Hugging Face's logo

philip-hightech
/
0a0f213e-837c-4674-9411-ee4ec5bf2503

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
0a0f213e-837c-4674-9411-ee4ec5bf2503
File size: 3,044 Bytes 
a1e85ca
 
 
1b5f367
a1e85ca
1b5f367
a1e85ca
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ef1dc97
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1b5f367
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a1e85ca
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1b5f367
a1e85ca
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0013986013986013986,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001554001554001554,
      "grad_norm": 2.461033582687378,
      "learning_rate": 2e-05,
      "loss": 5.5903,
      "step": 1
    },
    {
      "epoch": 0.0001554001554001554,
      "eval_loss": 5.979092121124268,
      "eval_runtime": 118.7787,
      "eval_samples_per_second": 22.816,
      "eval_steps_per_second": 11.408,
      "step": 1
    },
    {
      "epoch": 0.0003108003108003108,
      "grad_norm": 1.8061084747314453,
      "learning_rate": 4e-05,
      "loss": 4.2089,
      "step": 2
    },
    {
      "epoch": 0.0004662004662004662,
      "grad_norm": 2.806514024734497,
      "learning_rate": 6e-05,
      "loss": 5.928,
      "step": 3
    },
    {
      "epoch": 0.0004662004662004662,
      "eval_loss": 5.9718146324157715,
      "eval_runtime": 117.4419,
      "eval_samples_per_second": 23.075,
      "eval_steps_per_second": 11.538,
      "step": 3
    },
    {
      "epoch": 0.0006216006216006216,
      "grad_norm": 2.470583200454712,
      "learning_rate": 8e-05,
      "loss": 6.3336,
      "step": 4
    },
    {
      "epoch": 0.000777000777000777,
      "grad_norm": 1.9067507982254028,
      "learning_rate": 0.0001,
      "loss": 4.3592,
      "step": 5
    },
    {
      "epoch": 0.0009324009324009324,
      "grad_norm": 3.4067890644073486,
      "learning_rate": 0.00012,
      "loss": 5.8512,
      "step": 6
    },
    {
      "epoch": 0.0009324009324009324,
      "eval_loss": 5.809554576873779,
      "eval_runtime": 117.4521,
      "eval_samples_per_second": 23.073,
      "eval_steps_per_second": 11.537,
      "step": 6
    },
    {
      "epoch": 0.0010878010878010878,
      "grad_norm": 2.6836624145507812,
      "learning_rate": 0.00014,
      "loss": 4.7178,
      "step": 7
    },
    {
      "epoch": 0.0012432012432012432,
      "grad_norm": 3.25949764251709,
      "learning_rate": 0.00016,
      "loss": 5.602,
      "step": 8
    },
    {
      "epoch": 0.0013986013986013986,
      "grad_norm": 3.4510438442230225,
      "learning_rate": 0.00018,
      "loss": 4.7354,
      "step": 9
    },
    {
      "epoch": 0.0013986013986013986,
      "eval_loss": 5.102389335632324,
      "eval_runtime": 117.4294,
      "eval_samples_per_second": 23.078,
      "eval_steps_per_second": 11.539,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2450672628793344.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}