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
ed7f9f3
·
verified ·
1 Parent(s): eef192a

Training in progress, step 3990, 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:cb92eeee4f10b88452adab2b86e02b1a55219a9a903898c13345aafea5b652bf
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52058980f27362730349a840bf2be4ebe730657aeaeb68d6ecc9e93a60827b02
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:129b12ef463c9b415d145e672db9245320c03f48bd1109f0b8d857667b334fea
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eae6e7a6d7e53accdb89aef62dcb024803eee1c93ca17b7ebc2c64fb62ae721
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:e00055690825dfa08ac78e1506244a3a8ef6c7831d00d7a6c1a46e128b78da37
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de85dc2ef0df9e09a3ecc041205f95a03682eba3ae255aad1be4035a4c9c3a7b
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44f219189445926df0babc469312f611e8c019ba4849565af1d4190bf43f3386
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ea8ac7f0cc98ea018d8ed888b453c6459afdff01ca45f065d54c4674da7a865
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": 0.8490666666666666,
6
  "eval_steps": 500,
7
- "global_step": 3980,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -3998,6 +3998,16 @@
3998
  "mean_token_accuracy": 0.7435829386115074,
3999
  "num_tokens": 18560510.0,
4000
  "step": 3980
 
 
 
 
 
 
 
 
 
 
4001
  }
4002
  ],
4003
  "logging_steps": 10,
@@ -4017,7 +4027,7 @@
4017
  "attributes": {}
4018
  }
4019
  },
4020
- "total_flos": 8.787590296359936e+16,
4021
  "train_batch_size": 4,
4022
  "trial_name": null,
4023
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8512,
6
  "eval_steps": 500,
7
+ "global_step": 3990,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
3998
  "mean_token_accuracy": 0.7435829386115074,
3999
  "num_tokens": 18560510.0,
4000
  "step": 3980
4001
+ },
4002
+ {
4003
+ "entropy": 0.9280949518084526,
4004
+ "epoch": 0.8512,
4005
+ "grad_norm": 0.2419559508562088,
4006
+ "learning_rate": 6.448317723891237e-05,
4007
+ "loss": 1.0382183074951172,
4008
+ "mean_token_accuracy": 0.7698814913630485,
4009
+ "num_tokens": 18608764.0,
4010
+ "step": 3990
4011
  }
4012
  ],
4013
  "logging_steps": 10,
 
4027
  "attributes": {}
4028
  }
4029
  },
4030
+ "total_flos": 8.811176159048294e+16,
4031
  "train_batch_size": 4,
4032
  "trial_name": null,
4033
  "trial_params": null