Hugging Face's logo

chauhoang
/
9368a66a-7812-42d5-82b5-91eddf3aa1d4

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
9368a66a-7812-42d5-82b5-91eddf3aa1d4
File size: 3,718 Bytes 
6a0f0f6
 
 
12f755e
8a5a09f
12f755e
6a0f0f6
 
 
 
 
 
 
8a5a09f
 
 
6a0f0f6
8a5a09f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d041205
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
09d8fd5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12f755e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6a0f0f6
 
 
8a5a09f
6a0f0f6
 
8a5a09f
6a0f0f6
 
 
 
 
 
 
12f755e
6a0f0f6
 
 
 
12f755e
6a0f0f6
 
 
 
 
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": 0.02056343820686819,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00041126876413736374,
      "eval_loss": 1.1108553409576416,
      "eval_runtime": 27.293,
      "eval_samples_per_second": 37.519,
      "eval_steps_per_second": 18.759,
      "step": 1
    },
    {
      "epoch": 0.002056343820686819,
      "grad_norm": 1.055071234703064,
      "learning_rate": 5e-05,
      "loss": 1.0573,
      "step": 5
    },
    {
      "epoch": 0.004112687641373638,
      "grad_norm": 1.6324950456619263,
      "learning_rate": 0.0001,
      "loss": 1.0706,
      "step": 10
    },
    {
      "epoch": 0.004112687641373638,
      "eval_loss": 0.989827573299408,
      "eval_runtime": 27.3354,
      "eval_samples_per_second": 37.461,
      "eval_steps_per_second": 18.73,
      "step": 10
    },
    {
      "epoch": 0.006169031462060457,
      "grad_norm": 1.3293852806091309,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.866,
      "step": 15
    },
    {
      "epoch": 0.008225375282747275,
      "grad_norm": 1.1884467601776123,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8083,
      "step": 20
    },
    {
      "epoch": 0.008225375282747275,
      "eval_loss": 0.661908745765686,
      "eval_runtime": 27.2106,
      "eval_samples_per_second": 37.632,
      "eval_steps_per_second": 18.816,
      "step": 20
    },
    {
      "epoch": 0.010281719103434095,
      "grad_norm": 1.6942882537841797,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.6215,
      "step": 25
    },
    {
      "epoch": 0.012338062924120914,
      "grad_norm": 1.4033981561660767,
      "learning_rate": 5e-05,
      "loss": 0.5869,
      "step": 30
    },
    {
      "epoch": 0.012338062924120914,
      "eval_loss": 0.6099783182144165,
      "eval_runtime": 27.1649,
      "eval_samples_per_second": 37.696,
      "eval_steps_per_second": 18.848,
      "step": 30
    },
    {
      "epoch": 0.014394406744807731,
      "grad_norm": 1.5280038118362427,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.5931,
      "step": 35
    },
    {
      "epoch": 0.01645075056549455,
      "grad_norm": 1.2525250911712646,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.5129,
      "step": 40
    },
    {
      "epoch": 0.01645075056549455,
      "eval_loss": 0.589495062828064,
      "eval_runtime": 27.3301,
      "eval_samples_per_second": 37.468,
      "eval_steps_per_second": 18.734,
      "step": 40
    },
    {
      "epoch": 0.01850709438618137,
      "grad_norm": 1.1442337036132812,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.6124,
      "step": 45
    },
    {
      "epoch": 0.02056343820686819,
      "grad_norm": 0.9440557360649109,
      "learning_rate": 0.0,
      "loss": 0.5675,
      "step": 50
    },
    {
      "epoch": 0.02056343820686819,
      "eval_loss": 0.5864447355270386,
      "eval_runtime": 27.3552,
      "eval_samples_per_second": 37.434,
      "eval_steps_per_second": 18.717,
      "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": 1202727577190400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}