Training in progress, step 1780, 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 sha256:8dd8c9d9f3a7c16d903bfbdf3ec8e11c9c80eca3433008a9fbad2a1499ac03ef
|
| 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 sha256:0820825d1cbe5e4b2171da9ecc0b4c41d7ff8c68d644e762b46b474419c96599
|
| 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:ab90bfe956c498ef45b5837dd6c68b6aef218e020f33deefd3f7038eb4e4d37c
|
| 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 sha256:7fa7a683972005770285a082502bed9974df9e57676d0c317c846b544cdbc910
|
| 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,
|
|
@@ -1778,6 +1778,26 @@
|
|
| 1778 |
"mean_token_accuracy": 0.7568591669201851,
|
| 1779 |
"num_tokens": 8161702.0,
|
| 1780 |
"step": 1760
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1781 |
}
|
| 1782 |
],
|
| 1783 |
"logging_steps": 10,
|
|
@@ -1797,7 +1817,7 @@
|
|
| 1797 |
"attributes": {}
|
| 1798 |
}
|
| 1799 |
},
|
| 1800 |
-
"total_flos": 3.
|
| 1801 |
"train_batch_size": 4,
|
| 1802 |
"trial_name": null,
|
| 1803 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.3797333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1780,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1778 |
"mean_token_accuracy": 0.7568591669201851,
|
| 1779 |
"num_tokens": 8161702.0,
|
| 1780 |
"step": 1760
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"entropy": 0.8932637803256511,
|
| 1784 |
+
"epoch": 0.3776,
|
| 1785 |
+
"grad_norm": 0.2185504138469696,
|
| 1786 |
+
"learning_rate": 9.367418221248989e-05,
|
| 1787 |
+
"loss": 0.9898091316223144,
|
| 1788 |
+
"mean_token_accuracy": 0.7799834325909615,
|
| 1789 |
+
"num_tokens": 8205315.0,
|
| 1790 |
+
"step": 1770
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"entropy": 0.9569453194737434,
|
| 1794 |
+
"epoch": 0.3797333333333333,
|
| 1795 |
+
"grad_norm": 0.34778159856796265,
|
| 1796 |
+
"learning_rate": 9.358966030849072e-05,
|
| 1797 |
+
"loss": 1.0686969757080078,
|
| 1798 |
+
"mean_token_accuracy": 0.7559246391057968,
|
| 1799 |
+
"num_tokens": 8252919.0,
|
| 1800 |
+
"step": 1780
|
| 1801 |
}
|
| 1802 |
],
|
| 1803 |
"logging_steps": 10,
|
|
|
|
| 1817 |
"attributes": {}
|
| 1818 |
}
|
| 1819 |
},
|
| 1820 |
+
"total_flos": 3.917839612576358e+16,
|
| 1821 |
"train_batch_size": 4,
|
| 1822 |
"trial_name": null,
|
| 1823 |
"trial_params": null
|