Hugging Face's logo

ardaspear
/
85a121f1-a0cd-4cc1-a42f-54c3275b4007

PEFT
Safetensors
qwen2_moe
axolotl
Generated from Trainer
Model card Files Community
85a121f1-a0cd-4cc1-a42f-54c3275b4007
File size: 4,346 Bytes 
d3883fb
 
 
6c65ae4
d3883fb
6c65ae4
d3883fb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0c29c7a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
630f53c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f4ec83e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f6ec64f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
697291f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6c65ae4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d3883fb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6c65ae4
d3883fb
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.020633750921149593,
  "eval_steps": 5,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005895357406042742,
      "eval_loss": 11.93494987487793,
      "eval_runtime": 22.1509,
      "eval_samples_per_second": 128.979,
      "eval_steps_per_second": 16.162,
      "step": 1
    },
    {
      "epoch": 0.0017686072218128224,
      "grad_norm": 0.40249624848365784,
      "learning_rate": 3e-05,
      "loss": 11.9355,
      "step": 3
    },
    {
      "epoch": 0.0029476787030213707,
      "eval_loss": 11.932616233825684,
      "eval_runtime": 21.2141,
      "eval_samples_per_second": 134.675,
      "eval_steps_per_second": 16.876,
      "step": 5
    },
    {
      "epoch": 0.003537214443625645,
      "grad_norm": 0.31879347562789917,
      "learning_rate": 6e-05,
      "loss": 11.9335,
      "step": 6
    },
    {
      "epoch": 0.005305821665438467,
      "grad_norm": 0.3556462526321411,
      "learning_rate": 9e-05,
      "loss": 11.9286,
      "step": 9
    },
    {
      "epoch": 0.0058953574060427415,
      "eval_loss": 11.923737525939941,
      "eval_runtime": 21.1557,
      "eval_samples_per_second": 135.047,
      "eval_steps_per_second": 16.922,
      "step": 10
    },
    {
      "epoch": 0.00707442888725129,
      "grad_norm": 0.4747415781021118,
      "learning_rate": 9.938441702975689e-05,
      "loss": 11.9255,
      "step": 12
    },
    {
      "epoch": 0.008843036109064112,
      "grad_norm": 0.5072726607322693,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.9161,
      "step": 15
    },
    {
      "epoch": 0.008843036109064112,
      "eval_loss": 11.908404350280762,
      "eval_runtime": 21.5643,
      "eval_samples_per_second": 132.488,
      "eval_steps_per_second": 16.602,
      "step": 15
    },
    {
      "epoch": 0.010611643330876934,
      "grad_norm": 0.509223222732544,
      "learning_rate": 9.045084971874738e-05,
      "loss": 11.9059,
      "step": 18
    },
    {
      "epoch": 0.011790714812085483,
      "eval_loss": 11.8934907913208,
      "eval_runtime": 21.3386,
      "eval_samples_per_second": 133.889,
      "eval_steps_per_second": 16.777,
      "step": 20
    },
    {
      "epoch": 0.012380250552689757,
      "grad_norm": 0.49812066555023193,
      "learning_rate": 8.247240241650918e-05,
      "loss": 11.8962,
      "step": 21
    },
    {
      "epoch": 0.01414885777450258,
      "grad_norm": 0.4185691475868225,
      "learning_rate": 7.269952498697734e-05,
      "loss": 11.8831,
      "step": 24
    },
    {
      "epoch": 0.014738393515106854,
      "eval_loss": 11.88258171081543,
      "eval_runtime": 21.3695,
      "eval_samples_per_second": 133.695,
      "eval_steps_per_second": 16.753,
      "step": 25
    },
    {
      "epoch": 0.0159174649963154,
      "grad_norm": 0.444751113653183,
      "learning_rate": 6.167226819279528e-05,
      "loss": 11.8809,
      "step": 27
    },
    {
      "epoch": 0.017686072218128224,
      "grad_norm": 0.4151949882507324,
      "learning_rate": 5e-05,
      "loss": 11.8796,
      "step": 30
    },
    {
      "epoch": 0.017686072218128224,
      "eval_loss": 11.876304626464844,
      "eval_runtime": 21.2507,
      "eval_samples_per_second": 134.442,
      "eval_steps_per_second": 16.846,
      "step": 30
    },
    {
      "epoch": 0.019454679439941048,
      "grad_norm": 0.3371483385562897,
      "learning_rate": 3.832773180720475e-05,
      "loss": 11.8769,
      "step": 33
    },
    {
      "epoch": 0.020633750921149593,
      "eval_loss": 11.87283706665039,
      "eval_runtime": 21.1617,
      "eval_samples_per_second": 135.008,
      "eval_steps_per_second": 16.917,
      "step": 35
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "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": 38562693120000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}