Training in progress, step 3200, 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 sha256:4a6194decd5c41b1d392f5b6a5526c862c4e03d75a2dd8c8d3496b537164c924
|
| 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 sha256:73e03c1bb5699997b82591d17eabfada95cbe056a96727cf2d2ad69cbfdf5bd7
|
| 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:df60d642c5b261118910ad500cd47166ae3633ef9d95665fc8d6f01f0fcabd33
|
| 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 sha256:98f6aafd392baebf728bf16476f3c3f7a41f8a1d6e44904a5322e138fe82b0a6
|
| 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,
|
|
@@ -3208,6 +3208,16 @@
|
|
| 3208 |
"mean_token_accuracy": 0.7678594440221786,
|
| 3209 |
"num_tokens": 14851182.0,
|
| 3210 |
"step": 3190
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3211 |
}
|
| 3212 |
],
|
| 3213 |
"logging_steps": 10,
|
|
@@ -3227,7 +3237,7 @@
|
|
| 3227 |
"attributes": {}
|
| 3228 |
}
|
| 3229 |
},
|
| 3230 |
-
"total_flos": 7.
|
| 3231 |
"train_batch_size": 4,
|
| 3232 |
"trial_name": null,
|
| 3233 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.6826666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3208 |
"mean_token_accuracy": 0.7678594440221786,
|
| 3209 |
"num_tokens": 14851182.0,
|
| 3210 |
"step": 3190
|
| 3211 |
+
},
|
| 3212 |
+
{
|
| 3213 |
+
"entropy": 0.7769002497196198,
|
| 3214 |
+
"epoch": 0.6826666666666666,
|
| 3215 |
+
"grad_norm": 0.29509180784225464,
|
| 3216 |
+
"learning_rate": 7.68690349311016e-05,
|
| 3217 |
+
"loss": 0.8263790130615234,
|
| 3218 |
+
"mean_token_accuracy": 0.8022488832473755,
|
| 3219 |
+
"num_tokens": 14891820.0,
|
| 3220 |
+
"step": 3200
|
| 3221 |
}
|
| 3222 |
],
|
| 3223 |
"logging_steps": 10,
|
|
|
|
| 3237 |
"attributes": {}
|
| 3238 |
}
|
| 3239 |
},
|
| 3240 |
+
"total_flos": 7.052555948237722e+16,
|
| 3241 |
"train_batch_size": 4,
|
| 3242 |
"trial_name": null,
|
| 3243 |
"trial_params": null
|