Training in progress, step 2150, 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 sha256:9af2591401db89c8bcf5627116d9e4981f723c431cde3b541c032e1eddd70fc4
|
| 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 sha256:9429dc5bc2ae496071061cab33503c51766e22eb97a42ba4de97e945fe500e9d
|
| 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:a82a2faeef8f44f548e688d0bfad38b4dc444eed1d9b5de630a36c31ad2022b8
|
| 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 sha256:8193bdd060acd9eea78ef0a8acdfe4565aa2a7a858785f436b7cec03021cb345
|
| 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,
|
|
@@ -2158,6 +2158,16 @@
|
|
| 2158 |
"mean_token_accuracy": 0.7673163414001465,
|
| 2159 |
"num_tokens": 9924229.0,
|
| 2160 |
"step": 2140
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2161 |
}
|
| 2162 |
],
|
| 2163 |
"logging_steps": 10,
|
|
@@ -2177,7 +2187,7 @@
|
|
| 2177 |
"attributes": {}
|
| 2178 |
}
|
| 2179 |
},
|
| 2180 |
-
"total_flos": 4.
|
| 2181 |
"train_batch_size": 4,
|
| 2182 |
"trial_name": null,
|
| 2183 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.45866666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2150,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2158 |
"mean_token_accuracy": 0.7673163414001465,
|
| 2159 |
"num_tokens": 9924229.0,
|
| 2160 |
"step": 2140
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"entropy": 1.1109409362077713,
|
| 2164 |
+
"epoch": 0.45866666666666667,
|
| 2165 |
+
"grad_norm": 0.2716203033924103,
|
| 2166 |
+
"learning_rate": 9.010424564622353e-05,
|
| 2167 |
+
"loss": 1.1743658065795899,
|
| 2168 |
+
"mean_token_accuracy": 0.7358616881072522,
|
| 2169 |
+
"num_tokens": 9972409.0,
|
| 2170 |
+
"step": 2150
|
| 2171 |
}
|
| 2172 |
],
|
| 2173 |
"logging_steps": 10,
|
|
|
|
| 2187 |
"attributes": {}
|
| 2188 |
}
|
| 2189 |
},
|
| 2190 |
+
"total_flos": 4.731821330198016e+16,
|
| 2191 |
"train_batch_size": 4,
|
| 2192 |
"trial_name": null,
|
| 2193 |
"trial_params": null
|