Hugging Face's logo

stacknexus
/
311fontana

Text Generation
Transformers
PyTorch
TensorBoard
llama
Trained with AutoTrain
text-generation-inference
Model card Files
xet
Metrics Community
1
Jackmax5 commited on
Commit
0a91687
·
1 Parent(s): 489ee4f

Upload folder using huggingface_hub

Browse files
Files changed (31) hide show
  1. README.md +9 -0
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-160/README.md +34 -0
  5. checkpoint-160/adapter_config.json +21 -0
  6. checkpoint-160/adapter_model.bin +3 -0
  7. checkpoint-160/optimizer.pt +3 -0
  8. checkpoint-160/pytorch_model.bin +3 -0
  9. checkpoint-160/rng_state.pth +3 -0
  10. checkpoint-160/scheduler.pt +3 -0
  11. checkpoint-160/special_tokens_map.json +6 -0
  12. checkpoint-160/tokenizer.json +0 -0
  13. checkpoint-160/tokenizer.model +3 -0
  14. checkpoint-160/tokenizer_config.json +43 -0
  15. checkpoint-160/trainer_state.json +175 -0
  16. checkpoint-160/training_args.bin +3 -0
  17. config (1).json +26 -0
  18. config.json +26 -0
  19. model.bin +3 -0
  20. runs/Sep20_12-05-11_293540d829b7/events.out.tfevents.1695211511.293540d829b7.3459.0 +3 -0
  21. runs/Sep20_12-06-50_293540d829b7/events.out.tfevents.1695211610.293540d829b7.4189.0 +3 -0
  22. runs/Sep20_12-11-42_293540d829b7/events.out.tfevents.1695211902.293540d829b7.5524.0 +3 -0
  23. runs/Sep20_12-18-04_293540d829b7/events.out.tfevents.1695212284.293540d829b7.7227.0 +3 -0
  24. runs/Sep21_07-54-28_659996e06e21/events.out.tfevents.1695282868.659996e06e21.3633.0 +3 -0
  25. runs/Sep21_09-37-11_6a128a600e23/events.out.tfevents.1695289031.6a128a600e23.5422.0 +3 -0
  26. special_tokens_map.json +6 -0
  27. tokenizer.json +0 -0
  28. tokenizer.model +3 -0
  29. tokenizer_config.json +43 -0
  30. training_args.bin +3 -0
  31. training_params.json +1 -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": "lmsys/vicuna-7b-v1.5",
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": 0.05,
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 sha256:807e26d85d9a8a9175d1452fd8cbc41cfa34e9f55b405bff36bafd07293efd03
3
+ size 33600461
checkpoint-160/README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ### Framework versions
31
+
32
+ - PEFT 0.6.0.dev0
33
+
34
+ - PEFT 0.6.0.dev0
checkpoint-160/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "lmsys/vicuna-7b-v1.5",
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": 0.05,
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-160/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:807e26d85d9a8a9175d1452fd8cbc41cfa34e9f55b405bff36bafd07293efd03
3
+ size 33600461
checkpoint-160/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f80d03f55b4a80368a287c55c63618664309268448ec58ce5eb164459c2ef5c7
3
+ size 67216581
checkpoint-160/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c152074a486243089e4fc0fdee0a373a30fb0e0a6e40eb5fd0d36fdafc97a155
3
+ size 443
checkpoint-160/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e66c0cc0916baab371fbaa3ffb42b7ec48b15ebea0eca903965fb22470ef0e85
3
+ size 14575
checkpoint-160/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:799ed092fb350886e343bfac6eff042a22f6c5330bc27d3d8edec0f2f57c7b6b
3
+ size 627
checkpoint-160/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<unk>",
5
+ "unk_token": "<unk>"
6
+ }
