Training in progress, step 2, 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 204312
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98b2cf74a2b5d4bd40902b401fc380e1b8ef6161013caaa3aa9168b0d06003a4
|
| 3 |
size 204312
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 442938
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:302f8b6e002ca4408d7ef6b3f2cf11f5aa55b25a6ac5e2d9987fa542e4fc5384
|
| 3 |
size 442938
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d66fa99c562c6e3ce75a07c2582cf26da8b48f30d2f96295ec230f94991541d
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
|
| 3 |
size 1064
|
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":
|
| 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,
|
|
@@ -24,6 +24,22 @@
|
|
| 24 |
"rewards/reward_func_keywords": 0.0,
|
| 25 |
"rewards/reward_func_length": 664.5,
|
| 26 |
"step": 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
}
|
| 28 |
],
|
| 29 |
"logging_steps": 1,
|
|
@@ -38,7 +54,7 @@
|
|
| 38 |
"should_evaluate": false,
|
| 39 |
"should_log": false,
|
| 40 |
"should_save": true,
|
| 41 |
-
"should_training_stop":
|
| 42 |
},
|
| 43 |
"attributes": {}
|
| 44 |
}
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.846005922849121e-05,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 24 |
"rewards/reward_func_keywords": 0.0,
|
| 25 |
"rewards/reward_func_length": 664.5,
|
| 26 |
"step": 1
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"clip_ratio": 0.0,
|
| 30 |
+
"completion_length": 110.0,
|
| 31 |
+
"epoch": 3.846005922849121e-05,
|
| 32 |
+
"grad_norm": 0.4941328465938568,
|
| 33 |
+
"kl": 0.0,
|
| 34 |
+
"learning_rate": 2e-05,
|
| 35 |
+
"loss": -0.045,
|
| 36 |
+
"num_tokens": 592.0,
|
| 37 |
+
"reward": 404.5643005371094,
|
| 38 |
+
"reward_std": 7.8101983070373535,
|
| 39 |
+
"rewards/reward_func_conciseness": 1.0643115043640137,
|
| 40 |
+
"rewards/reward_func_keywords": 0.0,
|
| 41 |
+
"rewards/reward_func_length": 403.5,
|
| 42 |
+
"step": 2
|
| 43 |
}
|
| 44 |
],
|
| 45 |
"logging_steps": 1,
|
|
|
|
| 54 |
"should_evaluate": false,
|
| 55 |
"should_log": false,
|
| 56 |
"should_save": true,
|
| 57 |
+
"should_training_stop": true
|
| 58 |
},
|
| 59 |
"attributes": {}
|
| 60 |
}
|