mskov commited on
Commit
85a3d0d
1 Parent(s): 819e965

Upload 11 files

Browse files
results/checkpoint-400/README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
+
18
+ The following `bitsandbytes` quantization config was used during training:
19
+ - load_in_8bit: False
20
+ - load_in_4bit: True
21
+ - llm_int8_threshold: 6.0
22
+ - llm_int8_skip_modules: None
23
+ - llm_int8_enable_fp32_cpu_offload: False
24
+ - llm_int8_has_fp16_weight: False
25
+ - bnb_4bit_quant_type: nf4
26
+ - bnb_4bit_use_double_quant: False
27
+ - bnb_4bit_compute_dtype: float16
28
+
29
+ The following `bitsandbytes` quantization config was used during training:
30
+ - load_in_8bit: False
31
+ - load_in_4bit: True
32
+ - llm_int8_threshold: 6.0
33
+ - llm_int8_skip_modules: None
34
+ - llm_int8_enable_fp32_cpu_offload: False
35
+ - llm_int8_has_fp16_weight: False
36
+ - bnb_4bit_quant_type: nf4
37
+ - bnb_4bit_use_double_quant: False
38
+ - bnb_4bit_compute_dtype: float16
39
+
40
+ The following `bitsandbytes` quantization config was used during training:
41
+ - load_in_8bit: False
42
+ - load_in_4bit: True
43
+ - llm_int8_threshold: 6.0
44
+ - llm_int8_skip_modules: None
45
+ - llm_int8_enable_fp32_cpu_offload: False
46
+ - llm_int8_has_fp16_weight: False
47
+ - bnb_4bit_quant_type: nf4
48
+ - bnb_4bit_use_double_quant: False
49
+ - bnb_4bit_compute_dtype: float16
50
+ ### Framework versions
51
+
52
+ - PEFT 0.5.0.dev0
53
+ - PEFT 0.5.0.dev0
54
+ - PEFT 0.5.0.dev0
55
+
56
+ - PEFT 0.5.0.dev0
results/checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
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": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "query_key_value",
18
+ "dense",
19
+ "dense_h_to_4h",
20
+ "dense_4h_to_h"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
results/checkpoint-400/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9812045cf104fa1f918881e907898b4652a773ee4f40d9814a8fd70166bfe26
3
+ size 522284877
results/checkpoint-400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7be69e1183bb3341a8e99eb51d19b42079399c40c672d50c22e9c38c6160ac9b
3
+ size 1044539909
results/checkpoint-400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8aa695d6ff41defe8f0a0969a0a2c86a78e07f3dd9ef7782bf6f6746a712392
3
+ size 14575
results/checkpoint-400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
3
+ size 627
results/checkpoint-400/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>PREFIX<<",
12
+ ">>SUFFIX<<",
13
+ ">>MIDDLE<<"
14
+ ],
15
+ "eos_token": "<|endoftext|>",
16
+ "pad_token": "<|endoftext|>"
17
+ }
results/checkpoint-400/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
results/checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 2048,
6
+ "tokenizer_class": "PreTrainedTokenizerFast"
7
+ }
results/checkpoint-400/trainer_state.json ADDED
@@ -0,0 +1,256 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.63768115942029,
5
+ "global_step": 400,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.12,
12
+ "learning_rate": 0.0002,
13
+ "loss": 2.8625,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.23,
18
+ "learning_rate": 0.0002,
19
+ "loss": 2.8987,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.35,
24
+ "learning_rate": 0.0002,
25
+ "loss": 2.7552,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.46,
30
+ "learning_rate": 0.0002,
31
+ "loss": 2.8627,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.58,
36
+ "learning_rate": 0.0002,
37
+ "loss": 2.6602,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.7,
42
+ "learning_rate": 0.0002,
43
+ "loss": 2.8089,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.81,
48
+ "learning_rate": 0.0002,
49
+ "loss": 2.7102,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.93,
54
+ "learning_rate": 0.0002,
55
+ "loss": 2.772,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 1.04,
