akkky02 commited on
Commit
1bd01ae
1 Parent(s): 8e7b031

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +10 -0
  2. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/README.md +78 -0
  3. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/adapter_config.json +33 -0
  4. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/adapter_model.bin +3 -0
  5. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/added_tokens.json +5 -0
  6. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/all_results.json +23 -0
  7. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/README.md +202 -0
  8. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/adapter_config.json +33 -0
  9. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/adapter_model.bin +3 -0
  10. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/added_tokens.json +5 -0
  11. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/global_step550/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  12. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/global_step550/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  13. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/global_step550/mp_rank_00_model_states.pt +3 -0
  14. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/latest +1 -0
  15. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/merges.txt +0 -0
  16. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/rng_state_0.pth +3 -0
  17. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/rng_state_1.pth +3 -0
  18. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/scheduler.pt +3 -0
  19. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/special_tokens_map.json +14 -0
  20. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/tokenizer.json +0 -0
  21. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/tokenizer_config.json +43 -0
  22. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/trainer_state.json +527 -0
  23. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/training_args.bin +3 -0
  24. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/vocab.json +0 -0
  25. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/zero_to_fp32.py +604 -0
  26. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/eval_results.json +11 -0
  27. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/merges.txt +0 -0
  28. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/run.log +4 -0
  29. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/special_tokens_map.json +14 -0
  30. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/test_results.json +10 -0
  31. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/tokenizer.json +0 -0
  32. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/tokenizer_config.json +43 -0
  33. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/train_results.json +8 -0
  34. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/trainer_state.json +550 -0
  35. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/training_args.bin +3 -0
  36. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/vocab.json +0 -0
  37. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/README.md +75 -0
  38. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/adapter_config.json +33 -0
  39. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/adapter_model.bin +3 -0
  40. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/added_tokens.json +5 -0
  41. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/all_results.json +23 -0
  42. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/README.md +202 -0
  43. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/adapter_config.json +33 -0
  44. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/adapter_model.bin +3 -0
  45. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/added_tokens.json +5 -0
  46. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  47. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  48. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/global_step400/mp_rank_00_model_states.pt +3 -0
  49. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/latest +1 -0
  50. max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/merges.txt +0 -0
.gitattributes CHANGED
@@ -63,3 +63,13 @@ max_seq_length_512_experiments/google/gemma_2b_scotus/checkpoint-300/tokenizer.j
63
  max_seq_length_512_experiments/google/gemma_2b_scotus/tokenizer.json filter=lfs diff=lfs merge=lfs -text
64
  max_seq_length_512_experiments/google/gemma_2b_twitter/checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
65
  max_seq_length_512_experiments/google/gemma_2b_twitter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
63
  max_seq_length_512_experiments/google/gemma_2b_scotus/tokenizer.json filter=lfs diff=lfs merge=lfs -text
64
  max_seq_length_512_experiments/google/gemma_2b_twitter/checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
65
  max_seq_length_512_experiments/google/gemma_2b_twitter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
66
+ max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/tokenizer.json filter=lfs diff=lfs merge=lfs -text
67
+ max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/amazon_attrprompt_default/tokenizer.json filter=lfs diff=lfs merge=lfs -text
68
+ max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
69
+ max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_MAdAiLab/twitter_disaster_default/tokenizer.json filter=lfs diff=lfs merge=lfs -text
70
+ max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
71
+ max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_ccdv/patent_classification_abstract/tokenizer.json filter=lfs diff=lfs merge=lfs -text
72
+ max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/checkpoint-1750/tokenizer.json filter=lfs diff=lfs merge=lfs -text
73
+ max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_ledgar/tokenizer.json filter=lfs diff=lfs merge=lfs -text
74
+ max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
75
+ max_seq_length_512_experiments/LoRA/google/gemma_7b_LoRA_coastalcph/lex_glue_scotus/tokenizer.json filter=lfs diff=lfs merge=lfs -text
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/README.md ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: Qwen/Qwen1.5-7B
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: amazon_attrprompt_default
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # amazon_attrprompt_default
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen1.5-7B](https://huggingface.co/Qwen/Qwen1.5-7B) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.4968
22
+ - Accuracy: 0.8597
23
+ - F1 Macro: 0.8370
24
+ - F1 Micro: 0.8597
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 5e-06
44
+ - train_batch_size: 32
45
+ - eval_batch_size: 32
46
+ - seed: 42
47
+ - distributed_type: multi-GPU
48
+ - num_devices: 2
49
+ - total_train_batch_size: 64
50
+ - total_eval_batch_size: 64
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 3.0
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
58
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|
59
+ | 5.8578 | 0.26 | 50 | 5.5037 | 0.1252 | 0.0968 | 0.1252 |
60
+ | 2.3145 | 0.53 | 100 | 1.9805 | 0.5283 | 0.4222 | 0.5283 |
61
+ | 0.9115 | 0.79 | 150 | 0.9064 | 0.7721 | 0.7139 | 0.7721 |
62
+ | 0.7251 | 1.05 | 200 | 0.7034 | 0.8090 | 0.7669 | 0.8090 |
63
+ | 0.5086 | 1.32 | 250 | 0.6432 | 0.8267 | 0.7756 | 0.8267 |
64
+ | 0.5473 | 1.58 | 300 | 0.5911 | 0.8353 | 0.7983 | 0.8353 |
65
+ | 0.514 | 1.84 | 350 | 0.5454 | 0.8564 | 0.8329 | 0.8564 |
66
+ | 0.4493 | 2.11 | 400 | 0.5437 | 0.8465 | 0.8172 | 0.8465 |
67
+ | 0.516 | 2.37 | 450 | 0.5225 | 0.8531 | 0.8289 | 0.8531 |
68
+ | 0.343 | 2.63 | 500 | 0.4982 | 0.8557 | 0.8339 | 0.8557 |
69
+ | 0.4203 | 2.89 | 550 | 0.4968 | 0.8597 | 0.8370 | 0.8597 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - PEFT 0.9.0
75
+ - Transformers 4.39.0.dev0
76
+ - Pytorch 2.2.1+cu121
77
+ - Datasets 2.18.0
78
+ - Tokenizers 0.15.2
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen1.5-7B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 256,
13
+ "lora_dropout": 0.0,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 128,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "k_proj",
23
+ "o_proj",
24
+ "v_proj",
25
+ "down_proj",
26
+ "q_proj",
27
+ "up_proj",
28
+ "gate_proj"
29
+ ],
30
