Hugging Face's logo

shyam-incedoinc
/
codellama-7b-instruct-hf-finetuned-qa-1-3

Text Generation
TensorBoard
Trained with AutoTrain
Model card Files Metrics Community
shyam-incedoinc commited on
Commit
5bf2a6b
•
1 Parent(s): bbf6baf

Upload folder using huggingface_hub

Browse files
Files changed (22) hide show
  1. README.md +9 -0
  2. adapter_config.json +23 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-117/README.md +34 -0
  5. checkpoint-117/adapter_config.json +23 -0
  6. checkpoint-117/adapter_model.bin +3 -0
  7. checkpoint-117/optimizer.pt +3 -0
  8. checkpoint-117/rng_state.pth +3 -0
  9. checkpoint-117/scheduler.pt +3 -0
  10. checkpoint-117/special_tokens_map.json +12 -0
  11. checkpoint-117/tokenizer.json +0 -0
  12. checkpoint-117/tokenizer.model +3 -0
  13. checkpoint-117/tokenizer_config.json +81 -0
  14. checkpoint-117/trainer_state.json +793 -0
  15. checkpoint-117/training_args.bin +3 -0
  16. runs/Sep25_12-31-14_3025c0ae9f03/events.out.tfevents.1695645074.3025c0ae9f03.5818.0 +3 -0
  17. special_tokens_map.json +12 -0
  18. tokenizer.json +0 -0
  19. tokenizer.model +3 -0
  20. tokenizer_config.json +81 -0
  21. training_args.bin +3 -0
  22. training_params.json +40 -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 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
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
+ "lora_alpha": 32,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 16,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "q_proj",
20
+ "v_proj"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e54bff4c14de5c8cef76a7dc50e0325c7a366d63df92745948914a4e9972a5e1
3
+ size 33600461
checkpoint-117/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-117/adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
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
+ "lora_alpha": 32,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 16,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "q_proj",
20
+ "v_proj"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
checkpoint-117/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e54bff4c14de5c8cef76a7dc50e0325c7a366d63df92745948914a4e9972a5e1
3
+ size 33600461
checkpoint-117/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:645555772ba4f2c02b8a8af9eec10ae9498a56ee6ebad17ba6d85da623e2a110
3
+ size 67216581
checkpoint-117/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21046b2023a31da0b79ee90b6ad8df74299bd9c91f0391f3e0e718fda8bfb402
3
+ size 14575
checkpoint-117/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcac1b0ef8ad437f69c356f1b22102241bc4f17ea0b68d237b474fb253daec41
3
+ size 627
checkpoint-117/special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>"
7
+ ],
8
+ "bos_token": "<s>",
9
+ "eos_token": "</s>",
10
+ "pad_token": "</s>",
11
+ "unk_token": "<unk>"
12
+ }
