Training in progress, step 7430, 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 sha256:3704498791d13f63937208c3e0e379109286b2b7b26eff759293b279a53f8c2a
|
| 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:bd05be4ba9e1369355e9e566d00cf8f364577de83b2778865f2dcda217076266
|
| 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:b2b31e2c645e1db9b120cff648c0eefe6e89114aa77cbf7f933b1ea8d5b0119e
|
| 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,
|
|
@@ -13364,6 +13364,24 @@
|
|
| 13364 |
"mean_token_accuracy": 0.6512410253286361,
|
| 13365 |
"num_tokens": 27060805.0,
|
| 13366 |
"step": 7420
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13367 |
}
|
| 13368 |
],
|
| 13369 |
"logging_steps": 5,
|
|
@@ -13383,7 +13401,7 @@
|
|
| 13383 |
"attributes": {}
|
| 13384 |
}
|
| 13385 |
},
|
| 13386 |
-
"total_flos": 1.
|
| 13387 |
"train_batch_size": 4,
|
| 13388 |
"trial_name": null,
|
| 13389 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 57.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7430,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13364 |
"mean_token_accuracy": 0.6512410253286361,
|
| 13365 |
"num_tokens": 27060805.0,
|
| 13366 |
"step": 7420
|
| 13367 |
+
},
|
| 13368 |
+
{
|
| 13369 |
+
"epoch": 57.11538461538461,
|
| 13370 |
+
"grad_norm": 0.0,
|
| 13371 |
+
"learning_rate": 1.288e-05,
|
| 13372 |
+
"loss": 1.7818,
|
| 13373 |
+
"mean_token_accuracy": 0.6462918251752854,
|
| 13374 |
+
"num_tokens": 27078281.0,
|
| 13375 |
+
"step": 7425
|
| 13376 |
+
},
|
| 13377 |
+
{
|
| 13378 |
+
"epoch": 57.15384615384615,
|
| 13379 |
+
"grad_norm": 0.0,
|
| 13380 |
+
"learning_rate": 1.2855e-05,
|
| 13381 |
+
"loss": 1.7089,
|
| 13382 |
+
"mean_token_accuracy": 0.6547515660524368,
|
| 13383 |
+
"num_tokens": 27097554.0,
|
| 13384 |
+
"step": 7430
|
| 13385 |
}
|
| 13386 |
],
|
| 13387 |
"logging_steps": 5,
|
|
|
|
| 13401 |
"attributes": {}
|
| 13402 |
}
|
| 13403 |
},
|
| 13404 |
+
"total_flos": 1.3738427552283034e+18,
|
| 13405 |
"train_batch_size": 4,
|
| 13406 |
"trial_name": null,
|
| 13407 |
"trial_params": null
|