Training in progress, step 3160, 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 sha256:749803cc6f30a8ddddbfaa8d909c42223ac848574d87ba6b22a6a24dbf1265a7
|
| 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 sha256:4410156c81daf459ea4f13f9bfec98479dbced23f4cdedc6c6791cb65641f245
|
| 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 sha256:2087370115543fb55f65cc232b1dd1c068de72a2f5f799b41c4d6b7bc7f0cd25
|
| 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:ec0ba3aeafd1b8e7a62426695e2c37bb081525a6591384cba0958e024564900e
|
| 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,
|
|
@@ -3168,6 +3168,16 @@
|
|
| 3168 |
"mean_token_accuracy": 0.7730352610349656,
|
| 3169 |
"num_tokens": 14664132.0,
|
| 3170 |
"step": 3150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3171 |
}
|
| 3172 |
],
|
| 3173 |
"logging_steps": 10,
|
|
@@ -3187,7 +3197,7 @@
|
|
| 3187 |
"attributes": {}
|
| 3188 |
}
|
| 3189 |
},
|
| 3190 |
-
"total_flos": 6.
|
| 3191 |
"train_batch_size": 4,
|
| 3192 |
"trial_name": null,
|
| 3193 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.6741333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3160,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3168 |
"mean_token_accuracy": 0.7730352610349656,
|
| 3169 |
"num_tokens": 14664132.0,
|
| 3170 |
"step": 3150
|
| 3171 |
+
},
|
| 3172 |
+
{
|
| 3173 |
+
"entropy": 0.9587577134370804,
|
| 3174 |
+
"epoch": 0.6741333333333334,
|
| 3175 |
+
"grad_norm": 0.2750677168369293,
|
| 3176 |
+
"learning_rate": 7.74502729677194e-05,
|
| 3177 |
+
"loss": 1.1020426750183105,
|
| 3178 |
+
"mean_token_accuracy": 0.7670308589935303,
|
| 3179 |
+
"num_tokens": 14711920.0,
|
| 3180 |
+
"step": 3160
|
| 3181 |
}
|
| 3182 |
],
|
| 3183 |
"logging_steps": 10,
|
|
|
|
| 3197 |
"attributes": {}
|
| 3198 |
}
|
| 3199 |
},
|
| 3200 |
+
"total_flos": 6.966268206890189e+16,
|
| 3201 |
"train_batch_size": 4,
|
| 3202 |
"trial_name": null,
|
| 3203 |
"trial_params": null
|