checkpoint-117/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-117/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
3
+ size 500058
checkpoint-117/tokenizer_config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32007": {
28
+ "content": "▁<PRE>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32008": {
36
+ "content": "▁<SUF>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32009": {
44
+ "content": "▁<MID>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32010": {
52
+ "content": "▁<EOT>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [
61
+ "▁<PRE>",
62
+ "▁<MID>",
63
+ "▁<SUF>",
64
+ "▁<EOT>"
65
+ ],
66
+ "bos_token": "<s>",
67
+ "clean_up_tokenization_spaces": false,
68
+ "eos_token": "</s>",
69
+ "eot_token": "▁<EOT>",
70
+ "fill_token": "<FILL_ME>",
71
+ "legacy": null,
72
+ "middle_token": "▁<MID>",
73
+ "model_max_length": 1024,
74
+ "pad_token": null,
75
+ "prefix_token": "▁<PRE>",
76
+ "sp_model_kwargs": {},
77
+ "suffix_token": "▁<SUF>",
78
+ "tokenizer_class": "CodeLlamaTokenizer",
79
+ "unk_token": "<unk>",
80
+ "use_default_system_prompt": false
81
+ }
checkpoint-117/trainer_state.json ADDED
@@ -0,0 +1,793 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.23757965862751007,
3
+ "best_model_checkpoint": "qa-model-finetune/checkpoint-117",
4
+ "epoch": 8.26,
5
+ "eval_steps": 500,
6
+ "global_step": 117,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 4.000000000000001e-06,
14
+ "loss": 1.1156,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.04,
19
+ "learning_rate": 8.000000000000001e-06,
20
+ "loss": 1.225,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.06,
25
+ "learning_rate": 1.2e-05,
26
+ "loss": 1.0757,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.08,
31
+ "learning_rate": 1.6000000000000003e-05,
32
+ "loss": 0.8098,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.1,
37
+ "learning_rate": 2e-05,
38
+ "loss": 1.2561,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.12,
43
+ "learning_rate": 2.4e-05,
44
+ "loss": 1.2355,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.14,
49
+ "learning_rate": 2.8000000000000003e-05,
50
+ "loss": 1.0707,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.16,
55
+ "learning_rate": 3.2000000000000005e-05,
56
+ "loss": 1.3054,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.18,
61
+ "learning_rate": 3.6e-05,
62
+ "loss": 1.2546,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.2,
67
+ "learning_rate": 4e-05,
68
+ "loss": 1.2499,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.22,
73
+ "learning_rate": 4.4000000000000006e-05,
74
+ "loss": 1.0749,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.24,
79
+ "learning_rate": 4.8e-05,
80
+ "loss": 1.1383,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.26,
85
+ "learning_rate": 5.2000000000000004e-05,
86
+ "loss": 1.15,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.26,
91
+ "eval_loss": 0.841742217540741,
