Training in progress, step 630, 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:b3277891082031b37de45444bf38121241ba3659e984f2845bc3372057253d04
|
| 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 sha256:536ce9e94a9bcb8b56f348852470547d1de9e55ca21599c371d1637f08fb1091
|
| 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 sha256:7774b4456497075a0fa71051c36cdb0f9ea067cb78782a700017d95483faa493
|
| 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": 4.
|
| 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,
|
|
@@ -1124,6 +1124,24 @@
|
|
| 1124 |
"mean_token_accuracy": 0.6406325221061706,
|
| 1125 |
"num_tokens": 2261272.0,
|
| 1126 |
"step": 620
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1127 |
}
|
| 1128 |
],
|
| 1129 |
"logging_steps": 5,
|
|
@@ -1143,7 +1161,7 @@
|
|
| 1143 |
"attributes": {}
|
| 1144 |
}
|
| 1145 |
},
|
| 1146 |
-
"total_flos": 1.
|
| 1147 |
"train_batch_size": 4,
|
| 1148 |
"trial_name": null,
|
| 1149 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.846153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 630,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1124 |
"mean_token_accuracy": 0.6406325221061706,
|
| 1125 |
"num_tokens": 2261272.0,
|
| 1126 |
"step": 620
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 4.8076923076923075,
|
| 1130 |
+
"grad_norm": 0.0,
|
| 1131 |
+
"learning_rate": 4.688e-05,
|
| 1132 |
+
"loss": 1.7167,
|
| 1133 |
+
"mean_token_accuracy": 0.6534736841917038,
|
| 1134 |
+
"num_tokens": 2279807.0,
|
| 1135 |
+
"step": 625
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 4.846153846153846,
|
| 1139 |
+
"grad_norm": 0.0,
|
| 1140 |
+
"learning_rate": 4.6855000000000005e-05,
|
| 1141 |
+
"loss": 1.8479,
|
| 1142 |
+
"mean_token_accuracy": 0.6247967123985291,
|
| 1143 |
+
"num_tokens": 2297161.0,
|
| 1144 |
+
"step": 630
|
| 1145 |
}
|
| 1146 |
],
|
| 1147 |
"logging_steps": 5,
|
|
|
|
| 1161 |
"attributes": {}
|
| 1162 |
}
|
| 1163 |
},
|
| 1164 |
+
"total_flos": 1.164359235207168e+17,
|
| 1165 |
"train_batch_size": 4,
|
| 1166 |
"trial_name": null,
|
| 1167 |
"trial_params": null
|