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
fcac072
·
verified ·
1 Parent(s): 298ebed

Training in progress, step 4020, 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 sha256:4ea1de3774e7c271880f7a8a77078f44fbf282dc88e0948f63ca5b719ae54594
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4b6623f1ef93d5fefecc96758eec7070bd52c7df6b27a0f441530c505fa0e16
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed3a11cb8d53fbe6b49aac351b2583e647d3f982cc5057ded1e4cd7f6cf12c11
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a2d893cbda6a3f6a460e925880a58c52a247d6ef2f33ff129f2d42d0180905
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6252b2ac9b6f35852ab28b435cea70834a776d29732016a5958bf7e0b95d8351
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe9da9a84098eaeb27198038d90d883ac97f52291887d4b9fbd3f7ea21dccbfe
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e28950232c771fabe9948f58c5f393a45ca41740e3d0a7992a62a87079870ff1
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2182116c99968d1d7e745d44571cbb92070576de0f285f4c55659c013b912df8
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": 0.8554666666666667,
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,
@@ -4028,6 +4028,16 @@
4028
  "mean_token_accuracy": 0.752861674129963,
4029
  "num_tokens": 18701666.0,
4030
  "step": 4010
 
 
 
 
 
 
 
 
 
 
4031
  }
4032
  ],
4033
  "logging_steps": 10,
@@ -4047,7 +4057,7 @@
4047
  "attributes": {}
4048
  }
4049
  },
4050
- "total_flos": 8.856235502408294e+16,
4051
  "train_batch_size": 4,
4052
  "trial_name": null,
4053
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8576,
6
  "eval_steps": 500,
7
+ "global_step": 4020,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4028
  "mean_token_accuracy": 0.752861674129963,
4029
  "num_tokens": 18701666.0,
4030
  "step": 4010
4031
+ },
4032
+ {
4033
+ "entropy": 0.9462185628712177,
4034
+ "epoch": 0.8576,
4035
+ "grad_norm": 0.23720327019691467,
4036
+ "learning_rate": 6.398545047100321e-05,
4037
+ "loss": 1.023193359375,
4038
+ "mean_token_accuracy": 0.7677365422248841,
4039
+ "num_tokens": 18749563.0,
4040
+ "step": 4020
4041
  }
4042
  ],
4043
  "logging_steps": 10,
 
4057
  "attributes": {}
4058
  }
4059
  },
4060
+ "total_flos": 8.877190800631296e+16,
4061
  "train_batch_size": 4,
4062
  "trial_name": null,
4063
  "trial_params": null