Training in progress, step 2950, 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 108113968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c68faf74deefdd29413093abfaef7ebb8dd126861e6584e73de84c21bb26717e
|
| 3 |
size 108113968
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 57081771
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1f877a766882cdbbd3df575b7cf469708765b676d3aeb5104c02cea03505a76
|
| 3 |
size 57081771
|
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 sha256:9696e879d7dc0d0942f02d2cf1a6d762c5aa5217ce0fc6436c33696910e288ca
|
| 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,
|
|
@@ -1178,6 +1178,16 @@
|
|
| 1178 |
"mean_token_accuracy": 0.9417970848083496,
|
| 1179 |
"num_tokens": 4250466.0,
|
| 1180 |
"step": 2925
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1181 |
}
|
| 1182 |
],
|
| 1183 |
"logging_steps": 25,
|
|
@@ -1197,7 +1207,7 @@
|
|
| 1197 |
"attributes": {}
|
| 1198 |
}
|
| 1199 |
},
|
| 1200 |
-
"total_flos": 2.
|
| 1201 |
"train_batch_size": 4,
|
| 1202 |
"trial_name": null,
|
| 1203 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8939393939393939,
|
| 6 |
"eval_steps": 300,
|
| 7 |
+
"global_step": 2950,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1178 |
"mean_token_accuracy": 0.9417970848083496,
|
| 1179 |
"num_tokens": 4250466.0,
|
| 1180 |
"step": 2925
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"entropy": 0.17894761979579926,
|
| 1184 |
+
"epoch": 0.8939393939393939,
|
| 1185 |
+
"grad_norm": 0.28316518664360046,
|
| 1186 |
+
"learning_rate": 0.0002,
|
| 1187 |
+
"loss": 0.17671188354492187,
|
| 1188 |
+
"mean_token_accuracy": 0.9409358501434326,
|
| 1189 |
+
"num_tokens": 4291207.0,
|
| 1190 |
+
"step": 2950
|
| 1191 |
}
|
| 1192 |
],
|
| 1193 |
"logging_steps": 25,
|
|
|
|
| 1207 |
"attributes": {}
|
| 1208 |
}
|
| 1209 |
},
|
| 1210 |
+
"total_flos": 2.8521356478117888e+17,
|
| 1211 |
"train_batch_size": 4,
|
| 1212 |
"trial_name": null,
|
| 1213 |
"trial_params": null
|