Hugging Face's logo

mssongit
/
Qwen2.5-14B-SFT-LoRA-6e-5

PEFT
Safetensors
Generated from Trainer
Model card Files Community
Qwen2.5-14B-SFT-LoRA-6e-5
File size: 4,738 Bytes 
43669b6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
 
{
  "best_metric": 0.08133330941200256,
  "best_model_checkpoint": "./outputs/lora-out/checkpoint-900",
  "epoch": 0.8310249307479224,
  "eval_steps": 100,
  "global_step": 900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009233610341643582,
      "eval_loss": 0.4242709279060364,
      "eval_runtime": 91.8213,
      "eval_samples_per_second": 1.252,
      "eval_steps_per_second": 1.252,
      "step": 1
    },
    {
      "epoch": 0.09233610341643583,
      "grad_norm": 0.6968376040458679,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.2465,
      "step": 100
    },
    {
      "epoch": 0.09233610341643583,
      "eval_loss": 0.13379718363285065,
      "eval_runtime": 93.2896,
      "eval_samples_per_second": 1.233,
      "eval_steps_per_second": 1.233,
      "step": 100
    },
    {
      "epoch": 0.18467220683287167,
      "grad_norm": 0.38504940271377563,
      "learning_rate": 5.997756992048411e-05,
      "loss": 0.0425,
      "step": 200
    },
    {
      "epoch": 0.18467220683287167,
      "eval_loss": 0.11098360270261765,
      "eval_runtime": 93.1082,
      "eval_samples_per_second": 1.235,
      "eval_steps_per_second": 1.235,
      "step": 200
    },
    {
      "epoch": 0.2770083102493075,
      "grad_norm": 0.21793705224990845,
      "learning_rate": 5.970463299279944e-05,
      "loss": 0.0333,
      "step": 300
    },
    {
      "epoch": 0.2770083102493075,
      "eval_loss": 0.10511630773544312,
      "eval_runtime": 93.095,
      "eval_samples_per_second": 1.235,
      "eval_steps_per_second": 1.235,
      "step": 300
    },
    {
      "epoch": 0.36934441366574333,
      "grad_norm": 0.245796799659729,
      "learning_rate": 5.912431591443999e-05,
      "loss": 0.0319,
      "step": 400
    },
    {
      "epoch": 0.36934441366574333,
      "eval_loss": 0.09326907247304916,
      "eval_runtime": 93.3684,
      "eval_samples_per_second": 1.232,
      "eval_steps_per_second": 1.232,
      "step": 400
    },
    {
      "epoch": 0.4616805170821791,
      "grad_norm": 0.2685442864894867,
      "learning_rate": 5.824262374027476e-05,
      "loss": 0.0257,
      "step": 500
    },
    {
      "epoch": 0.4616805170821791,
      "eval_loss": 0.08864552527666092,
      "eval_runtime": 93.324,
      "eval_samples_per_second": 1.232,
      "eval_steps_per_second": 1.232,
      "step": 500
    },
    {
      "epoch": 0.554016620498615,
      "grad_norm": 0.2339438498020172,
      "learning_rate": 5.706868012025456e-05,
      "loss": 0.0245,
      "step": 600
    },
    {
      "epoch": 0.554016620498615,
      "eval_loss": 0.08980301022529602,
      "eval_runtime": 93.1142,
      "eval_samples_per_second": 1.235,
      "eval_steps_per_second": 1.235,
      "step": 600
    },
    {
      "epoch": 0.6463527239150508,
      "grad_norm": 0.17079927027225494,
      "learning_rate": 5.561463288892402e-05,
      "loss": 0.0262,
      "step": 700
    },
    {
      "epoch": 0.6463527239150508,
      "eval_loss": 0.08885745704174042,
      "eval_runtime": 93.2779,
      "eval_samples_per_second": 1.233,
      "eval_steps_per_second": 1.233,
      "step": 700
    },
    {
      "epoch": 0.7386888273314867,
      "grad_norm": 0.18653833866119385,
      "learning_rate": 5.389552836101671e-05,
      "loss": 0.025,
      "step": 800
    },
    {
      "epoch": 0.7386888273314867,
      "eval_loss": 0.08268226683139801,
      "eval_runtime": 92.9671,
      "eval_samples_per_second": 1.237,
      "eval_steps_per_second": 1.237,
      "step": 800
    },
    {
      "epoch": 0.8310249307479224,
      "grad_norm": 0.027869287878274918,
      "learning_rate": 5.192915563390816e-05,
      "loss": 0.0221,
      "step": 900
    },
    {
      "epoch": 0.8310249307479224,
      "eval_loss": 0.08133330941200256,
      "eval_runtime": 93.0513,
      "eval_samples_per_second": 1.236,
      "eval_steps_per_second": 1.236,
      "step": 900
    }
  ],
  "logging_steps": 100,
  "max_steps": 3249,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.204597114765312e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}