Training in progress, step 530, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f982b562a61d56ec88c927d94b2411635912f31e10481b36ab30b3cce791c977
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb30ea04c234d4ba96c9a55575da03e0537b8cd8d2ee0e07ce4471ccc4d4ddd7
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86db0c936b943210e7049764057f88776b6e2889685b63bc7fa74821938629ae
|
| 3 |
size 14645
|
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 sha256:142dde52320342a8b723fdcf9bf6931bda898c4bb30385516c999713759acce6
|
| 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": 0.
|
| 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,
|
|
@@ -538,6 +538,16 @@
|
|
| 538 |
"mean_token_accuracy": 0.7410315036773681,
|
| 539 |
"num_tokens": 2400184.0,
|
| 540 |
"step": 520
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 541 |
}
|
| 542 |
],
|
| 543 |
"logging_steps": 10,
|
|
@@ -557,7 +567,7 @@
|
|
| 557 |
"attributes": {}
|
| 558 |
}
|
| 559 |
},
|
| 560 |
-
"total_flos": 1.
|
| 561 |
"train_batch_size": 4,
|
| 562 |
"trial_name": null,
|
| 563 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.11306666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 530,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 538 |
"mean_token_accuracy": 0.7410315036773681,
|
| 539 |
"num_tokens": 2400184.0,
|
| 540 |
"step": 520
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"entropy": 1.0756568349897861,
|
| 544 |
+
"epoch": 0.11306666666666666,
|
| 545 |
+
"grad_norm": 0.322125107049942,
|
| 546 |
+
"learning_rate": 9.984300192212912e-05,
|
| 547 |
+
"loss": 1.15003662109375,
|
| 548 |
+
"mean_token_accuracy": 0.7418296962976456,
|
| 549 |
+
"num_tokens": 2445609.0,
|
| 550 |
+
"step": 530
|
| 551 |
}
|
| 552 |
],
|
| 553 |
"logging_steps": 10,
|
|
|
|
| 567 |
"attributes": {}
|
| 568 |
}
|
| 569 |
},
|
| 570 |
+
"total_flos": 1.1645244840382464e+16,
|
| 571 |
"train_batch_size": 4,
|
| 572 |
"trial_name": null,
|
| 573 |
"trial_params": null
|