Hugging Face's logo

fedovtt
/
98d3d7f5-bec2-44e1-a24b-ce2333b65fa4

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
Community
98d3d7f5-bec2-44e1-a24b-ce2333b65fa4
File size: 3,701 Bytes 
6f1e029
 
 
1e8e3aa
6f1e029
1e8e3aa
6f1e029
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1e8e3aa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6f1e029
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1e8e3aa
6f1e029
 
 
 
 
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": 0.00011343012704174228,
  "eval_steps": 2,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.1343012704174228e-05,
      "grad_norm": 1.3943215608596802,
      "learning_rate": 2e-05,
      "loss": 3.1809,
      "step": 1
    },
    {
      "epoch": 1.1343012704174228e-05,
      "eval_loss": 3.224539041519165,
      "eval_runtime": 873.4294,
      "eval_samples_per_second": 42.499,
      "eval_steps_per_second": 21.25,
      "step": 1
    },
    {
      "epoch": 2.2686025408348456e-05,
      "grad_norm": 1.2974414825439453,
      "learning_rate": 4e-05,
      "loss": 3.0873,
      "step": 2
    },
    {
      "epoch": 2.2686025408348456e-05,
      "eval_loss": 3.22213077545166,
      "eval_runtime": 873.1974,
      "eval_samples_per_second": 42.51,
      "eval_steps_per_second": 21.255,
      "step": 2
    },
    {
      "epoch": 3.402903811252269e-05,
      "grad_norm": 1.3224360942840576,
      "learning_rate": 6e-05,
      "loss": 3.0156,
      "step": 3
    },
    {
      "epoch": 4.537205081669691e-05,
      "grad_norm": 1.4221491813659668,
      "learning_rate": 8e-05,
      "loss": 3.1623,
      "step": 4
    },
    {
      "epoch": 4.537205081669691e-05,
      "eval_loss": 3.17517352104187,
      "eval_runtime": 873.0352,
      "eval_samples_per_second": 42.518,
      "eval_steps_per_second": 21.259,
      "step": 4
    },
    {
      "epoch": 5.671506352087114e-05,
      "grad_norm": 1.588068962097168,
      "learning_rate": 0.0001,
      "loss": 3.1715,
      "step": 5
    },
    {
      "epoch": 6.805807622504538e-05,
      "grad_norm": 1.5034862756729126,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.9514,
      "step": 6
    },
    {
      "epoch": 6.805807622504538e-05,
      "eval_loss": 2.9851348400115967,
      "eval_runtime": 873.7444,
      "eval_samples_per_second": 42.484,
      "eval_steps_per_second": 21.242,
      "step": 6
    },
    {
      "epoch": 7.94010889292196e-05,
      "grad_norm": 1.6210209131240845,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.9009,
      "step": 7
    },
    {
      "epoch": 9.074410163339382e-05,
      "grad_norm": 1.660132884979248,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.7984,
      "step": 8
    },
    {
      "epoch": 9.074410163339382e-05,
      "eval_loss": 2.79468035697937,
      "eval_runtime": 873.5775,
      "eval_samples_per_second": 42.492,
      "eval_steps_per_second": 21.246,
      "step": 8
    },
    {
      "epoch": 0.00010208711433756806,
      "grad_norm": 1.53206205368042,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.7431,
      "step": 9
    },
    {
      "epoch": 0.00011343012704174228,
      "grad_norm": 1.5387572050094604,
      "learning_rate": 5e-05,
      "loss": 2.6737,
      "step": 10
    },
    {
      "epoch": 0.00011343012704174228,
      "eval_loss": 2.7065184116363525,
      "eval_runtime": 873.6742,
      "eval_samples_per_second": 42.487,
      "eval_steps_per_second": 21.244,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 15,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 481091030876160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}