+ "task_type": "SEQ_CLS",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cedc29f0e3c70b05d17a273bde6f9c121acca7eb499a20c583e76da75799cbfb
3
+ size 1882260178
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/all_results.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.8596837944664032,
4
+ "eval_f1_macro": 0.8369626014217448,
5
+ "eval_f1_micro": 0.8596837944664032,
6
+ "eval_loss": 0.4968219995498657,
7
+ "eval_runtime": 69.9894,
8
+ "eval_samples": 1518,
9
+ "eval_samples_per_second": 21.689,
10
+ "eval_steps_per_second": 0.343,
11
+ "test_accuracy": 0.8656126482213439,
12
+ "test_f1_macro": 0.8325216055106754,
13
+ "test_f1_micro": 0.8656126482213439,
14
+ "test_loss": 0.4752732813358307,
15
+ "test_runtime": 71.3407,
16
+ "test_samples_per_second": 21.278,
17
+ "test_steps_per_second": 0.336,
18
+ "train_loss": 1.5545654296875,
19
+ "train_runtime": 6735.4111,
20
+ "train_samples": 12144,
21
+ "train_samples_per_second": 5.409,
22
+ "train_steps_per_second": 0.085
23
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: Qwen/Qwen1.5-7B
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.9.0
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen1.5-7B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 256,
13
+ "lora_dropout": 0.0,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 128,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "k_proj",
23
+ "o_proj",
24
+ "v_proj",
25
+ "down_proj",
26
+ "q_proj",
27
+ "up_proj",
28
+ "gate_proj"
29
+ ],
30
+ "task_type": "SEQ_CLS",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cedc29f0e3c70b05d17a273bde6f9c121acca7eb499a20c583e76da75799cbfb
3
+ size 1882260178
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/global_step550/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebaf6fa93d3430bc145598aa505e219ab667a5f938f820ac94c1169747e80395
3
+ size 1919487472
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/global_step550/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3397151de151c5dedad4dda7af68c85ab858df82dbf136614e81529bad333259
3
+ size 1919487600
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/global_step550/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7860285270e3c30292d40ae46c06834ae4b7394e3a03162fe85c73be54c8fb9f
3
+ size 640146476
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step550
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa878b9dab4c3723c4f5604b647f0a382b5b43b32ec9ed579e02f8f396f30f88
3
+ size 14512
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07a380ec5d7ef6434080f7e34913d8fb510f595347139628691d6320bcf76a7f
3
+ size 14512
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:398f41e79c8fa897296b46d4295b47f9f97b941419fa2b04df7bf09aa5e5015d
3
+ size 1064
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/special_tokens_map.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": "<|endoftext|>"
14
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|endoftext|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null
43
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/trainer_state.json ADDED
@@ -0,0 +1,527 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4968219995498657,
3
+ "best_model_checkpoint": "../experiments_checkpoints/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550",
4
+ "epoch": 2.8947368421052633,
5
+ "eval_steps": 50,
6
+ "global_step": 550,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05,
13
+ "grad_norm": 78.0635757446289,
14
+ "learning_rate": 4.912280701754386e-06,
15
+ "loss": 11.5813,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.11,
20
+ "grad_norm": 72.21075439453125,
21
+ "learning_rate": 4.824561403508772e-06,
22
+ "loss": 9.4297,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.16,
27
+ "grad_norm": 67.49365997314453,
28
+ "learning_rate": 4.736842105263158e-06,
29
+ "loss": 8.2891,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.21,
34
+ "grad_norm": 66.80319213867188,
35
+ "learning_rate": 4.649122807017544e-06,
36
+ "loss": 6.8797,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.26,
41
+ "grad_norm": 65.08647155761719,
42
+ "learning_rate": 4.56140350877193e-06,
43
+ "loss": 5.8578,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.26,
48
+ "eval_accuracy": 0.1251646903820817,
49
+ "eval_f1_macro": 0.09680804168971274,
50
+ "eval_f1_micro": 0.1251646903820817,
51
+ "eval_loss": 5.503664493560791,
52
+ "eval_runtime": 70.8056,
53
+ "eval_samples_per_second": 21.439,
54
+ "eval_steps_per_second": 0.339,
55
+ "step": 50
56
+ },
57
+ {
58
+ "epoch": 0.32,
59
+ "grad_norm": 56.8034553527832,
60
+ "learning_rate": 4.473684210526316e-06,
61
+ "loss": 5.1516,
62
+ "step": 60
63
+ },
64
+ {
65
+ "epoch": 0.37,
66
+ "grad_norm": 48.72732925415039,
67
+ "learning_rate": 4.385964912280702e-06,
68
+ "loss": 4.1211,
69
+ "step": 70
70
+ },
71
+ {
72
+ "epoch": 0.42,
73
+ "grad_norm": 52.9466667175293,
74
+ "learning_rate": 4.298245614035088e-06,
75
+ "loss": 3.4531,
76
+ "step": 80
77
+ },
78
+ {
79
+ "epoch": 0.47,
80
+ "grad_norm": 52.9542350769043,
81
+ "learning_rate": 4.210526315789474e-06,
82
+ "loss": 2.9504,
83
+ "step": 90
84
+ },
85
+ {
86
+ "epoch": 0.53,
87
+ "grad_norm": 49.08361053466797,
88
+ "learning_rate": 4.12280701754386e-06,
89
+ "loss": 2.3145,
90
+ "step": 100
91
+ },
92
+ {
93
+ "epoch": 0.53,
94
+ "eval_accuracy": 0.52832674571805,
95
+ "eval_f1_macro": 0.4222235273845894,
96
+ "eval_f1_micro": 0.52832674571805,
97
+ "eval_loss": 1.9804636240005493,
98
+ "eval_runtime": 70.8343,
99
+ "eval_samples_per_second": 21.43,
100
+ "eval_steps_per_second": 0.339,
101
+ "step": 100
102
+ },
103
+ {
104
+ "epoch": 0.58,
105
+ "grad_norm": 38.720149993896484,
106
+ "learning_rate": 4.035087719298246e-06,
107
+ "loss": 1.6187,
108
+ "step": 110
109
+ },
110
+ {
111
+ "epoch": 0.63,
112
+ "grad_norm": 51.675872802734375,
113
+ "learning_rate": 3.947368421052632e-06,
114
+ "loss": 1.4811,
115
+ "step": 120
116
+ },
117
+ {
118
+ "epoch": 0.68,
119
+ "grad_norm": 33.777587890625,
120
+ "learning_rate": 3.859649122807018e-06,
121
+ "loss": 1.3875,
122
+ "step": 130
123
+ },
124
+ {
125
+ "epoch": 0.74,
126
+ "grad_norm": 25.40624237060547,
127
+ "learning_rate": 3.7719298245614037e-06,
128
+ "loss": 1.1301,
129
+ "step": 140
130
+ },
131
+ {
132
+ "epoch": 0.79,
133
+ "grad_norm": 30.72103500366211,
134
+ "learning_rate": 3.6842105263157896e-06,
135
+ "loss": 0.9115,
136
+ "step": 150
137
+ },
138
+ {
139
+ "epoch": 0.79,
140
+ "eval_accuracy": 0.7720685111989459,
141
+ "eval_f1_macro": 0.7139330965236713,
142
+ "eval_f1_micro": 0.7720685111989459,
143
+ "eval_loss": 0.9063529372215271,
144
+ "eval_runtime": 70.8238,
145
+ "eval_samples_per_second": 21.433,
146
+ "eval_steps_per_second": 0.339,
147
+ "step": 150
148
+ },
149
+ {
150
+ "epoch": 0.84,
151
+ "grad_norm": 47.277923583984375,
152
+ "learning_rate": 3.596491228070176e-06,
153
+ "loss": 0.8274,
154
+ "step": 160
155
+ },
156
+ {
157
+ "epoch": 0.89,
158
+ "grad_norm": 34.87353515625,
159
+ "learning_rate": 3.5087719298245615e-06,
160
+ "loss": 0.9087,
161
+ "step": 170
162
+ },
163
+ {
164
+ "epoch": 0.95,
165
+ "grad_norm": 33.74974060058594,
166
+ "learning_rate": 3.421052631578948e-06,
167
+ "loss": 0.8381,
168
+ "step": 180
169
+ },
170
+ {
171
+ "epoch": 1.0,
172
+ "grad_norm": 30.923776626586914,
173
+ "learning_rate": 3.3333333333333333e-06,
174
+ "loss": 0.8215,
175
+ "step": 190
176
+ },
177
+ {
178
+ "epoch": 1.05,
179
+ "grad_norm": 30.552841186523438,
180
+ "learning_rate": 3.2456140350877197e-06,
181
+ "loss": 0.7251,
182
+ "step": 200
183
+ },
184
+ {
185
+ "epoch": 1.05,
186
+ "eval_accuracy": 0.8089591567852438,
187
+ "eval_f1_macro": 0.7669219918531099,
188
+ "eval_f1_micro": 0.8089591567852438,
189
+ "eval_loss": 0.7033617496490479,
190
+ "eval_runtime": 70.8095,
191
+ "eval_samples_per_second": 21.438,
192
+ "eval_steps_per_second": 0.339,
193
+ "step": 200
194
+ },
195
+ {
196
+ "epoch": 1.11,
197
+ "grad_norm": 40.9909553527832,
198
+ "learning_rate": 3.157894736842105e-06,
199
+ "loss": 0.6617,
200
+ "step": 210
201
+ },
202
+ {
203
+ "epoch": 1.16,
204
+ "grad_norm": 22.532026290893555,
205
+ "learning_rate": 3.0701754385964915e-06,
206
+ "loss": 0.6655,
207
+ "step": 220
208
+ },
209
+ {
210
+ "epoch": 1.21,
211
+ "grad_norm": 22.03099250793457,
212
+ "learning_rate": 2.9824561403508774e-06,
213
+ "loss": 0.6155,
214
+ "step": 230
215
+ },
216
+ {
217
+ "epoch": 1.26,
218
+ "grad_norm": 31.129398345947266,
219
