Hugging Face's logo

Defetya
/
simson_base

Safetensors
Model card Files
xet
Community
1
simson_base
File size: 4,824 Bytes 
592e96e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_global_step": 70000,
  "best_metric": 0.04956068471074104,
  "best_model_checkpoint": "/home/jovyan/simson_training_bolgov/regression/decoder_checkpoints/checkpoint-70000",
  "epoch": 4.00576830636116,
  "eval_steps": 10000,
  "global_step": 100000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.400576830636116,
      "grad_norm": 0.37913239002227783,
      "learning_rate": 4.6013064037829606e-05,
      "loss": 0.1577,
      "step": 10000
    },
    {
      "epoch": 0.400576830636116,
      "eval_loss": 0.07184838503599167,
      "eval_runtime": 325.2402,
      "eval_samples_per_second": 1034.153,
      "eval_steps_per_second": 4.04,
      "step": 10000
    },
    {
      "epoch": 0.801153661272232,
      "grad_norm": 0.36734315752983093,
      "learning_rate": 4.200729341989261e-05,
      "loss": 0.0699,
      "step": 20000
    },
    {
      "epoch": 0.801153661272232,
      "eval_loss": 0.06233175843954086,
      "eval_runtime": 326.1302,
      "eval_samples_per_second": 1031.33,
      "eval_steps_per_second": 4.029,
      "step": 20000
    },
    {
      "epoch": 1.201730491908348,
      "grad_norm": 0.43427732586860657,
      "learning_rate": 3.800192353931233e-05,
      "loss": 0.0619,
      "step": 30000
    },
    {
      "epoch": 1.201730491908348,
      "eval_loss": 0.05772605910897255,
      "eval_runtime": 327.0384,
      "eval_samples_per_second": 1028.466,
      "eval_steps_per_second": 4.018,
      "step": 30000
    },
    {
      "epoch": 1.6023073225444642,
      "grad_norm": 0.5037900805473328,
      "learning_rate": 3.3996553658732065e-05,
      "loss": 0.0577,
      "step": 40000
    },
    {
      "epoch": 1.6023073225444642,
      "eval_loss": 0.05496111884713173,
      "eval_runtime": 323.8521,
      "eval_samples_per_second": 1038.585,
      "eval_steps_per_second": 4.057,
      "step": 40000
    },
    {
      "epoch": 2.00288415318058,
      "grad_norm": 0.46178844571113586,
      "learning_rate": 2.99911837781518e-05,
      "loss": 0.0551,
      "step": 50000
    },
    {
      "epoch": 2.00288415318058,
      "eval_loss": 0.05280572175979614,
      "eval_runtime": 322.3602,
      "eval_samples_per_second": 1043.392,
      "eval_steps_per_second": 4.076,
      "step": 50000
    },
    {
      "epoch": 2.403460983816696,
      "grad_norm": 0.5070484280586243,
      "learning_rate": 2.5985413160214794e-05,
      "loss": 0.0532,
      "step": 60000
    },
    {
      "epoch": 2.403460983816696,
      "eval_loss": 0.05358376353979111,
      "eval_runtime": 325.0588,
      "eval_samples_per_second": 1034.73,
      "eval_steps_per_second": 4.042,
      "step": 60000
    },
    {
      "epoch": 2.804037814452812,
      "grad_norm": 0.5176772475242615,
      "learning_rate": 2.1980043279634528e-05,
      "loss": 0.0517,
      "step": 70000
    },
    {
      "epoch": 2.804037814452812,
      "eval_loss": 0.04956068471074104,
      "eval_runtime": 323.6366,
      "eval_samples_per_second": 1039.277,
      "eval_steps_per_second": 4.06,
      "step": 70000
    },
    {
      "epoch": 3.204614645088928,
      "grad_norm": 0.4495079815387726,
      "learning_rate": 1.7974673399054262e-05,
      "loss": 0.0505,
      "step": 80000
    },
    {
      "epoch": 3.204614645088928,
      "eval_loss": 0.05076293647289276,
      "eval_runtime": 325.2387,
      "eval_samples_per_second": 1034.157,
      "eval_steps_per_second": 4.04,
      "step": 80000
    },
    {
      "epoch": 3.605191475725044,
      "grad_norm": 0.49150699377059937,
      "learning_rate": 1.3969303518473992e-05,
      "loss": 0.0496,
      "step": 90000
    },
    {
      "epoch": 3.605191475725044,
      "eval_loss": 0.05038553848862648,
      "eval_runtime": 322.6375,
      "eval_samples_per_second": 1042.495,
      "eval_steps_per_second": 4.073,
      "step": 90000
    },
    {
      "epoch": 4.00576830636116,
      "grad_norm": 0.5493866205215454,
      "learning_rate": 9.963933637893724e-06,
      "loss": 0.0487,
      "step": 100000
    },
    {
      "epoch": 4.00576830636116,
      "eval_loss": 0.04964649677276611,
      "eval_runtime": 326.8677,
      "eval_samples_per_second": 1029.003,
      "eval_steps_per_second": 4.02,
      "step": 100000
    }
  ],
  "logging_steps": 10000,
  "max_steps": 124820,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}