Hugging Face's logo

xihajun
/
cnn_10k_0.001_30_16_32_0.1_0.01_add_10k_fix_20epoch_eos_0.001

Text Generation
Transformers
Safetensors
mistral
Trained with AutoTrain
text-generation-inference
Inference Endpoints
Model card Files Community
xihajun commited on
Commit
419e8c8
•
1 Parent(s): 5e57f22

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. README.md +9 -0
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-313/README.md +60 -0
  5. checkpoint-313/adapter_config.json +21 -0
  6. checkpoint-313/adapter_model.bin +3 -0
  7. checkpoint-313/optimizer.pt +3 -0
  8. checkpoint-313/pytorch_model.bin +3 -0
  9. checkpoint-313/rng_state_0.pth +3 -0
  10. checkpoint-313/rng_state_1.pth +3 -0
  11. checkpoint-313/rng_state_2.pth +3 -0
  12. checkpoint-313/rng_state_3.pth +3 -0
  13. checkpoint-313/scheduler.pt +3 -0
  14. checkpoint-313/special_tokens_map.json +24 -0
  15. checkpoint-313/tokenizer.json +0 -0
  16. checkpoint-313/tokenizer.model +3 -0
  17. checkpoint-313/tokenizer_config.json +40 -0
  18. checkpoint-313/trainer_state.json +37 -0
  19. checkpoint-313/training_args.bin +3 -0
  20. checkpoint-342/README.md +60 -0
  21. checkpoint-342/adapter_config.json +21 -0
  22. checkpoint-342/adapter_model.bin +3 -0
  23. checkpoint-342/optimizer.pt +3 -0
  24. checkpoint-342/pytorch_model.bin +3 -0
  25. checkpoint-342/rng_state_0.pth +3 -0
  26. checkpoint-342/rng_state_1.pth +3 -0
  27. checkpoint-342/rng_state_2.pth +3 -0
  28. checkpoint-342/rng_state_3.pth +3 -0
  29. checkpoint-342/scheduler.pt +3 -0
  30. checkpoint-342/special_tokens_map.json +24 -0
  31. checkpoint-342/tokenizer.json +0 -0
  32. checkpoint-342/tokenizer.model +3 -0
  33. checkpoint-342/tokenizer_config.json +40 -0
  34. checkpoint-342/trainer_state.json +37 -0
  35. checkpoint-342/training_args.bin +3 -0
  36. checkpoint-370/README.md +47 -0
  37. checkpoint-370/adapter_config.json +21 -0
  38. checkpoint-370/adapter_model.bin +3 -0
  39. checkpoint-370/optimizer.pt +3 -0
  40. checkpoint-370/pytorch_model.bin +3 -0
  41. checkpoint-370/rng_state_0.pth +3 -0
  42. checkpoint-370/rng_state_1.pth +3 -0
  43. checkpoint-370/rng_state_2.pth +3 -0
  44. checkpoint-370/rng_state_3.pth +3 -0
  45. checkpoint-370/scheduler.pt +3 -0
  46. checkpoint-370/special_tokens_map.json +24 -0
  47. checkpoint-370/tokenizer.json +0 -0
  48. checkpoint-370/tokenizer.model +3 -0
  49. checkpoint-370/tokenizer_config.json +40 -0
  50. checkpoint-370/trainer_state.json +43 -0
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - autotrain
4
+ - text-generation
5
+ widget:
6
+ - text: "I love AutoTrain because "
7
+ ---
8
+
9
+ # Model Trained Using AutoTrain
adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "xihajun/cnn_10k_0.001_30_16_32_0.1_0.01_merged",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 32,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16b3337bbcb48042f75266bb8d72bec5b07966ceec55a4961743524b0721f0c5
3
+ size 27309386
checkpoint-313/README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float16
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: False
22
+ - load_in_4bit: True
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: nf4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float16
30
+
31
+ The following `bitsandbytes` quantization config was used during training:
32
+ - quant_method: bitsandbytes
33
+ - load_in_8bit: False
34
+ - load_in_4bit: True
35
+ - llm_int8_threshold: 6.0
36
+ - llm_int8_skip_modules: None
37
+ - llm_int8_enable_fp32_cpu_offload: False
38
+ - llm_int8_has_fp16_weight: False
39