+ "learning_rate": 2.8947368421052634e-06,
220
+ "loss": 0.5786,
221
+ "step": 240
222
+ },
223
+ {
224
+ "epoch": 1.32,
225
+ "grad_norm": 22.806337356567383,
226
+ "learning_rate": 2.8070175438596493e-06,
227
+ "loss": 0.5086,
228
+ "step": 250
229
+ },
230
+ {
231
+ "epoch": 1.32,
232
+ "eval_accuracy": 0.8267457180500659,
233
+ "eval_f1_macro": 0.7755720185959084,
234
+ "eval_f1_micro": 0.8267457180500659,
235
+ "eval_loss": 0.6432034373283386,
236
+ "eval_runtime": 70.864,
237
+ "eval_samples_per_second": 21.421,
238
+ "eval_steps_per_second": 0.339,
239
+ "step": 250
240
+ },
241
+ {
242
+ "epoch": 1.37,
243
+ "grad_norm": 24.898916244506836,
244
+ "learning_rate": 2.7192982456140356e-06,
245
+ "loss": 0.537,
246
+ "step": 260
247
+ },
248
+ {
249
+ "epoch": 1.42,
250
+ "grad_norm": 33.29705047607422,
251
+ "learning_rate": 2.631578947368421e-06,
252
+ "loss": 0.5357,
253
+ "step": 270
254
+ },
255
+ {
256
+ "epoch": 1.47,
257
+ "grad_norm": 20.23432159423828,
258
+ "learning_rate": 2.5438596491228075e-06,
259
+ "loss": 0.5452,
260
+ "step": 280
261
+ },
262
+ {
263
+ "epoch": 1.53,
264
+ "grad_norm": 26.38104820251465,
265
+ "learning_rate": 2.456140350877193e-06,
266
+ "loss": 0.5015,
267
+ "step": 290
268
+ },
269
+ {
270
+ "epoch": 1.58,
271
+ "grad_norm": 23.257266998291016,
272
+ "learning_rate": 2.368421052631579e-06,
273
+ "loss": 0.5473,
274
+ "step": 300
275
+ },
276
+ {
277
+ "epoch": 1.58,
278
+ "eval_accuracy": 0.8353096179183136,
279
+ "eval_f1_macro": 0.7982776447477468,
280
+ "eval_f1_micro": 0.8353096179183136,
281
+ "eval_loss": 0.591135561466217,
282
+ "eval_runtime": 70.7822,
283
+ "eval_samples_per_second": 21.446,
284
+ "eval_steps_per_second": 0.339,
285
+ "step": 300
286
+ },
287
+ {
288
+ "epoch": 1.63,
289
+ "grad_norm": 31.060453414916992,
290
+ "learning_rate": 2.280701754385965e-06,
291
+ "loss": 0.5914,
292
+ "step": 310
293
+ },
294
+ {
295
+ "epoch": 1.68,
296
+ "grad_norm": 38.224273681640625,
297
+ "learning_rate": 2.192982456140351e-06,
298
+ "loss": 0.547,
299
+ "step": 320
300
+ },
301
+ {
302
+ "epoch": 1.74,
303
+ "grad_norm": 24.825180053710938,
304
+ "learning_rate": 2.105263157894737e-06,
305
+ "loss": 0.5009,
306
+ "step": 330
307
+ },
308
+ {
309
+ "epoch": 1.79,
310
+ "grad_norm": 33.94304656982422,
311
+ "learning_rate": 2.017543859649123e-06,
312
+ "loss": 0.607,
313
+ "step": 340
314
+ },
315
+ {
316
+ "epoch": 1.84,
317
+ "grad_norm": 47.21768569946289,
318
+ "learning_rate": 1.929824561403509e-06,
319
+ "loss": 0.514,
320
+ "step": 350
321
+ },
322
+ {
323
+ "epoch": 1.84,
324
+ "eval_accuracy": 0.8563899868247694,
325
+ "eval_f1_macro": 0.8328616425942686,
326
+ "eval_f1_micro": 0.8563899868247694,
327
+ "eval_loss": 0.5453721880912781,
328
+ "eval_runtime": 70.8148,
329
+ "eval_samples_per_second": 21.436,
330
+ "eval_steps_per_second": 0.339,
331
+ "step": 350
332
+ },
333
+ {
334
+ "epoch": 1.89,
335
+ "grad_norm": 22.25798797607422,
336
+ "learning_rate": 1.8421052631578948e-06,
337
+ "loss": 0.4804,
338
+ "step": 360
339
+ },
340
+ {
341
+ "epoch": 1.95,
342
+ "grad_norm": 25.627458572387695,
343
+ "learning_rate": 1.7543859649122807e-06,
344
+ "loss": 0.5387,
345
+ "step": 370
346
+ },
347
+ {
348
+ "epoch": 2.0,
349
+ "grad_norm": 26.785030364990234,
350
+ "learning_rate": 1.6666666666666667e-06,
351
+ "loss": 0.5375,
352
+ "step": 380
353
+ },
354
+ {
355
+ "epoch": 2.05,
356
+ "grad_norm": 24.151248931884766,
357
+ "learning_rate": 1.5789473684210526e-06,
358
+ "loss": 0.4375,
359
+ "step": 390
360
+ },
361
+ {
362
+ "epoch": 2.11,
363
+ "grad_norm": 31.1235408782959,
364
+ "learning_rate": 1.4912280701754387e-06,
365
+ "loss": 0.4493,
366
+ "step": 400
367
+ },
368
+ {
369
+ "epoch": 2.11,
370
+ "eval_accuracy": 0.8465085638998683,
371
+ "eval_f1_macro": 0.817214362989291,
372
+ "eval_f1_micro": 0.8465085638998683,
373
+ "eval_loss": 0.5436841249465942,
374
+ "eval_runtime": 70.7986,
375
+ "eval_samples_per_second": 21.441,
376
+ "eval_steps_per_second": 0.339,
377
+ "step": 400
378
+ },
379
+ {
380
+ "epoch": 2.16,
381
+ "grad_norm": 24.023176193237305,
382
+ "learning_rate": 1.4035087719298246e-06,
383
+ "loss": 0.4135,
384
+ "step": 410
385
+ },
386
+ {
387
+ "epoch": 2.21,
388
+ "grad_norm": 29.59303092956543,
389
+ "learning_rate": 1.3157894736842106e-06,
390
+ "loss": 0.4725,
391
+ "step": 420
392
+ },
393
+ {
394
+ "epoch": 2.26,
395
+ "grad_norm": 26.1127872467041,
396
+ "learning_rate": 1.2280701754385965e-06,
397
+ "loss": 0.3891,
398
+ "step": 430
399
+ },
400
+ {
401
+ "epoch": 2.32,
402
+ "grad_norm": 30.481605529785156,
403
+ "learning_rate": 1.1403508771929824e-06,
404
+ "loss": 0.4042,
405
+ "step": 440
406
+ },
407
+ {
408
+ "epoch": 2.37,
409
+ "grad_norm": 22.664913177490234,
410
+ "learning_rate": 1.0526315789473685e-06,
411
+ "loss": 0.516,
412
+ "step": 450
413
+ },
414
+ {
415
+ "epoch": 2.37,
416
+ "eval_accuracy": 0.8530961791831357,
417
+ "eval_f1_macro": 0.828913306836084,
418
+ "eval_f1_micro": 0.8530961791831357,
419
+ "eval_loss": 0.5225136876106262,
420
+ "eval_runtime": 70.8455,
421
+ "eval_samples_per_second": 21.427,
422
+ "eval_steps_per_second": 0.339,
423
+ "step": 450
424
+ },
425
+ {
426
+ "epoch": 2.42,
427
+ "grad_norm": 27.753475189208984,
428
+ "learning_rate": 9.649122807017545e-07,
429
+ "loss": 0.3435,
430
+ "step": 460
431
+ },
432
+ {
433
+ "epoch": 2.47,
434
+ "grad_norm": 28.056856155395508,
435
+ "learning_rate": 8.771929824561404e-07,
436
+ "loss": 0.4159,
437
+ "step": 470
438
+ },
439
+ {
440
+ "epoch": 2.53,
441
+ "grad_norm": 28.235706329345703,
442
+ "learning_rate": 7.894736842105263e-07,
443
+ "loss": 0.44,
444
+ "step": 480
445
+ },
446
+ {
447
+ "epoch": 2.58,
448
+ "grad_norm": 19.392196655273438,
449
+ "learning_rate": 7.017543859649123e-07,
450
+ "loss": 0.3991,
451
+ "step": 490
452
+ },
453
+ {
454
+ "epoch": 2.63,
455
+ "grad_norm": 24.779186248779297,
456
+ "learning_rate": 6.140350877192982e-07,
457
+ "loss": 0.343,
458
+ "step": 500
459
+ },
460
+ {
461
+ "epoch": 2.63,
462
+ "eval_accuracy": 0.8557312252964426,
463
+ "eval_f1_macro": 0.8339166245745164,
464
+ "eval_f1_micro": 0.8557312252964426,
465
+ "eval_loss": 0.4982321560382843,
466
+ "eval_runtime": 70.8133,
467
+ "eval_samples_per_second": 21.437,
468
+ "eval_steps_per_second": 0.339,
469
+ "step": 500
470
+ },
471
+ {
472
+ "epoch": 2.68,
473
+ "grad_norm": 21.358295440673828,
474
+ "learning_rate": 5.263157894736843e-07,
475
+ "loss": 0.3543,
476
+ "step": 510
477
+ },
478
+ {
479
+ "epoch": 2.74,
480
+ "grad_norm": 26.393150329589844,
481
+ "learning_rate": 4.385964912280702e-07,
482
+ "loss": 0.4026,
483
+ "step": 520
484
+ },
485
+ {
486
+ "epoch": 2.79,
487
+ "grad_norm": 26.136310577392578,
488
+ "learning_rate": 3.5087719298245616e-07,
489
+ "loss": 0.3974,
490
+ "step": 530
491
+ },
492
+ {
493
+ "epoch": 2.84,
494
+ "grad_norm": 20.45792579650879,
495
+ "learning_rate": 2.6315789473684213e-07,
496
+ "loss": 0.4142,
497
+ "step": 540
498
+ },
499
+ {
500
+ "epoch": 2.89,
501
+ "grad_norm": 24.060897827148438,
502
+ "learning_rate": 1.7543859649122808e-07,
503
+ "loss": 0.4203,
504
+ "step": 550
505
+ },
506
+ {
507
+ "epoch": 2.89,
508
+ "eval_accuracy": 0.8596837944664032,
509
+ "eval_f1_macro": 0.8369626014217448,
510
+ "eval_f1_micro": 0.8596837944664032,
511
+ "eval_loss": 0.4968219995498657,
512
+ "eval_runtime": 70.7643,
513
+ "eval_samples_per_second": 21.452,
514
+ "eval_steps_per_second": 0.339,
515
+ "step": 550
516
+ }
517
+ ],
518
+ "logging_steps": 10,
519
+ "max_steps": 570,
520
+ "num_input_tokens_seen": 0,
521
+ "num_train_epochs": 3,
522
+ "save_steps": 50,
523
+ "total_flos": 7.34953687000023e+17,
524
+ "train_batch_size": 32,
525
+ "trial_name": null,
526
+ "trial_params": null
527
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c352945f05514abeccc19c517e1b0f3bc31de7dfc5f7a93d0b302ba8e6938bcf
3
+ size 6008
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550/zero_to_fp32.py ADDED
@@ -0,0 +1,604 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example: python zero_to_fp32.py . pytorch_model.bin
14
+
15
+ import argparse
16
+ import torch
17
+ import glob
18
+ import math
19
+ import os
20
+ import re
21
+ from collections import OrderedDict
22
+ from dataclasses import dataclass
23
+
24
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
25
+ # DeepSpeed data structures it has to be available in the current python environment.
