Training in progress, step 1900, 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 sha256:1167122266955c58d336fcb3737918fa0cf2855602282a48b199fab96303200f
|
| 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 sha256:42f45ebf44a3f5123453867e6e8568bc5d10af64ff07d0bbbf9e2808428710b5
|
| 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 sha256:32a5528166168ffda74554ce3d9e46fbd51adb8f2e8a9328c3f66817bb311b54
|
| 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 sha256:3a50b6ada732039affb9dd5cc468ba0a686c56ff994976915da76196403c812f
|
| 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,
|
|
@@ -1908,6 +1908,16 @@
|
|
| 1908 |
"mean_token_accuracy": 0.7566848322749138,
|
| 1909 |
"num_tokens": 8753713.0,
|
| 1910 |
"step": 1890
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1911 |
}
|
| 1912 |
],
|
| 1913 |
"logging_steps": 10,
|
|
@@ -1927,7 +1937,7 @@
|
|
| 1927 |
"attributes": {}
|
| 1928 |
}
|
| 1929 |
},
|
| 1930 |
-
"total_flos": 4.
|
| 1931 |
"train_batch_size": 4,
|
| 1932 |
"trial_name": null,
|
| 1933 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.4053333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1900,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1908 |
"mean_token_accuracy": 0.7566848322749138,
|
| 1909 |
"num_tokens": 8753713.0,
|
| 1910 |
"step": 1890
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"entropy": 1.0487395107746125,
|
| 1914 |
+
"epoch": 0.4053333333333333,
|
| 1915 |
+
"grad_norm": 0.24727876484394073,
|
| 1916 |
+
"learning_rate": 9.25349563890463e-05,
|
| 1917 |
+
"loss": 1.254913330078125,
|
| 1918 |
+
"mean_token_accuracy": 0.7382492840290069,
|
| 1919 |
+
"num_tokens": 8801703.0,
|
| 1920 |
+
"step": 1900
|
| 1921 |
}
|
| 1922 |
],
|
| 1923 |
"logging_steps": 10,
|
|
|
|
| 1937 |
"attributes": {}
|
| 1938 |
}
|
| 1939 |
},
|
| 1940 |
+
"total_flos": 4.178739518938829e+16,
|
| 1941 |
"train_batch_size": 4,
|
| 1942 |
"trial_name": null,
|
| 1943 |
"trial_params": null
|