Hugging Face's logo

delta8tyome
/
llm-jp-3-13b-20241123-0

Transformers
Safetensors
Japanese
unsloth
Model card Files Community
delta8tyome commited on
Commit
eeef15e
·
verified ·
1 Parent(s): 2ef9423

Delete trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +0 -180
trainer_state.json DELETED
@@ -1,180 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 0.9988439306358381,
5
- "eval_steps": 500,
6
- "global_step": 216,
7
- "is_hyper_param_search": false,
8
- "is_local_process_zero": true,
9
- "is_world_process_zero": true,
10
- "log_history": [
11
- {
12
- "epoch": 0.046242774566473986,
13
- "grad_norm": 0.29475411772727966,
14
- "learning_rate": 0.0002,
15
- "loss": 2.2125,
16
- "step": 10
17
- },
18
- {
19
- "epoch": 0.09248554913294797,
20
- "grad_norm": 0.3760108947753906,
21
- "learning_rate": 0.00019029126213592236,
22
- "loss": 1.9606,
23
- "step": 20
24
- },
25
- {
26
- "epoch": 0.13872832369942195,
27
- "grad_norm": 0.31119468808174133,
28
- "learning_rate": 0.00018058252427184467,
29
- "loss": 1.8787,
30
- "step": 30
31
- },
32
- {
33
- "epoch": 0.18497109826589594,
34
- "grad_norm": 0.32787275314331055,
35
- "learning_rate": 0.000170873786407767,
36
- "loss": 1.8978,
37
- "step": 40
38
- },
39
- {
40
- "epoch": 0.23121387283236994,
41
- "grad_norm": 0.7112058401107788,
42
- "learning_rate": 0.0001611650485436893,
43
- "loss": 1.7504,
44
- "step": 50
45
- },
46
- {
47
- "epoch": 0.2774566473988439,
48
- "grad_norm": 0.2233152985572815,
49
- "learning_rate": 0.00015145631067961166,
50
- "loss": 2.0392,
51
- "step": 60
52
- },
53
- {
54
- "epoch": 0.3236994219653179,
55
- "grad_norm": 0.22356455028057098,
56
- "learning_rate": 0.000141747572815534,
57
- "loss": 1.8432,
58
- "step": 70
59
- },
60
- {
61
- "epoch": 0.3699421965317919,
62
- "grad_norm": 0.30998003482818604,
63
- "learning_rate": 0.00013203883495145632,
64
- "loss": 1.8597,
65
- "step": 80
66
- },
67
- {
68
- "epoch": 0.4161849710982659,
69
- "grad_norm": 0.3756067156791687,
70
- "learning_rate": 0.00012233009708737864,
71
- "loss": 1.7925,
72
- "step": 90
73
- },
74
- {
75
- "epoch": 0.4624277456647399,
76
- "grad_norm": 0.8105658292770386,
77
- "learning_rate": 0.00011262135922330097,
78
- "loss": 1.7537,
79
- "step": 100
80
- },
81
- {
82
- "epoch": 0.5086705202312138,
83
- "grad_norm": 0.19787977635860443,
84
- "learning_rate": 0.0001029126213592233,
85
- "loss": 1.9549,
86
- "step": 110
87
- },
88
- {
89
- "epoch": 0.5549132947976878,
90
- "grad_norm": 0.2306784689426422,
91
- "learning_rate": 9.320388349514564e-05,
92
- "loss": 1.8755,
93
- "step": 120
94
- },
95
- {
96
- "epoch": 0.6011560693641619,
97
- "grad_norm": 0.24941173195838928,
98
- "learning_rate": 8.349514563106797e-05,
99
- "loss": 1.8362,
100
- "step": 130
101
- },
102
- {
103
- "epoch": 0.6473988439306358,
104
- "grad_norm": 0.3020782768726349,
105
- "learning_rate": 7.37864077669903e-05,
106
- "loss": 1.7704,
107
- "step": 140
108
- },
109
- {
110
- "epoch": 0.6936416184971098,
111
- "grad_norm": 0.48686742782592773,
112
- "learning_rate": 6.407766990291263e-05,
113
- "loss": 1.672,
114
- "step": 150
115
- },
116
- {
117
- "epoch": 0.7398843930635838,
118
- "grad_norm": 0.22017759084701538,
119
- "learning_rate": 5.436893203883495e-05,
120
- "loss": 1.9731,
121
- "step": 160
122
- },
123
- {
124
- "epoch": 0.7861271676300579,
125
- "grad_norm": 0.22683261334896088,
126
- "learning_rate": 4.466019417475728e-05,
127
- "loss": 1.8569,
128
- "step": 170
129
- },
130
- {
131
- "epoch": 0.8323699421965318,
132
- "grad_norm": 0.2718450129032135,
133
- "learning_rate": 3.4951456310679615e-05,
134
- "loss": 1.8241,
135
- "step": 180
136
- },
137
- {
138
- "epoch": 0.8786127167630058,
139
- "grad_norm": 0.36181768774986267,
140
- "learning_rate": 2.5242718446601944e-05,
141
- "loss": 1.7315,
142
- "step": 190
143
- },
144
- {
145
- "epoch": 0.9248554913294798,
146
- "grad_norm": 0.6412150263786316,
147
- "learning_rate": 1.5533980582524273e-05,
148
- "loss": 1.7282,
149
- "step": 200
150
- },
151
- {
152
- "epoch": 0.9710982658959537,
153
- "grad_norm": 0.26944366097450256,
154
- "learning_rate": 5.825242718446602e-06,
155
- "loss": 1.8982,
156
- "step": 210
157
- }
158
- ],
159
- "logging_steps": 10,
160
- "max_steps": 216,
161
- "num_input_tokens_seen": 0,
162
- "num_train_epochs": 1,
163
- "save_steps": 100,
164
- "stateful_callbacks": {
165
- "TrainerControl": {
166
- "args": {
167
- "should_epoch_stop": false,
168
- "should_evaluate": false,
169
- "should_log": false,
170
- "should_save": true,
171
- "should_training_stop": true
172
- },
173
- "attributes": {}
174
- }
175
- },
176
- "total_flos": 2.79883718602752e+16,
177
- "train_batch_size": 2,
178
- "trial_name": null,
179
- "trial_params": null
180
- }