Hugging Face's logo

klcsp
/
llama3-8b-pissa-alpaca-11-v1

PEFT
TensorBoard
Safetensors
llama
trl
sft
Generated from Trainer
Model card Files Metrics Community
llama3-8b-pissa-alpaca-11-v1
File size: 4,456 Bytes 
0239b42
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.994535519125683,
  "eval_steps": 500,
  "global_step": 91,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01092896174863388,
      "grad_norm": 1.7711571016959918e+18,
      "learning_rate": 2e-05,
      "loss": 14.0238,
      "step": 1
    },
    {
      "epoch": 0.0546448087431694,
      "grad_norm": 3.320609228523045e+18,
      "learning_rate": 0.0001,
      "loss": 13.9905,
      "step": 5
    },
    {
      "epoch": 0.1092896174863388,
      "grad_norm": 1.1468547292982673e+19,
      "learning_rate": 0.0002,
      "loss": 14.0267,
      "step": 10
    },
    {
      "epoch": 0.16393442622950818,
      "grad_norm": 3.9691701809399726e+18,
      "learning_rate": 0.00019812553106273847,
      "loss": 14.0288,
      "step": 15
    },
    {
      "epoch": 0.2185792349726776,
      "grad_norm": 1.0431252630176006e+19,
      "learning_rate": 0.00019257239692688907,
      "loss": 14.0141,
      "step": 20
    },
    {
      "epoch": 0.273224043715847,
      "grad_norm": 1.0054431303639499e+19,
      "learning_rate": 0.00018354878114129367,
      "loss": 13.9837,
      "step": 25
    },
    {
      "epoch": 0.32786885245901637,
      "grad_norm": 4.974251626953966e+18,
      "learning_rate": 0.00017139297345578994,
      "loss": 13.9929,
      "step": 30
    },
    {
      "epoch": 0.3825136612021858,
      "grad_norm": Infinity,
      "learning_rate": 0.00015656068754865387,
      "loss": 13.9978,
      "step": 35
    },
    {
      "epoch": 0.4371584699453552,
      "grad_norm": Infinity,
      "learning_rate": 0.0001396079766039157,
      "loss": 13.9489,
      "step": 40
    },
    {
      "epoch": 0.4918032786885246,
      "grad_norm": 1.6553702809539707e+19,
      "learning_rate": 0.0001211703872229411,
      "loss": 13.9487,
      "step": 45
    },
    {
      "epoch": 0.546448087431694,
      "grad_norm": Infinity,
      "learning_rate": 0.00010193913317718244,
      "loss": 13.9381,
      "step": 50
    },
    {
      "epoch": 0.6010928961748634,
      "grad_norm": 4.656146420363952e+18,
      "learning_rate": 8.263518223330697e-05,
      "loss": 13.9454,
      "step": 55
    },
    {
      "epoch": 0.6557377049180327,
      "grad_norm": 8.26754403884073e+18,
      "learning_rate": 6.398222751952899e-05,
      "loss": 13.9116,
      "step": 60
    },
    {
      "epoch": 0.7103825136612022,
      "grad_norm": Infinity,
      "learning_rate": 4.66795567198309e-05,
      "loss": 13.9312,
      "step": 65
    },
    {
      "epoch": 0.7650273224043715,
      "grad_norm": 3.3132386523262484e+18,
      "learning_rate": 3.137583621312665e-05,
      "loss": 13.9726,
      "step": 70
    },
    {
      "epoch": 0.819672131147541,
      "grad_norm": 3.950367432593375e+18,
      "learning_rate": 1.864479297370325e-05,
      "loss": 13.9497,
      "step": 75
    },
    {
      "epoch": 0.8743169398907104,
      "grad_norm": 3.439258352910074e+18,
      "learning_rate": 8.963705903385345e-06,
      "loss": 13.9259,
      "step": 80
    },
    {
      "epoch": 0.9289617486338798,
      "grad_norm": Infinity,
      "learning_rate": 2.6955129420176196e-06,
      "loss": 13.9617,
      "step": 85
    },
    {
      "epoch": 0.9836065573770492,
      "grad_norm": Infinity,
      "learning_rate": 7.520474957699586e-08,
      "loss": 13.938,
      "step": 90
    },
    {
      "epoch": 0.994535519125683,
      "eval_loss": 14.016096115112305,
      "eval_runtime": 2.0876,
      "eval_samples_per_second": 83.349,
      "eval_steps_per_second": 0.958,
      "step": 91
    },
    {
      "epoch": 0.994535519125683,
      "step": 91,
      "total_flos": 4.03002565094015e+17,
      "train_loss": 13.96694589971186,
      "train_runtime": 1243.0718,
      "train_samples_per_second": 14.102,
      "train_steps_per_second": 0.073
    }
  ],
  "logging_steps": 5,
  "max_steps": 91,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.03002565094015e+17,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}