Training in progress, step 520, 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:e25752fbc6bacb285c1e08f02f5ff59ff4f180bb74e7fc2e1b4a6fdcb41f4623
|
| 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 sha256:7c8bf8b42149784d3b6b5833078e91de4a80498f936a587aeffd88d79e8d9e17
|
| 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 sha256:0162e534681b98e095b924affb3bb23d94ecd13778f1caa5a5f48319d1db2401
|
| 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:fe1ec560dde11559a3cc1e1fba4eb2cd38d4fa0c680747bd4c2d8206aa8975e1
|
| 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,
|
|
@@ -528,6 +528,16 @@
|
|
| 528 |
"mean_token_accuracy": 0.7657018698751926,
|
| 529 |
"num_tokens": 2352188.0,
|
| 530 |
"step": 510
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 531 |
}
|
| 532 |
],
|
| 533 |
"logging_steps": 10,
|
|
@@ -547,7 +557,7 @@
|
|
| 547 |
"attributes": {}
|
| 548 |
}
|
| 549 |
},
|
| 550 |
-
"total_flos": 1.
|
| 551 |
"train_batch_size": 4,
|
| 552 |
"trial_name": null,
|
| 553 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.11093333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 520,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 528 |
"mean_token_accuracy": 0.7657018698751926,
|
| 529 |
"num_tokens": 2352188.0,
|
| 530 |
"step": 510
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"entropy": 1.0380054742097855,
|
| 534 |
+
"epoch": 0.11093333333333333,
|
| 535 |
+
"grad_norm": 0.22924789786338806,
|
| 536 |
+
"learning_rate": 9.985640774073634e-05,
|
| 537 |
+
"loss": 1.0875710487365722,
|
| 538 |
+
"mean_token_accuracy": 0.7410315036773681,
|
| 539 |
+
"num_tokens": 2400184.0,
|
| 540 |
+
"step": 520
|
| 541 |
}
|
| 542 |
],
|
| 543 |
"logging_steps": 10,
|
|
|
|
| 557 |
"attributes": {}
|
| 558 |
}
|
| 559 |
},
|
| 560 |
+
"total_flos": 1.1423138325092352e+16,
|
| 561 |
"train_batch_size": 4,
|
| 562 |
"trial_name": null,
|
| 563 |
"trial_params": null
|