Training in progress, step 3550, 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 sha256:4b51414c66ccbe79968185f568ee6cc90e792c481386dbb61da1203c78b1311e
|
| 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 sha256:15db8acb4433c0e55e103b824f1a7c1d6b73cd495e0fe7be3aae7bde64f2999e
|
| 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:b9cd0888d0fd10e277932567dc9f606d4fd888a6b7cac45a1df4dc85f8f19c7b
|
| 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": 27.
|
| 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,
|
|
@@ -6380,6 +6380,24 @@
|
|
| 6380 |
"mean_token_accuracy": 0.6513606965541839,
|
| 6381 |
"num_tokens": 12910141.0,
|
| 6382 |
"step": 3540
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6383 |
}
|
| 6384 |
],
|
| 6385 |
"logging_steps": 5,
|
|
@@ -6399,7 +6417,7 @@
|
|
| 6399 |
"attributes": {}
|
| 6400 |
}
|
| 6401 |
},
|
| 6402 |
-
"total_flos": 6.
|
| 6403 |
"train_batch_size": 4,
|
| 6404 |
"trial_name": null,
|
| 6405 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 27.307692307692307,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3550,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6380 |
"mean_token_accuracy": 0.6513606965541839,
|
| 6381 |
"num_tokens": 12910141.0,
|
| 6382 |
"step": 3540
|
| 6383 |
+
},
|
| 6384 |
+
{
|
| 6385 |
+
"epoch": 27.26923076923077,
|
| 6386 |
+
"grad_norm": 0.0,
|
| 6387 |
+
"learning_rate": 3.2279999999999996e-05,
|
| 6388 |
+
"loss": 1.7847,
|
| 6389 |
+
"mean_token_accuracy": 0.6459431618452072,
|
| 6390 |
+
"num_tokens": 12927928.0,
|
| 6391 |
+
"step": 3545
|
| 6392 |
+
},
|
| 6393 |
+
{
|
| 6394 |
+
"epoch": 27.307692307692307,
|
| 6395 |
+
"grad_norm": 0.0,
|
| 6396 |
+
"learning_rate": 3.2255e-05,
|
| 6397 |
+
"loss": 1.745,
|
| 6398 |
+
"mean_token_accuracy": 0.6481869876384735,
|
| 6399 |
+
"num_tokens": 12945933.0,
|
| 6400 |
+
"step": 3550
|
| 6401 |
}
|
| 6402 |
],
|
| 6403 |
"logging_steps": 5,
|
|
|
|
| 6417 |
"attributes": {}
|
| 6418 |
}
|
| 6419 |
},
|
| 6420 |
+
"total_flos": 6.559533311002214e+17,
|
| 6421 |
"train_batch_size": 4,
|
| 6422 |
"trial_name": null,
|
| 6423 |
"trial_params": null
|