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
7c72e8b
·
verified ·
1 Parent(s): 75d64b9

Training in progress, step 840, 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 sha256:3eaf90d8cedec1ff12e3e7c4b352bab22257da6d241c9c9cce6def7e45c4e944
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8db3de053c2f72f9abbb9b5f0809ed5c4bdda08e8f42573491cdd78e10673722
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d00d96532f14bdf7f0e2c9cb1dfcf7a97f78ede6c375da59043178fbbc28c436
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df3324254f9f034f90c0425712616e0e0704f24838449df17188da66e3074d6d
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ad3e5c5bedc41596a899e1b7ab60b0934c2bc3efe6a53966c7c66bd51d2b43e
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ec31c45841f8cec7569244c4f4679b0a9accd231ac5e924ae024e7d487d040
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dc403043ab056906986eef9421e72db598abb0832c8e1fb3f2ec3a4f9bbead3
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a1a727045825fcc246ab7a09f9dd2aa3b80fa2aa395ee1c6a7a4445d8e2f428
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": 0.17706666666666668,
6
  "eval_steps": 500,
7
- "global_step": 830,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -848,6 +848,16 @@
848
  "mean_token_accuracy": 0.7569455504417419,
849
  "num_tokens": 3857657.0,
850
  "step": 830
 
 
 
 
 
 
 
 
 
 
851
  }
852
  ],
853
  "logging_steps": 10,
@@ -867,7 +877,7 @@
867
  "attributes": {}
868
  }
869
  },
870
- "total_flos": 1.8272266658236416e+16,
871
  "train_batch_size": 4,
872
  "trial_name": null,
873
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.1792,
6
  "eval_steps": 500,
7
+ "global_step": 840,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
848
  "mean_token_accuracy": 0.7569455504417419,
849
  "num_tokens": 3857657.0,
850
  "step": 830
851
+ },
852
+ {
853
+ "entropy": 1.116474264860153,
854
+ "epoch": 0.1792,
855
+ "grad_norm": 0.2815554738044739,
856
+ "learning_rate": 9.913230284383112e-05,
857
+ "loss": 1.1874059677124023,
858
+ "mean_token_accuracy": 0.7290896072983741,
859
+ "num_tokens": 3909965.0,
860
+ "step": 840
861
  }
862
  ],
863
  "logging_steps": 10,
 
877
  "attributes": {}
878
  }
879
  },
880
+ "total_flos": 1.852442775554765e+16,
881
  "train_batch_size": 4,
882
  "trial_name": null,
883
  "trial_params": null