Hugging Face's logo

VERSIL91
/
76e4febb-f98d-4874-bafc-52ccf4d4a570

PEFT
Safetensors
bloom
axolotl
Generated from Trainer
Model card Files Community
76e4febb-f98d-4874-bafc-52ccf4d4a570
File size: 2,912 Bytes 
284860a
 
 
00a8982
284860a
00a8982
284860a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0c74fe5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bbe998d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
00a8982
 
 
 
 
 
 
284860a
 
 
 
 
 
 
 
 
 
 
 
 
 
00a8982
284860a
 
 
 
00a8982
284860a
 
 
 
 
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": 1.08843537414966,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10884353741496598,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.10884353741496598,
      "eval_loss": NaN,
      "eval_runtime": 25.2352,
      "eval_samples_per_second": 0.634,
      "eval_steps_per_second": 0.317,
      "step": 1
    },
    {
      "epoch": 0.21768707482993196,
      "grad_norm": 0.0,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 0.0,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.32653061224489793,
      "eval_loss": NaN,
      "eval_runtime": 0.1076,
      "eval_samples_per_second": 148.701,
      "eval_steps_per_second": 74.35,
      "step": 3
    },
    {
      "epoch": 0.43537414965986393,
      "grad_norm": 0.0,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.54421768707483,
      "grad_norm": 0.0,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.6530612244897959,
      "grad_norm": 0.0,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.6530612244897959,
      "eval_loss": NaN,
      "eval_runtime": 0.1087,
      "eval_samples_per_second": 147.223,
      "eval_steps_per_second": 73.612,
      "step": 6
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.0,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.8707482993197279,
      "grad_norm": 0.0,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.9795918367346939,
      "grad_norm": 0.0,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.9795918367346939,
      "eval_loss": NaN,
      "eval_runtime": 0.1058,
      "eval_samples_per_second": 151.27,
      "eval_steps_per_second": 75.635,
      "step": 9
    },
    {
      "epoch": 1.08843537414966,
      "grad_norm": 0.0,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 300278611968000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}