Training in progress, step 5300, 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 sha256:42be3b4e166581aede6f1787e77121d6c1cdc374e8cde284924a08e2282b59ab
|
| 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:b955dad4375d2360e32024b5857188d35b0ca4032d1f5c9a15c9a0300a131448
|
| 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 sha256:20cd5cdcc6e92223fcb18fc6c12107a6a5bcdc264cf42b9a42d7adfc4f1b26d8
|
| 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": 40.
|
| 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,
|
|
@@ -9530,6 +9530,24 @@
|
|
| 9530 |
"mean_token_accuracy": 0.6521205425262451,
|
| 9531 |
"num_tokens": 19292138.0,
|
| 9532 |
"step": 5290
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9533 |
}
|
| 9534 |
],
|
| 9535 |
"logging_steps": 5,
|
|
@@ -9549,7 +9567,7 @@
|
|
| 9549 |
"attributes": {}
|
| 9550 |
}
|
| 9551 |
},
|
| 9552 |
-
"total_flos": 9.
|
| 9553 |
"train_batch_size": 4,
|
| 9554 |
"trial_name": null,
|
| 9555 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 40.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5300,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9530 |
"mean_token_accuracy": 0.6521205425262451,
|
| 9531 |
"num_tokens": 19292138.0,
|
| 9532 |
"step": 5290
|
| 9533 |
+
},
|
| 9534 |
+
{
|
| 9535 |
+
"epoch": 40.73076923076923,
|
| 9536 |
+
"grad_norm": 0.0,
|
| 9537 |
+
"learning_rate": 2.3530000000000003e-05,
|
| 9538 |
+
"loss": 1.7605,
|
| 9539 |
+
"mean_token_accuracy": 0.652343025803566,
|
| 9540 |
+
"num_tokens": 19310319.0,
|
| 9541 |
+
"step": 5295
|
| 9542 |
+
},
|
| 9543 |
+
{
|
| 9544 |
+
"epoch": 40.76923076923077,
|
| 9545 |
+
"grad_norm": 0.0,
|
| 9546 |
+
"learning_rate": 2.3505000000000003e-05,
|
| 9547 |
+
"loss": 1.7581,
|
| 9548 |
+
"mean_token_accuracy": 0.6503111094236373,
|
| 9549 |
+
"num_tokens": 19328485.0,
|
| 9550 |
+
"step": 5300
|
| 9551 |
}
|
| 9552 |
],
|
| 9553 |
"logging_steps": 5,
|
|
|
|
| 9567 |
"attributes": {}
|
| 9568 |
}
|
| 9569 |
},
|
| 9570 |
+
"total_flos": 9.794085222924288e+17,
|
| 9571 |
"train_batch_size": 4,
|
| 9572 |
"trial_name": null,
|
| 9573 |
"trial_params": null
|