Hugging Face's logo

great0001
/
ffeb776e-f2e1-459f-a5e5-936d255d0724

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
ffeb776e-f2e1-459f-a5e5-936d255d0724
File size: 3,229 Bytes 
9b02774
 
 
17bc429
9b02774
17bc429
9b02774
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a6f7925
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22d6304
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17bc429
 
 
 
 
 
 
9b02774
 
 
 
 
 
 
 
 
 
 
 
 
 
17bc429
9b02774
 
 
 
17bc429
9b02774
 
 
 
 
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": 0.00030028677386904494,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.0028677386904494e-05,
      "grad_norm": 0.19791345298290253,
      "learning_rate": 2e-05,
      "loss": 0.3476,
      "step": 1
    },
    {
      "epoch": 3.0028677386904494e-05,
      "eval_loss": 0.3906751573085785,
      "eval_runtime": 1090.9151,
      "eval_samples_per_second": 12.853,
      "eval_steps_per_second": 6.427,
      "step": 1
    },
    {
      "epoch": 6.005735477380899e-05,
      "grad_norm": 0.3280632793903351,
      "learning_rate": 4e-05,
      "loss": 0.5332,
      "step": 2
    },
    {
      "epoch": 9.008603216071348e-05,
      "grad_norm": 0.1621210128068924,
      "learning_rate": 6e-05,
      "loss": 0.2819,
      "step": 3
    },
    {
      "epoch": 9.008603216071348e-05,
      "eval_loss": 0.38882192969322205,
      "eval_runtime": 1090.3311,
      "eval_samples_per_second": 12.86,
      "eval_steps_per_second": 6.43,
      "step": 3
    },
    {
      "epoch": 0.00012011470954761798,
      "grad_norm": 0.27617770433425903,
      "learning_rate": 8e-05,
      "loss": 0.3775,
      "step": 4
    },
    {
      "epoch": 0.00015014338693452247,
      "grad_norm": 0.33552882075309753,
      "learning_rate": 0.0001,
      "loss": 0.3013,
      "step": 5
    },
    {
      "epoch": 0.00018017206432142696,
      "grad_norm": 0.31797710061073303,
      "learning_rate": 0.00012,
      "loss": 0.4089,
      "step": 6
    },
    {
      "epoch": 0.00018017206432142696,
      "eval_loss": 0.3593178689479828,
      "eval_runtime": 1091.0548,
      "eval_samples_per_second": 12.852,
      "eval_steps_per_second": 6.426,
      "step": 6
    },
    {
      "epoch": 0.00021020074170833146,
      "grad_norm": 0.25119438767433167,
      "learning_rate": 0.00014,
      "loss": 0.3608,
      "step": 7
    },
    {
      "epoch": 0.00024022941909523595,
      "grad_norm": 0.3067934811115265,
      "learning_rate": 0.00016,
      "loss": 0.2599,
      "step": 8
    },
    {
      "epoch": 0.0002702580964821404,
      "grad_norm": 0.5508508682250977,
      "learning_rate": 0.00018,
      "loss": 0.2038,
      "step": 9
    },
    {
      "epoch": 0.0002702580964821404,
      "eval_loss": 0.2343360334634781,
      "eval_runtime": 1089.6604,
      "eval_samples_per_second": 12.868,
      "eval_steps_per_second": 6.434,
      "step": 9
    },
    {
      "epoch": 0.00030028677386904494,
      "grad_norm": 0.4653288722038269,
      "learning_rate": 0.0002,
      "loss": 0.3119,
      "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": 5540857302220800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}