Training in progress, step 80, 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:d10131fb2bdabea59625c8c4edf334e6df6721f617bf0dec9aaa337ebb104f71
|
| 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 sha256:6a73c7d1b70990d010aed3d00a13855494c339ed8f762b75df50f3dea0d0a491
|
| 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:fd856c6151fe5255f7ba51db6b5d88b86efb0fa47af76b1fc101585c59f7e4b5
|
| 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,
|
|
@@ -134,6 +134,24 @@
|
|
| 134 |
"mean_token_accuracy": 0.6556680232286454,
|
| 135 |
"num_tokens": 254323.0,
|
| 136 |
"step": 70
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 137 |
}
|
| 138 |
],
|
| 139 |
"logging_steps": 5,
|
|
@@ -153,7 +171,7 @@
|
|
| 153 |
"attributes": {}
|
| 154 |
}
|
| 155 |
},
|
| 156 |
-
"total_flos": 1.
|
| 157 |
"train_batch_size": 4,
|
| 158 |
"trial_name": null,
|
| 159 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.6153846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 80,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 134 |
"mean_token_accuracy": 0.6556680232286454,
|
| 135 |
"num_tokens": 254323.0,
|
| 136 |
"step": 70
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.5769230769230769,
|
| 140 |
+
"grad_norm": 0.0,
|
| 141 |
+
"learning_rate": 4.9630000000000004e-05,
|
| 142 |
+
"loss": 1.6761,
|
| 143 |
+
"mean_token_accuracy": 0.6626079142093658,
|
| 144 |
+
"num_tokens": 273788.0,
|
| 145 |
+
"step": 75
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.6153846153846154,
|
| 149 |
+
"grad_norm": 0.0,
|
| 150 |
+
"learning_rate": 4.9605000000000004e-05,
|
| 151 |
+
"loss": 1.7992,
|
| 152 |
+
"mean_token_accuracy": 0.6399475276470185,
|
| 153 |
+
"num_tokens": 291226.0,
|
| 154 |
+
"step": 80
|
| 155 |
}
|
| 156 |
],
|
| 157 |
"logging_steps": 5,
|
|
|
|
| 171 |
"attributes": {}
|
| 172 |
}
|
| 173 |
},
|
| 174 |
+
"total_flos": 1.469040538927104e+16,
|
| 175 |
"train_batch_size": 4,
|
| 176 |
"trial_name": null,
|
| 177 |
"trial_params": null
|