+ - bnb_4bit_quant_type: nf4
40
+ - bnb_4bit_use_double_quant: False
41
+ - bnb_4bit_compute_dtype: float16
42
+
43
+ The following `bitsandbytes` quantization config was used during training:
44
+ - quant_method: bitsandbytes
45
+ - load_in_8bit: False
46
+ - load_in_4bit: True
47
+ - llm_int8_threshold: 6.0
48
+ - llm_int8_skip_modules: None
49
+ - llm_int8_enable_fp32_cpu_offload: False
50
+ - llm_int8_has_fp16_weight: False
51
+ - bnb_4bit_quant_type: nf4
52
+ - bnb_4bit_use_double_quant: False
53
+ - bnb_4bit_compute_dtype: float16
54
+ ### Framework versions
55
+
56
+ - PEFT 0.5.0
57
+ - PEFT 0.5.0
58
+ - PEFT 0.5.0
59
+
60
+ - PEFT 0.5.0
checkpoint-313/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "xihajun/cnn_10k_0.001_30_16_32_0.1_0.01_merged",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 32,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-313/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c6e9381dbf15f5ab7ca429614291e40a6704dc951f4aba4f2acdb8fcfd1b212
3
+ size 27309386
checkpoint-313/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a45e04e91a7f0b7e0501170a692fc4c4d060c59a14fb27251caa8f8312a0e88a
3
+ size 54633978
checkpoint-313/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
3
+ size 888
checkpoint-313/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77b14c09cbee9bcac46e5cce065769a5f91d4a493294b0414d0ab30be708e29c
3
+ size 15024
checkpoint-313/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:030fe2d0cad9b65f6b6fe12152d3f8ec71f7456a60f3402bddcc40b758b9e883
3
+ size 15024
checkpoint-313/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03d7e14e421a2ed3a863967bba5657fb01a1f4ae94a2f41d85d83b95c7db3d3a
3
+ size 15024
checkpoint-313/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e85efa0ece971fa50988b99059af5b55d4f9dba87240ec804a840593eb80d46
3
+ size 15024
checkpoint-313/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee9c8226afa78e814290479c0fa5f228ded7d744a5ae8ced7a2a8655bf0d5cd3
3
+ size 1064
checkpoint-313/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-313/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-313/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-313/tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "legacy": true,
33
+ "model_max_length": 2048,
34
+ "pad_token": "</s>",
35
+ "sp_model_kwargs": {},
36
+ "spaces_between_special_tokens": false,
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": true
40
+ }
checkpoint-313/trainer_state.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.982456140350877,
5
+ "eval_steps": 500,
6
+ "global_step": 313,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 3.16,
13
+ "learning_rate": 0.0009325396825396826,
14
+ "loss": 1.7533,
15
+ "step": 90
16
+ },
17
+ {
18
+ "epoch": 6.32,
19
+ "learning_rate": 0.000753968253968254,
20
+ "loss": 1.6016,
21
+ "step": 180
22
+ },
23
+ {
24
+ "epoch": 9.47,
25
+ "learning_rate": 0.0005753968253968254,
26
+ "loss": 1.5169,
27
+ "step": 270
28
+ }
29
+ ],
30
+ "logging_steps": 90,
31
+ "max_steps": 560,
32
+ "num_train_epochs": 20,
33
+ "save_steps": 500,
34
+ "total_flos": 3.5095764551283507e+18,
35
+ "trial_name": null,
36
+ "trial_params": null
37
+ }
checkpoint-313/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5cc2f65db6b6097048d9c37c79a4bbbdf2a0ef93cc9acedd207ffffd9bfd9d7
3
+ size 4600
checkpoint-342/README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float16
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: False
22
+ - load_in_4bit: True
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: nf4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float16
