Hugging Face's logo

trenden
/
63c7905c-f5ac-4fee-805a-a8e13f0f1a79

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
63c7905c-f5ac-4fee-805a-a8e13f0f1a79
File size: 3,217 Bytes 
a8bc019
 
 
59bb3f8
a8bc019
59bb3f8
a8bc019
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ec0efb8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6ce68c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59bb3f8
 
 
 
 
 
 
a8bc019
 
 
 
 
 
 
 
 
 
 
 
 
 
59bb3f8
a8bc019
 
 
 
59bb3f8
a8bc019
 
 
 
 
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": 0.005747952291995977,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005747952291995977,
      "grad_norm": 0.15190516412258148,
      "learning_rate": 2e-05,
      "loss": 10.4212,
      "step": 1
    },
    {
      "epoch": 0.0005747952291995977,
      "eval_loss": 10.403504371643066,
      "eval_runtime": 1.8462,
      "eval_samples_per_second": 397.04,
      "eval_steps_per_second": 198.791,
      "step": 1
    },
    {
      "epoch": 0.0011495904583991954,
      "grad_norm": 0.12761463224887848,
      "learning_rate": 4e-05,
      "loss": 10.4308,
      "step": 2
    },
    {
      "epoch": 0.001724385687598793,
      "grad_norm": 0.1444246619939804,
      "learning_rate": 6e-05,
      "loss": 10.3983,
      "step": 3
    },
    {
      "epoch": 0.001724385687598793,
      "eval_loss": 10.403398513793945,
      "eval_runtime": 1.8161,
      "eval_samples_per_second": 403.602,
      "eval_steps_per_second": 202.076,
      "step": 3
    },
    {
      "epoch": 0.0022991809167983907,
      "grad_norm": 0.14821669459342957,
      "learning_rate": 8e-05,
      "loss": 10.401,
      "step": 4
    },
    {
      "epoch": 0.0028739761459979883,
      "grad_norm": 0.17169639468193054,
      "learning_rate": 0.0001,
      "loss": 10.3765,
      "step": 5
    },
    {
      "epoch": 0.003448771375197586,
      "grad_norm": 0.19555452466011047,
      "learning_rate": 0.00012,
      "loss": 10.3845,
      "step": 6
    },
    {
      "epoch": 0.003448771375197586,
      "eval_loss": 10.402830123901367,
      "eval_runtime": 1.8997,
      "eval_samples_per_second": 385.849,
      "eval_steps_per_second": 193.188,
      "step": 6
    },
    {
      "epoch": 0.0040235666043971835,
      "grad_norm": 0.1419612467288971,
      "learning_rate": 0.00014,
      "loss": 10.4663,
      "step": 7
    },
    {
      "epoch": 0.0045983618335967815,
      "grad_norm": 0.13743838667869568,
      "learning_rate": 0.00016,
      "loss": 10.4017,
      "step": 8
    },
    {
      "epoch": 0.005173157062796379,
      "grad_norm": 0.15415261685848236,
      "learning_rate": 0.00018,
      "loss": 10.4247,
      "step": 9
    },
    {
      "epoch": 0.005173157062796379,
      "eval_loss": 10.401864051818848,
      "eval_runtime": 1.8876,
      "eval_samples_per_second": 388.331,
      "eval_steps_per_second": 194.43,
      "step": 9
    },
    {
      "epoch": 0.005747952291995977,
      "grad_norm": 0.2952269911766052,
      "learning_rate": 0.0002,
      "loss": 10.3284,
      "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": 129309081600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}