|
| 15421 |
+
"epoch": 65.88461538461539,
|
| 15422 |
+
"grad_norm": 0.0,
|
| 15423 |
+
"learning_rate": 7.180000000000001e-06,
|
| 15424 |
+
"loss": 1.7995,
|
| 15425 |
+
"mean_token_accuracy": 0.6446830004453659,
|
| 15426 |
+
"num_tokens": 31236938.0,
|
| 15427 |
+
"step": 8565
|
| 15428 |
+
},
|
| 15429 |
+
{
|
| 15430 |
+
"epoch": 65.92307692307692,
|
| 15431 |
+
"grad_norm": 0.0,
|
| 15432 |
+
"learning_rate": 7.155000000000001e-06,
|
| 15433 |
+
"loss": 1.7361,
|
| 15434 |
+
"mean_token_accuracy": 0.6507874131202698,
|
| 15435 |
+
"num_tokens": 31255303.0,
|
| 15436 |
+
"step": 8570
|
| 15437 |
}
|
| 15438 |
],
|
| 15439 |
"logging_steps": 5,
|
|
|
|
| 15453 |
"attributes": {}
|
| 15454 |
}
|
| 15455 |
},
|
| 15456 |
+
"total_flos": 1.5848310252183552e+18,
|
| 15457 |
"train_batch_size": 4,
|
| 15458 |
"trial_name": null,
|
| 15459 |
"trial_params": null
|