Hugging Face's logo

lesso06
/
94797c98-d8ba-4067-81cb-1908126d5327

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
94797c98-d8ba-4067-81cb-1908126d5327
File size: 3,220 Bytes 
de6524f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 1.1311993598937988,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.01059322033898305,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001059322033898305,
      "grad_norm": 1.1843385696411133,
      "learning_rate": 2e-05,
      "loss": 6.9729,
      "step": 1
    },
    {
      "epoch": 0.001059322033898305,
      "eval_loss": 1.7519381046295166,
      "eval_runtime": 62.8857,
      "eval_samples_per_second": 6.329,
      "eval_steps_per_second": 3.164,
      "step": 1
    },
    {
      "epoch": 0.00211864406779661,
      "grad_norm": 1.2905192375183105,
      "learning_rate": 4e-05,
      "loss": 7.1004,
      "step": 2
    },
    {
      "epoch": 0.0031779661016949155,
      "grad_norm": 1.0775989294052124,
      "learning_rate": 6e-05,
      "loss": 6.7495,
      "step": 3
    },
    {
      "epoch": 0.00423728813559322,
      "grad_norm": 1.23506498336792,
      "learning_rate": 8e-05,
      "loss": 7.1814,
      "step": 4
    },
    {
      "epoch": 0.005296610169491525,
      "grad_norm": 1.3882372379302979,
      "learning_rate": 0.0001,
      "loss": 6.7127,
      "step": 5
    },
    {
      "epoch": 0.005296610169491525,
      "eval_loss": 1.679090142250061,
      "eval_runtime": 60.2715,
      "eval_samples_per_second": 6.603,
      "eval_steps_per_second": 3.302,
      "step": 5
    },
    {
      "epoch": 0.006355932203389831,
      "grad_norm": 1.625010371208191,
      "learning_rate": 0.00012,
      "loss": 6.3487,
      "step": 6
    },
    {
      "epoch": 0.007415254237288136,
      "grad_norm": 2.2204973697662354,
      "learning_rate": 0.00014,
      "loss": 6.4336,
      "step": 7
    },
    {
      "epoch": 0.00847457627118644,
      "grad_norm": 2.3018980026245117,
      "learning_rate": 0.00016,
      "loss": 5.7187,
      "step": 8
    },
    {
      "epoch": 0.009533898305084746,
      "grad_norm": 2.3406448364257812,
      "learning_rate": 0.00018,
      "loss": 6.1801,
      "step": 9
    },
    {
      "epoch": 0.01059322033898305,
      "grad_norm": 2.687272548675537,
      "learning_rate": 0.0002,
      "loss": 4.7409,
      "step": 10
    },
    {
      "epoch": 0.01059322033898305,
      "eval_loss": 1.1311993598937988,
      "eval_runtime": 59.8086,
      "eval_samples_per_second": 6.655,
      "eval_steps_per_second": 3.327,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3137325131366400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}