Hugging Face's logo

mlfoundations-dev
/
ds_no_offload_liger_packing_dataloader32

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
ds_no_offload_liger_packing_dataloader32
File size: 3,914 Bytes
00f1a05
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 8.517562789142705,
      "learning_rate": 5e-06,
      "loss": 1.2823,
      "step": 1
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 9.015462437583418,
      "learning_rate": 1e-05,
      "loss": 1.3191,
      "step": 2
    },
    {
      "epoch": 0.5,
      "grad_norm": 6.200212432061452,
      "learning_rate": 9.903926402016153e-06,
      "loss": 1.2058,
      "step": 3
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 3.0219803487293007,
      "learning_rate": 9.619397662556434e-06,
      "loss": 1.1292,
      "step": 4
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 6.117576906768532,
      "learning_rate": 9.157348061512728e-06,
      "loss": 1.1441,
      "step": 5
    },
    {
      "epoch": 1.0,
      "grad_norm": 6.6779091440264535,
      "learning_rate": 8.535533905932739e-06,
      "loss": 1.0848,
      "step": 6
    },
    {
      "epoch": 1.1666666666666667,
      "grad_norm": 6.839691644412843,
      "learning_rate": 7.777851165098012e-06,
      "loss": 1.0696,
      "step": 7
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 4.965406358877329,
      "learning_rate": 6.913417161825449e-06,
      "loss": 1.0376,
      "step": 8
    },
    {
      "epoch": 1.5,
      "grad_norm": 3.215296058515271,
      "learning_rate": 5.975451610080643e-06,
      "loss": 1.0121,
      "step": 9
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 2.052195679039275,
      "learning_rate": 5e-06,
      "loss": 0.9653,
      "step": 10
    },
    {
      "epoch": 1.8333333333333335,
      "grad_norm": 2.1879191992058296,
      "learning_rate": 4.02454838991936e-06,
      "loss": 0.9329,
      "step": 11
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.00525141363875,
      "learning_rate": 3.0865828381745515e-06,
      "loss": 0.9326,
      "step": 12
    },
    {
      "epoch": 2.1666666666666665,
      "grad_norm": 1.6398261167373145,
      "learning_rate": 2.2221488349019903e-06,
      "loss": 0.9089,
      "step": 13
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 1.3158703472007227,
      "learning_rate": 1.4644660940672628e-06,
      "loss": 0.8942,
      "step": 14
    },
    {
      "epoch": 2.5,
      "grad_norm": 1.1396349115202784,
      "learning_rate": 8.426519384872733e-07,
      "loss": 0.9139,
      "step": 15
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.9117703391426344,
      "learning_rate": 3.8060233744356634e-07,
      "loss": 0.9051,
      "step": 16
    },
    {
      "epoch": 2.8333333333333335,
      "grad_norm": 0.7720607551825818,
      "learning_rate": 9.607359798384785e-08,
      "loss": 0.9043,
      "step": 17
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.7049680392913233,
      "learning_rate": 0.0,
      "loss": 0.8928,
      "step": 18
    },
    {
      "epoch": 3.0,
      "step": 18,
      "total_flos": 6.177445717318042e+16,
      "train_loss": 1.029695474439197,
      "train_runtime": 1057.5368,
      "train_samples_per_second": 1.631,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 18,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.177445717318042e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}