Hugging Face's logo

JacksonBrune
/
e59bf291-12d9-4153-99b1-f84d6ee9a666

PEFT
Safetensors
bloom
axolotl
Generated from Trainer
Model card Files Community
e59bf291-12d9-4153-99b1-f84d6ee9a666
File size: 3,201 Bytes 
8917003
 
 
dcea410
8917003
dcea410
8917003
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
459ac10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f7cccab
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dcea410
 
 
 
 
 
 
8917003
 
 
 
 
 
 
 
 
 
 
 
 
 
dcea410
8917003
 
 
 
dcea410
8917003
 
 
 
 
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": 0.004968326915911067,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004968326915911067,
      "grad_norm": 9.575961112976074,
      "learning_rate": 2e-05,
      "loss": 13.4967,
      "step": 1
    },
    {
      "epoch": 0.0004968326915911067,
      "eval_loss": 4.478808879852295,
      "eval_runtime": 9.6736,
      "eval_samples_per_second": 87.661,
      "eval_steps_per_second": 43.831,
      "step": 1
    },
    {
      "epoch": 0.0009936653831822133,
      "grad_norm": 14.79227066040039,
      "learning_rate": 4e-05,
      "loss": 18.8801,
      "step": 2
    },
    {
      "epoch": 0.0014904980747733202,
      "grad_norm": 11.625609397888184,
      "learning_rate": 6e-05,
      "loss": 16.0218,
      "step": 3
    },
    {
      "epoch": 0.0014904980747733202,
      "eval_loss": 4.443297863006592,
      "eval_runtime": 9.5987,
      "eval_samples_per_second": 88.345,
      "eval_steps_per_second": 44.173,
      "step": 3
    },
    {
      "epoch": 0.0019873307663644266,
      "grad_norm": 15.475156784057617,
      "learning_rate": 8e-05,
      "loss": 19.5836,
      "step": 4
    },
    {
      "epoch": 0.0024841634579555335,
      "grad_norm": 11.649445533752441,
      "learning_rate": 0.0001,
      "loss": 14.2257,
      "step": 5
    },
    {
      "epoch": 0.0029809961495466403,
      "grad_norm": 13.620771408081055,
      "learning_rate": 0.00012,
      "loss": 18.1914,
      "step": 6
    },
    {
      "epoch": 0.0029809961495466403,
      "eval_loss": 4.233336925506592,
      "eval_runtime": 9.9171,
      "eval_samples_per_second": 85.509,
      "eval_steps_per_second": 42.754,
      "step": 6
    },
    {
      "epoch": 0.0034778288411377468,
      "grad_norm": 10.729366302490234,
      "learning_rate": 0.00014,
      "loss": 16.1147,
      "step": 7
    },
    {
      "epoch": 0.003974661532728853,
      "grad_norm": 18.95943832397461,
      "learning_rate": 0.00016,
      "loss": 20.5381,
      "step": 8
    },
    {
      "epoch": 0.0044714942243199605,
      "grad_norm": 19.25127601623535,
      "learning_rate": 0.00018,
      "loss": 18.0612,
      "step": 9
    },
    {
      "epoch": 0.0044714942243199605,
      "eval_loss": 3.78324556350708,
      "eval_runtime": 9.6298,
      "eval_samples_per_second": 88.06,
      "eval_steps_per_second": 44.03,
      "step": 9
    },
    {
      "epoch": 0.004968326915911067,
      "grad_norm": 13.589359283447266,
      "learning_rate": 0.0002,
      "loss": 15.8584,
      "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": 75069652992000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}