Training in progress, step 660, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:503378e80c491daec80a03583c2aa12b48d779d327694ea3e79098a6726f4554
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6a9ea2c60b0039d31e41a70d68dfe378f56248684d309b1e7b7be9f5d6c1c74
|
| 3 |
size 14709
|
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:f553cc9664d278a2ee3e0ba26dbbecfd496e83a9ffb47eab38e79c18d0bd3605
|
| 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": 5.
|
| 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,
|
|
@@ -1178,6 +1178,24 @@
|
|
| 1178 |
"mean_token_accuracy": 0.6522481203079223,
|
| 1179 |
"num_tokens": 2370525.0,
|
| 1180 |
"step": 650
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1181 |
}
|
| 1182 |
],
|
| 1183 |
"logging_steps": 5,
|
|
@@ -1197,7 +1215,7 @@
|
|
| 1197 |
"attributes": {}
|
| 1198 |
}
|
| 1199 |
},
|
| 1200 |
-
"total_flos": 1.
|
| 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": 5.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 660,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1178 |
"mean_token_accuracy": 0.6522481203079223,
|
| 1179 |
"num_tokens": 2370525.0,
|
| 1180 |
"step": 650
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 5.038461538461538,
|
| 1184 |
+
"grad_norm": 0.0,
|
| 1185 |
+
"learning_rate": 4.673e-05,
|
| 1186 |
+
"loss": 1.7032,
|
| 1187 |
+
"mean_token_accuracy": 0.66204434633255,
|
| 1188 |
+
"num_tokens": 2388858.0,
|
| 1189 |
+
"step": 655
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 5.076923076923077,
|
| 1193 |
+
"grad_norm": 0.0,
|
| 1194 |
+
"learning_rate": 4.670500000000001e-05,
|
| 1195 |
+
"loss": 1.6985,
|
| 1196 |
+
"mean_token_accuracy": 0.6554162800312042,
|
| 1197 |
+
"num_tokens": 2408143.0,
|
| 1198 |
+
"step": 660
|
| 1199 |
}
|
| 1200 |
],
|
| 1201 |
"logging_steps": 5,
|
|
|
|
| 1215 |
"attributes": {}
|
| 1216 |
}
|
| 1217 |
},
|
| 1218 |
+
"total_flos": 1.2214133458255872e+17,
|
| 1219 |
"train_batch_size": 4,
|
| 1220 |
"trial_name": null,
|
| 1221 |
"trial_params": null
|