Training in progress, step 4300, 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 sha256:591057de2045f91c06d92bacd46c8c670bbcdeb3679439cc3171c6fa6b1d2b5e
|
| 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 sha256:7c10e7a8390d425d69b7e7129c842d44526d3329311272fade0d43d672c13788
|
| 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 sha256:1192914ebd2625f2ef9c95d07fc13f494650b554ecb7448bc203744491dcd281
|
| 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:ac321c0e85ad319b7f8df05655fea5c1a7e38017586ce3b92ba36567667240e9
|
| 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,
|
|
@@ -4308,6 +4308,16 @@
|
|
| 4308 |
"mean_token_accuracy": 0.7571895673871041,
|
| 4309 |
"num_tokens": 19976730.0,
|
| 4310 |
"step": 4290
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4311 |
}
|
| 4312 |
],
|
| 4313 |
"logging_steps": 10,
|
|
@@ -4327,7 +4337,7 @@
|
|
| 4327 |
"attributes": {}
|
| 4328 |
}
|
| 4329 |
},
|
| 4330 |
-
"total_flos": 9.
|
| 4331 |
"train_batch_size": 4,
|
| 4332 |
"trial_name": null,
|
| 4333 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9173333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4300,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4308 |
"mean_token_accuracy": 0.7571895673871041,
|
| 4309 |
"num_tokens": 19976730.0,
|
| 4310 |
"step": 4290
|
| 4311 |
+
},
|
| 4312 |
+
{
|
| 4313 |
+
"entropy": 0.9086124181747437,
|
| 4314 |
+
"epoch": 0.9173333333333333,
|
| 4315 |
+
"grad_norm": 0.331281453371048,
|
| 4316 |
+
"learning_rate": 5.927452517717558e-05,
|
| 4317 |
+
"loss": 1.0120928764343262,
|
| 4318 |
+
"mean_token_accuracy": 0.7699793577194214,
|
| 4319 |
+
"num_tokens": 20021630.0,
|
| 4320 |
+
"step": 4300
|
| 4321 |
}
|
| 4322 |
],
|
| 4323 |
"logging_steps": 10,
|
|
|
|
| 4337 |
"attributes": {}
|
| 4338 |
}
|
| 4339 |
},
|
| 4340 |
+
"total_flos": 9.476189885148058e+16,
|
| 4341 |
"train_batch_size": 4,
|
| 4342 |
"trial_name": null,
|
| 4343 |
"trial_params": null
|