60
+ "learning_rate": 0.0002,
61
+ "loss": 2.6953,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 1.16,
66
+ "learning_rate": 0.0002,
67
+ "loss": 2.6401,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 1.28,
72
+ "learning_rate": 0.0002,
73
+ "loss": 2.648,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 1.39,
78
+ "learning_rate": 0.0002,
79
+ "loss": 2.5756,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 1.51,
84
+ "learning_rate": 0.0002,
85
+ "loss": 2.6002,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 1.62,
90
+ "learning_rate": 0.0002,
91
+ "loss": 2.5801,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 1.74,
96
+ "learning_rate": 0.0002,
97
+ "loss": 2.6678,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 1.86,
102
+ "learning_rate": 0.0002,
103
+ "loss": 2.5758,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 1.97,
108
+ "learning_rate": 0.0002,
109
+ "loss": 2.6861,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 2.09,
114
+ "learning_rate": 0.0002,
115
+ "loss": 2.4169,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 2.2,
120
+ "learning_rate": 0.0002,
121
+ "loss": 2.3657,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 2.32,
126
+ "learning_rate": 0.0002,
127
+ "loss": 2.3153,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 2.43,
132
+ "learning_rate": 0.0002,
133
+ "loss": 2.3601,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 2.55,
138
+ "learning_rate": 0.0002,
139
+ "loss": 2.3498,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 2.67,
144
+ "learning_rate": 0.0002,
145
+ "loss": 2.4114,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 2.78,
150
+ "learning_rate": 0.0002,
151
+ "loss": 2.3708,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 2.9,
156
+ "learning_rate": 0.0002,
157
+ "loss": 2.4176,
158
+ "step": 250
159
+ },
160
+ {
161
+ "epoch": 3.01,
162
+ "learning_rate": 0.0002,
163
+ "loss": 2.3728,
164
+ "step": 260
165
+ },
166
+ {
167
+ "epoch": 3.13,
168
+ "learning_rate": 0.0002,
169
+ "loss": 2.1058,
170
+ "step": 270
171
+ },
172
+ {
173
+ "epoch": 3.25,
174
+ "learning_rate": 0.0002,
175
+ "loss": 2.0375,
176
+ "step": 280
177
+ },
178
+ {
179
+ "epoch": 3.36,
180
+ "learning_rate": 0.0002,
181
+ "loss": 2.0828,
182
+ "step": 290
183
+ },
184
+ {
185
+ "epoch": 3.48,
186
+ "learning_rate": 0.0002,
187
+ "loss": 2.081,
188
+ "step": 300
189
+ },
190
+ {
191
+ "epoch": 3.59,
192
+ "learning_rate": 0.0002,
193
+ "loss": 2.1004,
194
+ "step": 310
195
+ },
196
+ {
197
+ "epoch": 3.71,
198
+ "learning_rate": 0.0002,
199
+ "loss": 2.1472,
200
+ "step": 320
201
+ },
202
+ {
203
+ "epoch": 3.83,
204
+ "learning_rate": 0.0002,
205
+ "loss": 2.1437,
206
+ "step": 330
207
+ },
208
+ {
209
+ "epoch": 3.94,
210
+ "learning_rate": 0.0002,
211
+ "loss": 2.149,
212
+ "step": 340
213
+ },
214
+ {
215
+ "epoch": 4.06,
216
+ "learning_rate": 0.0002,
217
+ "loss": 1.9758,
218
+ "step": 350
219
+ },
220
+ {
221
+ "epoch": 4.17,
222
+ "learning_rate": 0.0002,
223
+ "loss": 1.791,
224
+ "step": 360
225
+ },
226
+ {
227
+ "epoch": 4.29,
228
+ "learning_rate": 0.0002,
229
+ "loss": 1.7366,
230
+ "step": 370
231
+ },
232
+ {
233
+ "epoch": 4.41,
234
+ "learning_rate": 0.0002,
235
+ "loss": 1.8066,
236
+ "step": 380
237
+ },
238
+ {
239
+ "epoch": 4.52,
240
+ "learning_rate": 0.0002,
241
+ "loss": 1.7821,
242
+ "step": 390
243
+ },
244
+ {
245
+ "epoch": 4.64,
246
+ "learning_rate": 0.0002,
247
+ "loss": 1.8661,
248
+ "step": 400
249
+ }
250
+ ],
251
+ "max_steps": 500,
252
+ "num_train_epochs": 6,
253
+ "total_flos": 1.897304296714445e+16,
254
+ "trial_name": null,
255
+ "trial_params": null
256
+ }
results/checkpoint-400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e32f6466c16ba713013fd98facddbea62a306618253d2be1824692787d74ffb
3
+ size 4027