Training in progress, step 3060, 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 sha256:7eab90834ce92be2488b1c41de5c5bec643ae3b118e8d9a90b96c409e596ec73
|
| 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:d6b399636d591a4041b9eb2e3be5f011d49aa6dba0880ddbed9a7c79c92b4574
|
| 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:c91e644f5fe4375242eef1c3d76cc8721564dcd0ed8f96a6a730a2c66becca72
|
| 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": 23.
|
| 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,
|
|
@@ -5498,6 +5498,24 @@
|
|
| 5498 |
"mean_token_accuracy": 0.6486080348491668,
|
| 5499 |
"num_tokens": 11124657.0,
|
| 5500 |
"step": 3050
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5501 |
}
|
| 5502 |
],
|
| 5503 |
"logging_steps": 5,
|
|
@@ -5517,7 +5535,7 @@
|
|
| 5517 |
"attributes": {}
|
| 5518 |
}
|
| 5519 |
},
|
| 5520 |
-
"total_flos": 5.
|
| 5521 |
"train_batch_size": 4,
|
| 5522 |
"trial_name": null,
|
| 5523 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 23.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3060,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5498 |
"mean_token_accuracy": 0.6486080348491668,
|
| 5499 |
"num_tokens": 11124657.0,
|
| 5500 |
"step": 3050
|
| 5501 |
+
},
|
| 5502 |
+
{
|
| 5503 |
+
"epoch": 23.5,
|
| 5504 |
+
"grad_norm": 0.0,
|
| 5505 |
+
"learning_rate": 3.473e-05,
|
| 5506 |
+
"loss": 1.7576,
|
| 5507 |
+
"mean_token_accuracy": 0.6459647357463837,
|
| 5508 |
+
"num_tokens": 11142612.0,
|
| 5509 |
+
"step": 3055
|
| 5510 |
+
},
|
| 5511 |
+
{
|
| 5512 |
+
"epoch": 23.53846153846154,
|
| 5513 |
+
"grad_norm": 0.0,
|
| 5514 |
+
"learning_rate": 3.470500000000001e-05,
|
| 5515 |
+
"loss": 1.7698,
|
| 5516 |
+
"mean_token_accuracy": 0.6444110184907913,
|
| 5517 |
+
"num_tokens": 11160572.0,
|
| 5518 |
+
"step": 3060
|
| 5519 |
}
|
| 5520 |
],
|
| 5521 |
"logging_steps": 5,
|
|
|
|
| 5535 |
"attributes": {}
|
| 5536 |
}
|
| 5537 |
},
|
| 5538 |
+
"total_flos": 5.6556480896188416e+17,
|
| 5539 |
"train_batch_size": 4,
|
| 5540 |
"trial_name": null,
|
| 5541 |
"trial_params": null
|