92
+ "eval_runtime": 24.118,
93
+ "eval_samples_per_second": 0.788,
94
+ "eval_steps_per_second": 0.207,
95
+ "step": 13
96
+ },
97
+ {
98
+ "epoch": 1.02,
99
+ "learning_rate": 5.6000000000000006e-05,
100
+ "loss": 0.9705,
101
+ "step": 14
102
+ },
103
+ {
104
+ "epoch": 1.04,
105
+ "learning_rate": 6e-05,
106
+ "loss": 1.2398,
107
+ "step": 15
108
+ },
109
+ {
110
+ "epoch": 1.06,
111
+ "learning_rate": 6.400000000000001e-05,
112
+ "loss": 0.9997,
113
+ "step": 16
114
+ },
115
+ {
116
+ "epoch": 1.08,
117
+ "learning_rate": 6.800000000000001e-05,
118
+ "loss": 1.2356,
119
+ "step": 17
120
+ },
121
+ {
122
+ "epoch": 1.1,
123
+ "learning_rate": 7.2e-05,
124
+ "loss": 0.8312,
125
+ "step": 18
126
+ },
127
+ {
128
+ "epoch": 1.12,
129
+ "learning_rate": 7.6e-05,
130
+ "loss": 1.0169,
131
+ "step": 19
132
+ },
133
+ {
134
+ "epoch": 1.14,
135
+ "learning_rate": 8e-05,
136
+ "loss": 0.8709,
137
+ "step": 20
138
+ },
139
+ {
140
+ "epoch": 1.16,
141
+ "learning_rate": 8.4e-05,
142
+ "loss": 1.121,
143
+ "step": 21
144
+ },
145
+ {
146
+ "epoch": 1.18,
147
+ "learning_rate": 8.800000000000001e-05,
148
+ "loss": 0.9481,
149
+ "step": 22
150
+ },
151
+ {
152
+ "epoch": 1.2,
153
+ "learning_rate": 9.200000000000001e-05,
154
+ "loss": 0.8888,
155
+ "step": 23
156
+ },
157
+ {
158
+ "epoch": 1.22,
159
+ "learning_rate": 9.6e-05,
160
+ "loss": 1.0233,
161
+ "step": 24
162
+ },
163
+ {
164
+ "epoch": 1.24,
165
+ "learning_rate": 0.0001,
166
+ "loss": 0.8382,
167
+ "step": 25
168
+ },
169
+ {
170
+ "epoch": 1.26,
171
+ "learning_rate": 0.00010400000000000001,
172
+ "loss": 0.8734,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 1.26,
177
+ "eval_loss": 0.7118059992790222,
178
+ "eval_runtime": 24.0715,
179
+ "eval_samples_per_second": 0.789,
180
+ "eval_steps_per_second": 0.208,
181
+ "step": 26
182
+ },
183
+ {
184
+ "epoch": 2.02,
185
+ "learning_rate": 0.00010800000000000001,
186
+ "loss": 0.9912,
187
+ "step": 27
188
+ },
189
+ {
190
+ "epoch": 2.04,
191
+ "learning_rate": 0.00011200000000000001,
192
+ "loss": 1.0997,
193
+ "step": 28
194
+ },
195
+ {
196
+ "epoch": 2.06,
197
+ "learning_rate": 0.000116,
198
+ "loss": 0.7957,
199
+ "step": 29
200
+ },
201
+ {
202
+ "epoch": 2.08,
203
+ "learning_rate": 0.00012,
204
+ "loss": 0.9109,
205
+ "step": 30
206
+ },
207
+ {
208
+ "epoch": 2.1,
209
+ "learning_rate": 0.000124,
210
+ "loss": 0.9713,
211
+ "step": 31
212
+ },
213
+ {
214
+ "epoch": 2.12,
215
+ "learning_rate": 0.00012800000000000002,
216
+ "loss": 0.7388,
217
+ "step": 32
218
+ },
219
+ {
220
+ "epoch": 2.14,
221
+ "learning_rate": 0.000132,
222
+ "loss": 0.481,
223
+ "step": 33
224
+ },
225
+ {
226
+ "epoch": 2.16,
227
+ "learning_rate": 0.00013600000000000003,
228
+ "loss": 0.9344,
229
+ "step": 34
230
+ },
231
+ {
232
+ "epoch": 2.18,
233
+ "learning_rate": 0.00014,
234
+ "loss": 0.8717,
235
+ "step": 35
236
+ },
237
+ {
238
