Training in progress, step 1950, 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:afd63afb4b8b083fa27e71fead1b6cb93a6135d76379b959f528692602e2143a
|
| 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 sha256:8ad395aeb5d904ef49b98c5bb646b1165e2206e1975e3cd0e55af9023312f2b4
|
| 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 sha256:24fa3e3032bc9eb2e95f070a6aa7710b53dd3a93c7b31c93731f95156daf373e
|
| 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":
|
| 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,
|
|
@@ -3500,6 +3500,24 @@
|
|
| 3500 |
"mean_token_accuracy": 0.6501289933919907,
|
| 3501 |
"num_tokens": 7074488.0,
|
| 3502 |
"step": 1940
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3503 |
}
|
| 3504 |
],
|
| 3505 |
"logging_steps": 5,
|
|
@@ -3519,7 +3537,7 @@
|
|
| 3519 |
"attributes": {}
|
| 3520 |
}
|
| 3521 |
},
|
| 3522 |
-
"total_flos": 3.
|
| 3523 |
"train_batch_size": 4,
|
| 3524 |
"trial_name": null,
|
| 3525 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 15.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1950,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3500 |
"mean_token_accuracy": 0.6501289933919907,
|
| 3501 |
"num_tokens": 7074488.0,
|
| 3502 |
"step": 1940
|
| 3503 |
+
},
|
| 3504 |
+
{
|
| 3505 |
+
"epoch": 14.961538461538462,
|
| 3506 |
+
"grad_norm": 0.0,
|
| 3507 |
+
"learning_rate": 4.028e-05,
|
| 3508 |
+
"loss": 1.7577,
|
| 3509 |
+
"mean_token_accuracy": 0.6519861459732056,
|
| 3510 |
+
"num_tokens": 7092711.0,
|
| 3511 |
+
"step": 1945
|
| 3512 |
+
},
|
| 3513 |
+
{
|
| 3514 |
+
"epoch": 15.0,
|
| 3515 |
+
"grad_norm": 0.0,
|
| 3516 |
+
"learning_rate": 4.025500000000001e-05,
|
| 3517 |
+
"loss": 1.6968,
|
| 3518 |
+
"mean_token_accuracy": 0.6624333202838898,
|
| 3519 |
+
"num_tokens": 7111575.0,
|
| 3520 |
+
"step": 1950
|
| 3521 |
}
|
| 3522 |
],
|
| 3523 |
"logging_steps": 5,
|
|
|
|
| 3537 |
"attributes": {}
|
| 3538 |
}
|
| 3539 |
},
|
| 3540 |
+
"total_flos": 3.6031497609609216e+17,
|
| 3541 |
"train_batch_size": 4,
|
| 3542 |
"trial_name": null,
|
| 3543 |
"trial_params": null
|