Hugging Face's logo

regisss
/
bridgetower-newyorker-gaudi2-8x

Transformers
PyTorch
TensorBoard
Habana
bridgetower
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
regisss HF staff commited on
Commit
a7b95f3
•
1 Parent(s): efe4340

End of training

Browse files
Files changed (6) hide show
  1. all_results.json +14 -0
  2. runs/Jun28_09-52-53_sysid552968gaudi2/events.out.tfevents.1687946587.sysid552968gaudi2.17755.2 +3 -0
  3. test_results.json +10 -0
  4. train_results.json +10 -0
  5. trainer_state.json +163 -0
  6. validation_results.json +10 -0
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 0.11474794149398804,
4
+ "eval_runtime": 1.4227,
5
+ "eval_samples_per_second": 371.12,
6
+ "eval_steps_per_second": 3.514,
7
+ "max_memory_allocated (GB)": 83.39,
8
+ "memory_allocated (GB)": 20.01,
9
+ "total_memory_available (GB)": 93.74,
10
+ "train_loss": 0.07280745967741936,
11
+ "train_runtime": 346.0342,
12
+ "train_samples_per_second": 638.618,
13
+ "train_steps_per_second": 2.022
14
+ }
runs/Jun28_09-52-53_sysid552968gaudi2/events.out.tfevents.1687946587.sysid552968gaudi2.17755.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b797572fe1fe5e28857bc9ffde0628907714bcd2afc017af4edddc8169f813f
3
+ size 998
test_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 0.11474794149398804,
4
+ "eval_runtime": 1.4227,
5
+ "eval_samples_per_second": 371.12,
6
+ "eval_steps_per_second": 3.514,
7
+ "max_memory_allocated (GB)": 83.39,
8
+ "memory_allocated (GB)": 20.01,
9
+ "total_memory_available (GB)": 93.74
10
+ }
train_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "max_memory_allocated (GB)": 83.39,
4
+ "memory_allocated (GB)": 19.37,
5
+ "total_memory_available (GB)": 93.74,
6
+ "train_loss": 0.07280745967741936,
7
+ "train_runtime": 346.0342,
8
+ "train_samples_per_second": 638.618,
9
+ "train_steps_per_second": 2.022
10
+ }
trainer_state.json ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 155,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.32,
12
+ "learning_rate": 9.35483870967742e-06,
13
+ "loss": 0.2297,
14
+ "max_memory_allocated (GB)": 83.39,
15
+ "memory_allocated (GB)": 19.37,
16
+ "step": 10,
17
+ "total_memory_available (GB)": 93.74
18
+ },
19
+ {
20
+ "epoch": 0.65,
21
+ "learning_rate": 8.70967741935484e-06,
22
+ "loss": 0.0863,
23
+ "max_memory_allocated (GB)": 83.39,
24
+ "memory_allocated (GB)": 19.37,
25
+ "step": 20,
26
+ "total_memory_available (GB)": 93.74
27
+ },
28
+ {
29
+ "epoch": 0.97,
30
+ "learning_rate": 8.064516129032258e-06,
31
+ "loss": 0.0828,
32
+ "max_memory_allocated (GB)": 83.39,
33
+ "memory_allocated (GB)": 19.37,
34
+ "step": 30,
35
+ "total_memory_available (GB)": 93.74
36
+ },
37
+ {
38
+ "epoch": 1.29,
39
+ "learning_rate": 7.4193548387096784e-06,
40
+ "loss": 0.0625,
41
+ "max_memory_allocated (GB)": 83.39,
42
+ "memory_allocated (GB)": 19.37,
43
+ "step": 40,
44
+ "total_memory_available (GB)": 93.74
45
+ },
46
+ {
47
+ "epoch": 1.61,
48
+ "learning_rate": 6.774193548387097e-06,
49
+ "loss": 0.0641,
50
+ "max_memory_allocated (GB)": 83.39,
51
+ "memory_allocated (GB)": 19.37,
52
+ "step": 50,
53
+ "total_memory_available (GB)": 93.74
54
+ },
55
+ {
56
+ "epoch": 1.94,
57
+ "learning_rate": 6.129032258064517e-06,