+ "epoch": 2.2,
239
+ "learning_rate": 0.000144,
240
+ "loss": 0.7509,
241
+ "step": 36
242
+ },
243
+ {
244
+ "epoch": 2.22,
245
+ "learning_rate": 0.000148,
246
+ "loss": 0.8116,
247
+ "step": 37
248
+ },
249
+ {
250
+ "epoch": 2.24,
251
+ "learning_rate": 0.000152,
252
+ "loss": 0.7251,
253
+ "step": 38
254
+ },
255
+ {
256
+ "epoch": 2.26,
257
+ "learning_rate": 0.00015600000000000002,
258
+ "loss": 0.7168,
259
+ "step": 39
260
+ },
261
+ {
262
+ "epoch": 2.26,
263
+ "eval_loss": 0.5603676438331604,
264
+ "eval_runtime": 23.997,
265
+ "eval_samples_per_second": 0.792,
266
+ "eval_steps_per_second": 0.208,
267
+ "step": 39
268
+ },
269
+ {
270
+ "epoch": 3.02,
271
+ "learning_rate": 0.00016,
272
+ "loss": 0.7851,
273
+ "step": 40
274
+ },
275
+ {
276
+ "epoch": 3.04,
277
+ "learning_rate": 0.000164,
278
+ "loss": 0.7412,
279
+ "step": 41
280
+ },
281
+ {
282
+ "epoch": 3.06,
283
+ "learning_rate": 0.000168,
284
+ "loss": 0.674,
285
+ "step": 42
286
+ },
287
+ {
288
+ "epoch": 3.08,
289
+ "learning_rate": 0.000172,
290
+ "loss": 0.7634,
291
+ "step": 43
292
+ },
293
+ {
294
+ "epoch": 3.1,
295
+ "learning_rate": 0.00017600000000000002,
296
+ "loss": 0.6933,
297
+ "step": 44
298
+ },
299
+ {
300
+ "epoch": 3.12,
301
+ "learning_rate": 0.00018,
302
+ "loss": 0.5634,
303
+ "step": 45
304
+ },
305
+ {
306
+ "epoch": 3.14,
307
+ "learning_rate": 0.00018400000000000003,
308
+ "loss": 0.6571,
309
+ "step": 46
310
+ },
311
+ {
312
+ "epoch": 3.16,
313
+ "learning_rate": 0.000188,
314
+ "loss": 0.5984,
315
+ "step": 47
316
+ },
317
+ {
318
+ "epoch": 3.18,
319
+ "learning_rate": 0.000192,
320
+ "loss": 0.674,
321
+ "step": 48
322
+ },
323
+ {
324
+ "epoch": 3.2,
325
+ "learning_rate": 0.000196,
326
+ "loss": 0.6171,
327
+ "step": 49
328
+ },
329
+ {
330
+ "epoch": 3.22,
331
+ "learning_rate": 0.0002,
332
+ "loss": 0.6129,
333
+ "step": 50
334
+ },
335
+ {
336
+ "epoch": 3.24,
337
+ "learning_rate": 0.00019955555555555558,
338
+ "loss": 0.5328,
339
+ "step": 51
340
+ },
341
+ {
342
+ "epoch": 3.26,
343
+ "learning_rate": 0.00019911111111111111,
344
+ "loss": 0.479,
345
+ "step": 52
346
+ },
347
+ {
348
+ "epoch": 3.26,
349
+ "eval_loss": 0.41886183619499207,
350
+ "eval_runtime": 23.9197,
351
+ "eval_samples_per_second": 0.794,
352
+ "eval_steps_per_second": 0.209,
353
+ "step": 52
354
+ },
355
+ {
356
+ "epoch": 4.02,
357
+ "learning_rate": 0.00019866666666666668,
358
+ "loss": 0.5089,
359
+ "step": 53
360
+ },
361
+ {
362
+ "epoch": 4.04,
363
+ "learning_rate": 0.00019822222222222225,
364
+ "loss": 0.5049,
365
+ "step": 54
366
+ },
367
+ {
368
+ "epoch": 4.06,
369
+ "learning_rate": 0.00019777777777777778,
370
+ "loss": 0.5407,
371
+ "step": 55
372
+ },
373
+ {
374
+ "epoch": 4.08,
375
+ "learning_rate": 0.00019733333333333335,
376
+ "loss": 0.3821,
377
+ "step": 56
378
+ },
379
+ {
380
+ "epoch": 4.1,
381
+ "learning_rate": 0.0001968888888888889,
