Hugging Face's logo

mlfoundations-dev
/
316_globalbatchsize64_lr2e5_epochs5

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
sedrickkeh commited on
Commit
8a30f59
·
verified ·
1 Parent(s): 5df4c08

End of training

Browse files
Files changed (5) hide show
  1. README.md +2 -1
  2. all_results.json +8 -0
  3. train_results.json +8 -0
  4. trainer_state.json +217 -0
  5. training_loss.png +0 -0
README.md CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
4
  base_model: Qwen/Qwen2.5-7B-Instruct
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: 316_globalbatchsize64_lr2e5_epochs5
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # 316_globalbatchsize64_lr2e5_epochs5
17
 
18
- This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
19
 
20
  ## Model description
21
 
 
4
  base_model: Qwen/Qwen2.5-7B-Instruct
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: 316_globalbatchsize64_lr2e5_epochs5
 
16
 
17
  # 316_globalbatchsize64_lr2e5_epochs5
18
 
19
+ This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/openthoughts_316 dataset.
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 3.2478016827293696e+16,
4
+ "train_loss": 0.6328057992458344,
5
+ "train_runtime": 2119.4087,
6
+ "train_samples_per_second": 0.745,
7
+ "train_steps_per_second": 0.012
8
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 3.2478016827293696e+16,
4
+ "train_loss": 0.6328057992458344,
5
+ "train_runtime": 2119.4087,
6
+ "train_samples_per_second": 0.745,
7
+ "train_steps_per_second": 0.012
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,217 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 25,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.2,
13
+ "grad_norm": 5.582018382418061,
14
+ "learning_rate": 6.666666666666667e-06,
15
+ "loss": 0.832,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.4,
20
+ "grad_norm": 6.008115759273852,
21
+ "learning_rate": 1.3333333333333333e-05,
22
+ "loss": 0.8909,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.6,
27
+ "grad_norm": 4.203158365014558,
28
+ "learning_rate": 2e-05,
29
+ "loss": 0.856,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.8,
34
+ "grad_norm": 5.330103222720995,
35
+ "learning_rate": 1.989821441880933e-05,
36
+ "loss": 0.8935,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "grad_norm": 6.604796866941393,
42
+ "learning_rate": 1.9594929736144978e-05,
43
+ "loss": 0.8573,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 1.2,
48
+ "grad_norm": 4.889759493234221,
49
+ "learning_rate": 1.9096319953545186e-05,
50
+ "loss": 0.8122,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 1.4,
55
+ "grad_norm": 2.6673253563493007,
56
+ "learning_rate": 1.8412535328311813e-05,
57
+ "loss": 0.7676,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 1.6,
62
+ "grad_norm": 1.6708268813136478,
63
+ "learning_rate": 1.7557495743542586e-05,
64
+ "loss": 0.7087,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 1.8,
69
+ "grad_norm": 1.8635895305372137,
70
+ "learning_rate": 1.6548607339452853e-05,
71
+ "loss": 0.695,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 2.0,
76
+ "grad_norm": 1.1743860615942052,
77
+ "learning_rate": 1.5406408174555978e-05,
78
+ "loss": 0.6507,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 2.2,
83
+ "grad_norm": 0.9577383518041913,
84
+ "learning_rate": 1.4154150130018867e-05,
85
+ "loss": 0.626,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 2.4,
90
+ "grad_norm": 0.9653843420006609,
91
+ "learning_rate": 1.2817325568414299e-05,
92
+ "loss": 0.5799,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 2.6,
97
+ "grad_norm": 0.7211363515893529,
98
+ "learning_rate": 1.1423148382732854e-05,
99
+ "loss": 0.5685,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 2.8,
104
+ "grad_norm": 0.90772975706778,
105
+ "learning_rate": 1e-05,
106
+ "loss": 0.5919,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 3.0,
111
+ "grad_norm": 0.7164003657107308,
112
+ "learning_rate": 8.576851617267151e-06,
113
+ "loss": 0.5679,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 3.2,
118
+ "grad_norm": 1.2467863416781333,
119
+ "learning_rate": 7.182674431585703e-06,
120
+ "loss": 0.498,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 3.4,
125
+ "grad_norm": 0.9480737486309809,
126
+ "learning_rate": 5.845849869981137e-06,
127
+ "loss": 0.5647,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 3.6,
132
+ "grad_norm": 0.5516119711486823,
133
+ "learning_rate": 4.593591825444028e-06,
134
+ "loss": 0.5169,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 3.8,
139
+ "grad_norm": 0.7064792732116788,
140
+ "learning_rate": 3.4513926605471504e-06,
141
+ "loss": 0.5086,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 4.0,
146
+ "grad_norm": 0.5816794153324469,
147
+ "learning_rate": 2.4425042564574186e-06,
148
+ "loss": 0.4558,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 4.2,
153
+ "grad_norm": 0.5315955082840325,
154
+ "learning_rate": 1.587464671688187e-06,
155
+ "loss": 0.4984,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 4.4,
160
+ "grad_norm": 0.4271511280028261,
161
+ "learning_rate": 9.036800464548157e-07,
162
+ "loss": 0.4525,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 4.6,
167
+ "grad_norm": 0.45389257042160547,
168
+ "learning_rate": 4.0507026385502747e-07,
169
+ "loss": 0.4713,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 4.8,
174
+ "grad_norm": 0.443007797239538,
175
+ "learning_rate": 1.0178558119067316e-07,
176
+ "loss": 0.4809,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 5.0,
181
+ "grad_norm": 0.44135326132925484,
182
+ "learning_rate": 0.0,
183
+ "loss": 0.4748,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 5.0,
188
+ "step": 25,
189
+ "total_flos": 3.2478016827293696e+16,
190
+ "train_loss": 0.6328057992458344,
191
+ "train_runtime": 2119.4087,
192
+ "train_samples_per_second": 0.745,
193
+ "train_steps_per_second": 0.012
194
+ }
195
+ ],
196
+ "logging_steps": 1.0,
197
+ "max_steps": 25,
198
+ "num_input_tokens_seen": 0,
199
+ "num_train_epochs": 5,
200
+ "save_steps": 500,
201
+ "stateful_callbacks": {
202
+ "TrainerControl": {
203
+ "args": {
204
+ "should_epoch_stop": false,
205
+ "should_evaluate": false,
206
+ "should_log": false,
207
+ "should_save": true,
208
+ "should_training_stop": true
209
+ },
210
+ "attributes": {}
211
+ }
212
+ },
213
+ "total_flos": 3.2478016827293696e+16,
214
+ "train_batch_size": 1,
215
+ "trial_name": null,
216
+ "trial_params": null
217
+ }
training_loss.png ADDED