30
+
31
+ The following `bitsandbytes` quantization config was used during training:
32
+ - quant_method: bitsandbytes
33
+ - load_in_8bit: False
34
+ - load_in_4bit: True
35
+ - llm_int8_threshold: 6.0
36
+ - llm_int8_skip_modules: None
37
+ - llm_int8_enable_fp32_cpu_offload: False
38
+ - llm_int8_has_fp16_weight: False
39
+ - bnb_4bit_quant_type: nf4
40
+ - bnb_4bit_use_double_quant: False
41
+ - bnb_4bit_compute_dtype: float16
42
+
43
+ The following `bitsandbytes` quantization config was used during training:
44
+ - quant_method: bitsandbytes
45
+ - load_in_8bit: False
46
+ - load_in_4bit: True
47
+ - llm_int8_threshold: 6.0
48
+ - llm_int8_skip_modules: None
49
+ - llm_int8_enable_fp32_cpu_offload: False
50
+ - llm_int8_has_fp16_weight: False
51
+ - bnb_4bit_quant_type: nf4
52
+ - bnb_4bit_use_double_quant: False
53
+ - bnb_4bit_compute_dtype: float16
54
+ ### Framework versions
55
+
56
+ - PEFT 0.5.0
57
+ - PEFT 0.5.0
58
+ - PEFT 0.5.0
59
+
60
+ - PEFT 0.5.0
checkpoint-342/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "xihajun/cnn_10k_0.001_30_16_32_0.1_0.01_merged",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 32,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-342/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf4ff25e239d8aea06ac0b8cbad968e48d1f3ddb9e70246e65b8cf0372238deb
3
+ size 27309386
checkpoint-342/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b27ee1316b0d2f6b4e78dd7db4025efa59ad333e2f9b1de397eaa00d4205c6a7
3
+ size 54633978
checkpoint-342/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
3
+ size 888
checkpoint-342/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b829cc69ceccec5d7ca5987829df60b33e37b2bbc6e91ffe1a9711c8712ef33
3
+ size 15024
checkpoint-342/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec3a71b2f5b349f5bc9c4e239515fd866cbb120256436aed41ba2e930e73bd9a
3
+ size 15024
checkpoint-342/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a43af49393266eeae448bf3c1f760aa8f583b2a3906dfb3adca05971a46a4f55
3
+ size 15024
checkpoint-342/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a477e2de9015ed16c17b946f06aa6f3a8c3b94ac9f5a75e4b03aac57a0340022
3
+ size 15024
checkpoint-342/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae9ed31c4f73432cb212f56dba94adc97c796db1e17f0e51cda802d6a1c837c7
3
+ size 1064
checkpoint-342/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-342/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-342/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-342/tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "legacy": true,
33
+ "model_max_length": 2048,
34
+ "pad_token": "</s>",
35
+ "sp_model_kwargs": {},
36
+ "spaces_between_special_tokens": false,
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": true
40
+ }
checkpoint-342/trainer_state.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 12.0,
5
+ "eval_steps": 500,
6
+ "global_step": 342,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 3.16,
13
+ "learning_rate": 0.0009325396825396826,
14
+ "loss": 1.7533,
15
+ "step": 90
16
+ },
17
+ {
18
+ "epoch": 6.32,
19
+ "learning_rate": 0.000753968253968254,
20
+ "loss": 1.6016,
21
+ "step": 180
22
+ },
23
+ {
24
+ "epoch": 9.47,
25
+ "learning_rate": 0.0005753968253968254,
26
+ "loss": 1.5169,
27
+ "step": 270
28
+ }
29
+ ],
30
+ "logging_steps": 90,
31
+ "max_steps": 560,
32
+ "num_train_epochs": 20,
33
+ "save_steps": 500,
34
+ "total_flos": 3.828628856625955e+18,
35
+ "trial_name": null,
36
+ "trial_params": null
37
+ }