382
+ "loss": 0.484,
383
+ "step": 57
384
+ },
385
+ {
386
+ "epoch": 4.12,
387
+ "learning_rate": 0.00019644444444444445,
388
+ "loss": 0.5705,
389
+ "step": 58
390
+ },
391
+ {
392
+ "epoch": 4.14,
393
+ "learning_rate": 0.000196,
394
+ "loss": 0.5301,
395
+ "step": 59
396
+ },
397
+ {
398
+ "epoch": 4.16,
399
+ "learning_rate": 0.00019555555555555556,
400
+ "loss": 0.6168,
401
+ "step": 60
402
+ },
403
+ {
404
+ "epoch": 4.18,
405
+ "learning_rate": 0.0001951111111111111,
406
+ "loss": 0.4745,
407
+ "step": 61
408
+ },
409
+ {
410
+ "epoch": 4.2,
411
+ "learning_rate": 0.0001946666666666667,
412
+ "loss": 0.6383,
413
+ "step": 62
414
+ },
415
+ {
416
+ "epoch": 4.22,
417
+ "learning_rate": 0.00019422222222222223,
418
+ "loss": 0.3682,
419
+ "step": 63
420
+ },
421
+ {
422
+ "epoch": 4.24,
423
+ "learning_rate": 0.0001937777777777778,
424
+ "loss": 0.5654,
425
+ "step": 64
426
+ },
427
+ {
428
+ "epoch": 4.26,
429
+ "learning_rate": 0.00019333333333333333,
430
+ "loss": 0.451,
431
+ "step": 65
432
+ },
433
+ {
434
+ "epoch": 4.26,
435
+ "eval_loss": 0.3399796783924103,
436
+ "eval_runtime": 24.1635,
437
+ "eval_samples_per_second": 0.786,
438
+ "eval_steps_per_second": 0.207,
439
+ "step": 65
440
+ },
441
+ {
442
+ "epoch": 5.02,
443
+ "learning_rate": 0.0001928888888888889,
444
+ "loss": 0.4663,
445
+ "step": 66
446
+ },
447
+ {
448
+ "epoch": 5.04,
449
+ "learning_rate": 0.00019244444444444444,
450
+ "loss": 0.4582,
451
+ "step": 67
452
+ },
453
+ {
454
+ "epoch": 5.06,
455
+ "learning_rate": 0.000192,
456
+ "loss": 0.3941,
457
+ "step": 68
458
+ },
459
+ {
460
+ "epoch": 5.08,
461
+ "learning_rate": 0.00019155555555555554,
462
+ "loss": 0.401,
463
+ "step": 69
464
+ },
465
+ {
466
+ "epoch": 5.1,
467
+ "learning_rate": 0.00019111111111111114,
468
+ "loss": 0.5281,
469
+ "step": 70
470
+ },
471
+ {
472
+ "epoch": 5.12,
473
+ "learning_rate": 0.00019066666666666668,
474
+ "loss": 0.4658,
475
+ "step": 71
476
+ },
477
+ {
478
+ "epoch": 5.14,
479
+ "learning_rate": 0.00019022222222222224,
480
+ "loss": 0.4215,
481
+ "step": 72
482
+ },
483
+ {
484
+ "epoch": 5.16,
485
+ "learning_rate": 0.00018977777777777778,
486
+ "loss": 0.33,
487
+ "step": 73
488
+ },
489
+ {
490
+ "epoch": 5.18,
491
+ "learning_rate": 0.00018933333333333335,
492
+ "loss": 0.5385,
493
+ "step": 74
494
+ },
495
+ {
496
+ "epoch": 5.2,
497
+ "learning_rate": 0.00018888888888888888,
498
+ "loss": 0.3539,
499
+ "step": 75
500
+ },
501
+ {
502
+ "epoch": 5.22,
503
+ "learning_rate": 0.00018844444444444445,
504
+ "loss": 0.4084,
505
+ "step": 76
506
+ },
507
+ {
508
+ "epoch": 5.24,
509
+ "learning_rate": 0.000188,
510
+ "loss": 0.2773,
511
+ "step": 77
512
+ },
513
+ {
514
+ "epoch": 5.26,
515
+ "learning_rate": 0.00018755555555555558,
516
+ "loss": 0.3543,
517
+ "step": 78
518
+ },
519
+ {
520
+ "epoch": 5.26,
521
+ "eval_loss": 0.29384246468544006,
522
+ "eval_runtime": 24.1775,
