Hugging Face's logo

mlfoundations-dev
/
316_globalbatchsize64_lr1e5_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
e750c99
·
verified ·
1 Parent(s): c831a81

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_lr1e5_epochs5
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # 316_globalbatchsize64_lr1e5_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_lr1e5_epochs5
 
16
 
17
  # 316_globalbatchsize64_lr1e5_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": 0.6773358273506165,
5
+ "train_runtime": 2116.0034,
6
+ "train_samples_per_second": 0.747,
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": 0.6773358273506165,
5
+ "train_runtime": 2116.0034,
6
+ "train_samples_per_second": 0.747,
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": 5.582047512699039,
14
+ "learning_rate": 3.3333333333333333e-06,
15
+ "loss": 0.832,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.4,
20
+ "grad_norm": 6.008045063224414,
21
+ "learning_rate": 6.666666666666667e-06,
22
+ "loss": 0.8909,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.6,
27
+ "grad_norm": 5.619691260140896,
28
+ "learning_rate": 1e-05,
29
+ "loss": 0.895,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.8,
34
+ "grad_norm": 2.4419954363812546,
35
+ "learning_rate": 9.949107209404664e-06,
36
+ "loss": 0.8295,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "grad_norm": 4.388419710102024,
42
+ "learning_rate": 9.797464868072489e-06,
43
+ "loss": 0.8042,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 1.2,
48
+ "grad_norm": 4.783176654227559,
49
+ "learning_rate": 9.548159976772593e-06,
50
+ "loss": 0.7827,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 1.4,
55
+ "grad_norm": 5.091132431503279,
56
+ "learning_rate": 9.206267664155906e-06,
57
+ "loss": 0.7791,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 1.6,
62
+ "grad_norm": 3.822231767141275,
63
+ "learning_rate": 8.778747871771293e-06,
64
+ "loss": 0.7468,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 1.8,
69
+ "grad_norm": 2.5817851399644267,
70
+ "learning_rate": 8.274303669726427e-06,
71
+ "loss": 0.7373,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 2.0,
76
+ "grad_norm": 1.6946946923157924,
77
+ "learning_rate": 7.703204087277989e-06,
78
+ "loss": 0.6852,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 2.2,
83
+ "grad_norm": 1.6248909167963212,
84
+ "learning_rate": 7.0770750650094335e-06,
85
+ "loss": 0.6784,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 2.4,
90
+ "grad_norm": 1.5707404220045935,
91
+ "learning_rate": 6.408662784207149e-06,
92
+ "loss": 0.6349,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 2.6,
97
+ "grad_norm": 0.9743312920477364,
98
+ "learning_rate": 5.711574191366427e-06,
99
+ "loss": 0.6179,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 2.8,
104
+ "grad_norm": 1.1820747823709539,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.6468,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 3.0,
111
+ "grad_norm": 1.0613411323142574,
112
+ "learning_rate": 4.2884258086335755e-06,
113
+ "loss": 0.6264,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 3.2,
118
+ "grad_norm": 0.9343671083929717,
119
+ "learning_rate": 3.5913372157928515e-06,
120
+ "loss": 0.5678,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 3.4,
125
+ "grad_norm": 0.825169270658582,
126
+ "learning_rate": 2.9229249349905686e-06,
127
+ "loss": 0.6467,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 3.6,
132
+ "grad_norm": 0.7335904450059882,
133
+ "learning_rate": 2.296795912722014e-06,
134
+ "loss": 0.5901,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 3.8,
139
+ "grad_norm": 0.7118131164733261,
140
+ "learning_rate": 1.7256963302735752e-06,
141
+ "loss": 0.5917,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 4.0,
146
+ "grad_norm": 0.5995644006563385,
147
+ "learning_rate": 1.2212521282287093e-06,
148
+ "loss": 0.5287,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 4.2,
153
+ "grad_norm": 0.5329284210983056,
154
+ "learning_rate": 7.937323358440935e-07,
155
+ "loss": 0.5862,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 4.4,
160
+ "grad_norm": 0.49244683959100055,
161
+ "learning_rate": 4.5184002322740784e-07,
162
+ "loss": 0.5381,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 4.6,
167
+ "grad_norm": 0.5407056028850911,
168
+ "learning_rate": 2.0253513192751374e-07,
169
+ "loss": 0.5601,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 4.8,
174
+ "grad_norm": 0.48949102048400017,
175
+ "learning_rate": 5.089279059533658e-08,
176
+ "loss": 0.5729,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 5.0,
181
+ "grad_norm": 0.5481083314386501,
182
+ "learning_rate": 0.0,
183
+ "loss": 0.5641,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 5.0,
188
+ "step": 25,
189
+ "total_flos": 3.2478016827293696e+16,
190
+ "train_loss": 0.6773358273506165,
191
+ "train_runtime": 2116.0034,
192
+ "train_samples_per_second": 0.747,
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