Training in progress, step 2975, 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 20814808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd92e726a6b7ed50eb3b58654f0558f5e1dad21dbc9338efbe872046d7fb8215
|
| 3 |
size 20814808
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21506325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98a713cd297d49229319bb13573f97f60da6c33f94ed39f682bc6dc4f399dff9
|
| 3 |
size 21506325
|
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 sha256:07cbb23d370e7724e6174914cf52236d3fc9800f5d4e9aaa18bc96016209034c
|
| 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": 300,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1188,6 +1188,16 @@
|
|
| 1188 |
"mean_token_accuracy": 0.9455317616462707,
|
| 1189 |
"num_tokens": 4824646.0,
|
| 1190 |
"step": 2950
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1191 |
}
|
| 1192 |
],
|
| 1193 |
"logging_steps": 25,
|
|
@@ -1207,7 +1217,7 @@
|
|
| 1207 |
"attributes": {}
|
| 1208 |
}
|
| 1209 |
},
|
| 1210 |
-
"total_flos": 6.
|
| 1211 |
"train_batch_size": 2,
|
| 1212 |
"trial_name": null,
|
| 1213 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9016517654190028,
|
| 6 |
"eval_steps": 300,
|
| 7 |
+
"global_step": 2975,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1188 |
"mean_token_accuracy": 0.9455317616462707,
|
| 1189 |
"num_tokens": 4824646.0,
|
| 1190 |
"step": 2950
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"entropy": 0.17551869243383408,
|
| 1194 |
+
"epoch": 0.9016517654190028,
|
| 1195 |
+
"grad_norm": 0.26953125,
|
| 1196 |
+
"learning_rate": 0.0002,
|
| 1197 |
+
"loss": 0.1772,
|
| 1198 |
+
"mean_token_accuracy": 0.9419298887252807,
|
| 1199 |
+
"num_tokens": 4866662.0,
|
| 1200 |
+
"step": 2975
|
| 1201 |
}
|
| 1202 |
],
|
| 1203 |
"logging_steps": 25,
|
|
|
|
| 1217 |
"attributes": {}
|
| 1218 |
}
|
| 1219 |
},
|
| 1220 |
+
"total_flos": 6.499001694578278e+16,
|
| 1221 |
"train_batch_size": 2,
|
| 1222 |
"trial_name": null,
|
| 1223 |
"trial_params": null
|