26
+ from deepspeed.utils import logger
27
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
28
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
29
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
30
+
31
+
32
+ @dataclass
33
+ class zero_model_state:
34
+ buffers: dict()
35
+ param_shapes: dict()
36
+ shared_params: list
37
+ ds_version: int
38
+ frozen_param_shapes: dict()
39
+ frozen_param_fragments: dict()
40
+
41
+
42
+ debug = 0
43
+
44
+ # load to cpu
45
+ device = torch.device('cpu')
46
+
47
+
48
+ def atoi(text):
49
+ return int(text) if text.isdigit() else text
50
+
51
+
52
+ def natural_keys(text):
53
+ '''
54
+ alist.sort(key=natural_keys) sorts in human order
55
+ http://nedbatchelder.com/blog/200712/human_sorting.html
56
+ (See Toothy's implementation in the comments)
57
+ '''
58
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
59
+
60
+
61
+ def get_model_state_file(checkpoint_dir, zero_stage):
62
+ if not os.path.isdir(checkpoint_dir):
63
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
64
+
65
+ # there should be only one file
66
+ if zero_stage <= 2:
67
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
68
+ elif zero_stage == 3:
69
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
70
+
71
+ if not os.path.exists(file):
72
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
73
+
74
+ return file
75
+
76
+
77
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
78
+ # XXX: need to test that this simple glob rule works for multi-node setup too
79
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
80
+
81
+ if len(ckpt_files) == 0:
82
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
83
+
84
+ return ckpt_files
85
+
86
+
87
+ def get_optim_files(checkpoint_dir):
88
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
89
+
90
+
91
+ def get_model_state_files(checkpoint_dir):
92
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
93
+
94
+
95
+ def parse_model_states(files):
96
+ zero_model_states = []
97
+ for file in files:
98
+ state_dict = torch.load(file, map_location=device)
99
+
100
+ if BUFFER_NAMES not in state_dict:
101
+ raise ValueError(f"{file} is not a model state checkpoint")
102
+ buffer_names = state_dict[BUFFER_NAMES]
103
+ if debug:
104
+ print("Found buffers:", buffer_names)
105
+
106
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
107
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
108
+ param_shapes = state_dict[PARAM_SHAPES]
109
+
110
+ # collect parameters that are included in param_shapes
111
+ param_names = []
112
+ for s in param_shapes:
113
+ for name in s.keys():
114
+ param_names.append(name)
115
+
116
+ # update with frozen parameters
117
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
118
+ if frozen_param_shapes is not None:
119
+ if debug:
120
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
121
+ param_names += list(frozen_param_shapes.keys())
122
+
123
+ # handle shared params
124
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
125
+
126
+ ds_version = state_dict.get(DS_VERSION, None)
127
+
128
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
129
+
130
+ z_model_state = zero_model_state(buffers=buffers,
131
+ param_shapes=param_shapes,
132
+ shared_params=shared_params,
133
+ ds_version=ds_version,
134
+ frozen_param_shapes=frozen_param_shapes,
135
+ frozen_param_fragments=frozen_param_fragments)
136
+ zero_model_states.append(z_model_state)
137
+
138
+ return zero_model_states
139
+
140
+
141
+ def parse_optim_states(files, ds_checkpoint_dir):
142
+
143
+ total_files = len(files)
144
+ state_dicts = []
145
+ for f in files:
146
+ state_dict = torch.load(f, map_location=device)
147
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
148
+ # and also handle the case where it was already removed by another helper script
149
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
150
+ state_dicts.append(state_dict)
151
+
152
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
153
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
154
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
155
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
156
+
157
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
158
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
159
+ # use the max of the partition_count to get the dp world_size.
160
+
161
+ if type(world_size) is list:
162
+ world_size = max(world_size)
163
+
164
+ if world_size != total_files:
165
+ raise ValueError(
166
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
167
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
168
+ )
169
+
170
+ # the groups are named differently in each stage
171
+ if zero_stage <= 2:
172
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
173
+ elif zero_stage == 3:
174
+ fp32_groups_key = FP32_FLAT_GROUPS
175
+ else:
176
+ raise ValueError(f"unknown zero stage {zero_stage}")
177
+
178
+ if zero_stage <= 2:
179
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
180
+ elif zero_stage == 3:
181
+ # if there is more than one param group, there will be multiple flattened tensors - one
182
+ # flattened tensor per group - for simplicity merge them into a single tensor
183
+ #
184
+ # XXX: could make the script more memory efficient for when there are multiple groups - it
185
+ # will require matching the sub-lists of param_shapes for each param group flattened tensor
186
+
187
+ fp32_flat_groups = [
188
+ torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
189
+ ]
190
+
191
+ return zero_stage, world_size, fp32_flat_groups
192
+
193
+
194
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
195
+ """
196
+ Returns fp32 state_dict reconstructed from ds checkpoint
197
+
198
+ Args:
199
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
200
+
201
+ """
202
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
203
+
204
+ optim_files = get_optim_files(ds_checkpoint_dir)
205
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
206
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
207
+
208
+ model_files = get_model_state_files(ds_checkpoint_dir)
209
+
210
+ zero_model_states = parse_model_states(model_files)
211
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
212
+
213
+ if zero_stage <= 2:
214
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
215
+ exclude_frozen_parameters)
216
+ elif zero_stage == 3:
217
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
218
+ exclude_frozen_parameters)
219
+
220
+
221
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
222
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
223
+ return
224
+
225
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
226
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
227
+
228
+ if debug:
229
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
230
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
231
+
232
+ wanted_params = len(frozen_param_shapes)
233
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
234
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
235
+ print(f'Frozen params: Have {avail_numel} numels to process.')
