Hugging Face's logo

duyphu
/
3d129001-be65-406a-a409-10f99a17a16f

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
1
3d129001-be65-406a-a409-10f99a17a16f
File size: 3,703 Bytes 
6019232
 
 
065e3f8
830ecff
065e3f8
6019232
 
 
 
 
 
 
830ecff
 
 
6019232
830ecff
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d161955
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c853bf7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
065e3f8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6019232
 
 
830ecff
6019232
 
830ecff
6019232
 
 
 
 
 
 
065e3f8
6019232
 
 
 
065e3f8
6019232
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02126528442317916,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004253056884635832,
      "eval_loss": 7.85447359085083,
      "eval_runtime": 43.0645,
      "eval_samples_per_second": 22.989,
      "eval_steps_per_second": 11.494,
      "step": 1
    },
    {
      "epoch": 0.002126528442317916,
      "grad_norm": 6.904982089996338,
      "learning_rate": 5e-05,
      "loss": 8.2507,
      "step": 5
    },
    {
      "epoch": 0.004253056884635832,
      "grad_norm": 8.058303833007812,
      "learning_rate": 0.0001,
      "loss": 7.2992,
      "step": 10
    },
    {
      "epoch": 0.004253056884635832,
      "eval_loss": 6.549283981323242,
      "eval_runtime": 42.3073,
      "eval_samples_per_second": 23.4,
      "eval_steps_per_second": 11.7,
      "step": 10
    },
    {
      "epoch": 0.006379585326953748,
      "grad_norm": 8.274881362915039,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.7451,
      "step": 15
    },
    {
      "epoch": 0.008506113769271665,
      "grad_norm": 3.4021964073181152,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.2782,
      "step": 20
    },
    {
      "epoch": 0.008506113769271665,
      "eval_loss": 3.175553798675537,
      "eval_runtime": 41.6034,
      "eval_samples_per_second": 23.796,
      "eval_steps_per_second": 11.898,
      "step": 20
    },
    {
      "epoch": 0.01063264221158958,
      "grad_norm": 3.960761308670044,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.7442,
      "step": 25
    },
    {
      "epoch": 0.012759170653907496,
      "grad_norm": 8.499146461486816,
      "learning_rate": 5e-05,
      "loss": 3.3788,
      "step": 30
    },
    {
      "epoch": 0.012759170653907496,
      "eval_loss": 2.4144866466522217,
      "eval_runtime": 41.7376,
      "eval_samples_per_second": 23.72,
      "eval_steps_per_second": 11.86,
      "step": 30
    },
    {
      "epoch": 0.014885699096225412,
      "grad_norm": 3.365118980407715,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.7027,
      "step": 35
    },
    {
      "epoch": 0.01701222753854333,
      "grad_norm": 4.345822811126709,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.571,
      "step": 40
    },
    {
      "epoch": 0.01701222753854333,
      "eval_loss": 2.0501210689544678,
      "eval_runtime": 41.8304,
      "eval_samples_per_second": 23.667,
      "eval_steps_per_second": 11.833,
      "step": 40
    },
    {
      "epoch": 0.019138755980861243,
      "grad_norm": 1.684922456741333,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.47,
      "step": 45
    },
    {
      "epoch": 0.02126528442317916,
      "grad_norm": 1.7763071060180664,
      "learning_rate": 0.0,
      "loss": 1.1022,
      "step": 50
    },
    {
      "epoch": 0.02126528442317916,
      "eval_loss": 2.0081968307495117,
      "eval_runtime": 41.6129,
      "eval_samples_per_second": 23.791,
      "eval_steps_per_second": 11.895,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2399807113003008.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}