Training in progress, step 3850, 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 108113968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c17b3858423bba0fb2b5edc743a7df2572d5fd6f45d489b6d4705e7371285fac
|
| 3 |
size 108113968
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 57081771
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:803bfb2fdae19a336d36103ef624b159b3d307951397b653d6ea01b6f182d0cb
|
| 3 |
size 57081771
|
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 sha256:5f6cffd80bda1ce53a45de072fdb2b92cfaa27299f72bb76b0f46cfcfc865ede
|
| 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": 300,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1538,6 +1538,16 @@
|
|
| 1538 |
"mean_token_accuracy": 0.9428924822807312,
|
| 1539 |
"num_tokens": 335722.0,
|
| 1540 |
"step": 3825
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1541 |
}
|
| 1542 |
],
|
| 1543 |
"logging_steps": 25,
|
|
@@ -1557,7 +1567,7 @@
|
|
| 1557 |
"attributes": {}
|
| 1558 |
}
|
| 1559 |
},
|
| 1560 |
-
"total_flos": 3.
|
| 1561 |
"train_batch_size": 4,
|
| 1562 |
"trial_name": null,
|
| 1563 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8751989088429188,
|
| 6 |
"eval_steps": 300,
|
| 7 |
+
"global_step": 3850,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1538 |
"mean_token_accuracy": 0.9428924822807312,
|
| 1539 |
"num_tokens": 335722.0,
|
| 1540 |
"step": 3825
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"entropy": 0.1638861256837845,
|
| 1544 |
+
"epoch": 0.8751989088429188,
|
| 1545 |
+
"grad_norm": 0.2881450355052948,
|
| 1546 |
+
"learning_rate": 0.0002,
|
| 1547 |
+
"loss": 0.1645718002319336,
|
| 1548 |
+
"mean_token_accuracy": 0.9459069275856018,
|
| 1549 |
+
"num_tokens": 366055.0,
|
| 1550 |
+
"step": 3850
|
| 1551 |
}
|
| 1552 |
],
|
| 1553 |
"logging_steps": 25,
|
|
|
|
| 1567 |
"attributes": {}
|
| 1568 |
}
|
| 1569 |
},
|
| 1570 |
+
"total_flos": 3.373595952701399e+17,
|
| 1571 |
"train_batch_size": 4,
|
| 1572 |
"trial_name": null,
|
| 1573 |
"trial_params": null
|