Hugging Face's logo

NguyenAn05
/
qwen2.5-coder-logic-sft-lora

Transformers
Safetensors
Generated from Trainer
trl
sft
Model card Files
xet
 Community
NguyenAn05 commited on
Commit
bd1a723
·
verified ·
1 Parent(s): 5cf28ac

Training in progress, step 132, 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 +11 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef9c3a3bcd245268c3e868b07883866eb700d66006a0ea515bc69867b4108362
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1caa400561e1c71e14aefa51e94805f46adb2f218e9d33b8fe12485c323f4200
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4211464de43ef4029796d31b7a8a39239ec1d212f8d5fccfb24d9a074ac3bf12
3
  size 1292181937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8268f8ded77d158c572d15c88b371cc9121ae2f1a5114e7e7ad1d27f28211259
3
  size 1292181937
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6be555987e2bcbe035f080fc8299b12cb968872b69b68f491a5dd576a9ca6f4c
3
  size 14443
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c30a770bcbcfc00b7e9dce936d31f06095a9aab511e27758e5de39bc7ad2559
3
  size 14443
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1111b3f0f56a49aa4114529836853f0b2f69b02c1d0397ccabfb4341dfd3123
3
  size 1263
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b56aeeb042fb16a26b3bd79705aca1fbd9b4be53f12657c4e4d0b511d1f9f0a
3
  size 1263
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 120,
3
  "best_metric": 0.12572850286960602,
4
  "best_model_checkpoint": "models/qwen2.5-coder-logic-sft-lora/checkpoint-120",
5
- "epoch": 2.735632183908046,
6
  "eval_steps": 20,
7
- "global_step": 120,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -140,6 +140,13 @@
140
  "eval_samples_per_second": 10.525,
141
  "eval_steps_per_second": 1.346,
142
  "step": 120
 
 
 
 
 
 
 
143
  }
144
  ],
145
  "logging_steps": 10,
@@ -154,12 +161,12 @@
154
  "should_evaluate": false,
155
  "should_log": false,
156
  "should_save": true,
157
- "should_training_stop": false
158
  },
159
  "attributes": {}
160
  }
161
  },
162
- "total_flos": 1.9193930779301376e+17,
163
  "train_batch_size": 8,
164
  "trial_name": null,
165
  "trial_params": null
 
2
  "best_global_step": 120,
3
  "best_metric": 0.12572850286960602,
4
  "best_model_checkpoint": "models/qwen2.5-coder-logic-sft-lora/checkpoint-120",
5
+ "epoch": 3.0,
6
  "eval_steps": 20,
7
+ "global_step": 132,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
140
  "eval_samples_per_second": 10.525,
141
  "eval_steps_per_second": 1.346,
142
  "step": 120
143
+ },
144
+ {
145
+ "epoch": 2.9655172413793105,
146
+ "grad_norm": 0.13226890563964844,
147
+ "learning_rate": 2.7095433213097933e-08,
148
+ "loss": 0.121,
149
+ "step": 130
150
  }
151
  ],
152
  "logging_steps": 10,
 
161
  "should_evaluate": false,
162
  "should_log": false,
163
  "should_save": true,
164
+ "should_training_stop": true
165
  },
166
  "attributes": {}
167
  }
168
  },
169
+ "total_flos": 2.0984665235003904e+17,
170
  "train_batch_size": 8,
171
  "trial_name": null,
172
  "trial_params": null