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
c9dac17
·
verified ·
1 Parent(s): 059d6cd

Training in progress, step 1260, 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 sha256:5616f477fd639cdf29ad5c7d118b3e915d2b27f07c4d208cd0ace5cd3bf5bc01
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8cd4b7a968b52b018eedd57778bcd1b9892c7973186cd1ac62138c2dae334a2
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d948c44a079a96a9a9cdaeebea3b3583d465b51a14ea5d12d7942da62b9778c
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a08e35a29eec25205d86807ed2487d5c80f6a58396b6cd75ee84790c99df4128
3
  size 141058579
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:280a4a0a7e9600df169eef0cfd95b920be72c06632c470a2a48e52ec9a82f22f
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:727ca64f211e96fd591858ac677598eaa043ad8bd5939368650c0dc00acc8970
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de4e95e7c05aac68a45971509c4b26f22299fdf966b12971000c0752608308db
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb82055eb2f772bee9f77a4b8ed0f8cace697f04a7108fbfa7269523d0567c5a
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": 0.26666666666666666,
6
  "eval_steps": 500,
7
- "global_step": 1250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1268,6 +1268,16 @@
1268
  "mean_token_accuracy": 0.7673991709947586,
1269
  "num_tokens": 5817721.0,
1270
  "step": 1250
 
 
 
 
 
 
 
 
 
 
1271
  }
1272
  ],
1273
  "logging_steps": 10,
@@ -1287,7 +1297,7 @@
1287
  "attributes": {}
1288
  }
1289
  },
1290
- "total_flos": 2.7567098994668544e+16,
1291
  "train_batch_size": 4,
1292
  "trial_name": null,
1293
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.2688,
6
  "eval_steps": 500,
7
+ "global_step": 1260,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1268
  "mean_token_accuracy": 0.7673991709947586,
1269
  "num_tokens": 5817721.0,
1270
  "step": 1250
1271
+ },
1272
+ {
1273
+ "entropy": 1.0725971311330795,
1274
+ "epoch": 0.2688,
1275
+ "grad_norm": 0.25890064239501953,
1276
+ "learning_rate": 9.727041663220989e-05,
1277
+ "loss": 1.2022390365600586,
1278
+ "mean_token_accuracy": 0.7427652187645435,
1279
+ "num_tokens": 5864952.0,
1280
+ "step": 1260
1281
  }
1282
  ],
1283
  "logging_steps": 10,
 
1297
  "attributes": {}
1298
  }
1299
  },
1300
+ "total_flos": 2.780468790033715e+16,
1301
  "train_batch_size": 4,
1302
  "trial_name": null,
1303
  "trial_params": null