Hugging Face's logo

pemix09
/
paperstack_document_data_retrieval

TF-Keras
LiteRT
TensorBoard
Safetensors
Model card Files
xet
Metrics Community
paperstack_document_data_retrieval
File size: 4,430 Bytes 
60087f0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.092896174863388,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0546448087431694,
      "grad_norm": 2.1467645168304443,
      "learning_rate": 0.0004973224043715847,
      "loss": 5.4078,
      "step": 50
    },
    {
      "epoch": 0.1092896174863388,
      "grad_norm": 0.8721267580986023,
      "learning_rate": 0.0004945901639344262,
      "loss": 1.2654,
      "step": 100
    },
    {
      "epoch": 0.16393442622950818,
      "grad_norm": 0.8103071451187134,
      "learning_rate": 0.0004918579234972678,
      "loss": 1.0538,
      "step": 150
    },
    {
      "epoch": 0.2185792349726776,
      "grad_norm": 1.3929318189620972,
      "learning_rate": 0.0004891256830601093,
      "loss": 1.0236,
      "step": 200
    },
    {
      "epoch": 0.273224043715847,
      "grad_norm": 0.970960259437561,
      "learning_rate": 0.00048639344262295083,
      "loss": 1.075,
      "step": 250
    },
    {
      "epoch": 0.32786885245901637,
      "grad_norm": 0.9727946519851685,
      "learning_rate": 0.00048366120218579234,
      "loss": 1.0434,
      "step": 300
    },
    {
      "epoch": 0.3825136612021858,
      "grad_norm": 0.6411604285240173,
      "learning_rate": 0.0004809289617486339,
      "loss": 0.9285,
      "step": 350
    },
    {
      "epoch": 0.4371584699453552,
      "grad_norm": 0.8864787817001343,
      "learning_rate": 0.0004781967213114754,
      "loss": 0.9315,
      "step": 400
    },
    {
      "epoch": 0.4918032786885246,
      "grad_norm": 0.8886504173278809,
      "learning_rate": 0.0004754644808743169,
      "loss": 0.8818,
      "step": 450
    },
    {
      "epoch": 0.546448087431694,
      "grad_norm": 0.7289233803749084,
      "learning_rate": 0.0004727322404371585,
      "loss": 0.92,
      "step": 500
    },
    {
      "epoch": 0.6010928961748634,
      "grad_norm": 1.0301029682159424,
      "learning_rate": 0.00047,
      "loss": 0.8222,
      "step": 550
    },
    {
      "epoch": 0.6557377049180327,
      "grad_norm": 0.808475136756897,
      "learning_rate": 0.00046726775956284155,
      "loss": 0.8767,
      "step": 600
    },
    {
      "epoch": 0.7103825136612022,
      "grad_norm": 0.8232861161231995,
      "learning_rate": 0.0004645355191256831,
      "loss": 0.835,
      "step": 650
    },
    {
      "epoch": 0.7650273224043715,
      "grad_norm": 0.9552908539772034,
      "learning_rate": 0.0004618032786885246,
      "loss": 0.8203,
      "step": 700
    },
    {
      "epoch": 0.819672131147541,
      "grad_norm": 0.7888686656951904,
      "learning_rate": 0.00045907103825136613,
      "loss": 0.8296,
      "step": 750
    },
    {
      "epoch": 0.8743169398907104,
      "grad_norm": 0.7473599910736084,
      "learning_rate": 0.0004563387978142077,
      "loss": 0.7801,
      "step": 800
    },
    {
      "epoch": 0.9289617486338798,
      "grad_norm": 0.8543986678123474,
      "learning_rate": 0.0004536065573770492,
      "loss": 0.9248,
      "step": 850
    },
    {
      "epoch": 0.9836065573770492,
      "grad_norm": 0.7910193204879761,
      "learning_rate": 0.0004508743169398907,
      "loss": 0.8386,
      "step": 900
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6989373564720154,
      "eval_runtime": 35.1236,
      "eval_samples_per_second": 23.175,
      "eval_steps_per_second": 2.904,
      "step": 915
    },
    {
      "epoch": 1.0382513661202186,
      "grad_norm": 1.1451815366744995,
      "learning_rate": 0.00044814207650273227,
      "loss": 0.7198,
      "step": 950
    },
    {
      "epoch": 1.092896174863388,
      "grad_norm": 0.7096536755561829,
      "learning_rate": 0.0004454098360655738,
      "loss": 0.7374,
      "step": 1000
    }
  ],
  "logging_steps": 50,
  "max_steps": 9150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 1487124037632000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}