Hugging Face's logo

filipesantoscv11
/
bed2b6e0-2296-4859-a94c-cfb7b90a1d58

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
bed2b6e0-2296-4859-a94c-cfb7b90a1d58
File size: 2,827 Bytes 
3388030
 
 
d81947e
3388030
d81947e
3388030
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d81947e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3388030
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d81947e
3388030
 
 
 
 
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": 0.031189083820662766,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015594541910331384,
      "eval_loss": 1.508385419845581,
      "eval_runtime": 26.969,
      "eval_samples_per_second": 10.049,
      "eval_steps_per_second": 5.043,
      "step": 1
    },
    {
      "epoch": 0.004678362573099415,
      "grad_norm": 0.39213576912879944,
      "learning_rate": 3e-05,
      "loss": 1.5605,
      "step": 3
    },
    {
      "epoch": 0.007797270955165692,
      "eval_loss": 1.4978253841400146,
      "eval_runtime": 26.4506,
      "eval_samples_per_second": 10.246,
      "eval_steps_per_second": 5.142,
      "step": 5
    },
    {
      "epoch": 0.00935672514619883,
      "grad_norm": 0.36995622515678406,
      "learning_rate": 6e-05,
      "loss": 1.4723,
      "step": 6
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 0.3752123713493347,
      "learning_rate": 9e-05,
      "loss": 1.3854,
      "step": 9
    },
    {
      "epoch": 0.015594541910331383,
      "eval_loss": 1.4332730770111084,
      "eval_runtime": 26.4493,
      "eval_samples_per_second": 10.246,
      "eval_steps_per_second": 5.142,
      "step": 10
    },
    {
      "epoch": 0.01871345029239766,
      "grad_norm": 0.3255695104598999,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.3539,
      "step": 12
    },
    {
      "epoch": 0.023391812865497075,
      "grad_norm": 0.2485169768333435,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.3517,
      "step": 15
    },
    {
      "epoch": 0.023391812865497075,
      "eval_loss": 1.3882832527160645,
      "eval_runtime": 26.4826,
      "eval_samples_per_second": 10.233,
      "eval_steps_per_second": 5.135,
      "step": 15
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": 0.3311094343662262,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.4781,
      "step": 18
    },
    {
      "epoch": 0.031189083820662766,
      "eval_loss": 1.3644858598709106,
      "eval_runtime": 26.4672,
      "eval_samples_per_second": 10.239,
      "eval_steps_per_second": 5.138,
      "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": 1.1680565359017984e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}