236
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
237
+
238
+ total_params = 0
239
+ total_numel = 0
240
+ for name, shape in frozen_param_shapes.items():
241
+ total_params += 1
242
+ unpartitioned_numel = shape.numel()
243
+ total_numel += unpartitioned_numel
244
+
245
+ state_dict[name] = frozen_param_fragments[name]
246
+
247
+ if debug:
248
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
249
+
250
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
251
+
252
+
253
+ def _has_callable(obj, fn):
254
+ attr = getattr(obj, fn, None)
255
+ return callable(attr)
256
+
257
+
258
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
259
+ param_shapes = zero_model_states[0].param_shapes
260
+
261
+ # Reconstruction protocol:
262
+ #
263
+ # XXX: document this
264
+
265
+ if debug:
266
+ for i in range(world_size):
267
+ for j in range(len(fp32_flat_groups[0])):
268
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
269
+
270
+ # XXX: memory usage doubles here (zero2)
271
+ num_param_groups = len(fp32_flat_groups[0])
272
+ merged_single_partition_of_fp32_groups = []
273
+ for i in range(num_param_groups):
274
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
275
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
276
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
277
+ avail_numel = sum(
278
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
279
+
280
+ if debug:
281
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
282
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
283
+ # not asserting if there is a mismatch due to possible padding
284
+ print(f"Have {avail_numel} numels to process.")
285
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
286
+
287
+ # params
288
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
289
+ # out-of-core computing solution
290
+ total_numel = 0
291
+ total_params = 0
292
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
293
+ offset = 0
294
+ avail_numel = full_single_fp32_vector.numel()
295
+ for name, shape in shapes.items():
296
+
297
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
298
+ total_numel += unpartitioned_numel
299
+ total_params += 1
300
+
301
+ if debug:
302
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
303
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
304
+ offset += unpartitioned_numel
305
+
306
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
307
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
308
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
309
+ # live optimizer object, so we are checking that the numbers are within the right range
310
+ align_to = 2 * world_size
311
+
312
+ def zero2_align(x):
313
+ return align_to * math.ceil(x / align_to)
314
+
315
+ if debug:
316
+ print(f"original offset={offset}, avail_numel={avail_numel}")
317
+
318
+ offset = zero2_align(offset)
319
+ avail_numel = zero2_align(avail_numel)
320
+
321
+ if debug:
322
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
323
+
324
+ # Sanity check
325
+ if offset != avail_numel:
326
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
327
+
328
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
329
+
330
+
331
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
332
+ exclude_frozen_parameters):
333
+ state_dict = OrderedDict()
334
+
335
+ # buffers
336
+ buffers = zero_model_states[0].buffers
337
+ state_dict.update(buffers)
338
+ if debug:
339
+ print(f"added {len(buffers)} buffers")
340
+
341
+ if not exclude_frozen_parameters:
342
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
343
+
344
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
345
+
346
+ # recover shared parameters
347
+ for pair in zero_model_states[0].shared_params:
348
+ if pair[1] in state_dict:
349
+ state_dict[pair[0]] = state_dict[pair[1]]
350
+
351
+ return state_dict
352
+
353
+
354
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
355
+ remainder = unpartitioned_numel % world_size
356
+ padding_numel = (world_size - remainder) if remainder else 0
357
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
358
+ return partitioned_numel, padding_numel
359
+
360
+
361
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
362
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
363
+ return
364
+
365
+ if debug:
366
+ for i in range(world_size):
367
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
368
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
369
+
370
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
371
+ wanted_params = len(frozen_param_shapes)
372
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
373
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
374
+ print(f'Frozen params: Have {avail_numel} numels to process.')
375
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
376
+
377
+ total_params = 0
378
+ total_numel = 0
379
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
380
+ total_params += 1
381
+ unpartitioned_numel = shape.numel()
382
+ total_numel += unpartitioned_numel
383
+
384
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
385
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
386
+
387
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
388
+
389
+ if debug:
390
+ print(
391
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
392
+ )
393
+
394
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
395
+
396
+
397
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
398
+ param_shapes = zero_model_states[0].param_shapes
399
+ avail_numel = fp32_flat_groups[0].numel() * world_size
400
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
401
+ # param, re-consolidating each param, while dealing with padding if any
402
+
403
+ # merge list of dicts, preserving order
404
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
405
+
406
+ if debug:
407
+ for i in range(world_size):
408
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
409
+
410
+ wanted_params = len(param_shapes)
411
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
412
+ # not asserting if there is a mismatch due to possible padding
413
+ avail_numel = fp32_flat_groups[0].numel() * world_size
414
+ print(f"Trainable params: Have {avail_numel} numels to process.")
415
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
416
+
417
+ # params
418
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
419
+ # out-of-core computing solution
420
+ offset = 0
421
+ total_numel = 0
422
+ total_params = 0
423
+ for name, shape in param_shapes.items():
424
+
425
+ unpartitioned_numel = shape.numel()
426
+ total_numel += unpartitioned_numel
427
+ total_params += 1
428
+
429
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
430
+
431
+ if debug:
432
+ print(
433
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
434
+ )
435
+
436
+ # XXX: memory usage doubles here
437
+ state_dict[name] = torch.cat(
438
+ tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
439
+ 0).narrow(0, 0, unpartitioned_numel).view(shape)
440
+ offset += partitioned_numel
441
+
442
+ offset *= world_size
443
+
444
+ # Sanity check
445
+ if offset != avail_numel:
446
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
447
+
448
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
449
+
450
+
451
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
452
+ exclude_frozen_parameters):
453
+ state_dict = OrderedDict()
454
+
455
+ # buffers
456
+ buffers = zero_model_states[0].buffers
457
+ state_dict.update(buffers)
458
+ if debug:
459
+ print(f"added {len(buffers)} buffers")
460
+
461
+ if not exclude_frozen_parameters:
462
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
463
+
464
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
465
+
466
+ # recover shared parameters
467
+ for pair in zero_model_states[0].shared_params:
468
+ if pair[1] in state_dict:
469
+ state_dict[pair[0]] = state_dict[pair[1]]
470
+
471
+ return state_dict
472
+
473
+
474
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
475
+ """
476
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
477
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
478
+ via a model hub.
479
+
480
+ Args:
481
+ - ``checkpoint_dir``: path to the desired checkpoint folder
482
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
483
+ - ``exclude_frozen_parameters``: exclude frozen parameters
484
+
485
+ Returns:
486
+ - pytorch ``state_dict``
487
+
488
+ Note: this approach may not work if your application doesn't have sufficient free CPU memory and
489
+ you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
490
+ the checkpoint.
491
+
492
+ A typical usage might be ::
493
+
494
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
495
+ # do the training and checkpoint saving
496
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
497
+ model = model.cpu() # move to cpu
498
+ model.load_state_dict(state_dict)
499
+ # submit to model hub or save the model to share with others
500
+
501
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
502
+ application. i.e. you will need to re-initialize the deepspeed engine, since
503
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
504
+
505
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
506
+
507
+ """
508
+ if tag is None:
509
+ latest_path = os.path.join(checkpoint_dir, 'latest')
510
+ if os.path.isfile(latest_path):
511
+ with open(latest_path, 'r') as fd:
512
+ tag = fd.read().strip()
513
+ else:
514
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
515
+
516
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
517
+
518
+ if not os.path.isdir(ds_checkpoint_dir):
519
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
520
+
521
+ return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
522
+
523
+
524
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
525
+ """
526
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
527
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
528
+
529
+ Args:
530
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
531
+ - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
532
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
533
+ - ``exclude_frozen_parameters``: exclude frozen parameters
534
+ """
535
+
536
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
537
+ print(f"Saving fp32 state dict to {output_file}")
538
+ torch.save(state_dict, output_file)
539
+
540
+
541
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
542
+ """
543
+ 1. Put the provided model to cpu
544
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
545
+ 3. Load it into the provided model
546
+
547
+ Args:
548
+ - ``model``: the model object to update
549
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
550
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
551
+
552
+ Returns:
553
+ - ``model`: modified model
554
+
555
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
556
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
557
+ conveniently placed for you in the checkpoint folder.
558
+
559
+ A typical usage might be ::
560
+
561
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
562
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
563
+ # submit to model hub or save the model to share with others
564
+
565
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
566
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
567
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
568
+
569
+ """
570
+ logger.info(f"Extracting fp32 weights")
571
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
572
+
573
+ logger.info(f"Overwriting model with fp32 weights")
574
+ model = model.cpu()
575
+ model.load_state_dict(state_dict, strict=False)
576
+
577
+ return model
578
+
579
+
580
+ if __name__ == "__main__":
581
+
582
+ parser = argparse.ArgumentParser()
583
+ parser.add_argument("checkpoint_dir",
584
+ type=str,
585
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
586
+ parser.add_argument(
587
+ "output_file",
588
+ type=str,
589
+ help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
590
+ parser.add_argument("-t",
591
+ "--tag",
592
+ type=str,
593
+ default=None,
594
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
595
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
596
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
597
+ args = parser.parse_args()
598
+
599
+ debug = args.debug
600
+
601
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
602
+ args.output_file,
603
+ tag=args.tag,
604
+ exclude_frozen_parameters=args.exclude_frozen_parameters)
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.8596837944664032,
4
+ "eval_f1_macro": 0.8369626014217448,
5
+ "eval_f1_micro": 0.8596837944664032,
6
+ "eval_loss": 0.4968219995498657,
7
+ "eval_runtime": 69.9894,
8
+ "eval_samples": 1518,
9
+ "eval_samples_per_second": 21.689,
10
+ "eval_steps_per_second": 0.343
11
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/run.log ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ 03/25/2024 02:21:11 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, 16-bits training: False
2
+ 03/25/2024 02:21:11 - WARNING - __main__ - Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, 16-bits training: False
3
+ 03/25/2024 02:21:39 - WARNING - __main__ - The label2id key in the model config.json is not equal to the label2id key of this run. You can ignore this if you are doing finetuning.
