Training in progress, step 2500, 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 sha256:4c9f70d58ebf13c9ecb546f4c25a85a36c3dc254ce3f0354daabe3f13b8f679f
|
| 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 sha256:0eea26540931c94eff40c20543509cb1b147a82bb8a2216c152740aeac0b623d
|
| 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 sha256:970620a2dd432e2b7c7527c94c24b58b76503f4147e797b13670ca1eb259ba54
|
| 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": 19.
|
| 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,
|
|
@@ -4490,6 +4490,24 @@
|
|
| 4490 |
"mean_token_accuracy": 0.6509835839271545,
|
| 4491 |
"num_tokens": 9080800.0,
|
| 4492 |
"step": 2490
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4493 |
}
|
| 4494 |
],
|
| 4495 |
"logging_steps": 5,
|
|
@@ -4509,7 +4527,7 @@
|
|
| 4509 |
"attributes": {}
|
| 4510 |
}
|
| 4511 |
},
|
| 4512 |
-
"total_flos": 4.
|
| 4513 |
"train_batch_size": 4,
|
| 4514 |
"trial_name": null,
|
| 4515 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 19.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4490 |
"mean_token_accuracy": 0.6509835839271545,
|
| 4491 |
"num_tokens": 9080800.0,
|
| 4492 |
"step": 2490
|
| 4493 |
+
},
|
| 4494 |
+
{
|
| 4495 |
+
"epoch": 19.192307692307693,
|
| 4496 |
+
"grad_norm": 0.0,
|
| 4497 |
+
"learning_rate": 3.753e-05,
|
| 4498 |
+
"loss": 1.749,
|
| 4499 |
+
"mean_token_accuracy": 0.6524321138858795,
|
| 4500 |
+
"num_tokens": 9099027.0,
|
| 4501 |
+
"step": 2495
|
| 4502 |
+
},
|
| 4503 |
+
{
|
| 4504 |
+
"epoch": 19.23076923076923,
|
| 4505 |
+
"grad_norm": 0.0,
|
| 4506 |
+
"learning_rate": 3.7505e-05,
|
| 4507 |
+
"loss": 1.7379,
|
| 4508 |
+
"mean_token_accuracy": 0.6502025574445724,
|
| 4509 |
+
"num_tokens": 9117027.0,
|
| 4510 |
+
"step": 2500
|
| 4511 |
}
|
| 4512 |
],
|
| 4513 |
"logging_steps": 5,
|
|
|
|
| 4527 |
"attributes": {}
|
| 4528 |
}
|
| 4529 |
},
|
| 4530 |
+
"total_flos": 4.620147658334208e+17,
|
| 4531 |
"train_batch_size": 4,
|
| 4532 |
"trial_name": null,
|
| 4533 |
"trial_params": null
|