Training in progress, step 2570, 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:b644e512c89843d97d997f8a9c53bf1ce6be1554e3802234674d774f8014328a
|
| 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 sha256:244ef5d25a5a82e09cea12d17f1b198217012526842ef2c65441d505fac6635b
|
| 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 sha256:48d4ff4c1ac80a437a2b457e1a9cb435b917049919abfd5a51eb188115254ac8
|
| 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:a541264643bd1ce7de970e9b47b3a04a702c2dd2cd8a9962cc93dd00e4370124
|
| 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,
|
|
@@ -2578,6 +2578,16 @@
|
|
| 2578 |
"mean_token_accuracy": 0.7738461554050445,
|
| 2579 |
"num_tokens": 11895685.0,
|
| 2580 |
"step": 2560
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2581 |
}
|
| 2582 |
],
|
| 2583 |
"logging_steps": 10,
|
|
@@ -2597,7 +2607,7 @@
|
|
| 2597 |
"attributes": {}
|
| 2598 |
}
|
| 2599 |
},
|
| 2600 |
-
"total_flos": 5.
|
| 2601 |
"train_batch_size": 4,
|
| 2602 |
"trial_name": null,
|
| 2603 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5482666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2570,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2578 |
"mean_token_accuracy": 0.7738461554050445,
|
| 2579 |
"num_tokens": 11895685.0,
|
| 2580 |
"step": 2560
|
| 2581 |
+
},
|
| 2582 |
+
{
|
| 2583 |
+
"entropy": 0.8330970570445061,
|
| 2584 |
+
"epoch": 0.5482666666666667,
|
| 2585 |
+
"grad_norm": 0.25935855507850647,
|
| 2586 |
+
"learning_rate": 8.535533905932738e-05,
|
| 2587 |
+
"loss": 0.9135859489440918,
|
| 2588 |
+
"mean_token_accuracy": 0.7793566673994065,
|
| 2589 |
+
"num_tokens": 11940774.0,
|
| 2590 |
+
"step": 2570
|
| 2591 |
}
|
| 2592 |
],
|
| 2593 |
"logging_steps": 10,
|
|
|
|
| 2607 |
"attributes": {}
|
| 2608 |
}
|
| 2609 |
},
|
| 2610 |
+
"total_flos": 5.662076880986419e+16,
|
| 2611 |
"train_batch_size": 4,
|
| 2612 |
"trial_name": null,
|
| 2613 |
"trial_params": null
|