ahmedheakl commited on
Commit
5cbe464
·
verified ·
1 Parent(s): ff5a02f

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
@@ -3,6 +3,7 @@ library_name: peft
3
  base_model: Qwen/Qwen2.5-VL-3B-Instruct
4
  tags:
5
  - llama-factory
 
6
  - generated_from_trainer
7
  model-index:
8
  - name: iter0_mm_llamafactory_high_eps20250902_144629
@@ -14,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # iter0_mm_llamafactory_high_eps20250902_144629
16
 
17
- This model is a fine-tuned version of [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct) on an unknown dataset.
18
 
19
  ## Model description
20
 
 
3
  base_model: Qwen/Qwen2.5-VL-3B-Instruct
4
  tags:
5
  - llama-factory
6
+ - lora
7
  - generated_from_trainer
8
  model-index:
9
  - name: iter0_mm_llamafactory_high_eps20250902_144629
 
15
 
16
  # iter0_mm_llamafactory_high_eps20250902_144629
17
 
18
+ This model is a fine-tuned version of [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct) on the infographics50 dataset.
19
 
20
  ## Model description
21
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 823182961410048.0,
4
+ "train_loss": 0.6852799654006958,
5
+ "train_runtime": 28.8533,
6
+ "train_samples_per_second": 1.525,
7
+ "train_steps_per_second": 0.139
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "total_flos": 823182961410048.0,
4
+ "train_loss": 0.6852799654006958,
5
+ "train_runtime": 28.8533,
6
+ "train_samples_per_second": 1.525,
7
+ "train_steps_per_second": 0.139
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": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 4,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 2.0,
14
+ "step": 4,
15
+ "total_flos": 823182961410048.0,
16
+ "train_loss": 0.6852799654006958,
17
+ "train_runtime": 28.8533,
18
+ "train_samples_per_second": 1.525,
19
+ "train_steps_per_second": 0.139
20
+ }
21
+ ],
22
+ "logging_steps": 10,
23
+ "max_steps": 4,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 2,
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": 823182961410048.0,
40
+ "train_batch_size": 1,
41
+ "trial_name": null,
42
+ "trial_params": null
43
+ }