Training in progress, step 1870, 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:b7f7c08832e92f3eeaa3fffe9fcce3c0dad0fb6473cfb08d2095dbee016d00a7
|
| 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 sha256:43d094aa248f0598f9d95ed9c986ffa93a3fabcbfc45787cae041ac00ed84917
|
| 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:cc34e013baf527021face29460cea50f3e631686955bd2ca7ee9759fff2228e1
|
| 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:d713ff246b23b74f0424998c9c9a109a8f309e2172ab9e5adad25868e58ead9f
|
| 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,
|
|
@@ -1878,6 +1878,16 @@
|
|
| 1878 |
"mean_token_accuracy": 0.7888635769486427,
|
| 1879 |
"num_tokens": 8623046.0,
|
| 1880 |
"step": 1860
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1881 |
}
|
| 1882 |
],
|
| 1883 |
"logging_steps": 10,
|
|
@@ -1897,7 +1907,7 @@
|
|
| 1897 |
"attributes": {}
|
| 1898 |
}
|
| 1899 |
},
|
| 1900 |
-
"total_flos": 4.
|
| 1901 |
"train_batch_size": 4,
|
| 1902 |
"trial_name": null,
|
| 1903 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.3989333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1870,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1878 |
"mean_token_accuracy": 0.7888635769486427,
|
| 1879 |
"num_tokens": 8623046.0,
|
| 1880 |
"step": 1860
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"entropy": 0.9134793929755688,
|
| 1884 |
+
"epoch": 0.3989333333333333,
|
| 1885 |
+
"grad_norm": 0.25643301010131836,
|
| 1886 |
+
"learning_rate": 9.280558467355907e-05,
|
| 1887 |
+
"loss": 1.0032004356384276,
|
| 1888 |
+
"mean_token_accuracy": 0.7722208425402641,
|
| 1889 |
+
"num_tokens": 8665201.0,
|
| 1890 |
+
"step": 1870
|
| 1891 |
}
|
| 1892 |
],
|
| 1893 |
"logging_steps": 10,
|
|
|
|
| 1907 |
"attributes": {}
|
| 1908 |
}
|
| 1909 |
},
|
| 1910 |
+
"total_flos": 4.115056247781274e+16,
|
| 1911 |
"train_batch_size": 4,
|
| 1912 |
"trial_name": null,
|
| 1913 |
"trial_params": null
|