Hugging Face's logo

moos124
/
code-reasoning-0.5b

Transformers
Safetensors
Generated from Trainer
trl
hf_jobs
sft
Model card Files
xet
 Community
moos124 commited on
Commit
8cac397
·
verified ·
1 Parent(s): 72c08e4

Training in progress, step 4010, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +13 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68ef2cc357e334b7cad60da13e7b18d535567433003ea00f23bd0488be410fee
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ea1de3774e7c271880f7a8a77078f44fbf282dc88e0948f63ca5b719ae54594
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5eb9ce9c22c77903baa47a533de8ee839001407b24098aaffed6ff3d7a3e583
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed3a11cb8d53fbe6b49aac351b2583e647d3f982cc5057ded1e4cd7f6cf12c11
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1df6435006d15a8b7d09818f92631653559555b49a3ebc1947e10ab5b709bf04
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6252b2ac9b6f35852ab28b435cea70834a776d29732016a5958bf7e0b95d8351
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c6234c59f9b6c21a5de476be7a0561593c0fdc52d479d1e4485dd66fe66c4a3
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e28950232c771fabe9948f58c5f393a45ca41740e3d0a7992a62a87079870ff1
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": 0.8533333333333334,
6
  "eval_steps": 500,
7
- "global_step": 4000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -4018,6 +4018,16 @@
4018
  "mean_token_accuracy": 0.7703951939940452,
4019
  "num_tokens": 18653703.0,
4020
  "step": 4000
 
 
 
 
 
 
 
 
 
 
4021
  }
4022
  ],
4023
  "logging_steps": 10,
@@ -4037,7 +4047,7 @@
4037
  "attributes": {}
4038
  }
4039
  },
4040
- "total_flos": 8.832539694922138e+16,
4041
  "train_batch_size": 4,
4042
  "trial_name": null,
4043
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8554666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 4010,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4018
  "mean_token_accuracy": 0.7703951939940452,
4019
  "num_tokens": 18653703.0,
4020
  "step": 4000
4021
+ },
4022
+ {
4023
+ "entropy": 0.9708857566118241,
4024
+ "epoch": 0.8554666666666667,
4025
+ "grad_norm": 0.2541143000125885,
4026
+ "learning_rate": 6.415152961247186e-05,
4027
+ "loss": 1.07316312789917,
4028
+ "mean_token_accuracy": 0.752861674129963,
4029
+ "num_tokens": 18701666.0,
4030
+ "step": 4010
4031
  }
4032
  ],
4033
  "logging_steps": 10,
 
4047
  "attributes": {}
4048
  }
4049
  },
4050
+ "total_flos": 8.856235502408294e+16,
4051
  "train_batch_size": 4,
4052
  "trial_name": null,
4053
  "trial_params": null