Hugging Face's logo

leixa
/
e15bb719-ea8f-46ea-8290-e5573063df0e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
e15bb719-ea8f-46ea-8290-e5573063df0e
File size: 3,541 Bytes 
04c34d4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13680781758957655,
  "eval_steps": 42,
  "global_step": 42,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003257328990228013,
      "eval_loss": 6.045982360839844,
      "eval_runtime": 22.8171,
      "eval_samples_per_second": 22.658,
      "eval_steps_per_second": 5.697,
      "step": 1
    },
    {
      "epoch": 0.009771986970684038,
      "grad_norm": 7.921604633331299,
      "learning_rate": 3e-05,
      "loss": 5.6539,
      "step": 3
    },
    {
      "epoch": 0.019543973941368076,
      "grad_norm": 8.00938606262207,
      "learning_rate": 6e-05,
      "loss": 4.9183,
      "step": 6
    },
    {
      "epoch": 0.029315960912052116,
      "grad_norm": 7.276914596557617,
      "learning_rate": 9e-05,
      "loss": 3.1081,
      "step": 9
    },
    {
      "epoch": 0.03908794788273615,
      "grad_norm": 4.77871036529541,
      "learning_rate": 9.999588943391597e-05,
      "loss": 2.5988,
      "step": 12
    },
    {
      "epoch": 0.048859934853420196,
      "grad_norm": 4.304369926452637,
      "learning_rate": 9.99743108100344e-05,
      "loss": 2.3816,
      "step": 15
    },
    {
      "epoch": 0.05863192182410423,
      "grad_norm": 4.264029502868652,
      "learning_rate": 9.993424445916923e-05,
      "loss": 2.302,
      "step": 18
    },
    {
      "epoch": 0.06840390879478828,
      "grad_norm": 3.8603391647338867,
      "learning_rate": 9.987570520365104e-05,
      "loss": 2.205,
      "step": 21
    },
    {
      "epoch": 0.0781758957654723,
      "grad_norm": 3.673312187194824,
      "learning_rate": 9.979871469976196e-05,
      "loss": 1.9937,
      "step": 24
    },
    {
      "epoch": 0.08794788273615635,
      "grad_norm": 3.670795202255249,
      "learning_rate": 9.970330142972401e-05,
      "loss": 1.9628,
      "step": 27
    },
    {
      "epoch": 0.09771986970684039,
      "grad_norm": 4.024224281311035,
      "learning_rate": 9.95895006911623e-05,
      "loss": 1.9128,
      "step": 30
    },
    {
      "epoch": 0.10749185667752444,
      "grad_norm": 3.246854782104492,
      "learning_rate": 9.945735458404681e-05,
      "loss": 1.8845,
      "step": 33
    },
    {
      "epoch": 0.11726384364820847,
      "grad_norm": 3.4581379890441895,
      "learning_rate": 9.930691199511775e-05,
      "loss": 1.7264,
      "step": 36
    },
    {
      "epoch": 0.1270358306188925,
      "grad_norm": 3.0552656650543213,
      "learning_rate": 9.91382285798002e-05,
      "loss": 1.6868,
      "step": 39
    },
    {
      "epoch": 0.13680781758957655,
      "grad_norm": 2.96836519241333,
      "learning_rate": 9.895136674161465e-05,
      "loss": 1.7595,
      "step": 42
    },
    {
      "epoch": 0.13680781758957655,
      "eval_loss": 1.7990862131118774,
      "eval_runtime": 22.1331,
      "eval_samples_per_second": 23.359,
      "eval_steps_per_second": 5.874,
      "step": 42
    }
  ],
  "logging_steps": 3,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 42,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.1678785153662976e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}