4
+ 03/25/2024 02:21:39 - WARNING - __main__ - The label2id key in the model config.json is not equal to the label2id key of this run. You can ignore this if you are doing finetuning.
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/special_tokens_map.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": "<|endoftext|>"
14
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/test_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "test_accuracy": 0.8656126482213439,
4
+ "test_f1_macro": 0.8325216055106754,
5
+ "test_f1_micro": 0.8656126482213439,
6
+ "test_loss": 0.4752732813358307,
7
+ "test_runtime": 71.3407,
8
+ "test_samples_per_second": 21.278,
9
+ "test_steps_per_second": 0.336
10
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|endoftext|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null
43
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 1.5545654296875,
4
+ "train_runtime": 6735.4111,
5
+ "train_samples": 12144,
6
+ "train_samples_per_second": 5.409,
7
+ "train_steps_per_second": 0.085
8
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/trainer_state.json ADDED
@@ -0,0 +1,550 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4968219995498657,
3
+ "best_model_checkpoint": "../experiments_checkpoints/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/checkpoint-550",
4
+ "epoch": 3.0,
5
+ "eval_steps": 50,
6
+ "global_step": 570,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05,
13
+ "grad_norm": 78.0635757446289,
14
+ "learning_rate": 4.912280701754386e-06,
15
+ "loss": 11.5813,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.11,
20
+ "grad_norm": 72.21075439453125,
21
+ "learning_rate": 4.824561403508772e-06,
22
+ "loss": 9.4297,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.16,
27
+ "grad_norm": 67.49365997314453,
28
+ "learning_rate": 4.736842105263158e-06,
29
+ "loss": 8.2891,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.21,
34
+ "grad_norm": 66.80319213867188,
35
+ "learning_rate": 4.649122807017544e-06,
36
+ "loss": 6.8797,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.26,
41
+ "grad_norm": 65.08647155761719,
42
+ "learning_rate": 4.56140350877193e-06,
43
+ "loss": 5.8578,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.26,
48
+ "eval_accuracy": 0.1251646903820817,
49
+ "eval_f1_macro": 0.09680804168971274,
50
+ "eval_f1_micro": 0.1251646903820817,
51
+ "eval_loss": 5.503664493560791,
52
+ "eval_runtime": 70.8056,
53
+ "eval_samples_per_second": 21.439,
54
+ "eval_steps_per_second": 0.339,
55
+ "step": 50
56
+ },
57
+ {
58
+ "epoch": 0.32,
59
+ "grad_norm": 56.8034553527832,
60
+ "learning_rate": 4.473684210526316e-06,
61
+ "loss": 5.1516,
62
+ "step": 60
63
+ },
64
+ {
65
+ "epoch": 0.37,
66
+ "grad_norm": 48.72732925415039,
67
+ "learning_rate": 4.385964912280702e-06,
68
+ "loss": 4.1211,
69
+ "step": 70
70
+ },
71
+ {
72
+ "epoch": 0.42,
73
+ "grad_norm": 52.9466667175293,
74
+ "learning_rate": 4.298245614035088e-06,
75
+ "loss": 3.4531,
76
+ "step": 80
77
+ },
78
+ {
79
+ "epoch": 0.47,
80
+ "grad_norm": 52.9542350769043,
81
+ "learning_rate": 4.210526315789474e-06,
82
+ "loss": 2.9504,
83
+ "step": 90
84
+ },
85
+ {
86
+ "epoch": 0.53,
87
+ "grad_norm": 49.08361053466797,
88
+ "learning_rate": 4.12280701754386e-06,
89
+ "loss": 2.3145,
90
+ "step": 100
91
+ },
92
+ {
93
+ "epoch": 0.53,
94
+ "eval_accuracy": 0.52832674571805,
95
+ "eval_f1_macro": 0.4222235273845894,
96
+ "eval_f1_micro": 0.52832674571805,
97
+ "eval_loss": 1.9804636240005493,
98
+ "eval_runtime": 70.8343,
99
+ "eval_samples_per_second": 21.43,
100
+ "eval_steps_per_second": 0.339,
101
+ "step": 100
102
+ },
103
+ {
104
+ "epoch": 0.58,
105
+ "grad_norm": 38.720149993896484,
106
+ "learning_rate": 4.035087719298246e-06,
107
+ "loss": 1.6187,
108
+ "step": 110
109
+ },
110
+ {
111
+ "epoch": 0.63,
112
+ "grad_norm": 51.675872802734375,
113
+ "learning_rate": 3.947368421052632e-06,
114
+ "loss": 1.4811,
115
+ "step": 120
116
+ },
117
+ {
118
+ "epoch": 0.68,
119
+ "grad_norm": 33.777587890625,
120
+ "learning_rate": 3.859649122807018e-06,
121
+ "loss": 1.3875,
122
+ "step": 130
123
+ },
124
+ {
125
+ "epoch": 0.74,
126
+ "grad_norm": 25.40624237060547,
127
+ "learning_rate": 3.7719298245614037e-06,
128
+ "loss": 1.1301,
129
+ "step": 140
130
+ },
131
+ {
132
+ "epoch": 0.79,
133
+ "grad_norm": 30.72103500366211,
134
+ "learning_rate": 3.6842105263157896e-06,
135
+ "loss": 0.9115,
136
+ "step": 150
137
+ },
138
+ {
139
+ "epoch": 0.79,
140
+ "eval_accuracy": 0.7720685111989459,
141
+ "eval_f1_macro": 0.7139330965236713,
142
+ "eval_f1_micro": 0.7720685111989459,
143
+ "eval_loss": 0.9063529372215271,
144
+ "eval_runtime": 70.8238,
145
+ "eval_samples_per_second": 21.433,
146
+ "eval_steps_per_second": 0.339,
147
+ "step": 150
148
+ },
149
+ {
150
+ "epoch": 0.84,
151
+ "grad_norm": 47.277923583984375,
152
+ "learning_rate": 3.596491228070176e-06,
153
+ "loss": 0.8274,
154
+ "step": 160
155
+ },
156
+ {
157
+ "epoch": 0.89,
158
+ "grad_norm": 34.87353515625,
159
+ "learning_rate": 3.5087719298245615e-06,
160
+ "loss": 0.9087,
161
+ "step": 170
162
+ },
163
+ {
164
+ "epoch": 0.95,
165
+ "grad_norm": 33.74974060058594,
166
+ "learning_rate": 3.421052631578948e-06,
167
+ "loss": 0.8381,
168
+ "step": 180
169
+ },
170
+ {
171
+ "epoch": 1.0,
172
+ "grad_norm": 30.923776626586914,
173
+ "learning_rate": 3.3333333333333333e-06,
174
+ "loss": 0.8215,
175
+ "step": 190
176
+ },
177
+ {
178
+ "epoch": 1.05,
179
+ "grad_norm": 30.552841186523438,
180
+ "learning_rate": 3.2456140350877197e-06,
181
+ "loss": 0.7251,
182
+ "step": 200
183
+ },
184
+ {
185
+ "epoch": 1.05,
186
+ "eval_accuracy": 0.8089591567852438,
187
+ "eval_f1_macro": 0.7669219918531099,
188
+ "eval_f1_micro": 0.8089591567852438,
189
+ "eval_loss": 0.7033617496490479,
190
+ "eval_runtime": 70.8095,
191
+ "eval_samples_per_second": 21.438,
192
+ "eval_steps_per_second": 0.339,
193
+ "step": 200
194
+ },
195
+ {
196
+ "epoch": 1.11,
197
+ "grad_norm": 40.9909553527832,
198
+ "learning_rate": 3.157894736842105e-06,
199
+ "loss": 0.6617,
200
+ "step": 210
201
+ },
202
+ {
203
+ "epoch": 1.16,
204
+ "grad_norm": 22.532026290893555,
205
+ "learning_rate": 3.0701754385964915e-06,
206
+ "loss": 0.6655,
207
+ "step": 220
208
+ },
209
+ {
210
+ "epoch": 1.21,
211
+ "grad_norm": 22.03099250793457,
212
+ "learning_rate": 2.9824561403508774e-06,
213
+ "loss": 0.6155,
214
+ "step": 230
215
+ },
216
+ {
217
+ "epoch": 1.26,
218
+ "grad_norm": 31.129398345947266,
