Training in progress, step 1150, 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 sha256:193e52d1b30645e034cdadc5cc041374447e045c39ffec0bf9828c1451dd098e
|
| 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:b60a0f959f23d70b24c1b529a5fbe6dc728a4d302e1a547a24a2458f95be31f9
|
| 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:a87a2b2412069a95b08bf0cc6f794ff9caee0c927a2e14476e375428fe4d3cb4
|
| 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 sha256:98b58ada4f5a3ed51c6bd6af3d4dd4c1aceca50ec3161348efc6a42e67f3f403
|
| 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,
|
|
@@ -1158,6 +1158,16 @@
|
|
| 1158 |
"mean_token_accuracy": 0.7390920028090477,
|
| 1159 |
"num_tokens": 5302986.0,
|
| 1160 |
"step": 1140
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1161 |
}
|
| 1162 |
],
|
| 1163 |
"logging_steps": 10,
|
|
@@ -1177,7 +1187,7 @@
|
|
| 1177 |
"attributes": {}
|
| 1178 |
}
|
| 1179 |
},
|
| 1180 |
-
"total_flos": 2.
|
| 1181 |
"train_batch_size": 4,
|
| 1182 |
"trial_name": null,
|
| 1183 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.24533333333333332,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1150,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1158 |
"mean_token_accuracy": 0.7390920028090477,
|
| 1159 |
"num_tokens": 5302986.0,
|
| 1160 |
"step": 1140
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"entropy": 0.9476075693964958,
|
| 1164 |
+
"epoch": 0.24533333333333332,
|
| 1165 |
+
"grad_norm": 0.2797292470932007,
|
| 1166 |
+
"learning_rate": 9.785642670599479e-05,
|
| 1167 |
+
"loss": 1.0823354721069336,
|
| 1168 |
+
"mean_token_accuracy": 0.765032921731472,
|
| 1169 |
+
"num_tokens": 5348946.0,
|
| 1170 |
+
"step": 1150
|
| 1171 |
}
|
| 1172 |
],
|
| 1173 |
"logging_steps": 10,
|
|
|
|
| 1187 |
"attributes": {}
|
| 1188 |
}
|
| 1189 |
},
|
| 1190 |
+
"total_flos": 2.5292097807765504e+16,
|
| 1191 |
"train_batch_size": 4,
|
| 1192 |
"trial_name": null,
|
| 1193 |
"trial_params": null
|