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
3526422
·
verified ·
1 Parent(s): d590adc

Training in progress, step 80, 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 sha256:67a5ebd43c6b0eb06f24819ccd7f974745943b082a33128f374d2cad5977ef3e
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:449e100f7d2fa98ff866bd296d28e08aad073f1b8306f54f00ad22c38492c6f4
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32ec795f94077f1cd91c3de99ccdffe58998aa8aa271ec225a52b9b37ce9f321
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9abe4b2b1d6a3114623a72ed2b5a9b3584e2f49035522dc3ad63d054a11da4ec
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:e2d1a9b0c6e5ed8d453c40152acd651e81120324758155bef2120f881705c704
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65e88e58f0685db473c51c9f389a727b329107204c5feac290a62c79cedffb27
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:889ace47455a5c6021da8f63a84919330cb72fb98e7b813fa3bef17050e28ee7
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a3fcb3702a6e54612151d99234bce6653bbe56892383454427aa66bfc903ab6
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": 0.014933333333333333,
6
  "eval_steps": 500,
7
- "global_step": 70,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -88,6 +88,16 @@
88
  "mean_token_accuracy": 0.6667077802121639,
89
  "num_tokens": 330352.0,
90
  "step": 70
 
 
 
 
 
 
 
 
 
 
91
  }
92
  ],
93
  "logging_steps": 10,
@@ -107,7 +117,7 @@
107
  "attributes": {}
108
  }
109
  },
110
- "total_flos": 1619865370054656.0,
111
  "train_batch_size": 4,
112
  "trial_name": null,
113
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.017066666666666667,
6
  "eval_steps": 500,
7
+ "global_step": 80,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
88
  "mean_token_accuracy": 0.6667077802121639,
89
  "num_tokens": 330352.0,
90
  "step": 70
91
+ },
92
+ {
93
+ "entropy": 1.4339179992675781,
94
+ "epoch": 0.017066666666666667,
95
+ "grad_norm": 1.2848966121673584,
96
+ "learning_rate": 2.633333333333333e-05,
97
+ "loss": 1.6212703704833984,
98
+ "mean_token_accuracy": 0.6736222848296165,
99
+ "num_tokens": 373039.0,
100
+ "step": 80
101
  }
102
  ],
103
  "logging_steps": 10,
 
117
  "attributes": {}
118
  }
119
  },
120
+ "total_flos": 1825705462391808.0,
121
  "train_batch_size": 4,
122
  "trial_name": null,
123
  "trial_params": null