219
+ "learning_rate": 2.8947368421052634e-06,
220
+ "loss": 0.5786,
221
+ "step": 240
222
+ },
223
+ {
224
+ "epoch": 1.32,
225
+ "grad_norm": 22.806337356567383,
226
+ "learning_rate": 2.8070175438596493e-06,
227
+ "loss": 0.5086,
228
+ "step": 250
229
+ },
230
+ {
231
+ "epoch": 1.32,
232
+ "eval_accuracy": 0.8267457180500659,
233
+ "eval_f1_macro": 0.7755720185959084,
234
+ "eval_f1_micro": 0.8267457180500659,
235
+ "eval_loss": 0.6432034373283386,
236
+ "eval_runtime": 70.864,
237
+ "eval_samples_per_second": 21.421,
238
+ "eval_steps_per_second": 0.339,
239
+ "step": 250
240
+ },
241
+ {
242
+ "epoch": 1.37,
243
+ "grad_norm": 24.898916244506836,
244
+ "learning_rate": 2.7192982456140356e-06,
245
+ "loss": 0.537,
246
+ "step": 260
247
+ },
248
+ {
249
+ "epoch": 1.42,
250
+ "grad_norm": 33.29705047607422,
251
+ "learning_rate": 2.631578947368421e-06,
252
+ "loss": 0.5357,
253
+ "step": 270
254
+ },
255
+ {
256
+ "epoch": 1.47,
257
+ "grad_norm": 20.23432159423828,
258
+ "learning_rate": 2.5438596491228075e-06,
259
+ "loss": 0.5452,
260
+ "step": 280
261
+ },
262
+ {
263
+ "epoch": 1.53,
264
+ "grad_norm": 26.38104820251465,
265
+ "learning_rate": 2.456140350877193e-06,
266
+ "loss": 0.5015,
267
+ "step": 290
268
+ },
269
+ {
270
+ "epoch": 1.58,
271
+ "grad_norm": 23.257266998291016,
272
+ "learning_rate": 2.368421052631579e-06,
273
+ "loss": 0.5473,
274
+ "step": 300
275
+ },
276
+ {
277
+ "epoch": 1.58,
278
+ "eval_accuracy": 0.8353096179183136,
279
+ "eval_f1_macro": 0.7982776447477468,
280
+ "eval_f1_micro": 0.8353096179183136,
281
+ "eval_loss": 0.591135561466217,
282
+ "eval_runtime": 70.7822,
283
+ "eval_samples_per_second": 21.446,
284
+ "eval_steps_per_second": 0.339,
285
+ "step": 300
286
+ },
287
+ {
288
+ "epoch": 1.63,
289
+ "grad_norm": 31.060453414916992,
290
+ "learning_rate": 2.280701754385965e-06,
291
+ "loss": 0.5914,
292
+ "step": 310
293
+ },
294
+ {
295
+ "epoch": 1.68,
296
+ "grad_norm": 38.224273681640625,
297
+ "learning_rate": 2.192982456140351e-06,
298
+ "loss": 0.547,
299
+ "step": 320
300
+ },
301
+ {
302
+ "epoch": 1.74,
303
+ "grad_norm": 24.825180053710938,
304
+ "learning_rate": 2.105263157894737e-06,
305
+ "loss": 0.5009,
306
+ "step": 330
307
+ },
308
+ {
309
+ "epoch": 1.79,
310
+ "grad_norm": 33.94304656982422,
311
+ "learning_rate": 2.017543859649123e-06,
312
+ "loss": 0.607,
313
+ "step": 340
314
+ },
315
+ {
316
+ "epoch": 1.84,
317
+ "grad_norm": 47.21768569946289,
318
+ "learning_rate": 1.929824561403509e-06,
319
+ "loss": 0.514,
320
+ "step": 350
321
+ },
322
+ {
323
+ "epoch": 1.84,
324
+ "eval_accuracy": 0.8563899868247694,
325
+ "eval_f1_macro": 0.8328616425942686,
326
+ "eval_f1_micro": 0.8563899868247694,
327
+ "eval_loss": 0.5453721880912781,
328
+ "eval_runtime": 70.8148,
329
+ "eval_samples_per_second": 21.436,
330
+ "eval_steps_per_second": 0.339,
331
+ "step": 350
332
+ },
333
+ {
334
+ "epoch": 1.89,
335
+ "grad_norm": 22.25798797607422,
336
+ "learning_rate": 1.8421052631578948e-06,
337
+ "loss": 0.4804,
338
+ "step": 360
339
+ },
340
+ {
341
+ "epoch": 1.95,
342
+ "grad_norm": 25.627458572387695,
343
+ "learning_rate": 1.7543859649122807e-06,
344
+ "loss": 0.5387,
345
+ "step": 370
346
+ },
347
+ {
348
+ "epoch": 2.0,
349
+ "grad_norm": 26.785030364990234,
350
+ "learning_rate": 1.6666666666666667e-06,
351
+ "loss": 0.5375,
352
+ "step": 380
353
+ },
354
+ {
355
+ "epoch": 2.05,
356
+ "grad_norm": 24.151248931884766,
357
+ "learning_rate": 1.5789473684210526e-06,
358
+ "loss": 0.4375,
359
+ "step": 390
360
+ },
361
+ {
362
+ "epoch": 2.11,
363
+ "grad_norm": 31.1235408782959,
364
+ "learning_rate": 1.4912280701754387e-06,
365
+ "loss": 0.4493,
366
+ "step": 400
367
+ },
368
+ {
369
+ "epoch": 2.11,
370
+ "eval_accuracy": 0.8465085638998683,
371
+ "eval_f1_macro": 0.817214362989291,
372
+ "eval_f1_micro": 0.8465085638998683,
373
+ "eval_loss": 0.5436841249465942,
374
+ "eval_runtime": 70.7986,
375
+ "eval_samples_per_second": 21.441,
376
+ "eval_steps_per_second": 0.339,
377
+ "step": 400
378
+ },
379
+ {
380
+ "epoch": 2.16,
381
+ "grad_norm": 24.023176193237305,
382
+ "learning_rate": 1.4035087719298246e-06,
383
+ "loss": 0.4135,
384
+ "step": 410
385
+ },
386
+ {
387
+ "epoch": 2.21,
388
+ "grad_norm": 29.59303092956543,
389
+ "learning_rate": 1.3157894736842106e-06,
390
+ "loss": 0.4725,
391
+ "step": 420
392
+ },
393
+ {
394
+ "epoch": 2.26,
395
+ "grad_norm": 26.1127872467041,
396
+ "learning_rate": 1.2280701754385965e-06,
397
+ "loss": 0.3891,
398
+ "step": 430
399
+ },
400
+ {
401
+ "epoch": 2.32,
402
+ "grad_norm": 30.481605529785156,
403
+ "learning_rate": 1.1403508771929824e-06,
404
+ "loss": 0.4042,
405
+ "step": 440
406
+ },
407
+ {
408
+ "epoch": 2.37,
409
+ "grad_norm": 22.664913177490234,
410
+ "learning_rate": 1.0526315789473685e-06,
411
+ "loss": 0.516,
412
+ "step": 450
413
+ },
414
+ {
415
+ "epoch": 2.37,
416
+ "eval_accuracy": 0.8530961791831357,
417
+ "eval_f1_macro": 0.828913306836084,
418
+ "eval_f1_micro": 0.8530961791831357,
419
+ "eval_loss": 0.5225136876106262,
420
+ "eval_runtime": 70.8455,
421
+ "eval_samples_per_second": 21.427,
422
+ "eval_steps_per_second": 0.339,
423
+ "step": 450
424
+ },
425
+ {
426
+ "epoch": 2.42,
427
+ "grad_norm": 27.753475189208984,
428
+ "learning_rate": 9.649122807017545e-07,
429
+ "loss": 0.3435,
430
+ "step": 460
431
+ },
432
+ {
433
+ "epoch": 2.47,
434
+ "grad_norm": 28.056856155395508,
435
+ "learning_rate": 8.771929824561404e-07,
436
+ "loss": 0.4159,
437
+ "step": 470
438
+ },
439
+ {
440
+ "epoch": 2.53,
441
+ "grad_norm": 28.235706329345703,
442
+ "learning_rate": 7.894736842105263e-07,
443
+ "loss": 0.44,
444
+ "step": 480
445
+ },
446
+ {
447
+ "epoch": 2.58,
448
+ "grad_norm": 19.392196655273438,
449
+ "learning_rate": 7.017543859649123e-07,
450
+ "loss": 0.3991,
451
+ "step": 490
452
+ },
453
+ {
454
+ "epoch": 2.63,
455
+ "grad_norm": 24.779186248779297,
456
+ "learning_rate": 6.140350877192982e-07,
457
+ "loss": 0.343,
458
+ "step": 500
459
+ },
460
+ {
461
+ "epoch": 2.63,
462
+ "eval_accuracy": 0.8557312252964426,
463
+ "eval_f1_macro": 0.8339166245745164,
464
+ "eval_f1_micro": 0.8557312252964426,
465
+ "eval_loss": 0.4982321560382843,
466
+ "eval_runtime": 70.8133,
467
+ "eval_samples_per_second": 21.437,
468
+ "eval_steps_per_second": 0.339,
469
+ "step": 500
470
+ },
471
+ {
472
+ "epoch": 2.68,
473
+ "grad_norm": 21.358295440673828,
474
+ "learning_rate": 5.263157894736843e-07,
475
+ "loss": 0.3543,
