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
ccd4868
·
verified ·
1 Parent(s): dccf448

Training in progress, step 70, 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 sha256:46611663ddb003d3fad551f919f2842a07905148212f3c6637e4dea024b6c395
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67a5ebd43c6b0eb06f24819ccd7f974745943b082a33128f374d2cad5977ef3e
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a388d9fae69b03af0d2595f3c9c59c84a3d4b776eb6c70ee6d21850d61e4d80
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32ec795f94077f1cd91c3de99ccdffe58998aa8aa271ec225a52b9b37ce9f321
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:c4ecc53428755d63edd79679db9a5440d4ba97bc0f29104ed9e3084e2b71d80d
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2d1a9b0c6e5ed8d453c40152acd651e81120324758155bef2120f881705c704
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0c163eafc31042a3869aade40f9de5eee80d532c8ab9aab522757e6431256f5
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:889ace47455a5c6021da8f63a84919330cb72fb98e7b813fa3bef17050e28ee7
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": 0.0128,
6
  "eval_steps": 500,
7
- "global_step": 60,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -78,6 +78,16 @@
78
  "mean_token_accuracy": 0.6761457294225692,
79
  "num_tokens": 279475.0,
80
  "step": 60
 
 
 
 
 
 
 
 
 
 
81
  }
82
  ],
83
  "logging_steps": 10,
@@ -97,7 +107,7 @@
97
  "attributes": {}
98
  }
99
  },
100
- "total_flos": 1370353762132992.0,
101
  "train_batch_size": 4,
102
  "trial_name": null,
103
  "trial_params": null
 
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,
 
78
  "mean_token_accuracy": 0.6761457294225692,
79
  "num_tokens": 279475.0,
80
  "step": 60
81
+ },
82
+ {
83
+ "entropy": 1.4092280209064483,
84
+ "epoch": 0.014933333333333333,
85
+ "grad_norm": 0.6658427119255066,
86
+ "learning_rate": 2.3000000000000003e-05,
87
+ "loss": 1.7947965621948243,
88
+ "mean_token_accuracy": 0.6667077802121639,
89
+ "num_tokens": 330352.0,
90
+ "step": 70
91
  }
92
  ],
93
  "logging_steps": 10,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1619865370054656.0,
111
  "train_batch_size": 4,
112
  "trial_name": null,
113
  "trial_params": null