Training in progress, step 6900, 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 sha256:9450d5e5bf09083149ccad269b663bda51fb8d31b4fdbcd8a0b605958ab493fc
|
| 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 sha256:588b477b2a066f926662b9842f06f5fb46d82c58d994f2e0503ae30635d3e911
|
| 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:b29dbbfe2b0f5fcbc36b82b233745c1de9715e0659f74344d84d9adbc11795dd
|
| 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": 53.
|
| 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,
|
|
@@ -12410,6 +12410,24 @@
|
|
| 12410 |
"mean_token_accuracy": 0.6363903671503067,
|
| 12411 |
"num_tokens": 25127565.0,
|
| 12412 |
"step": 6890
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12413 |
}
|
| 12414 |
],
|
| 12415 |
"logging_steps": 5,
|
|
@@ -12429,7 +12447,7 @@
|
|
| 12429 |
"attributes": {}
|
| 12430 |
}
|
| 12431 |
},
|
| 12432 |
-
"total_flos": 1.
|
| 12433 |
"train_batch_size": 4,
|
| 12434 |
"trial_name": null,
|
| 12435 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 53.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6900,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12410 |
"mean_token_accuracy": 0.6363903671503067,
|
| 12411 |
"num_tokens": 25127565.0,
|
| 12412 |
"step": 6890
|
| 12413 |
+
},
|
| 12414 |
+
{
|
| 12415 |
+
"epoch": 53.03846153846154,
|
| 12416 |
+
"grad_norm": 0.0,
|
| 12417 |
+
"learning_rate": 1.553e-05,
|
| 12418 |
+
"loss": 1.7896,
|
| 12419 |
+
"mean_token_accuracy": 0.6396276503801346,
|
| 12420 |
+
"num_tokens": 25145088.0,
|
| 12421 |
+
"step": 6895
|
| 12422 |
+
},
|
| 12423 |
+
{
|
| 12424 |
+
"epoch": 53.07692307692308,
|
| 12425 |
+
"grad_norm": 0.0,
|
| 12426 |
+
"learning_rate": 1.5505e-05,
|
| 12427 |
+
"loss": 1.717,
|
| 12428 |
+
"mean_token_accuracy": 0.6515821665525436,
|
| 12429 |
+
"num_tokens": 25163828.0,
|
| 12430 |
+
"step": 6900
|
| 12431 |
}
|
| 12432 |
],
|
| 12433 |
"logging_steps": 5,
|
|
|
|
| 12447 |
"attributes": {}
|
| 12448 |
}
|
| 12449 |
},
|
| 12450 |
+
"total_flos": 1.2758477593101926e+18,
|
| 12451 |
"train_batch_size": 4,
|
| 12452 |
"trial_name": null,
|
| 12453 |
"trial_params": null
|