Hugging Face's logo

kostiantynk1205
/
3f6f4c11-4c0f-48e8-a711-5e3b38b07579

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
3f6f4c11-4c0f-48e8-a711-5e3b38b07579
File size: 3,227 Bytes 
d9dc690
 
 
5734483
d9dc690
5734483
d9dc690
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0b99006
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8a27cbe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5734483
 
 
 
 
 
 
d9dc690
 
 
 
 
 
 
 
 
 
 
 
 
 
5734483
d9dc690
 
 
 
5734483
d9dc690
 
 
 
 
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": 0.0047175374454534735,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00047175374454534735,
      "grad_norm": 0.02135482057929039,
      "learning_rate": 2e-05,
      "loss": 10.3884,
      "step": 1
    },
    {
      "epoch": 0.00047175374454534735,
      "eval_loss": 10.383219718933105,
      "eval_runtime": 3.2242,
      "eval_samples_per_second": 276.968,
      "eval_steps_per_second": 138.639,
      "step": 1
    },
    {
      "epoch": 0.0009435074890906947,
      "grad_norm": 0.05195602774620056,
      "learning_rate": 4e-05,
      "loss": 10.3795,
      "step": 2
    },
    {
      "epoch": 0.001415261233636042,
      "grad_norm": 0.026217341423034668,
      "learning_rate": 6e-05,
      "loss": 10.39,
      "step": 3
    },
    {
      "epoch": 0.001415261233636042,
      "eval_loss": 10.383208274841309,
      "eval_runtime": 3.2353,
      "eval_samples_per_second": 276.014,
      "eval_steps_per_second": 138.162,
      "step": 3
    },
    {
      "epoch": 0.0018870149781813894,
      "grad_norm": 0.023581691086292267,
      "learning_rate": 8e-05,
      "loss": 10.3762,
      "step": 4
    },
    {
      "epoch": 0.0023587687227267368,
      "grad_norm": 0.029611019417643547,
      "learning_rate": 0.0001,
      "loss": 10.3863,
      "step": 5
    },
    {
      "epoch": 0.002830522467272084,
      "grad_norm": 0.024547450244426727,
      "learning_rate": 0.00012,
      "loss": 10.377,
      "step": 6
    },
    {
      "epoch": 0.002830522467272084,
      "eval_loss": 10.383139610290527,
      "eval_runtime": 3.3048,
      "eval_samples_per_second": 270.213,
      "eval_steps_per_second": 135.258,
      "step": 6
    },
    {
      "epoch": 0.0033022762118174315,
      "grad_norm": 0.018600204959511757,
      "learning_rate": 0.00014,
      "loss": 10.3892,
      "step": 7
    },
    {
      "epoch": 0.003774029956362779,
      "grad_norm": 0.023554163053631783,
      "learning_rate": 0.00016,
      "loss": 10.3856,
      "step": 8
    },
    {
      "epoch": 0.004245783700908126,
      "grad_norm": 0.01966540701687336,
      "learning_rate": 0.00018,
      "loss": 10.3806,
      "step": 9
    },
    {
      "epoch": 0.004245783700908126,
      "eval_loss": 10.38302230834961,
      "eval_runtime": 3.2947,
      "eval_samples_per_second": 271.045,
      "eval_steps_per_second": 135.674,
      "step": 9
    },
    {
      "epoch": 0.0047175374454534735,
      "grad_norm": 0.02262878604233265,
      "learning_rate": 0.0002,
      "loss": 10.379,
      "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": 258618163200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}