Training in progress, step 2630, 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 sha256:5c9b8512aa1be3612a01e56e95534d2aafc3e03fe46fab0417ce5b86711a2568
|
| 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 sha256:1c842bf85026d7b26bcb687872072c5172dfe807bdec1a3e6f1dff3d7329272d
|
| 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 sha256:7dc4ba2aa5c153f7d4ec40f47dab69d6b3b54f645f81bfc17911e09fab786004
|
| 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 sha256:3eba85d8a959c650472bba485c18e1136a0db94e9ee761b395692036382b4b88
|
| 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,
|
|
@@ -2638,6 +2638,16 @@
|
|
| 2638 |
"mean_token_accuracy": 0.7624668940901757,
|
| 2639 |
"num_tokens": 12177100.0,
|
| 2640 |
"step": 2620
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2641 |
}
|
| 2642 |
],
|
| 2643 |
"logging_steps": 10,
|
|
@@ -2657,7 +2667,7 @@
|
|
| 2657 |
"attributes": {}
|
| 2658 |
}
|
| 2659 |
},
|
| 2660 |
-
"total_flos": 5.
|
| 2661 |
"train_batch_size": 4,
|
| 2662 |
"trial_name": null,
|
| 2663 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5610666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2630,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2638 |
"mean_token_accuracy": 0.7624668940901757,
|
| 2639 |
"num_tokens": 12177100.0,
|
| 2640 |
"step": 2620
|
| 2641 |
+
},
|
| 2642 |
+
{
|
| 2643 |
+
"entropy": 0.9657470785081387,
|
| 2644 |
+
"epoch": 0.5610666666666667,
|
| 2645 |
+
"grad_norm": 0.2379087507724762,
|
| 2646 |
+
"learning_rate": 8.461348724250384e-05,
|
| 2647 |
+
"loss": 1.075094223022461,
|
| 2648 |
+
"mean_token_accuracy": 0.7620343893766404,
|
| 2649 |
+
"num_tokens": 12223113.0,
|
| 2650 |
+
"step": 2630
|
| 2651 |
}
|
| 2652 |
],
|
| 2653 |
"logging_steps": 10,
|
|
|
|
| 2667 |
"attributes": {}
|
| 2668 |
}
|
| 2669 |
},
|
| 2670 |
+
"total_flos": 5.791965845342822e+16,
|
| 2671 |
"train_batch_size": 4,
|
| 2672 |
"trial_name": null,
|
| 2673 |
"trial_params": null
|