Training in progress, step 3250, 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 sha256:22ed3532f5b11e54de85642629efcfd9f7c0e2a2770508cbceb3134a01f156ec
|
| 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:cfba78d9a9f1c83bf8c3051e70ab0dff569dd18ef23936e1f56d5a86c28d8343
|
| 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 sha256:0528a8e731164fe038b69287f829516372e3210481061b2bb434269a6b516298
|
| 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 sha256:3ea07e7d812f63f155b75aaffd73c48f3d2b8161636db0769e0c9e2e451ee3f1
|
| 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,
|
|
@@ -3258,6 +3258,16 @@
|
|
| 3258 |
"mean_token_accuracy": 0.768897658586502,
|
| 3259 |
"num_tokens": 15075297.0,
|
| 3260 |
"step": 3240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3261 |
}
|
| 3262 |
],
|
| 3263 |
"logging_steps": 10,
|
|
@@ -3277,7 +3287,7 @@
|
|
| 3277 |
"attributes": {}
|
| 3278 |
}
|
| 3279 |
},
|
| 3280 |
-
"total_flos": 7.
|
| 3281 |
"train_batch_size": 4,
|
| 3282 |
"trial_name": null,
|
| 3283 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.6933333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3250,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3258 |
"mean_token_accuracy": 0.768897658586502,
|
| 3259 |
"num_tokens": 15075297.0,
|
| 3260 |
"step": 3240
|
| 3261 |
+
},
|
| 3262 |
+
{
|
| 3263 |
+
"entropy": 0.8848231807351112,
|
| 3264 |
+
"epoch": 0.6933333333333334,
|
| 3265 |
+
"grad_norm": 0.3329085111618042,
|
| 3266 |
+
"learning_rate": 7.613525720466965e-05,
|
| 3267 |
+
"loss": 0.9568095207214355,
|
| 3268 |
+
"mean_token_accuracy": 0.7773910194635392,
|
| 3269 |
+
"num_tokens": 15117055.0,
|
| 3270 |
+
"step": 3250
|
| 3271 |
}
|
| 3272 |
],
|
| 3273 |
"logging_steps": 10,
|
|
|
|
| 3287 |
"attributes": {}
|
| 3288 |
}
|
| 3289 |
},
|
| 3290 |
+
"total_flos": 7.158806781067469e+16,
|
| 3291 |
"train_batch_size": 4,
|
| 3292 |
"trial_name": null,
|
| 3293 |
"trial_params": null
|