Hugging Face's logo

lesso
/
f15b3006-e1c8-4c7c-8a98-bc85290389da

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
f15b3006-e1c8-4c7c-8a98-bc85290389da
File size: 3,179 Bytes 
79382de
 
 
95083ae
79382de
95083ae
79382de
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b807d58
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
983d714
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
95083ae
 
 
 
 
 
 
79382de
 
 
 
 
 
 
 
 
 
 
 
 
 
95083ae
79382de
 
 
 
95083ae
79382de
 
 
 
 
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": 0.026281208935611037,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002628120893561104,
      "grad_norm": 1.3634989261627197,
      "learning_rate": 2e-05,
      "loss": 3.5272,
      "step": 1
    },
    {
      "epoch": 0.002628120893561104,
      "eval_loss": 3.377916097640991,
      "eval_runtime": 11.2615,
      "eval_samples_per_second": 14.296,
      "eval_steps_per_second": 7.193,
      "step": 1
    },
    {
      "epoch": 0.005256241787122208,
      "grad_norm": 1.4552209377288818,
      "learning_rate": 4e-05,
      "loss": 3.5758,
      "step": 2
    },
    {
      "epoch": 0.00788436268068331,
      "grad_norm": 1.2623372077941895,
      "learning_rate": 6e-05,
      "loss": 3.3248,
      "step": 3
    },
    {
      "epoch": 0.00788436268068331,
      "eval_loss": 3.3656370639801025,
      "eval_runtime": 11.1958,
      "eval_samples_per_second": 14.38,
      "eval_steps_per_second": 7.235,
      "step": 3
    },
    {
      "epoch": 0.010512483574244415,
      "grad_norm": 1.6191483736038208,
      "learning_rate": 8e-05,
      "loss": 3.4872,
      "step": 4
    },
    {
      "epoch": 0.013140604467805518,
      "grad_norm": 1.4146218299865723,
      "learning_rate": 0.0001,
      "loss": 3.1748,
      "step": 5
    },
    {
      "epoch": 0.01576872536136662,
      "grad_norm": 1.7842243909835815,
      "learning_rate": 0.00012,
      "loss": 3.2239,
      "step": 6
    },
    {
      "epoch": 0.01576872536136662,
      "eval_loss": 3.25826358795166,
      "eval_runtime": 11.3071,
      "eval_samples_per_second": 14.239,
      "eval_steps_per_second": 7.164,
      "step": 6
    },
    {
      "epoch": 0.018396846254927726,
      "grad_norm": 1.9601093530654907,
      "learning_rate": 0.00014,
      "loss": 3.2528,
      "step": 7
    },
    {
      "epoch": 0.02102496714848883,
      "grad_norm": 1.72002375125885,
      "learning_rate": 0.00016,
      "loss": 2.8813,
      "step": 8
    },
    {
      "epoch": 0.023653088042049936,
      "grad_norm": 1.4412205219268799,
      "learning_rate": 0.00018,
      "loss": 2.7633,
      "step": 9
    },
    {
      "epoch": 0.023653088042049936,
      "eval_loss": 3.0437607765197754,
      "eval_runtime": 11.297,
      "eval_samples_per_second": 14.252,
      "eval_steps_per_second": 7.17,
      "step": 9
    },
    {
      "epoch": 0.026281208935611037,
      "grad_norm": 1.9171342849731445,
      "learning_rate": 0.0002,
      "loss": 2.8412,
      "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": 3699128496291840.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}