Training in progress, step 3220, 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 sha256:6224b8301f176e3907cdc6ebd99122f7198ad0b9776da28c0e69ab47da4bc7c1
|
| 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:ed5c71ccd2531236ac0873e7c3b21c4c112b99ba3e94d722e52622c1d98d9c6b
|
| 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:f12c9114af6536e88da3f583d7fb14a75cc2768b8ea85e6afe72423438db0889
|
| 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:efb81c82f9a4ce340a667c5d03539ada05fd84dd8cb42e35aa6e1716e46e1926
|
| 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,
|
|
@@ -3228,6 +3228,16 @@
|
|
| 3228 |
"mean_token_accuracy": 0.754035946726799,
|
| 3229 |
"num_tokens": 14942310.0,
|
| 3230 |
"step": 3210
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3231 |
}
|
| 3232 |
],
|
| 3233 |
"logging_steps": 10,
|
|
@@ -3247,7 +3257,7 @@
|
|
| 3247 |
"attributes": {}
|
| 3248 |
}
|
| 3249 |
},
|
| 3250 |
-
"total_flos": 7.
|
| 3251 |
"train_batch_size": 4,
|
| 3252 |
"trial_name": null,
|
| 3253 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.6869333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3220,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3228 |
"mean_token_accuracy": 0.754035946726799,
|
| 3229 |
"num_tokens": 14942310.0,
|
| 3230 |
"step": 3210
|
| 3231 |
+
},
|
| 3232 |
+
{
|
| 3233 |
+
"entropy": 0.9065248876810074,
|
| 3234 |
+
"epoch": 0.6869333333333333,
|
| 3235 |
+
"grad_norm": 0.22744986414909363,
|
| 3236 |
+
"learning_rate": 7.657647735466302e-05,
|
| 3237 |
+
"loss": 0.9641946792602539,
|
| 3238 |
+
"mean_token_accuracy": 0.772594378888607,
|
| 3239 |
+
"num_tokens": 14986110.0,
|
| 3240 |
+
"step": 3220
|
| 3241 |
}
|
| 3242 |
],
|
| 3243 |
"logging_steps": 10,
|
|
|
|
| 3257 |
"attributes": {}
|
| 3258 |
}
|
| 3259 |
},
|
| 3260 |
+
"total_flos": 7.09698806553815e+16,
|
| 3261 |
"train_batch_size": 4,
|
| 3262 |
"trial_name": null,
|
| 3263 |
"trial_params": null
|