griffio commited on
Commit
fda4559
1 Parent(s): fcab3f3

Training in progress, step 10

Browse files
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 56.666666666666664,
3
+ "total_flos": 2.576884875160781e+16,
4
+ "train_loss": 1.7478609253378476,
5
+ "train_runtime": 55.2269,
6
+ "train_samples_per_second": 69.26,
7
+ "train_steps_per_second": 1.539
8
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c203ee2730ab7937e241d9925bae5007c355c23cb1bc6df5de7896ebdf3bcf99
3
  size 44774596
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62bc9d2b590eed0af938e95e47d7f0771263d223db42ab3626d3b7ad39dd518d
3
  size 44774596
runs/Nov11_11-43-44_9dbf826d7e63/events.out.tfevents.1731325518.9dbf826d7e63.838.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9974cd827402dc2576099d7ab6726452cf8c1b49c154929d817cb3a643718db
3
+ size 5798
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 56.666666666666664,
3
+ "total_flos": 2.576884875160781e+16,
4
+ "train_loss": 1.7478609253378476,
5
+ "train_runtime": 55.2269,
6
+ "train_samples_per_second": 69.26,
7
+ "train_steps_per_second": 1.539
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.9495443105697632,
3
+ "best_model_checkpoint": "resnet-18-dungeons-001/checkpoint-80",
4
+ "epoch": 56.666666666666664,
5
+ "eval_steps": 10,
6
+ "global_step": 85,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 6.666666666666667,
13
+ "grad_norm": 11.739578247070312,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 2.3193,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 6.666666666666667,
20
+ "eval_accuracy": 0.16666666666666666,
21
+ "eval_loss": 2.3046061992645264,
22
+ "eval_runtime": 0.1857,
23
+ "eval_samples_per_second": 64.614,
24
+ "eval_steps_per_second": 10.769,
25
+ "step": 10
26
+ },
27
+ {
28
+ "epoch": 13.333333333333334,
29
+ "grad_norm": 12.655901908874512,
30
+ "learning_rate": 2.0000000000000003e-06,
31
+ "loss": 2.2945,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 13.333333333333334,
36
+ "eval_accuracy": 0.16666666666666666,
37
+ "eval_loss": 2.28173828125,
38
+ "eval_runtime": 0.1043,
39
+ "eval_samples_per_second": 115.034,
40
+ "eval_steps_per_second": 19.172,
41
+ "step": 20
42
+ },
43
+ {
44
+ "epoch": 20.0,
45
+ "grad_norm": 10.712946891784668,
46
+ "learning_rate": 3e-06,
47
+ "loss": 2.1285,
48
+ "step": 30
49
+ },
50
+ {
51
+ "epoch": 20.0,
52
+ "eval_accuracy": 0.16666666666666666,
53
+ "eval_loss": 2.242919921875,
54
+ "eval_runtime": 0.1024,
55
+ "eval_samples_per_second": 117.157,
56
+ "eval_steps_per_second": 19.526,
57
+ "step": 30
58
+ },
59
+ {
60
+ "epoch": 26.666666666666668,
61
+ "grad_norm": 10.430768966674805,
62
+ "learning_rate": 4.000000000000001e-06,
63
+ "loss": 1.9822,
64
+ "step": 40
65
+ },
66
+ {
67
+ "epoch": 26.666666666666668,
68
+ "eval_accuracy": 0.16666666666666666,
69
+ "eval_loss": 2.1981608867645264,
70
+ "eval_runtime": 0.1069,
71
+ "eval_samples_per_second": 112.291,
72
+ "eval_steps_per_second": 18.715,
73
+ "step": 40
74
+ },
75
+ {
76
+ "epoch": 33.333333333333336,
77
+ "grad_norm": 13.252127647399902,
78
+ "learning_rate": 5e-06,
79
+ "loss": 1.8001,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 33.333333333333336,
84
+ "eval_accuracy": 0.16666666666666666,
85
+ "eval_loss": 2.156494140625,
86
+ "eval_runtime": 0.165,
87
+ "eval_samples_per_second": 72.742,
88
+ "eval_steps_per_second": 12.124,
89
+ "step": 50
90
+ },
91
+ {
92
+ "epoch": 40.0,
93
+ "grad_norm": 10.211044311523438,
94
+ "learning_rate": 6e-06,
95
+ "loss": 1.5728,
96
+ "step": 60
97
+ },
98
+ {
99
+ "epoch": 40.0,
100
+ "eval_accuracy": 0.25,
101
+ "eval_loss": 2.1058757305145264,
102
+ "eval_runtime": 0.1024,
103
+ "eval_samples_per_second": 117.237,
104
+ "eval_steps_per_second": 19.539,
105
+ "step": 60
106
+ },
107
+ {
108
+ "epoch": 46.666666666666664,
109
+ "grad_norm": 8.858285903930664,
110
+ "learning_rate": 7e-06,
111
+ "loss": 1.2919,
112
+ "step": 70
113
+ },
114
+ {
115
+ "epoch": 46.666666666666664,
116
+ "eval_accuracy": 0.25,
117
+ "eval_loss": 2.0252277851104736,
118
+ "eval_runtime": 0.1047,
119
+ "eval_samples_per_second": 114.573,
120
+ "eval_steps_per_second": 19.096,
121
+ "step": 70
122
+ },
123
+ {
124
+ "epoch": 53.333333333333336,
125
+ "grad_norm": 8.067765235900879,
126
+ "learning_rate": 8.000000000000001e-06,
127
+ "loss": 1.0619,
128
+ "step": 80
129
+ },
130
+ {
131
+ "epoch": 53.333333333333336,
132
+ "eval_accuracy": 0.3333333333333333,
133
+ "eval_loss": 1.9495443105697632,
134
+ "eval_runtime": 0.1294,
135
+ "eval_samples_per_second": 92.703,
136
+ "eval_steps_per_second": 15.451,
137
+ "step": 80
138
+ },
139
+ {
140
+ "epoch": 56.666666666666664,
141
+ "step": 85,
142
+ "total_flos": 2.576884875160781e+16,
143
+ "train_loss": 1.7478609253378476,
144
+ "train_runtime": 55.2269,
145
+ "train_samples_per_second": 69.26,
146
+ "train_steps_per_second": 1.539
147
+ }
148
+ ],
149
+ "logging_steps": 10,
150
+ "max_steps": 85,
151
+ "num_input_tokens_seen": 0,
152
+ "num_train_epochs": 85,
153
+ "save_steps": 10,
154
+ "stateful_callbacks": {
155
+ "TrainerControl": {
156
+ "args": {
157
+ "should_epoch_stop": false,
158
+ "should_evaluate": false,
159
+ "should_log": false,
160
+ "should_save": true,
161
+ "should_training_stop": true
162
+ },
163
+ "attributes": {}
164
+ }
165
+ },
166
+ "total_flos": 2.576884875160781e+16,
167
+ "train_batch_size": 8,
168
+ "trial_name": null,
169
+ "trial_params": null
170
+ }