Training in progress, step 3000, 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 sha256:835afb22284010f0722ee4dde463cc525f0afac4b97ab8c09ed75e0d9eb6a67f
|
| 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 sha256:94a7781bc4304e4442fa5fa6e3470d9c37a332d00bae5d0eb1edc5d0a16c188b
|
| 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 sha256:036773445d58c68539196eb42d9c6b2e7da93a8517928d9bcf71c46a42fcf167
|
| 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,
|
|
@@ -5390,6 +5390,24 @@
|
|
| 5390 |
"mean_token_accuracy": 0.65148167014122,
|
| 5391 |
"num_tokens": 10904415.0,
|
| 5392 |
"step": 2990
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5393 |
}
|
| 5394 |
],
|
| 5395 |
"logging_steps": 5,
|
|
@@ -5409,7 +5427,7 @@
|
|
| 5409 |
"attributes": {}
|
| 5410 |
}
|
| 5411 |
},
|
| 5412 |
-
"total_flos": 5.
|
| 5413 |
"train_batch_size": 4,
|
| 5414 |
"trial_name": null,
|
| 5415 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 23.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5390 |
"mean_token_accuracy": 0.65148167014122,
|
| 5391 |
"num_tokens": 10904415.0,
|
| 5392 |
"step": 2990
|
| 5393 |
+
},
|
| 5394 |
+
{
|
| 5395 |
+
"epoch": 23.03846153846154,
|
| 5396 |
+
"grad_norm": 0.0,
|
| 5397 |
+
"learning_rate": 3.503e-05,
|
| 5398 |
+
"loss": 1.7296,
|
| 5399 |
+
"mean_token_accuracy": 0.6501170575618744,
|
| 5400 |
+
"num_tokens": 10922228.0,
|
| 5401 |
+
"step": 2995
|
| 5402 |
+
},
|
| 5403 |
+
{
|
| 5404 |
+
"epoch": 23.076923076923077,
|
| 5405 |
+
"grad_norm": 0.0,
|
| 5406 |
+
"learning_rate": 3.5005e-05,
|
| 5407 |
+
"loss": 1.7787,
|
| 5408 |
+
"mean_token_accuracy": 0.6366728276014328,
|
| 5409 |
+
"num_tokens": 10940239.0,
|
| 5410 |
+
"step": 3000
|
| 5411 |
}
|
| 5412 |
],
|
| 5413 |
"logging_steps": 5,
|
|
|
|
| 5427 |
"attributes": {}
|
| 5428 |
}
|
| 5429 |
},
|
| 5430 |
+
"total_flos": 5.5439072654524416e+17,
|
| 5431 |
"train_batch_size": 4,
|
| 5432 |
"trial_name": null,
|
| 5433 |
"trial_params": null
|