Hugging Face's logo

lesso
/
a876cc0f-a872-4b1d-976d-a66f4d406648

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
a876cc0f-a872-4b1d-976d-a66f4d406648
File size: 3,208 Bytes 
93c2370
 
 
b8a6cd4
93c2370
b8a6cd4
93c2370
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
911b4c9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3201a23
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b8a6cd4
 
 
 
 
 
 
93c2370
 
 
 
 
 
 
 
 
 
 
 
 
 
b8a6cd4
93c2370
 
 
 
b8a6cd4
93c2370
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0023949227637408694,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00023949227637408692,
      "grad_norm": 4.3014726638793945,
      "learning_rate": 2e-05,
      "loss": 2.4864,
      "step": 1
    },
    {
      "epoch": 0.00023949227637408692,
      "eval_loss": 3.196671962738037,
      "eval_runtime": 56.3772,
      "eval_samples_per_second": 15.609,
      "eval_steps_per_second": 15.609,
      "step": 1
    },
    {
      "epoch": 0.00047898455274817384,
      "grad_norm": 3.2757163047790527,
      "learning_rate": 4e-05,
      "loss": 3.3358,
      "step": 2
    },
    {
      "epoch": 0.0007184768291222608,
      "grad_norm": 2.781923294067383,
      "learning_rate": 6e-05,
      "loss": 3.3958,
      "step": 3
    },
    {
      "epoch": 0.0007184768291222608,
      "eval_loss": 3.0978620052337646,
      "eval_runtime": 57.0247,
      "eval_samples_per_second": 15.432,
      "eval_steps_per_second": 15.432,
      "step": 3
    },
    {
      "epoch": 0.0009579691054963477,
      "grad_norm": 2.6946146488189697,
      "learning_rate": 8e-05,
      "loss": 2.7689,
      "step": 4
    },
    {
      "epoch": 0.0011974613818704347,
      "grad_norm": 3.1957530975341797,
      "learning_rate": 0.0001,
      "loss": 2.8025,
      "step": 5
    },
    {
      "epoch": 0.0014369536582445215,
      "grad_norm": 2.734419584274292,
      "learning_rate": 0.00012,
      "loss": 1.8246,
      "step": 6
    },
    {
      "epoch": 0.0014369536582445215,
      "eval_loss": 2.6213483810424805,
      "eval_runtime": 57.0839,
      "eval_samples_per_second": 15.416,
      "eval_steps_per_second": 15.416,
      "step": 6
    },
    {
      "epoch": 0.0016764459346186086,
      "grad_norm": 2.242945909500122,
      "learning_rate": 0.00014,
      "loss": 2.6675,
      "step": 7
    },
    {
      "epoch": 0.0019159382109926954,
      "grad_norm": 1.637675404548645,
      "learning_rate": 0.00016,
      "loss": 1.9593,
      "step": 8
    },
    {
      "epoch": 0.0021554304873667826,
      "grad_norm": 1.1237943172454834,
      "learning_rate": 0.00018,
      "loss": 1.7248,
      "step": 9
    },
    {
      "epoch": 0.0021554304873667826,
      "eval_loss": 2.173261880874634,
      "eval_runtime": 57.6011,
      "eval_samples_per_second": 15.277,
      "eval_steps_per_second": 15.277,
      "step": 9
    },
    {
      "epoch": 0.0023949227637408694,
      "grad_norm": 1.9361770153045654,
      "learning_rate": 0.0002,
      "loss": 1.5842,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1643164226027520.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}