Hugging Face's logo

chauhoang
/
3a6301f8-134e-4091-85a5-0083de9c222f

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
3a6301f8-134e-4091-85a5-0083de9c222f
File size: 3,758 Bytes 
d7fe2b2
 
 
666d29d
5899600
666d29d
d7fe2b2
 
 
 
 
 
 
5899600
 
 
d7fe2b2
5899600
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5d92f2a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
510c5fa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
666d29d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d7fe2b2
 
 
5899600
d7fe2b2
 
5899600
d7fe2b2
 
 
 
 
 
 
666d29d
d7fe2b2
 
 
 
666d29d
d7fe2b2
 
 
 
 
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
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0023054223533751383,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.610844706750277e-05,
      "eval_loss": 7.478056907653809,
      "eval_runtime": 646.3745,
      "eval_samples_per_second": 14.128,
      "eval_steps_per_second": 7.064,
      "step": 1
    },
    {
      "epoch": 0.00023054223533751383,
      "grad_norm": 235.5802001953125,
      "learning_rate": 5e-05,
      "loss": 30.1518,
      "step": 5
    },
    {
      "epoch": 0.00046108447067502766,
      "grad_norm": 107.33450317382812,
      "learning_rate": 0.0001,
      "loss": 8.7946,
      "step": 10
    },
    {
      "epoch": 0.00046108447067502766,
      "eval_loss": 0.8460701107978821,
      "eval_runtime": 649.6744,
      "eval_samples_per_second": 14.056,
      "eval_steps_per_second": 7.028,
      "step": 10
    },
    {
      "epoch": 0.0006916267060125415,
      "grad_norm": 9.170708656311035,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.8558,
      "step": 15
    },
    {
      "epoch": 0.0009221689413500553,
      "grad_norm": 0.2867533564567566,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.1771,
      "step": 20
    },
    {
      "epoch": 0.0009221689413500553,
      "eval_loss": 0.21382905542850494,
      "eval_runtime": 647.7178,
      "eval_samples_per_second": 14.099,
      "eval_steps_per_second": 7.049,
      "step": 20
    },
    {
      "epoch": 0.0011527111766875691,
      "grad_norm": 0.2146027535200119,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0012,
      "step": 25
    },
    {
      "epoch": 0.001383253412025083,
      "grad_norm": 0.003302945988252759,
      "learning_rate": 5e-05,
      "loss": 0.7641,
      "step": 30
    },
    {
      "epoch": 0.001383253412025083,
      "eval_loss": 0.20368286967277527,
      "eval_runtime": 647.9929,
      "eval_samples_per_second": 14.093,
      "eval_steps_per_second": 7.046,
      "step": 30
    },
    {
      "epoch": 0.0016137956473625968,
      "grad_norm": 0.02023138664662838,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.5793,
      "step": 35
    },
    {
      "epoch": 0.0018443378827001106,
      "grad_norm": 0.017362723127007484,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0001,
      "step": 40
    },
    {
      "epoch": 0.0018443378827001106,
      "eval_loss": 0.13715976476669312,
      "eval_runtime": 643.8616,
      "eval_samples_per_second": 14.183,
      "eval_steps_per_second": 7.092,
      "step": 40
    },
    {
      "epoch": 0.0020748801180376247,
      "grad_norm": 0.004537283908575773,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.7151,
      "step": 45
    },
    {
      "epoch": 0.0023054223533751383,
      "grad_norm": 0.007345356047153473,
      "learning_rate": 0.0,
      "loss": 0.7912,
      "step": 50
    },
    {
      "epoch": 0.0023054223533751383,
      "eval_loss": 0.12374379485845566,
      "eval_runtime": 646.8445,
      "eval_samples_per_second": 14.118,
      "eval_steps_per_second": 7.059,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9464427715756032.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}