58
+ "loss": 0.0613,
59
+ "max_memory_allocated (GB)": 83.39,
60
+ "memory_allocated (GB)": 19.37,
61
+ "step": 60,
62
+ "total_memory_available (GB)": 93.74
63
+ },
64
+ {
65
+ "epoch": 2.26,
66
+ "learning_rate": 5.483870967741935e-06,
67
+ "loss": 0.0559,
68
+ "max_memory_allocated (GB)": 83.39,
69
+ "memory_allocated (GB)": 19.37,
70
+ "step": 70,
71
+ "total_memory_available (GB)": 93.74
72
+ },
73
+ {
74
+ "epoch": 2.58,
75
+ "learning_rate": 4.838709677419355e-06,
76
+ "loss": 0.0602,
77
+ "max_memory_allocated (GB)": 83.39,
78
+ "memory_allocated (GB)": 19.37,
79
+ "step": 80,
80
+ "total_memory_available (GB)": 93.74
81
+ },
82
+ {
83
+ "epoch": 2.9,
84
+ "learning_rate": 4.193548387096774e-06,
85
+ "loss": 0.066,
86
+ "max_memory_allocated (GB)": 83.39,
87
+ "memory_allocated (GB)": 19.37,
88
+ "step": 90,
89
+ "total_memory_available (GB)": 93.74
90
+ },
91
+ {
92
+ "epoch": 3.23,
93
+ "learning_rate": 3.548387096774194e-06,
94
+ "loss": 0.0539,
95
+ "max_memory_allocated (GB)": 83.39,
96
+ "memory_allocated (GB)": 19.37,
97
+ "step": 100,
98
+ "total_memory_available (GB)": 93.74
99
+ },
100
+ {
101
+ "epoch": 3.55,
102
+ "learning_rate": 2.903225806451613e-06,
103
+ "loss": 0.0523,
104
+ "max_memory_allocated (GB)": 83.39,
105
+ "memory_allocated (GB)": 19.37,
106
+ "step": 110,
107
+ "total_memory_available (GB)": 93.74
108
+ },
109
+ {
110
+ "epoch": 3.87,
111
+ "learning_rate": 2.2580645161290324e-06,
112
+ "loss": 0.0555,
113
+ "max_memory_allocated (GB)": 83.39,
114
+ "memory_allocated (GB)": 19.37,
115
+ "step": 120,
116
+ "total_memory_available (GB)": 93.74
117
+ },
118
+ {
119
+ "epoch": 4.19,
120
+ "learning_rate": 1.6129032258064516e-06,
121
+ "loss": 0.0586,
122
+ "max_memory_allocated (GB)": 83.39,
123
+ "memory_allocated (GB)": 19.37,
124
+ "step": 130,
125
+ "total_memory_available (GB)": 93.74
126
+ },
127
+ {
128
+ "epoch": 4.52,
129
+ "learning_rate": 9.67741935483871e-07,
130
+ "loss": 0.0555,
131
+ "max_memory_allocated (GB)": 83.39,
132
+ "memory_allocated (GB)": 19.37,
133
+ "step": 140,
134
+ "total_memory_available (GB)": 93.74
135
+ },
136
+ {
137
+ "epoch": 4.84,
138
+ "learning_rate": 3.2258064516129035e-07,
139
+ "loss": 0.0527,
140
+ "max_memory_allocated (GB)": 83.39,
141
+ "memory_allocated (GB)": 19.37,
142
+ "step": 150,
143
+ "total_memory_available (GB)": 93.74
144
+ },
145
+ {
146
+ "epoch": 5.0,
147
+ "max_memory_allocated (GB)": 83.39,
148
+ "memory_allocated (GB)": 19.37,
149
+ "step": 155,
150
+ "total_flos": 3.0973626685587456e+16,
151
+ "total_memory_available (GB)": 93.74,
152
+ "train_loss": 0.07280745967741936,
153
+ "train_runtime": 346.0342,
154
+ "train_samples_per_second": 638.618,
155
+ "train_steps_per_second": 2.022
156
+ }
157
+ ],
158
+ "max_steps": 155,
159
+ "num_train_epochs": 5,
160
+ "total_flos": 3.0973626685587456e+16,
161
+ "trial_name": null,
162
+ "trial_params": null
163
+ }
validation_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_loss": 0.11240951716899872,
4
+ "eval_runtime": 10.7088,
5
+ "eval_samples_per_second": 49.585,
6
+ "eval_steps_per_second": 0.467,
7
+ "max_memory_allocated (GB)": 83.39,
8
+ "memory_allocated (GB)": 20.01,
9
+ "total_memory_available (GB)": 93.74
10
+ }