checkpoint-342/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5cc2f65db6b6097048d9c37c79a4bbbdf2a0ef93cc9acedd207ffffd9bfd9d7
3
+ size 4600
checkpoint-370/README.md ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float16
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: False
22
+ - load_in_4bit: True
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: nf4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float16
30
+
31
+ The following `bitsandbytes` quantization config was used during training:
32
+ - quant_method: bitsandbytes
33
+ - load_in_8bit: False
34
+ - load_in_4bit: True
35
+ - llm_int8_threshold: 6.0
36
+ - llm_int8_skip_modules: None
37
+ - llm_int8_enable_fp32_cpu_offload: False
38
+ - llm_int8_has_fp16_weight: False
39
+ - bnb_4bit_quant_type: nf4
40
+ - bnb_4bit_use_double_quant: False
41
+ - bnb_4bit_compute_dtype: float16
42
+ ### Framework versions
43
+
44
+ - PEFT 0.5.0
45
+ - PEFT 0.5.0
46
+
47
+ - PEFT 0.5.0
checkpoint-370/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "xihajun/cnn_10k_0.001_30_16_32_0.1_0.01_merged",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 32,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-370/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94ff015c1006e0c4f04651f06bfcb5ffeb06bd3eebc1f6ce5884432fcedc7e34
3
+ size 27309386
checkpoint-370/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfc81e11f12ffd10e337a42190a12f62d1bd4785e2df74f9e4be92d387700b5d
3
+ size 54633978
checkpoint-370/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
3
+ size 888
checkpoint-370/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:738a452a74c023554c0b609dc3249fac4f5939b616df8368667a27622518e59d
3
+ size 15024
checkpoint-370/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9339e495f6a9fa7404dd3d419a5f200d4341f30f36c644f7766ac0e4e694b25a
3
+ size 15024
checkpoint-370/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eba70932600943919c61131e1aafb1d3f8ceaeff7df9201c18e9e4a890803e13
3
+ size 15024
checkpoint-370/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e03f86124a53eeb123d8539b6bb3531a16736fdd79883197a13a95b2baf96a0
3
+ size 15024
checkpoint-370/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c1ca7ffd6832ed08a2e8deb0ee4b89553f8006c5924fd31783fa3167f5f07e
3
+ size 1064
checkpoint-370/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-370/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-370/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-370/tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "legacy": true,
33
+ "model_max_length": 2048,
34
+ "pad_token": "</s>",
35
+ "sp_model_kwargs": {},
36
+ "spaces_between_special_tokens": false,
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": true
40
+ }
checkpoint-370/trainer_state.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 12.982456140350877,
5
+ "eval_steps": 500,
6
+ "global_step": 370,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 3.16,
13
+ "learning_rate": 0.0009325396825396826,
14
+ "loss": 1.7533,
15
+ "step": 90
16
+ },
17
+ {
18
+ "epoch": 6.32,
19
+ "learning_rate": 0.000753968253968254,
20
+ "loss": 1.6016,
21
+ "step": 180
22
+ },
23
+ {
24
+ "epoch": 9.47,
25
+ "learning_rate": 0.0005753968253968254,
26
+ "loss": 1.5169,
27
+ "step": 270
28
+ },
29
+ {
30
+ "epoch": 12.63,
31
+ "learning_rate": 0.0003968253968253968,
32
+ "loss": 1.4522,
33
+ "step": 360
34
+ }
35
+ ],
36
+ "logging_steps": 90,
37
+ "max_steps": 560,
38
+ "num_train_epochs": 20,
39
+ "save_steps": 500,
40
+ "total_flos": 4.147681275303428e+18,
41
+ "trial_name": null,
42
+ "trial_params": null
43
+ }