Hugging Face's logo

kostiantynk1205
/
b8990ad7-df54-4125-9382-53ba2814d151

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
b8990ad7-df54-4125-9382-53ba2814d151
File size: 2,975 Bytes 
26f9e67
 
 
44695ca
26f9e67
44695ca
26f9e67
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7aaaf1d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2a2bcfc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
44695ca
 
 
 
 
 
 
26f9e67
 
 
 
 
 
 
 
 
 
 
 
 
 
44695ca
26f9e67
 
 
 
44695ca
26f9e67
 
 
 
 
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": 0.0008437038599451593,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.437038599451593e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 8.437038599451593e-05,
      "eval_loss": NaN,
      "eval_runtime": 12.4091,
      "eval_samples_per_second": 402.204,
      "eval_steps_per_second": 201.142,
      "step": 1
    },
    {
      "epoch": 0.00016874077198903185,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0002531111579835478,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0002531111579835478,
      "eval_loss": NaN,
      "eval_runtime": 11.648,
      "eval_samples_per_second": 428.484,
      "eval_steps_per_second": 214.285,
      "step": 3
    },
    {
      "epoch": 0.0003374815439780637,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0004218519299725796,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0005062223159670956,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0005062223159670956,
      "eval_loss": NaN,
      "eval_runtime": 11.7815,
      "eval_samples_per_second": 423.629,
      "eval_steps_per_second": 211.857,
      "step": 6
    },
    {
      "epoch": 0.0005905927019616115,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0006749630879561274,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0007593334739506433,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0007593334739506433,
      "eval_loss": NaN,
      "eval_runtime": 11.6685,
      "eval_samples_per_second": 427.733,
      "eval_steps_per_second": 213.909,
      "step": 9
    },
    {
      "epoch": 0.0008437038599451593,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "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": 256648151040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}