Training in progress, step 1600, 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:dc39f73ea42dc9acbbc3dfde7059989d8d956689678643fc0116efe63ea09d8d
|
| 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 sha256:60cc6c4734cc1b7f9ed5a1967e2566b5d88112a923c88bbadc22a78369e10206
|
| 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 sha256:5972c779189e86156c49034d69b6fee8d7db0fbe05b826d83094cbf4c2951ca1
|
| 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 sha256:248ed2f56978cfdca5e0556182d3c61a6a6a35385b06f5e0627995c12392623b
|
| 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,
|
|
@@ -1608,6 +1608,16 @@
|
|
| 1608 |
"mean_token_accuracy": 0.7759940758347511,
|
| 1609 |
"num_tokens": 7393383.0,
|
| 1610 |
"step": 1590
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1611 |
}
|
| 1612 |
],
|
| 1613 |
"logging_steps": 10,
|
|
@@ -1627,7 +1637,7 @@
|
|
| 1627 |
"attributes": {}
|
| 1628 |
}
|
| 1629 |
},
|
| 1630 |
-
"total_flos": 3.
|
| 1631 |
"train_batch_size": 4,
|
| 1632 |
"trial_name": null,
|
| 1633 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.3413333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1600,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1608 |
"mean_token_accuracy": 0.7759940758347511,
|
| 1609 |
"num_tokens": 7393383.0,
|
| 1610 |
"step": 1590
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"entropy": 0.9520958945155144,
|
| 1614 |
+
"epoch": 0.3413333333333333,
|
| 1615 |
+
"grad_norm": 0.2607707679271698,
|
| 1616 |
+
"learning_rate": 9.50301906378154e-05,
|
| 1617 |
+
"loss": 1.0628732681274413,
|
| 1618 |
+
"mean_token_accuracy": 0.7598425537347794,
|
| 1619 |
+
"num_tokens": 7439670.0,
|
| 1620 |
+
"step": 1600
|
| 1621 |
}
|
| 1622 |
],
|
| 1623 |
"logging_steps": 10,
|
|
|
|
| 1637 |
"attributes": {}
|
| 1638 |
}
|
| 1639 |
},
|
| 1640 |
+
"total_flos": 3.5268200380194816e+16,
|
| 1641 |
"train_batch_size": 4,
|
| 1642 |
"trial_name": null,
|
| 1643 |
"trial_params": null
|