Hugging Face's logo

ClarenceDan
/
b7b5aa07-d3be-4882-a0b0-4d460dda730c

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
b7b5aa07-d3be-4882-a0b0-4d460dda730c
File size: 3,195 Bytes 
99c7846
 
 
b95e57d
99c7846
b95e57d
99c7846
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
af4c050
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ba04310
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b95e57d
 
 
 
 
 
 
99c7846
 
 
 
 
 
 
 
 
 
 
 
 
 
b95e57d
99c7846
 
 
 
b95e57d
99c7846
 
 
 
 
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": 0.001886080724254998,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001886080724254998,
      "grad_norm": 11.620072364807129,
      "learning_rate": 2e-05,
      "loss": 3.832,
      "step": 1
    },
    {
      "epoch": 0.0001886080724254998,
      "eval_loss": 1.0258384943008423,
      "eval_runtime": 72.4949,
      "eval_samples_per_second": 30.802,
      "eval_steps_per_second": 15.408,
      "step": 1
    },
    {
      "epoch": 0.0003772161448509996,
      "grad_norm": 9.528853416442871,
      "learning_rate": 4e-05,
      "loss": 3.3093,
      "step": 2
    },
    {
      "epoch": 0.0005658242172764995,
      "grad_norm": 9.460070610046387,
      "learning_rate": 6e-05,
      "loss": 3.2833,
      "step": 3
    },
    {
      "epoch": 0.0005658242172764995,
      "eval_loss": 1.0034009218215942,
      "eval_runtime": 70.92,
      "eval_samples_per_second": 31.486,
      "eval_steps_per_second": 15.75,
      "step": 3
    },
    {
      "epoch": 0.0007544322897019992,
      "grad_norm": 9.758016586303711,
      "learning_rate": 8e-05,
      "loss": 3.4399,
      "step": 4
    },
    {
      "epoch": 0.000943040362127499,
      "grad_norm": 19.836227416992188,
      "learning_rate": 0.0001,
      "loss": 4.7794,
      "step": 5
    },
    {
      "epoch": 0.001131648434552999,
      "grad_norm": 12.299468040466309,
      "learning_rate": 0.00012,
      "loss": 3.0613,
      "step": 6
    },
    {
      "epoch": 0.001131648434552999,
      "eval_loss": 0.9074329733848572,
      "eval_runtime": 68.176,
      "eval_samples_per_second": 32.753,
      "eval_steps_per_second": 16.384,
      "step": 6
    },
    {
      "epoch": 0.0013202565069784986,
      "grad_norm": 18.84109115600586,
      "learning_rate": 0.00014,
      "loss": 4.0897,
      "step": 7
    },
    {
      "epoch": 0.0015088645794039985,
      "grad_norm": 12.41354751586914,
      "learning_rate": 0.00016,
      "loss": 2.6245,
      "step": 8
    },
    {
      "epoch": 0.0016974726518294984,
      "grad_norm": 9.773690223693848,
      "learning_rate": 0.00018,
      "loss": 2.8458,
      "step": 9
    },
    {
      "epoch": 0.0016974726518294984,
      "eval_loss": 0.7293293476104736,
      "eval_runtime": 70.9246,
      "eval_samples_per_second": 31.484,
      "eval_steps_per_second": 15.749,
      "step": 9
    },
    {
      "epoch": 0.001886080724254998,
      "grad_norm": 13.274161338806152,
      "learning_rate": 0.0002,
      "loss": 2.9545,
      "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": 1752671799214080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}