523
+ "eval_samples_per_second": 0.786,
524
+ "eval_steps_per_second": 0.207,
525
+ "step": 78
526
+ },
527
+ {
528
+ "epoch": 6.02,
529
+ "learning_rate": 0.00018711111111111112,
530
+ "loss": 0.4595,
531
+ "step": 79
532
+ },
533
+ {
534
+ "epoch": 6.04,
535
+ "learning_rate": 0.0001866666666666667,
536
+ "loss": 0.4364,
537
+ "step": 80
538
+ },
539
+ {
540
+ "epoch": 6.06,
541
+ "learning_rate": 0.00018622222222222223,
542
+ "loss": 0.2679,
543
+ "step": 81
544
+ },
545
+ {
546
+ "epoch": 6.08,
547
+ "learning_rate": 0.0001857777777777778,
548
+ "loss": 0.3882,
549
+ "step": 82
550
+ },
551
+ {
552
+ "epoch": 6.1,
553
+ "learning_rate": 0.00018533333333333333,
554
+ "loss": 0.3004,
555
+ "step": 83
556
+ },
557
+ {
558
+ "epoch": 6.12,
559
+ "learning_rate": 0.0001848888888888889,
560
+ "loss": 0.3132,
561
+ "step": 84
562
+ },
563
+ {
564
+ "epoch": 6.14,
565
+ "learning_rate": 0.00018444444444444446,
566
+ "loss": 0.4519,
567
+ "step": 85
568
+ },
569
+ {
570
+ "epoch": 6.16,
571
+ "learning_rate": 0.00018400000000000003,
572
+ "loss": 0.2922,
573
+ "step": 86
574
+ },
575
+ {
576
+ "epoch": 6.18,
577
+ "learning_rate": 0.00018355555555555557,
578
+ "loss": 0.3561,
579
+ "step": 87
580
+ },
581
+ {
582
+ "epoch": 6.2,
583
+ "learning_rate": 0.00018311111111111113,
584
+ "loss": 0.3193,
585
+ "step": 88
586
+ },
587
+ {
588
+ "epoch": 6.22,
589
+ "learning_rate": 0.00018266666666666667,
590
+ "loss": 0.3153,
591
+ "step": 89
592
+ },
593
+ {
594
+ "epoch": 6.24,
595
+ "learning_rate": 0.00018222222222222224,
596
+ "loss": 0.2202,
597
+ "step": 90
598
+ },
599
+ {
600
+ "epoch": 6.26,
601
+ "learning_rate": 0.00018177777777777778,
602
+ "loss": 0.2222,
603
+ "step": 91
604
+ },
605
+ {
606
+ "epoch": 6.26,
607
+ "eval_loss": 0.2629795968532562,
608
+ "eval_runtime": 24.1398,
609
+ "eval_samples_per_second": 0.787,
610
+ "eval_steps_per_second": 0.207,
611
+ "step": 91
612
+ },
613
+ {
614
+ "epoch": 7.02,
615
+ "learning_rate": 0.00018133333333333334,
616
+ "loss": 0.1878,
617
+ "step": 92
618
+ },
619
+ {
620
+ "epoch": 7.04,
621
+ "learning_rate": 0.0001808888888888889,
622
+ "loss": 0.2644,
623
+ "step": 93
624
+ },
625
+ {
626
+ "epoch": 7.06,
627
+ "learning_rate": 0.00018044444444444447,
628
+ "loss": 0.2501,
629
+ "step": 94
630
+ },
631
+ {
632
+ "epoch": 7.08,
633
+ "learning_rate": 0.00018,
634
+ "loss": 0.2801,
635
+ "step": 95
636
+ },
637
+ {
638
+ "epoch": 7.1,
639
+ "learning_rate": 0.00017955555555555558,
640
+ "loss": 0.3479,
641
+ "step": 96
642
+ },
643
+ {
644
+ "epoch": 7.12,
645
+ "learning_rate": 0.00017911111111111112,
646
+ "loss": 0.3556,
647
+ "step": 97
648
+ },
649
+ {
650
+ "epoch": 7.14,
651
+ "learning_rate": 0.00017866666666666668,
652
+ "loss": 0.2206,
653
+ "step": 98
654
+ },
655
+ {
656
+ "epoch": 7.16,
657
+ "learning_rate": 0.00017822222222222222,
658
+ "loss": 0.2939,
659
+ "step": 99
