Training in progress, step 6860, 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 sha256:417bd99ef7555423067fd223198358f68bd208d48e40891ac774f0862ddade30
|
| 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 sha256:432f005c282df10d4c57cbab21327f68ba0311c0bdff320ae155d95605987573
|
| 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:cafdaf55b3aec65eb4b153c955b9faca45a195acbdfe1d98168fc359a7521915
|
| 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": 52.
|
| 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,
|
|
@@ -12338,6 +12338,24 @@
|
|
| 12338 |
"mean_token_accuracy": 0.6502928107976913,
|
| 12339 |
"num_tokens": 24983952.0,
|
| 12340 |
"step": 6850
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12341 |
}
|
| 12342 |
],
|
| 12343 |
"logging_steps": 5,
|
|
@@ -12357,7 +12375,7 @@
|
|
| 12357 |
"attributes": {}
|
| 12358 |
}
|
| 12359 |
},
|
| 12360 |
-
"total_flos": 1.
|
| 12361 |
"train_batch_size": 4,
|
| 12362 |
"trial_name": null,
|
| 12363 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 52.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6860,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12338 |
"mean_token_accuracy": 0.6502928107976913,
|
| 12339 |
"num_tokens": 24983952.0,
|
| 12340 |
"step": 6850
|
| 12341 |
+
},
|
| 12342 |
+
{
|
| 12343 |
+
"epoch": 52.73076923076923,
|
| 12344 |
+
"grad_norm": 0.0,
|
| 12345 |
+
"learning_rate": 1.573e-05,
|
| 12346 |
+
"loss": 1.6641,
|
| 12347 |
+
"mean_token_accuracy": 0.6641529649496078,
|
| 12348 |
+
"num_tokens": 25002526.0,
|
| 12349 |
+
"step": 6855
|
| 12350 |
+
},
|
| 12351 |
+
{
|
| 12352 |
+
"epoch": 52.76923076923077,
|
| 12353 |
+
"grad_norm": 0.0,
|
| 12354 |
+
"learning_rate": 1.5705e-05,
|
| 12355 |
+
"loss": 1.7879,
|
| 12356 |
+
"mean_token_accuracy": 0.6445726931095124,
|
| 12357 |
+
"num_tokens": 25020198.0,
|
| 12358 |
+
"step": 6860
|
| 12359 |
}
|
| 12360 |
],
|
| 12361 |
"logging_steps": 5,
|
|
|
|
| 12375 |
"attributes": {}
|
| 12376 |
}
|
| 12377 |
},
|
| 12378 |
+
"total_flos": 1.2685451888163226e+18,
|
| 12379 |
"train_batch_size": 4,
|
| 12380 |
"trial_name": null,
|
| 12381 |
"trial_params": null
|