Training in progress, step 1480, 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:c7f3dd89596fe102e77c2f1597d78e39442ccc6d20543a89fa4bd62a07e94b3f
|
| 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 sha256:7f186021b5ade9d4953387468b6aebc6dccbc2727cdde65b05d58f0497e54042
|
| 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:bda3e3a5c0bd72eceda960afd912c2626af55965c4c14a4ff43705eafeaf6f4b
|
| 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": 11.
|
| 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,
|
|
@@ -2654,6 +2654,24 @@
|
|
| 2654 |
"mean_token_accuracy": 0.6595575481653213,
|
| 2655 |
"num_tokens": 5361091.0,
|
| 2656 |
"step": 1470
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2657 |
}
|
| 2658 |
],
|
| 2659 |
"logging_steps": 5,
|
|
@@ -2673,7 +2691,7 @@
|
|
| 2673 |
"attributes": {}
|
| 2674 |
}
|
| 2675 |
},
|
| 2676 |
-
"total_flos": 2.
|
| 2677 |
"train_batch_size": 4,
|
| 2678 |
"trial_name": null,
|
| 2679 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 11.384615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1480,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2654 |
"mean_token_accuracy": 0.6595575481653213,
|
| 2655 |
"num_tokens": 5361091.0,
|
| 2656 |
"step": 1470
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 11.346153846153847,
|
| 2660 |
+
"grad_norm": 0.0,
|
| 2661 |
+
"learning_rate": 4.2630000000000004e-05,
|
| 2662 |
+
"loss": 1.8037,
|
| 2663 |
+
"mean_token_accuracy": 0.639024817943573,
|
| 2664 |
+
"num_tokens": 5378623.0,
|
| 2665 |
+
"step": 1475
|
| 2666 |
+
},
|
| 2667 |
+
{
|
| 2668 |
+
"epoch": 11.384615384615385,
|
| 2669 |
+
"grad_norm": 0.0,
|
| 2670 |
+
"learning_rate": 4.2605e-05,
|
| 2671 |
+
"loss": 1.7528,
|
| 2672 |
+
"mean_token_accuracy": 0.6455299586057663,
|
| 2673 |
+
"num_tokens": 5397097.0,
|
| 2674 |
+
"step": 1480
|
| 2675 |
}
|
| 2676 |
],
|
| 2677 |
"logging_steps": 5,
|
|
|
|
| 2691 |
"attributes": {}
|
| 2692 |
}
|
| 2693 |
},
|
| 2694 |
+
"total_flos": 2.7349009311596544e+17,
|
| 2695 |
"train_batch_size": 4,
|
| 2696 |
"trial_name": null,
|
| 2697 |
"trial_params": null
|