checkpoint-160/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-160/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-160/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 1024,
36
+ "pad_token": "<unk>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": true
43
+ }
checkpoint-160/trainer_state.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 19.393939393939394,
5
+ "eval_steps": 500,
6
+ "global_step": 160,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.73,
13
+ "learning_rate": 7.500000000000001e-05,
14
+ "loss": 2.5979,
15
+ "step": 6
16
+ },
17
+ {
18
+ "epoch": 1.45,
19
+ "learning_rate": 0.00015000000000000001,
20
+ "loss": 2.5438,
21
+ "step": 12
22
+ },
23
+ {
24
+ "epoch": 2.18,
25
+ "learning_rate": 0.00019722222222222225,
26
+ "loss": 2.4147,
27
+ "step": 18
28
+ },
29
+ {
30
+ "epoch": 2.91,
31
+ "learning_rate": 0.00018888888888888888,
32
+ "loss": 2.1395,
33
+ "step": 24
34
+ },
35
+ {
36
+ "epoch": 3.64,
37
+ "learning_rate": 0.00018055555555555557,
38
+ "loss": 2.0771,
39
+ "step": 30
40
+ },
41
+ {
42
+ "epoch": 4.36,
43
+ "learning_rate": 0.00017222222222222224,
44
+ "loss": 1.9096,
45
+ "step": 36
46
+ },
47
+ {
48
+ "epoch": 5.09,
49
+ "learning_rate": 0.0001638888888888889,
50
+ "loss": 1.9748,
51
+ "step": 42
52
+ },
53
+ {
54
+ "epoch": 5.82,
55
+ "learning_rate": 0.00015555555555555556,
56
+ "loss": 1.8121,
57
+ "step": 48
58
+ },
59
+ {
60
+ "epoch": 6.55,
61
+ "learning_rate": 0.00014722222222222223,
62
+ "loss": 1.7856,
63
+ "step": 54
64
+ },
65
+ {
66
+ "epoch": 7.27,
67
+ "learning_rate": 0.0001388888888888889,
68
+ "loss": 1.7752,
69
+ "step": 60
70
+ },
71
+ {
72
+ "epoch": 8.0,
73
+ "learning_rate": 0.00013055555555555555,
74
+ "loss": 1.6423,
75
+ "step": 66
76
+ },
77
+ {
78
+ "epoch": 8.73,
79
+ "learning_rate": 0.00012222222222222224,
80
+ "loss": 1.6135,
81
+ "step": 72
82
+ },
83
+ {
84
+ "epoch": 9.45,
85
+ "learning_rate": 0.00011388888888888889,
86
+ "loss": 1.574,
87
+ "step": 78
88
+ },
89
+ {
90
+ "epoch": 10.18,
91
+ "learning_rate": 0.00010555555555555557,
92
+ "loss": 1.4749,
93
+ "step": 84
94
+ },
95
+ {
96
+ "epoch": 10.91,
97
+ "learning_rate": 9.722222222222223e-05,
98
+ "loss": 1.4809,
99
+ "step": 90
100
+ },
101
+ {
102
+ "epoch": 11.64,
103
+ "learning_rate": 8.888888888888889e-05,
104
+ "loss": 1.4328,
105
+ "step": 96
106
+ },
107
+ {
108
+ "epoch": 12.36,
109
+ "learning_rate": 8.055555555555556e-05,
110
+ "loss": 1.299,
111
+ "step": 102
112
+ },
113
+ {
114
+ "epoch": 13.09,
115
+ "learning_rate": 7.222222222222222e-05,
116
+ "loss": 1.2881,
117
+ "step": 108
118
+ },
119
+ {
120
+ "epoch": 13.82,
121
+ "learning_rate": 6.388888888888888e-05,
122
+ "loss": 1.2392,
123
+ "step": 114
124
+ },
125
+ {
126
+ "epoch": 14.55,
127
+ "learning_rate": 5.555555555555556e-05,
128
+ "loss": 1.1873,
129
+ "step": 120
130
+ },
131
+ {
132
+ "epoch": 15.27,
133
+ "learning_rate": 4.722222222222222e-05,
134
+ "loss": 1.1339,
135
+ "step": 126
136
+ },
137
+ {
138
+ "epoch": 16.0,
139
+ "learning_rate": 3.888888888888889e-05,
140
+ "loss": 1.0971,
141
+ "step": 132
142
+ },
143
+ {
144
+ "epoch": 16.73,
145
+ "learning_rate": 3.055555555555556e-05,
146
+ "loss": 1.0632,
147
+ "step": 138
148
+ },
149
+ {
150
+ "epoch": 17.45,
151
+ "learning_rate": 2.2222222222222223e-05,
152
+ "loss": 0.9817,
153
+ "step": 144
154
+ },
155
+ {
156
+ "epoch": 18.18,
157
+ "learning_rate": 1.388888888888889e-05,
158
+ "loss": 1.0649,
