Hugging Face's logo

Chris126
/
qwen-r1-aha-moment

Transformers
TensorBoard
Safetensors
Generated from Trainer
trl
grpo
Inference Endpoints
Model card Files Metrics Community
Chris126 commited on
Commit
f63e5f3
·
verified ·
1 Parent(s): 6054e27

End of training

Browse files
Files changed (5) hide show
  1. all_results.json +4 -4
  2. runs/Feb05_11-56-04_AVA-STATION/events.out.tfevents.1738752970.AVA-STATION.622808.0 +3 -0
  3. train_results.json +4 -4
  4. trainer_state.json +14 -8
  5. training_args.bin +1 -1
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
- "train_loss": 5.925413926080284e-07,
4
- "train_runtime": 35343.127,
5
  "train_samples": 45000,
6
- "train_samples_per_second": 0.013,
7
- "train_steps_per_second": 0.013
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 1.3050906145387637e-09,
4
+ "train_runtime": 4363.1554,
5
  "train_samples": 45000,
6
+ "train_samples_per_second": 0.103,
7
+ "train_steps_per_second": 0.103
8
  }
runs/Feb05_11-56-04_AVA-STATION/events.out.tfevents.1738752970.AVA-STATION.622808.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2ce2e9c2b0b18ba719590a91665a096f24a7f5edaa1581d8e231d7d1b8d7cf3
3
+ size 6109
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "total_flos": 0.0,
3
- "train_loss": 5.925413926080284e-07,
4
- "train_runtime": 35343.127,
5
  "train_samples": 45000,
6
- "train_samples_per_second": 0.013,
7
- "train_steps_per_second": 0.013
8
  }
 
1
  {
2
  "total_flos": 0.0,
3
+ "train_loss": 1.3050906145387637e-09,
4
+ "train_runtime": 4363.1554,
5
  "train_samples": 45000,
6
+ "train_samples_per_second": 0.103,
7
+ "train_steps_per_second": 0.103
8
  }
trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.01,
5
  "eval_steps": 500,
6
- "global_step": 450,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -594,13 +594,19 @@
594
  "step": 450
595
  },
596
  {
597
- "epoch": 0.01,
598
- "step": 450,
 
 
 
 
 
 
599
  "total_flos": 0.0,
600
- "train_loss": 5.925413926080284e-07,
601
- "train_runtime": 35343.127,
602
- "train_samples_per_second": 0.013,
603
- "train_steps_per_second": 0.013
604
  }
605
  ],
606
  "logging_steps": 10,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.010022222222222222,
5
  "eval_steps": 500,
6
+ "global_step": 451,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
594
  "step": 450
595
  },
596
  {
597
+ "completion_length": 379.875,
598
+ "epoch": 0.010022222222222222,
599
+ "kl": 0.0005991907673887908,
600
+ "reward": 0.375,
601
+ "reward_std": 0.5175491571426392,
602
+ "rewards/equation_reward_func": 0.0,
603
+ "rewards/format_reward_func": 0.375,
604
+ "step": 451,
605
  "total_flos": 0.0,
606
+ "train_loss": 1.3050906145387637e-09,
607
+ "train_runtime": 4363.1554,
608
+ "train_samples_per_second": 0.103,
609
+ "train_steps_per_second": 0.103
610
  }
611
  ],
612
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d875b2ce3ec833cc1adfdd719f3e676ad7c17cebd64ffc4e6f8bed2655a8f164
3
  size 5624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f712c19fc1e1946e5e4bb43eccae4449788e72205cdd94458e1f84efc985453b
3
  size 5624