Hugging Face's logo

mcdevzs
/
tests

Safetensors
qwen3
Model card Files
xet
 Community
tests
File size: 4,784 Bytes
4675c86
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 115,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.043478260869565216,
      "grad_norm": 2.125,
      "learning_rate": 1.9768115942028986e-05,
      "loss": 1.4752726554870605,
      "step": 5
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 1.859375,
      "learning_rate": 1.947826086956522e-05,
      "loss": 1.246222686767578,
      "step": 10
    },
    {
      "epoch": 0.13043478260869565,
      "grad_norm": 1.6875,
      "learning_rate": 1.918840579710145e-05,
      "loss": 1.1879362106323241,
      "step": 15
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8898550724637685e-05,
      "loss": 1.1490286827087401,
      "step": 20
    },
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 1.703125,
      "learning_rate": 1.8608695652173912e-05,
      "loss": 1.2483633041381836,
      "step": 25
    },
    {
      "epoch": 0.2608695652173913,
      "grad_norm": 1.640625,
      "learning_rate": 1.8318840579710146e-05,
      "loss": 1.2286408424377442,
      "step": 30
    },
    {
      "epoch": 0.30434782608695654,
      "grad_norm": 1.78125,
      "learning_rate": 1.802898550724638e-05,
      "loss": 1.1528528213500977,
      "step": 35
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 1.5703125,
      "learning_rate": 1.773913043478261e-05,
      "loss": 1.1953392028808594,
      "step": 40
    },
    {
      "epoch": 0.391304347826087,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7449275362318842e-05,
      "loss": 1.2230706214904785,
      "step": 45
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 1.6953125,
      "learning_rate": 1.7159420289855073e-05,
      "loss": 1.1725500106811524,
      "step": 50
    },
    {
      "epoch": 0.4782608695652174,
      "grad_norm": 1.625,
      "learning_rate": 1.6869565217391307e-05,
      "loss": 1.1918975830078125,
      "step": 55
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6579710144927538e-05,
      "loss": 1.1676328659057618,
      "step": 60
    },
    {
      "epoch": 0.5652173913043478,
      "grad_norm": 1.515625,
      "learning_rate": 1.628985507246377e-05,
      "loss": 1.1679247856140136,
      "step": 65
    },
    {
      "epoch": 0.6086956521739131,
      "grad_norm": 1.53125,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.0870880126953124,
      "step": 70
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 1.6171875,
      "learning_rate": 1.5710144927536233e-05,
      "loss": 1.1582844734191895,
      "step": 75
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 1.65625,
      "learning_rate": 1.5420289855072464e-05,
      "loss": 1.1640958786010742,
      "step": 80
    },
    {
      "epoch": 0.7391304347826086,
      "grad_norm": 1.6484375,
      "learning_rate": 1.5130434782608697e-05,
      "loss": 1.1900686264038085,
      "step": 85
    },
    {
      "epoch": 0.782608695652174,
      "grad_norm": 1.6796875,
      "learning_rate": 1.484057971014493e-05,
      "loss": 1.1477184295654297,
      "step": 90
    },
    {
      "epoch": 0.8260869565217391,
      "grad_norm": 1.703125,
      "learning_rate": 1.455072463768116e-05,
      "loss": 1.1650050163269043,
      "step": 95
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 1.8046875,
      "learning_rate": 1.4260869565217392e-05,
      "loss": 1.1436158180236817,
      "step": 100
    },
    {
      "epoch": 0.9130434782608695,
      "grad_norm": 1.7734375,
      "learning_rate": 1.3971014492753625e-05,
      "loss": 1.1357536315917969,
      "step": 105
    },
    {
      "epoch": 0.9565217391304348,
      "grad_norm": 1.6015625,
      "learning_rate": 1.3681159420289856e-05,
      "loss": 1.0976995468139648,
      "step": 110
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.5546875,
      "learning_rate": 1.3391304347826088e-05,
      "loss": 1.116806697845459,
      "step": 115
    }
  ],
  "logging_steps": 5,
  "max_steps": 345,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.581608545026048e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}