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
0c0ffae
·
verified ·
1 Parent(s): 827f1e3

Training in progress, step 1120, 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 sha256:7bc35203b5066f57c10ec28912e17ca7c2993c85147f5c6d9e968f6b9c083fdf
3
  size 70430032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e52628a0c7aae39af49a19bc026383eb668cf1ee77f536f8c5265988e4a89521
3
  size 70430032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb267a645f0b9e467798a50121cfc90a60ac78850c44bddaa8430cf08de5882b
3
  size 141058579
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bebc472578678417f863749ba663c136aa45b4ed02bddb3b2d4dd2a080abec45
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:f6049540202e3691d3cd2e092394351bff4b3df9ffce3cee9dc9fa33a88b4632
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cac05f14d800772ea9ca17de810c8b6ad818100db3a04e7de62285443c3fa04
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:792814134ab3636c6daba60a1bcb22ef4e22491c83bb44ed84495cf7562de8dd
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8180f29921749336731381af4512d6a7af639725681bd9e8dbf49efe4382b618
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": 0.2368,
6
  "eval_steps": 500,
7
- "global_step": 1110,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1128,6 +1128,16 @@
1128
  "mean_token_accuracy": 0.7565312668681144,
1129
  "num_tokens": 5167690.0,
1130
  "step": 1110
 
 
 
 
 
 
 
 
 
 
1131
  }
1132
  ],
1133
  "logging_steps": 10,
@@ -1147,7 +1157,7 @@
1147
  "attributes": {}
1148
  }
1149
  },
1150
- "total_flos": 2.443419494579712e+16,
1151
  "train_batch_size": 4,
1152
  "trial_name": null,
1153
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.23893333333333333,
6
  "eval_steps": 500,
7
+ "global_step": 1120,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1128
  "mean_token_accuracy": 0.7565312668681144,
1129
  "num_tokens": 5167690.0,
1130
  "step": 1110
1131
+ },
1132
+ {
1133
+ "entropy": 0.9320930615067482,
1134
+ "epoch": 0.23893333333333333,
1135
+ "grad_norm": 0.2536001205444336,
1136
+ "learning_rate": 9.800424122015802e-05,
1137
+ "loss": 1.0100153923034667,
1138
+ "mean_token_accuracy": 0.7664023399353027,
1139
+ "num_tokens": 5209976.0,
1140
+ "step": 1120
1141
  }
1142
  ],
1143
  "logging_steps": 10,
 
1157
  "attributes": {}
1158
  }
1159
  },
1160
+ "total_flos": 2.463681780101837e+16,
1161
  "train_batch_size": 4,
1162
  "trial_name": null,
1163
  "trial_params": null