Training in progress, step 9220, 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 sha256:964668699a09f3231d1acc38e0e8036cce8695aa175f222398a654c6212c87a9
|
| 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 sha256:9813f4a0eb8b732db73586146dfae0e2b6979465ee941aa7cf32e99a5e1ea91f
|
| 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:d28397521f6e58f458784edb381a18f0c0c4af64f059ce5fe7b040f7ff994fc6
|
| 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": 70.
|
| 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,
|
|
@@ -16586,6 +16586,24 @@
|
|
| 16586 |
"mean_token_accuracy": 0.6454756885766983,
|
| 16587 |
"num_tokens": 33587052.0,
|
| 16588 |
"step": 9210
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16589 |
}
|
| 16590 |
],
|
| 16591 |
"logging_steps": 5,
|
|
@@ -16605,7 +16623,7 @@
|
|
| 16605 |
"attributes": {}
|
| 16606 |
}
|
| 16607 |
},
|
| 16608 |
-
"total_flos": 1.
|
| 16609 |
"train_batch_size": 4,
|
| 16610 |
"trial_name": null,
|
| 16611 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 70.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9220,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16586 |
"mean_token_accuracy": 0.6454756885766983,
|
| 16587 |
"num_tokens": 33587052.0,
|
| 16588 |
"step": 9210
|
| 16589 |
+
},
|
| 16590 |
+
{
|
| 16591 |
+
"epoch": 70.88461538461539,
|
| 16592 |
+
"grad_norm": 0.0,
|
| 16593 |
+
"learning_rate": 3.9300000000000005e-06,
|
| 16594 |
+
"loss": 1.7387,
|
| 16595 |
+
"mean_token_accuracy": 0.6554303973913193,
|
| 16596 |
+
"num_tokens": 33604732.0,
|
| 16597 |
+
"step": 9215
|
| 16598 |
+
},
|
| 16599 |
+
{
|
| 16600 |
+
"epoch": 70.92307692307692,
|
| 16601 |
+
"grad_norm": 0.0,
|
| 16602 |
+
"learning_rate": 3.905000000000001e-06,
|
| 16603 |
+
"loss": 1.7101,
|
| 16604 |
+
"mean_token_accuracy": 0.6562773436307907,
|
| 16605 |
+
"num_tokens": 33623715.0,
|
| 16606 |
+
"step": 9220
|
| 16607 |
}
|
| 16608 |
],
|
| 16609 |
"logging_steps": 5,
|
|
|
|
| 16623 |
"attributes": {}
|
| 16624 |
}
|
| 16625 |
},
|
| 16626 |
+
"total_flos": 1.7049547531896422e+18,
|
| 16627 |
"train_batch_size": 4,
|
| 16628 |
"trial_name": null,
|
| 16629 |
"trial_params": null
|