476
+ "step": 510
477
+ },
478
+ {
479
+ "epoch": 2.74,
480
+ "grad_norm": 26.393150329589844,
481
+ "learning_rate": 4.385964912280702e-07,
482
+ "loss": 0.4026,
483
+ "step": 520
484
+ },
485
+ {
486
+ "epoch": 2.79,
487
+ "grad_norm": 26.136310577392578,
488
+ "learning_rate": 3.5087719298245616e-07,
489
+ "loss": 0.3974,
490
+ "step": 530
491
+ },
492
+ {
493
+ "epoch": 2.84,
494
+ "grad_norm": 20.45792579650879,
495
+ "learning_rate": 2.6315789473684213e-07,
496
+ "loss": 0.4142,
497
+ "step": 540
498
+ },
499
+ {
500
+ "epoch": 2.89,
501
+ "grad_norm": 24.060897827148438,
502
+ "learning_rate": 1.7543859649122808e-07,
503
+ "loss": 0.4203,
504
+ "step": 550
505
+ },
506
+ {
507
+ "epoch": 2.89,
508
+ "eval_accuracy": 0.8596837944664032,
509
+ "eval_f1_macro": 0.8369626014217448,
510
+ "eval_f1_micro": 0.8596837944664032,
511
+ "eval_loss": 0.4968219995498657,
512
+ "eval_runtime": 70.7643,
513
+ "eval_samples_per_second": 21.452,
514
+ "eval_steps_per_second": 0.339,
515
+ "step": 550
516
+ },
517
+ {
518
+ "epoch": 2.95,
519
+ "grad_norm": 21.141916275024414,
520
+ "learning_rate": 8.771929824561404e-08,
521
+ "loss": 0.4682,
522
+ "step": 560
523
+ },
524
+ {
525
+ "epoch": 3.0,
526
+ "grad_norm": 26.661828994750977,
527
+ "learning_rate": 0.0,
528
+ "loss": 0.4384,
529
+ "step": 570
530
+ },
531
+ {
532
+ "epoch": 3.0,
533
+ "step": 570,
534
+ "total_flos": 7.616792756182057e+17,
535
+ "train_loss": 1.5545654296875,
536
+ "train_runtime": 6735.4111,
537
+ "train_samples_per_second": 5.409,
538
+ "train_steps_per_second": 0.085
539
+ }
540
+ ],
541
+ "logging_steps": 10,
542
+ "max_steps": 570,
543
+ "num_input_tokens_seen": 0,
544
+ "num_train_epochs": 3,
545
+ "save_steps": 50,
546
+ "total_flos": 7.616792756182057e+17,
547
+ "train_batch_size": 32,
548
+ "trial_name": null,
549
+ "trial_params": null
550
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c352945f05514abeccc19c517e1b0f3bc31de7dfc5f7a93d0b302ba8e6938bcf
3
+ size 6008
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/amazon_attrprompt_default/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/README.md ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: Qwen/Qwen1.5-7B
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: twitter_disaster_default
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # twitter_disaster_default
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen1.5-7B](https://huggingface.co/Qwen/Qwen1.5-7B) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.7973
22
+ - Accuracy: 0.7151
23
+ - F1 Macro: 0.6612
24
+ - F1 Micro: 0.7151
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 5e-06
44
+ - train_batch_size: 32
45
+ - eval_batch_size: 32
46
+ - seed: 42
47
+ - distributed_type: multi-GPU
48
+ - num_devices: 2
49
+ - total_train_batch_size: 64
50
+ - total_eval_batch_size: 64
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 3.0
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro |
58
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|
59
+ | 1.0791 | 0.37 | 50 | 1.3147 | 0.6765 | 0.6068 | 0.6765 |
60
+ | 0.8888 | 0.74 | 100 | 1.0283 | 0.6884 | 0.6494 | 0.6884 |
61
+ | 0.6325 | 1.1 | 150 | 0.8961 | 0.6912 | 0.6240 | 0.6912 |
62
+ | 0.7378 | 1.47 | 200 | 0.8683 | 0.7105 | 0.6437 | 0.7105 |
63
+ | 0.5979 | 1.84 | 250 | 0.8460 | 0.7243 | 0.6393 | 0.7243 |
64
+ | 0.4513 | 2.21 | 300 | 0.8070 | 0.7142 | 0.6592 | 0.7142 |
65
+ | 0.5699 | 2.57 | 350 | 0.8001 | 0.7114 | 0.6636 | 0.7114 |
66
+ | 0.4189 | 2.94 | 400 | 0.7973 | 0.7151 | 0.6612 | 0.7151 |
67
+
68
+
69
+ ### Framework versions
70
+
71
+ - PEFT 0.9.0
72
+ - Transformers 4.39.0.dev0
73
+ - Pytorch 2.2.1+cu121
74
+ - Datasets 2.18.0
75
+ - Tokenizers 0.15.2
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen1.5-7B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 256,
13
+ "lora_dropout": 0.0,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 128,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "o_proj",
23
+ "q_proj",
24
+ "gate_proj",
25
+ "v_proj",
26
+ "k_proj",
27
+ "down_proj",
28
+ "up_proj"
29
+ ],
30
+ "task_type": "SEQ_CLS",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2597662e929c041bde6c94fcb1ef7b879f93c6a81c59504a0f9450cc504d3753
3
+ size 1882088146
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/all_results.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.7150735294117647,
4
+ "eval_f1_macro": 0.6611572572705318,
5
+ "eval_f1_micro": 0.7150735294117647,
6
+ "eval_loss": 0.7973345518112183,
7
+ "eval_runtime": 49.6177,
8
+ "eval_samples": 1088,
9
+ "eval_samples_per_second": 21.928,
10
+ "eval_steps_per_second": 0.343,
11
+ "test_accuracy": 0.7417279411764706,
12
+ "test_f1_macro": 0.6892802878238908,
13
+ "test_f1_micro": 0.7417279411764706,
14
+ "test_loss": 0.7253561615943909,
15
+ "test_runtime": 51.0672,
16
+ "test_samples_per_second": 21.305,
17
+ "test_steps_per_second": 0.333,
18
+ "train_loss": 0.7515426336550245,
19
+ "train_runtime": 4685.4738,
20
+ "train_samples": 8700,
21
+ "train_samples_per_second": 5.57,
22
+ "train_steps_per_second": 0.087
23
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: Qwen/Qwen1.5-7B
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.9.0
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen1.5-7B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 256,
13
+ "lora_dropout": 0.0,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 128,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "o_proj",
23
+ "q_proj",
24
+ "gate_proj",
25
+ "v_proj",
26
+ "k_proj",
27
+ "down_proj",
28
+ "up_proj"
29
+ ],
30
+ "task_type": "SEQ_CLS",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2597662e929c041bde6c94fcb1ef7b879f93c6a81c59504a0f9450cc504d3753
3
+ size 1882088146
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f31a3ada65c23868f51012d3b6043f0a51210668a988ebf13af85c5c8d071f98
3
+ size 1918971376
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:808d47ea51a83854ffa8c9308cfb08212c5e1f9fa8efe01304d240d6ef81555a
3
+ size 1918971504
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/global_step400/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60f953adf8ae05c2c89096dc7d063d8b4b40f73ddc6c7dabc46c014ca9d2aee4
3
+ size 639974444
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step400
max_seq_length_512_experiments/LoRA/Qwen/Qwen1.5_7B_LoRA_MAdAiLab/twitter_disaster_default/checkpoint-400/merges.txt ADDED
The diff for this file is too large to render. See raw diff