660
+ },
661
+ {
662
+ "epoch": 7.18,
663
+ "learning_rate": 0.00017777777777777779,
664
+ "loss": 0.2029,
665
+ "step": 100
666
+ },
667
+ {
668
+ "epoch": 7.2,
669
+ "learning_rate": 0.00017733333333333335,
670
+ "loss": 0.2979,
671
+ "step": 101
672
+ },
673
+ {
674
+ "epoch": 7.22,
675
+ "learning_rate": 0.0001768888888888889,
676
+ "loss": 0.2793,
677
+ "step": 102
678
+ },
679
+ {
680
+ "epoch": 7.24,
681
+ "learning_rate": 0.00017644444444444446,
682
+ "loss": 0.2809,
683
+ "step": 103
684
+ },
685
+ {
686
+ "epoch": 7.26,
687
+ "learning_rate": 0.00017600000000000002,
688
+ "loss": 0.2748,
689
+ "step": 104
690
+ },
691
+ {
692
+ "epoch": 7.26,
693
+ "eval_loss": 0.25376519560813904,
694
+ "eval_runtime": 24.0872,
695
+ "eval_samples_per_second": 0.789,
696
+ "eval_steps_per_second": 0.208,
697
+ "step": 104
698
+ },
699
+ {
700
+ "epoch": 8.02,
701
+ "learning_rate": 0.00017555555555555556,
702
+ "loss": 0.116,
703
+ "step": 105
704
+ },
705
+ {
706
+ "epoch": 8.04,
707
+ "learning_rate": 0.00017511111111111113,
708
+ "loss": 0.2272,
709
+ "step": 106
710
+ },
711
+ {
712
+ "epoch": 8.06,
713
+ "learning_rate": 0.00017466666666666667,
714
+ "loss": 0.1273,
715
+ "step": 107
716
+ },
717
+ {
718
+ "epoch": 8.08,
719
+ "learning_rate": 0.00017422222222222223,
720
+ "loss": 0.1605,
721
+ "step": 108
722
+ },
723
+ {
724
+ "epoch": 8.1,
725
+ "learning_rate": 0.0001737777777777778,
726
+ "loss": 0.2263,
727
+ "step": 109
728
+ },
729
+ {
730
+ "epoch": 8.12,
731
+ "learning_rate": 0.00017333333333333334,
732
+ "loss": 0.2452,
733
+ "step": 110
734
+ },
735
+ {
736
+ "epoch": 8.14,
737
+ "learning_rate": 0.0001728888888888889,
738
+ "loss": 0.2009,
739
+ "step": 111
740
+ },
741
+ {
742
+ "epoch": 8.16,
743
+ "learning_rate": 0.00017244444444444444,
744
+ "loss": 0.2372,
745
+ "step": 112
746
+ },
747
+ {
748
+ "epoch": 8.18,
749
+ "learning_rate": 0.000172,
750
+ "loss": 0.2736,
751
+ "step": 113
752
+ },
753
+ {
754
+ "epoch": 8.2,
755
+ "learning_rate": 0.00017155555555555555,
756
+ "loss": 0.3009,
757
+ "step": 114
758
+ },
759
+ {
760
+ "epoch": 8.22,
761
+ "learning_rate": 0.0001711111111111111,
762
+ "loss": 0.2619,
763
+ "step": 115
764
+ },
765
+ {
766
+ "epoch": 8.24,
767
+ "learning_rate": 0.00017066666666666668,
768
+ "loss": 0.2698,
769
+ "step": 116
770
+ },
771
+ {
772
+ "epoch": 8.26,
773
+ "learning_rate": 0.00017022222222222224,
774
+ "loss": 0.1716,
775
+ "step": 117
776
+ },
777
+ {
778
+ "epoch": 8.26,
779
+ "eval_loss": 0.23757965862751007,
780
+ "eval_runtime": 24.2556,
781
+ "eval_samples_per_second": 0.783,
782
+ "eval_steps_per_second": 0.206,
783
+ "step": 117
784
+ }
785
+ ],
786
+ "logging_steps": 1,
787
+ "max_steps": 500,
788
+ "num_train_epochs": 10,
789
+ "save_steps": 500,
790
+ "total_flos": 1.8291357646848e+16,
791
+ "trial_name": null,
792
+ "trial_params": null
793
+ }
