Training in progress, step 7420, 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:a1b5726fe714a39adde59e1ebbcf2660bdfe73e5587e8808f30eb433db57419b
|
| 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 sha256:4d3d3c9c5aeb9e04bdcf3e0547c005ab2db279cd9abc366b04b6378ae124ebc0
|
| 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 sha256:470d0f16a53e7d08cf087739ab37a3a2f50fbd53f6f143d3114d70e240579979
|
| 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": 57.
|
| 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,
|
|
@@ -13346,6 +13346,24 @@
|
|
| 13346 |
"mean_token_accuracy": 0.6442842125892639,
|
| 13347 |
"num_tokens": 27023985.0,
|
| 13348 |
"step": 7410
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13349 |
}
|
| 13350 |
],
|
| 13351 |
"logging_steps": 5,
|
|
@@ -13365,7 +13383,7 @@
|
|
| 13365 |
"attributes": {}
|
| 13366 |
}
|
| 13367 |
},
|
| 13368 |
-
"total_flos": 1.
|
| 13369 |
"train_batch_size": 4,
|
| 13370 |
"trial_name": null,
|
| 13371 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 57.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7420,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13346 |
"mean_token_accuracy": 0.6442842125892639,
|
| 13347 |
"num_tokens": 27023985.0,
|
| 13348 |
"step": 7410
|
| 13349 |
+
},
|
| 13350 |
+
{
|
| 13351 |
+
"epoch": 57.03846153846154,
|
| 13352 |
+
"grad_norm": 0.0,
|
| 13353 |
+
"learning_rate": 1.293e-05,
|
| 13354 |
+
"loss": 1.7412,
|
| 13355 |
+
"mean_token_accuracy": 0.6453804969787598,
|
| 13356 |
+
"num_tokens": 27042588.0,
|
| 13357 |
+
"step": 7415
|
| 13358 |
+
},
|
| 13359 |
+
{
|
| 13360 |
+
"epoch": 57.07692307692308,
|
| 13361 |
+
"grad_norm": 0.0,
|
| 13362 |
+
"learning_rate": 1.2905000000000001e-05,
|
| 13363 |
+
"loss": 1.7348,
|
| 13364 |
+
"mean_token_accuracy": 0.6512410253286361,
|
| 13365 |
+
"num_tokens": 27060805.0,
|
| 13366 |
+
"step": 7420
|
| 13367 |
}
|
| 13368 |
],
|
| 13369 |
"logging_steps": 5,
|
|
|
|
| 13383 |
"attributes": {}
|
| 13384 |
}
|
| 13385 |
},
|
| 13386 |
+
"total_flos": 1.3719440741975654e+18,
|
| 13387 |
"train_batch_size": 4,
|
| 13388 |
"trial_name": null,
|
| 13389 |
"trial_params": null
|