Hugging Face's logo

filipesantoscv11
/
49c6d079-0cb3-45db-99ff-c391e569697e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
49c6d079-0cb3-45db-99ff-c391e569697e
File size: 2,849 Bytes 
772be27
 
 
8f2088b
772be27
8f2088b
772be27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8f2088b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
772be27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8f2088b
772be27
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006005735477380899,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.0028677386904494e-05,
      "eval_loss": 1.0328869819641113,
      "eval_runtime": 1647.1723,
      "eval_samples_per_second": 8.513,
      "eval_steps_per_second": 4.256,
      "step": 1
    },
    {
      "epoch": 9.008603216071348e-05,
      "grad_norm": 0.2662915587425232,
      "learning_rate": 3e-05,
      "loss": 0.965,
      "step": 3
    },
    {
      "epoch": 0.00015014338693452247,
      "eval_loss": 1.0183448791503906,
      "eval_runtime": 1647.4187,
      "eval_samples_per_second": 8.511,
      "eval_steps_per_second": 4.256,
      "step": 5
    },
    {
      "epoch": 0.00018017206432142696,
      "grad_norm": 0.44537869095802307,
      "learning_rate": 6e-05,
      "loss": 0.9669,
      "step": 6
    },
    {
      "epoch": 0.0002702580964821404,
      "grad_norm": 0.6517441868782043,
      "learning_rate": 9e-05,
      "loss": 0.9603,
      "step": 9
    },
    {
      "epoch": 0.00030028677386904494,
      "eval_loss": 0.8726487159729004,
      "eval_runtime": 1647.1028,
      "eval_samples_per_second": 8.513,
      "eval_steps_per_second": 4.257,
      "step": 10
    },
    {
      "epoch": 0.00036034412864285393,
      "grad_norm": 0.27762144804000854,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7966,
      "step": 12
    },
    {
      "epoch": 0.0004504301608035674,
      "grad_norm": 0.4063872694969177,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.7659,
      "step": 15
    },
    {
      "epoch": 0.0004504301608035674,
      "eval_loss": 0.7490118741989136,
      "eval_runtime": 1647.3075,
      "eval_samples_per_second": 8.512,
      "eval_steps_per_second": 4.256,
      "step": 15
    },
    {
      "epoch": 0.0005405161929642808,
      "grad_norm": 0.29023927450180054,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7313,
      "step": 18
    },
    {
      "epoch": 0.0006005735477380899,
      "eval_loss": 0.6987407803535461,
      "eval_runtime": 1647.474,
      "eval_samples_per_second": 8.511,
      "eval_steps_per_second": 4.256,
      "step": 20
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.68216426971136e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}