checkpoint-117/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07edd43c395cc41361c3f2c11b487d986844b6c8297be64ac6f42b2fb6d25642
3
+ size 4091
runs/Sep25_12-31-14_3025c0ae9f03/events.out.tfevents.1695645074.3025c0ae9f03.5818.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:815f05a7ad7002f88647cb7ffd1783874f71ca21570583ca73834bcac6b14432
3
+ size 27574
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "▁<PRE>",
4
+ "▁<MID>",
5
+ "▁<SUF>",
6
+ "▁<EOT>"
7
+ ],
8
+ "bos_token": "<s>",
9
+ "eos_token": "</s>",
10
+ "pad_token": "</s>",
11
+ "unk_token": "<unk>"
12
+ }
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 sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
3
+ size 500058
tokenizer_config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32007": {
28
+ "content": "▁<PRE>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32008": {
36
+ "content": "▁<SUF>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32009": {
44
+ "content": "▁<MID>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32010": {
52
+ "content": "▁<EOT>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [
61
+ "▁<PRE>",
62
+ "▁<MID>",
63
+ "▁<SUF>",
64
+ "▁<EOT>"
65
+ ],
66
+ "bos_token": "<s>",
67
+ "clean_up_tokenization_spaces": false,
68
+ "eos_token": "</s>",
69
+ "eot_token": "▁<EOT>",
70
+ "fill_token": "<FILL_ME>",
71
+ "legacy": null,
72
+ "middle_token": "▁<MID>",
73
+ "model_max_length": 1024,
74
+ "pad_token": null,
75
+ "prefix_token": "▁<PRE>",
76
+ "sp_model_kwargs": {},
77
+ "suffix_token": "▁<SUF>",
78
+ "tokenizer_class": "CodeLlamaTokenizer",
79
+ "unk_token": "<unk>",
80
+ "use_default_system_prompt": false
81
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07edd43c395cc41361c3f2c11b487d986844b6c8297be64ac6f42b2fb6d25642
3
+ size 4091
training_params.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "codellama/CodeLlama-7b-Instruct-hf",
3
+ "data_path": ".",
4
+ "project_name": "qa-model-finetune",
5
+ "train_split": "train",
6
+ "valid_split": "valid",
7
+ "text_column": "text",
8
+ "token": null,
9
+ "lr": 0.0002,
10
+ "epochs": 10,
11
+ "batch_size": 4,
12
+ "warmup_ratio": 0.1,
13
+ "gradient_accumulation": 1,
14
+ "optimizer": "adamw_torch",
15
+ "scheduler": "linear",
16
+ "weight_decay": 0.0,
17
+ "max_grad_norm": 1.0,
18
+ "seed": 42,
19
+ "add_eos_token": false,
20
+ "block_size": -1,
21
+ "use_peft": true,
22
+ "lora_r": 16,
23
+ "lora_alpha": 32,
24
+ "lora_dropout": 0.05,
25
+ "logging_steps": -1,
26
+ "evaluation_strategy": "epoch",
27
+ "save_total_limit": 1,
28
+ "save_strategy": "epoch",
29
+ "auto_find_batch_size": false,
30
+ "fp16": false,
31
+ "push_to_hub": true,
32
+ "use_int8": false,
33
+ "model_max_length": 1024,
34
+ "repo_id": "shyam-incedoinc/codellama-7b-instruct-hf-finetuned-qa-1-3",
35
+ "use_int4": true,
36
+ "trainer": "sft",
37
+ "target_modules": null,
38
+ "merge_adapter": true,
39
+ "username": null
40
+ }