Hugging Face's logo

alicogniai
/
Qwen2.5-1.5B-Open-R1-Distill

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
trl
sft
conversational
text-generation-inference
Model card Files
xet
 Community
1
alicogniai commited on
Commit
b8b5aae
·
verified ·
1 Parent(s): c89c53e

Model save

Browse files
Files changed (7) hide show
  1. README.md +1 -1
  2. all_results.json +10 -5
  3. eval_results.json +5 -6
  4. model.safetensors +2 -2
  5. train_results.json +5 -5
  6. trainer_state.json +21 -13
  7. training_args.bin +1 -1
README.md CHANGED
@@ -27,7 +27,7 @@ print(output["generated_text"])
27
 
28
  ## Training procedure
29
 
30
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/alicogniai-cognichip/huggingface/runs/fp28nxtc)
31
 
32
 
33
  This model was trained with SFT.
 
27
 
28
  ## Training procedure
29
 
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/alicogniai-cognichip/huggingface/runs/ugrxdaei)
31
 
32
 
33
  This model was trained with SFT.
all_results.json CHANGED
@@ -1,8 +1,13 @@
1
  {
2
- "total_flos": 333840384000.0,
3
- "train_loss": 0.35875171422958374,
4
- "train_runtime": 14.4271,
 
 
 
 
 
5
  "train_samples": 1097,
6
- "train_samples_per_second": 5.407,
7
- "train_steps_per_second": 0.069
8
  }
 
1
  {
2
+ "eval_loss": 0.2394731640815735,
3
+ "eval_runtime": 0.9108,
4
+ "eval_samples": 843,
5
+ "eval_samples_per_second": 59.289,
6
+ "eval_steps_per_second": 2.196,
7
+ "total_flos": 3345047902748672.0,
8
+ "train_loss": 0.18449299203024971,
9
+ "train_runtime": 21.9388,
10
  "train_samples": 1097,
11
+ "train_samples_per_second": 3.555,
12
+ "train_steps_per_second": 0.41
13
  }
eval_results.json CHANGED
@@ -1,8 +1,7 @@
1
  {
2
- "epoch": 1.0,
3
- "eval_loss": 0.7804026007652283,
4
- "eval_runtime": 0.7988,
5
- "eval_samples": 100,
6
- "eval_samples_per_second": 160.238,
7
- "eval_steps_per_second": 5.007
8
  }
 
1
  {
2
+ "eval_loss": 0.2394731640815735,
3
+ "eval_runtime": 0.9108,
4
+ "eval_samples": 843,
5
+ "eval_samples_per_second": 59.289,
6
+ "eval_steps_per_second": 2.196
 
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd924a11b4c220f385b51ffa522daea7c9f3d850e31b162bb5661df483c6d3ee
3
- size 3087467144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2baa415c431b3e0c69ca0065979e0ee8127c2f06f44ac2b4c68d8c6b5241eeb
3
+ size 3554214752
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "total_flos": 333840384000.0,
3
- "train_loss": 0.35875171422958374,
4
- "train_runtime": 14.4271,
5
  "train_samples": 1097,
6
- "train_samples_per_second": 5.407,
7
- "train_steps_per_second": 0.069
8
  }
 
1
  {
2
+ "total_flos": 3345047902748672.0,
3
+ "train_loss": 0.18449299203024971,
4
+ "train_runtime": 21.9388,
5
  "train_samples": 1097,
6
+ "train_samples_per_second": 3.555,
7
+ "train_steps_per_second": 0.41
8
  }
trainer_state.json CHANGED
@@ -1,26 +1,34 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.0,
5
  "eval_steps": 100,
6
- "global_step": 1,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 1.0,
13
- "mean_token_accuracy": 0.9492798329413153,
14
- "step": 1,
15
- "total_flos": 333840384000.0,
16
- "train_loss": 0.35875171422958374,
17
- "train_runtime": 14.4271,
18
- "train_samples_per_second": 5.407,
19
- "train_steps_per_second": 0.069
 
 
 
 
 
 
 
 
20
  }
21
  ],
22
  "logging_steps": 5,
23
- "max_steps": 1,
24
  "num_input_tokens_seen": 0,
25
  "num_train_epochs": 1,
26
  "save_steps": 500,
@@ -36,8 +44,8 @@
36
  "attributes": {}
37
  }
38
  },
39
- "total_flos": 333840384000.0,
40
- "train_batch_size": 2,
41
  "trial_name": null,
42
  "trial_params": null
43
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.9230769230769231,
5
  "eval_steps": 100,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.5128205128205128,
13
+ "grad_norm": 0.5559384822845459,
14
+ "learning_rate": 1e-05,
15
+ "loss": 0.2367,
16
+ "mean_token_accuracy": 0.9557622533964742,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.9230769230769231,
21
+ "mean_token_accuracy": 0.9720920825971266,
22
+ "step": 9,
23
+ "total_flos": 3345047902748672.0,
24
+ "train_loss": 0.18449299203024971,
25
+ "train_runtime": 21.9388,
26
+ "train_samples_per_second": 3.555,
27
+ "train_steps_per_second": 0.41
28
  }
29
  ],
30
  "logging_steps": 5,
31
+ "max_steps": 9,
32
  "num_input_tokens_seen": 0,
33
  "num_train_epochs": 1,
34
  "save_steps": 500,
 
44
  "attributes": {}
45
  }
46
  },
47
+ "total_flos": 3345047902748672.0,
48
+ "train_batch_size": 1,
49
  "trial_name": null,
50
  "trial_params": null
51
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a02bff04ef8af8e499dbbcf331138d7ad9540070c8f083abe6f6e2e56b8004a2
3
  size 7160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9581172b8deaf0ef914db42abf801181238df10634ba664216aaa426665059c7
3
  size 7160