Hugging Face's logo

Best000
/
03f05a54-f711-4c98-940a-e06473c3786c

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
03f05a54-f711-4c98-940a-e06473c3786c
File size: 3,029 Bytes 
3f99d94
 
 
63c9912
3f99d94
63c9912
3f99d94
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f7089c9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63c9912
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3f99d94
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63c9912
3f99d94
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012738853503184714,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014154281670205238,
      "grad_norm": 0.35979539155960083,
      "learning_rate": 2e-05,
      "loss": 6.0737,
      "step": 1
    },
    {
      "epoch": 0.0014154281670205238,
      "eval_loss": 1.550566554069519,
      "eval_runtime": 31.4921,
      "eval_samples_per_second": 9.463,
      "eval_steps_per_second": 4.731,
      "step": 1
    },
    {
      "epoch": 0.0028308563340410475,
      "grad_norm": 0.3379415273666382,
      "learning_rate": 4e-05,
      "loss": 5.9829,
      "step": 2
    },
    {
      "epoch": 0.004246284501061571,
      "grad_norm": 0.41088634729385376,
      "learning_rate": 6e-05,
      "loss": 5.6532,
      "step": 3
    },
    {
      "epoch": 0.004246284501061571,
      "eval_loss": 1.5500292778015137,
      "eval_runtime": 31.4992,
      "eval_samples_per_second": 9.461,
      "eval_steps_per_second": 4.73,
      "step": 3
    },
    {
      "epoch": 0.005661712668082095,
      "grad_norm": 0.3271850347518921,
      "learning_rate": 8e-05,
      "loss": 6.2798,
      "step": 4
    },
    {
      "epoch": 0.007077140835102618,
      "grad_norm": 0.4017261266708374,
      "learning_rate": 0.0001,
      "loss": 6.1845,
      "step": 5
    },
    {
      "epoch": 0.008492569002123142,
      "grad_norm": 0.4634651839733124,
      "learning_rate": 0.00012,
      "loss": 6.5431,
      "step": 6
    },
    {
      "epoch": 0.008492569002123142,
      "eval_loss": 1.5396825075149536,
      "eval_runtime": 31.5091,
      "eval_samples_per_second": 9.458,
      "eval_steps_per_second": 4.729,
      "step": 6
    },
    {
      "epoch": 0.009907997169143666,
      "grad_norm": 0.45960116386413574,
      "learning_rate": 0.00014,
      "loss": 5.9549,
      "step": 7
    },
    {
      "epoch": 0.01132342533616419,
      "grad_norm": 0.64166259765625,
      "learning_rate": 0.00016,
      "loss": 6.081,
      "step": 8
    },
    {
      "epoch": 0.012738853503184714,
      "grad_norm": 0.6194164752960205,
      "learning_rate": 0.00018,
      "loss": 6.0523,
      "step": 9
    },
    {
      "epoch": 0.012738853503184714,
      "eval_loss": 1.4865055084228516,
      "eval_runtime": 31.5385,
      "eval_samples_per_second": 9.449,
      "eval_steps_per_second": 4.724,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5699203749642240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}