159
+ "step": 150
160
+ },
161
+ {
162
+ "epoch": 18.91,
163
+ "learning_rate": 5.555555555555556e-06,
164
+ "loss": 0.9804,
165
+ "step": 156
166
+ }
167
+ ],
168
+ "logging_steps": 6,
169
+ "max_steps": 160,
170
+ "num_train_epochs": 20,
171
+ "save_steps": 500,
172
+ "total_flos": 2.601411762192384e+16,
173
+ "trial_name": null,
174
+ "trial_params": null
175
+ }
checkpoint-160/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe1b9b4995ebc24fafa6a1ce589352772090fcf8adb4343f7fc157a319f88d34
3
+ size 4091
config (1).json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vicuna-7b-v1.5",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 32,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.31.0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vicuna-7b-v1.5",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 32,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.31.0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff76cecb95ab8d03ea932de472949350a3187f5d0fa47510afea2bb3ec10295a
3
+ size 33600461
runs/Sep20_12-05-11_293540d829b7/events.out.tfevents.1695211511.293540d829b7.3459.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4042cc80aace7dfd92a47db5919167c7319837d46d931b660165d32c85858f65
3
+ size 5010
runs/Sep20_12-06-50_293540d829b7/events.out.tfevents.1695211610.293540d829b7.4189.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40a19030557836bc8d77cf217e4a53de86e761bfdf54728e49f7543fb36415a2
3
+ size 5780
runs/Sep20_12-11-42_293540d829b7/events.out.tfevents.1695211902.293540d829b7.5524.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:811cd115c029dccdd055fd8c2354985b4708baa1aabe0dec7a8b6a90e33762fc
3
+ size 7281
runs/Sep20_12-18-04_293540d829b7/events.out.tfevents.1695212284.293540d829b7.7227.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bff6d5824b9ccc3d13a683ef8669ba4d5af3aacd91ee16590bb00e16a62ebbcc
3
+ size 8882
runs/Sep21_07-54-28_659996e06e21/events.out.tfevents.1695282868.659996e06e21.3633.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a206471c396f4a84f805c6730e482029a33414fcbf0735e2bff7e6e4ea5ae544
3
+ size 6859
runs/Sep21_09-37-11_6a128a600e23/events.out.tfevents.1695289031.6a128a600e23.5422.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:185a5cd0343f2c3be9be98d545f613fb9e0104a7ef2aff4bbf0036ddea1b9f9c
3
+ size 8882
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<unk>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 1024,
36
+ "pad_token": "<unk>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": true
43
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe1b9b4995ebc24fafa6a1ce589352772090fcf8adb4343f7fc157a319f88d34
3
+ size 4091
training_params.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "lmsys/vicuna-7b-v1.5", "data_path": "Jackmax5/data", "project_name": "fontana_311", "train_split": "train", "valid_split": null, "text_column": "Answer", "lr": 0.0002, "epochs": 20, "batch_size": 1, "warmup_ratio": 0.1, "gradient_accumulation": 4, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.01, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": 1024, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": true, "push_to_hub": true, "use_int8": false, "model_max_length": 1024, "repo_id": "stacknexus/311fontana", "use_int4": true, "trainer": "default", "target_modules": null, "merge_adapter": false, "username": null}