yujunzhou commited on
Commit
a867125
·
verified ·
1 Parent(s): 6e1db72

End of training

Browse files
Files changed (4) hide show
  1. README.md +2 -1
  2. all_results.json +8 -0
  3. train_results.json +8 -0
  4. trainer_state.json +43 -0
README.md CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
4
  base_model: Qwen/Qwen3-4B-Base
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: SFT_Advanced_Risk_Dice_Qwen3_4B_Base
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # SFT_Advanced_Risk_Dice_Qwen3_4B_Base
17
 
18
- This model is a fine-tuned version of [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base) on an unknown dataset.
19
 
20
  ## Model description
21
 
 
4
  base_model: Qwen/Qwen3-4B-Base
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: SFT_Advanced_Risk_Dice_Qwen3_4B_Base
 
16
 
17
  # SFT_Advanced_Risk_Dice_Qwen3_4B_Base
18
 
19
+ This model is a fine-tuned version of [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base) on the Advanced_Risk_Dice_Qwen3_4B_Base dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9230769230769231,
3
+ "total_flos": 143598747648.0,
4
+ "train_loss": 0.4763137102127075,
5
+ "train_runtime": 235.6976,
6
+ "train_samples_per_second": 1.714,
7
+ "train_steps_per_second": 0.025
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9230769230769231,
3
+ "total_flos": 143598747648.0,
4
+ "train_loss": 0.4763137102127075,
5
+ "train_runtime": 235.6976,
6
+ "train_samples_per_second": 1.714,
7
+ "train_steps_per_second": 0.025
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9230769230769231,
6
+ "eval_steps": 500,
7
+ "global_step": 6,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.9230769230769231,
14
+ "step": 6,
15
+ "total_flos": 143598747648.0,
16
+ "train_loss": 0.4763137102127075,
17
+ "train_runtime": 235.6976,
18
+ "train_samples_per_second": 1.714,
19
+ "train_steps_per_second": 0.025
20
+ }
21
+ ],
22
+ "logging_steps": 10,
23
+ "max_steps": 6,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 1,
26
+ "save_steps": 500,
27
+ "stateful_callbacks": {
28
+ "TrainerControl": {
29
+ "args": {
30
+ "should_epoch_stop": false,
31
+ "should_evaluate": false,
32
+ "should_log": false,
33
+ "should_save": true,
34
+ "should_training_stop": true
35
+ },
36
+ "attributes": {}
37
+ }
38
+ },
39
+ "total_flos": 143598747648.0,
40
+ "train_batch_size": 2,
41
+ "trial_name": null,
42
+ "trial_params": null
43
+ }