Hugging Face's logo

tuanna08go
/
a2ae530a-991c-4435-97a5-372f28eb8126

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
a2ae530a-991c-4435-97a5-372f28eb8126
File size: 3,731 Bytes 
1bc6380
 
 
474027f
aba7b67
474027f
1bc6380
 
 
 
 
 
 
aba7b67
 
 
1bc6380
aba7b67
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ec2f454
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8f9cb83
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
474027f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1bc6380
 
 
aba7b67
1bc6380
 
aba7b67
1bc6380
 
 
 
 
 
 
474027f
1bc6380
 
 
 
474027f
1bc6380
 
 
 
 
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": 0.06105006105006105,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001221001221001221,
      "eval_loss": 11.934243202209473,
      "eval_runtime": 5.9922,
      "eval_samples_per_second": 57.575,
      "eval_steps_per_second": 28.871,
      "step": 1
    },
    {
      "epoch": 0.006105006105006105,
      "grad_norm": 0.010467967949807644,
      "learning_rate": 5e-05,
      "loss": 11.9338,
      "step": 5
    },
    {
      "epoch": 0.01221001221001221,
      "grad_norm": 0.012429132126271725,
      "learning_rate": 0.0001,
      "loss": 11.934,
      "step": 10
    },
    {
      "epoch": 0.01221001221001221,
      "eval_loss": 11.934219360351562,
      "eval_runtime": 6.086,
      "eval_samples_per_second": 56.688,
      "eval_steps_per_second": 28.426,
      "step": 10
    },
    {
      "epoch": 0.018315018315018316,
      "grad_norm": 0.010163530707359314,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.9346,
      "step": 15
    },
    {
      "epoch": 0.02442002442002442,
      "grad_norm": 0.010413922369480133,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9359,
      "step": 20
    },
    {
      "epoch": 0.02442002442002442,
      "eval_loss": 11.934165954589844,
      "eval_runtime": 5.9793,
      "eval_samples_per_second": 57.699,
      "eval_steps_per_second": 28.933,
      "step": 20
    },
    {
      "epoch": 0.030525030525030524,
      "grad_norm": 0.010765035636723042,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.933,
      "step": 25
    },
    {
      "epoch": 0.03663003663003663,
      "grad_norm": 0.017171213403344154,
      "learning_rate": 5e-05,
      "loss": 11.9326,
      "step": 30
    },
    {
      "epoch": 0.03663003663003663,
      "eval_loss": 11.934120178222656,
      "eval_runtime": 6.1064,
      "eval_samples_per_second": 56.498,
      "eval_steps_per_second": 28.331,
      "step": 30
    },
    {
      "epoch": 0.042735042735042736,
      "grad_norm": 0.009910144843161106,
      "learning_rate": 3.086582838174551e-05,
      "loss": 11.9316,
      "step": 35
    },
    {
      "epoch": 0.04884004884004884,
      "grad_norm": 0.014119105413556099,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 11.9326,
      "step": 40
    },
    {
      "epoch": 0.04884004884004884,
      "eval_loss": 11.934100151062012,
      "eval_runtime": 6.0973,
      "eval_samples_per_second": 56.582,
      "eval_steps_per_second": 28.373,
      "step": 40
    },
    {
      "epoch": 0.054945054945054944,
      "grad_norm": 0.00930514745414257,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 11.9322,
      "step": 45
    },
    {
      "epoch": 0.06105006105006105,
      "grad_norm": 0.010311778634786606,
      "learning_rate": 0.0,
      "loss": 11.9343,
      "step": 50
    },
    {
      "epoch": 0.06105006105006105,
      "eval_loss": 11.934097290039062,
      "eval_runtime": 6.0342,
      "eval_samples_per_second": 57.174,
      "eval_steps_per_second": 28.67,
      "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": 5908070400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}