Training in progress, step 3010, 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 sha256:027ff7c7be1a07722c7d5ff04f22e2826e455ba715a13b39513b7539eb24ad1f
|
| 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 sha256:6ad4c2d66639efaa392107089d190433b77af2afdb70f3b740ef9d778d92292b
|
| 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 sha256:5920f96f62a47e658004fe68b09c79780c85ba11e0e00c9c663b9d533f342bf4
|
| 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,
|
|
@@ -5408,6 +5408,24 @@
|
|
| 5408 |
"mean_token_accuracy": 0.6366728276014328,
|
| 5409 |
"num_tokens": 10940239.0,
|
| 5410 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5411 |
}
|
| 5412 |
],
|
| 5413 |
"logging_steps": 5,
|
|
@@ -5427,7 +5445,7 @@
|
|
| 5427 |
"attributes": {}
|
| 5428 |
}
|
| 5429 |
},
|
| 5430 |
-
"total_flos": 5.
|
| 5431 |
"train_batch_size": 4,
|
| 5432 |
"trial_name": null,
|
| 5433 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 23.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3010,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5408 |
"mean_token_accuracy": 0.6366728276014328,
|
| 5409 |
"num_tokens": 10940239.0,
|
| 5410 |
"step": 3000
|
| 5411 |
+
},
|
| 5412 |
+
{
|
| 5413 |
+
"epoch": 23.115384615384617,
|
| 5414 |
+
"grad_norm": 0.0,
|
| 5415 |
+
"learning_rate": 3.498e-05,
|
| 5416 |
+
"loss": 1.7362,
|
| 5417 |
+
"mean_token_accuracy": 0.6528029084205628,
|
| 5418 |
+
"num_tokens": 10958391.0,
|
| 5419 |
+
"step": 3005
|
| 5420 |
+
},
|
| 5421 |
+
{
|
| 5422 |
+
"epoch": 23.153846153846153,
|
| 5423 |
+
"grad_norm": 0.0,
|
| 5424 |
+
"learning_rate": 3.495500000000001e-05,
|
| 5425 |
+
"loss": 1.7442,
|
| 5426 |
+
"mean_token_accuracy": 0.6534345805644989,
|
| 5427 |
+
"num_tokens": 10976257.0,
|
| 5428 |
+
"step": 3010
|
| 5429 |
}
|
| 5430 |
],
|
| 5431 |
"logging_steps": 5,
|
|
|
|
| 5445 |
"attributes": {}
|
| 5446 |
}
|
| 5447 |
},
|
| 5448 |
+
"total_flos": 5.5625987465478144e+17,
|
| 5449 |
"train_batch_size": 4,
|
| 5450 |
"trial_name": null,
|
| 5451 |
"trial_params": null
|