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
c6f54f7
·
verified ·
1 Parent(s): 3cbdcf5

Training in progress, step 2190, 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 sha256:7a39fb275b783bc5452fdcfdea48eaf5078ba4a25a5087f3acc2973d817ab4d8
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d50b0db003b0e4849422a680436a6f85d8c430030fdef2b06905fbbc25300782
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80b111dbf15da74fe616e6afc0e3b74c096802276d01a15d115a66182e756c9f
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdbd8173961b979bf5d5eeae90b6ded931991d909be7d028befb2d689150315d
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:f90bdee1749f591dfc70db1ad36d11093e7d4fd24288bb105a84234dd0c04894
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed7324b862753bcd4f637366d09b8a7b2affe05ad03ec9d02039705a73af90f1
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0666b25813a2805dfea98332b3af2e5d220b64c251c9e75bc0ea2e42bb3696d
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:762167d444d04ce74f8ab2b70e3ee8b57183dbd1bee3039ce9785a72ad322e71
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": 0.4650666666666667,
6
  "eval_steps": 500,
7
- "global_step": 2180,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2198,6 +2198,16 @@
2198
  "mean_token_accuracy": 0.7799090445041656,
2199
  "num_tokens": 10112591.0,
2200
  "step": 2180
 
 
 
 
 
 
 
 
 
 
2201
  }
2202
  ],
2203
  "logging_steps": 10,
@@ -2217,7 +2227,7 @@
2217
  "attributes": {}
2218
  }
2219
  },
2220
- "total_flos": 4.79722046115072e+16,
2221
  "train_batch_size": 4,
2222
  "trial_name": null,
2223
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.4672,
6
  "eval_steps": 500,
7
+ "global_step": 2190,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2198
  "mean_token_accuracy": 0.7799090445041656,
2199
  "num_tokens": 10112591.0,
2200
  "step": 2180
2201
+ },
2202
+ {
2203
+ "entropy": 0.880243568867445,
2204
+ "epoch": 0.4672,
2205
+ "grad_norm": 0.21990089118480682,
2206
+ "learning_rate": 8.968697488166435e-05,
2207
+ "loss": 0.9580593109130859,
2208
+ "mean_token_accuracy": 0.7760828763246537,
2209
+ "num_tokens": 10159849.0,
2210
+ "step": 2190
2211
  }
2212
  ],
2213
  "logging_steps": 10,
 
2227
  "attributes": {}
2228
  }
2229
  },
2230
+ "total_flos": 4.818689435888026e+16,
2231
  "train_batch_size": 4,
2232
  "trial_name": null,
2233
  "trial_params": null