Hugging Face's logo

tokhey
/
question_generation_1.5B_model

Text Generation
PEFT
Safetensors
Transformers
llama-factory
lora
conversational
Model card Files
xet
Community
tokhey commited on
Commit
abbda43
·
verified ·
1 Parent(s): ab36aec

End of training

Browse files
Files changed (7) hide show
  1. README.md +2 -2
  2. all_results.json +12 -0
  3. eval_results.json +7 -0
  4. train_results.json +8 -0
  5. trainer_state.json +205 -0
  6. training_eval_loss.png +0 -0
  7. training_loss.png +0 -0
README.md CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # question_generation_1.5B_model
20
 
21
- This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.8379
24
 
25
  ## Model description
26
 
 
18
 
19
  # question_generation_1.5B_model
20
 
21
+ This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the questions_finetune_train dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.8382
24
 
25
  ## Model description
26
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.8382031917572021,
4
+ "eval_runtime": 6.3298,
5
+ "eval_samples_per_second": 2.686,
6
+ "eval_steps_per_second": 2.686,
7
+ "total_flos": 7347762207129600.0,
8
+ "train_loss": 0.6599949598312378,
9
+ "train_runtime": 1100.6114,
10
+ "train_samples_per_second": 0.818,
11
+ "train_steps_per_second": 0.104
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.8382031917572021,
4
+ "eval_runtime": 6.3298,
5
+ "eval_samples_per_second": 2.686,
6
+ "eval_steps_per_second": 2.686
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 7347762207129600.0,
4
+ "train_loss": 0.6599949598312378,
5
+ "train_runtime": 1100.6114,
6
+ "train_samples_per_second": 0.818,
7
+ "train_steps_per_second": 0.104
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,205 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 100,
7
+ "global_step": 114,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.13333333333333333,
14
+ "grad_norm": 0.14584249258041382,
15
+ "learning_rate": 0.00016666666666666666,
16
+ "loss": 0.9293,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.26666666666666666,
21
+ "grad_norm": 0.1325272023677826,
22
+ "learning_rate": 0.000375,
23
+ "loss": 0.8556,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.4,
28
+ "grad_norm": 0.15272639691829681,
29
+ "learning_rate": 0.0004995258321842611,
30
+ "loss": 0.8414,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.5333333333333333,
35
+ "grad_norm": 0.1267966479063034,
36
+ "learning_rate": 0.0004942120794399002,
37
+ "loss": 0.7606,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.6666666666666666,
42
+ "grad_norm": 0.13581494987010956,
43
+ "learning_rate": 0.00048311805735108893,
44
+ "loss": 0.7522,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.8,
49
+ "grad_norm": 0.12239090353250504,
50
+ "learning_rate": 0.00046650635094610973,
51
+ "loss": 0.7444,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.9333333333333333,
56
+ "grad_norm": 0.12692460417747498,
57
+ "learning_rate": 0.0004447701436314176,
58
+ "loss": 0.6762,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 1.0533333333333332,
63
+ "grad_norm": 0.12733194231987,
64
+ "learning_rate": 0.0004184239109116393,
65
+ "loss": 0.7014,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 1.1866666666666668,
70
+ "grad_norm": 0.13756456971168518,
71
+ "learning_rate": 0.00038809124324012647,
72
+ "loss": 0.6655,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 1.32,
77
+ "grad_norm": 0.14693589508533478,
78
+ "learning_rate": 0.00035449008622169586,
79
+ "loss": 0.6315,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 1.4533333333333334,
84
+ "grad_norm": 0.16421127319335938,
85
+ "learning_rate": 0.0003184157475180208,
86
+ "loss": 0.6525,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 1.5866666666666667,
91
+ "grad_norm": 0.1636400669813156,
92
+ "learning_rate": 0.00028072207266617854,
93
+ "loss": 0.6398,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 1.72,
98
+ "grad_norm": 0.16314196586608887,
99
+ "learning_rate": 0.00024230123536095747,
100
+ "loss": 0.6836,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 1.8533333333333335,
105
+ "grad_norm": 0.1881810426712036,
106
+ "learning_rate": 0.0002040626205458574,
107
+ "loss": 0.6227,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 1.9866666666666668,
112
+ "grad_norm": 0.1938481628894806,
113
+ "learning_rate": 0.00016691130013008512,
114
+ "loss": 0.6343,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 2.1066666666666665,
119
+ "grad_norm": 0.18422311544418335,
120
+ "learning_rate": 0.0001317266107909975,
121
+ "loss": 0.6193,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 2.24,
126
+ "grad_norm": 0.19134873151779175,
127
+ "learning_rate": 9.934134090518593e-05,
128
+ "loss": 0.5563,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 2.3733333333333335,
133
+ "grad_norm": 0.19149252772331238,
134
+ "learning_rate": 7.052201923388955e-05,
135
+ "loss": 0.5774,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 2.506666666666667,
140
+ "grad_norm": 0.2055027186870575,
141
+ "learning_rate": 4.59507719109446e-05,
142
+ "loss": 0.5472,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 2.64,
147
+ "grad_norm": 0.20931023359298706,
148
+ "learning_rate": 2.6209177161234443e-05,
149
+ "loss": 0.5133,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 2.64,
154
+ "eval_loss": 0.8378572463989258,
155
+ "eval_runtime": 6.3722,
156
+ "eval_samples_per_second": 2.668,
157
+ "eval_steps_per_second": 2.668,
158
+ "step": 100
159
+ },
160
+ {
161
+ "epoch": 2.7733333333333334,
162
+ "grad_norm": 0.19245073199272156,
163
+ "learning_rate": 1.1764499893210877e-05,
164
+ "loss": 0.5179,
165
+ "step": 105
166
+ },
167
+ {
168
+ "epoch": 2.9066666666666667,
169
+ "grad_norm": 0.20502211153507233,
170
+ "learning_rate": 2.9586319796851556e-06,
171
+ "loss": 0.525,
172
+ "step": 110
173
+ },
174
+ {
175
+ "epoch": 3.0,
176
+ "step": 114,
177
+ "total_flos": 7347762207129600.0,
178
+ "train_loss": 0.6599949598312378,
179
+ "train_runtime": 1100.6114,
180
+ "train_samples_per_second": 0.818,
181
+ "train_steps_per_second": 0.104
182
+ }
183
+ ],
184
+ "logging_steps": 5,
185
+ "max_steps": 114,
186
+ "num_input_tokens_seen": 0,
187
+ "num_train_epochs": 3,
188
+ "save_steps": 40,
189
+ "stateful_callbacks": {
190
+ "TrainerControl": {
191
+ "args": {
192
+ "should_epoch_stop": false,
193
+ "should_evaluate": false,
194
+ "should_log": false,
195
+ "should_save": true,
196
+ "should_training_stop": true
197
+ },
198
+ "attributes": {}
199
+ }
200
+ },
201
+ "total_flos": 7347762207129600.0,
202
+ "train_batch_size": 1,
203
+ "trial_name": null,
204
+ "trial_params": null
205
+ }
training_eval_loss.png ADDED
training_loss.png ADDED