Training in progress, step 1940, 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:f974b9fd7c3c50ae872ffde2d6652dccfe70bf849c44c8f91bd6c6d067fad257
|
| 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 sha256:3f4991e29cf1e510335ca5b0c251145a8b6afeae73be7d252d159a671c961c4e
|
| 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 sha256:59ddaa7f986a829f7993f9cbbadeb6d736d7b98583bc45af51fd96785af24f8e
|
| 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": 14.
|
| 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,
|
|
@@ -3482,6 +3482,24 @@
|
|
| 3482 |
"mean_token_accuracy": 0.6525963991880417,
|
| 3483 |
"num_tokens": 7037790.0,
|
| 3484 |
"step": 1930
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3485 |
}
|
| 3486 |
],
|
| 3487 |
"logging_steps": 5,
|
|
@@ -3501,7 +3519,7 @@
|
|
| 3501 |
"attributes": {}
|
| 3502 |
}
|
| 3503 |
},
|
| 3504 |
-
"total_flos": 3.
|
| 3505 |
"train_batch_size": 4,
|
| 3506 |
"trial_name": null,
|
| 3507 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 14.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1940,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3482 |
"mean_token_accuracy": 0.6525963991880417,
|
| 3483 |
"num_tokens": 7037790.0,
|
| 3484 |
"step": 1930
|
| 3485 |
+
},
|
| 3486 |
+
{
|
| 3487 |
+
"epoch": 14.884615384615385,
|
| 3488 |
+
"grad_norm": 0.0,
|
| 3489 |
+
"learning_rate": 4.033e-05,
|
| 3490 |
+
"loss": 1.7614,
|
| 3491 |
+
"mean_token_accuracy": 0.6488069415092468,
|
| 3492 |
+
"num_tokens": 7055472.0,
|
| 3493 |
+
"step": 1935
|
| 3494 |
+
},
|
| 3495 |
+
{
|
| 3496 |
+
"epoch": 14.923076923076923,
|
| 3497 |
+
"grad_norm": 0.0,
|
| 3498 |
+
"learning_rate": 4.0305e-05,
|
| 3499 |
+
"loss": 1.7207,
|
| 3500 |
+
"mean_token_accuracy": 0.6501289933919907,
|
| 3501 |
+
"num_tokens": 7074488.0,
|
| 3502 |
+
"step": 1940
|
| 3503 |
}
|
| 3504 |
],
|
| 3505 |
"logging_steps": 5,
|
|
|
|
| 3519 |
"attributes": {}
|
| 3520 |
}
|
| 3521 |
},
|
| 3522 |
+
"total_flos": 3.5845678374764544e+17,
|
| 3523 |
"train_batch_size": 4,
|
| 3524 |
"trial_name": null,
|
| 3525 |
"trial_params": null
|