Hugging Face's logo

kokovova
/
d0bdbcf6-ea3e-48d3-b1b4-ce0665ed4dd7

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
d0bdbcf6-ea3e-48d3-b1b4-ce0665ed4dd7
File size: 3,620 Bytes 
4736d05
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005963918294319368,
  "eval_steps": 2,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005963918294319368,
      "grad_norm": 1.5163764953613281,
      "learning_rate": 2e-05,
      "loss": 0.9264,
      "step": 1
    },
    {
      "epoch": 0.0005963918294319368,
      "eval_loss": 0.988461434841156,
      "eval_runtime": 77.0662,
      "eval_samples_per_second": 9.161,
      "eval_steps_per_second": 4.58,
      "step": 1
    },
    {
      "epoch": 0.0011927836588638736,
      "grad_norm": 1.2068827152252197,
      "learning_rate": 4e-05,
      "loss": 0.8253,
      "step": 2
    },
    {
      "epoch": 0.0011927836588638736,
      "eval_loss": 0.9857558012008667,
      "eval_runtime": 76.5737,
      "eval_samples_per_second": 9.22,
      "eval_steps_per_second": 4.61,
      "step": 2
    },
    {
      "epoch": 0.0017891754882958103,
      "grad_norm": 1.454573631286621,
      "learning_rate": 6e-05,
      "loss": 0.901,
      "step": 3
    },
    {
      "epoch": 0.0023855673177277472,
      "grad_norm": 1.681971788406372,
      "learning_rate": 8e-05,
      "loss": 1.0454,
      "step": 4
    },
    {
      "epoch": 0.0023855673177277472,
      "eval_loss": 0.9374808073043823,
      "eval_runtime": 76.5425,
      "eval_samples_per_second": 9.224,
      "eval_steps_per_second": 4.612,
      "step": 4
    },
    {
      "epoch": 0.002981959147159684,
      "grad_norm": 1.7881622314453125,
      "learning_rate": 0.0001,
      "loss": 0.8865,
      "step": 5
    },
    {
      "epoch": 0.0035783509765916206,
      "grad_norm": 1.8039438724517822,
      "learning_rate": 0.00012,
      "loss": 0.8906,
      "step": 6
    },
    {
      "epoch": 0.0035783509765916206,
      "eval_loss": 0.7199013829231262,
      "eval_runtime": 76.5601,
      "eval_samples_per_second": 9.222,
      "eval_steps_per_second": 4.611,
      "step": 6
    },
    {
      "epoch": 0.004174742806023557,
      "grad_norm": 1.78489351272583,
      "learning_rate": 0.00014,
      "loss": 0.8658,
      "step": 7
    },
    {
      "epoch": 0.0047711346354554944,
      "grad_norm": 1.3335764408111572,
      "learning_rate": 0.00016,
      "loss": 0.5989,
      "step": 8
    },
    {
      "epoch": 0.0047711346354554944,
      "eval_loss": 0.45117324590682983,
      "eval_runtime": 76.584,
      "eval_samples_per_second": 9.219,
      "eval_steps_per_second": 4.609,
      "step": 8
    },
    {
      "epoch": 0.005367526464887431,
      "grad_norm": 1.000693440437317,
      "learning_rate": 0.00018,
      "loss": 0.4353,
      "step": 9
    },
    {
      "epoch": 0.005963918294319368,
      "grad_norm": 0.9320959448814392,
      "learning_rate": 0.0002,
      "loss": 0.4002,
      "step": 10
    },
    {
      "epoch": 0.005963918294319368,
      "eval_loss": 0.33094078302383423,
      "eval_runtime": 76.5684,
      "eval_samples_per_second": 9.221,
      "eval_steps_per_second": 4.61,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "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": 6591291693465600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}