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
9a70636
·
verified ·
1 Parent(s): c2d723c

Training in progress, step 2430, 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 sha256:732c0620b6620ef6660996fb3e9ac9b3137a5be7d76d703d0da370eb307d81be
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e3036f1bd1d113794042d30a0210336c19a28c1d7ec2b1bb13ee7ebe2dd8a87
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1f5635ff69b136f998e3689dd52ca5c58e366dfb22327b9c502b824aa3c2873
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aea2181db4bfdc554cd84ddec80a06fd020e85a7dd04766e6b1c3c451c95feea
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:087df49092c52e165c9723e1486ab1a345be983cc3e4358e5f1f7a951597f5da
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40f301f9c7d420dacece57883f485f067d5252e982ded97dfa3a625554fea7e6
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40611b5bb16b881c328c8279653d601536ae911d7590faf37b8b15b51cf90f5e
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:125c4d2f8b9a0192330a1055ef3d4eb3b72971394011b6a04025a68d0b5bd5c4
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": 0.5162666666666667,
6
  "eval_steps": 500,
7
- "global_step": 2420,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -2438,6 +2438,16 @@
2438
  "mean_token_accuracy": 0.7819159016013145,
2439
  "num_tokens": 11257215.0,
2440
  "step": 2420
 
 
 
 
 
 
 
 
 
 
2441
  }
2442
  ],
2443
  "logging_steps": 10,
@@ -2457,7 +2467,7 @@
2457
  "attributes": {}
2458
  }
2459
  },
2460
- "total_flos": 5.338501230383923e+16,
2461
  "train_batch_size": 4,
2462
  "trial_name": null,
2463
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.5184,
6
  "eval_steps": 500,
7
+ "global_step": 2430,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
2438
  "mean_token_accuracy": 0.7819159016013145,
2439
  "num_tokens": 11257215.0,
2440
  "step": 2420
2441
+ },
2442
+ {
2443
+ "entropy": 1.030208633840084,
2444
+ "epoch": 0.5184,
2445
+ "grad_norm": 0.34487199783325195,
2446
+ "learning_rate": 8.702648271265559e-05,
2447
+ "loss": 1.1172332763671875,
2448
+ "mean_token_accuracy": 0.7529917880892754,
2449
+ "num_tokens": 11302807.0,
2450
+ "step": 2430
2451
  }
2452
  ],
2453
  "logging_steps": 10,
 
2467
  "attributes": {}
2468
  }
2469
  },
2470
+ "total_flos": 5.360216229135974e+16,
2471
  "train_batch_size": 4,
2472
  "trial_name": null,
2473
  "trial_params": null