Hugging Face's logo

sergioalves
/
2add043c-9088-4917-9cf1-b28940acc57a

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
2add043c-9088-4917-9cf1-b28940acc57a
File size: 3,071 Bytes 
878963a
ad37001
 
 
878963a
ad37001
878963a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ad37001
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
878963a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ad37001
878963a
 
 
 
 
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
 
{
  "best_metric": 2.66746187210083,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.003270913402567667,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016354567012838336,
      "eval_loss": 4.267529487609863,
      "eval_runtime": 507.3022,
      "eval_samples_per_second": 5.076,
      "eval_steps_per_second": 2.539,
      "step": 1
    },
    {
      "epoch": 0.00049063701038515,
      "grad_norm": 1.061664342880249,
      "learning_rate": 3e-05,
      "loss": 3.8929,
      "step": 3
    },
    {
      "epoch": 0.0008177283506419167,
      "eval_loss": 4.160350322723389,
      "eval_runtime": 510.5273,
      "eval_samples_per_second": 5.044,
      "eval_steps_per_second": 2.523,
      "step": 5
    },
    {
      "epoch": 0.0009812740207703,
      "grad_norm": 1.6031444072723389,
      "learning_rate": 6e-05,
      "loss": 4.122,
      "step": 6
    },
    {
      "epoch": 0.0014719110311554502,
      "grad_norm": 1.1639562845230103,
      "learning_rate": 9e-05,
      "loss": 3.4398,
      "step": 9
    },
    {
      "epoch": 0.0016354567012838335,
      "eval_loss": 3.4370737075805664,
      "eval_runtime": 510.509,
      "eval_samples_per_second": 5.044,
      "eval_steps_per_second": 2.523,
      "step": 10
    },
    {
      "epoch": 0.0019625480415406,
      "grad_norm": 1.746925711631775,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.4661,
      "step": 12
    },
    {
      "epoch": 0.0024531850519257502,
      "grad_norm": 1.3604792356491089,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.7556,
      "step": 15
    },
    {
      "epoch": 0.0024531850519257502,
      "eval_loss": 2.8416481018066406,
      "eval_runtime": 510.5806,
      "eval_samples_per_second": 5.043,
      "eval_steps_per_second": 2.523,
      "step": 15
    },
    {
      "epoch": 0.0029438220623109004,
      "grad_norm": 1.0310943126678467,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.6629,
      "step": 18
    },
    {
      "epoch": 0.003270913402567667,
      "eval_loss": 2.66746187210083,
      "eval_runtime": 510.8032,
      "eval_samples_per_second": 5.041,
      "eval_steps_per_second": 2.522,
      "step": 20
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2695579394048e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}