Hugging Face's logo

embunna
/
resnet-18-finetuned-resnet

Image Classification
Transformers
TensorBoard
Safetensors
resnet
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
embunna commited on
Commit
24b5092
•
1 Parent(s): 7476cf0

Training in progress, epoch 0

Browse files
Files changed (8) hide show
  1. all_results.json +11 -11
  2. eval_results.json +6 -6
  3. model.safetensors +1 -1
  4. runs/Jun06_03-20-45_d5995827060b/events.out.tfevents.1717644130.d5995827060b.459.1 +3 -0
  5. runs/Jun06_03-22-28_d5995827060b/events.out.tfevents.1717644157.d5995827060b.459.2 +3 -0
  6. train_results.json +6 -6
  7. trainer_state.json +128 -39
  8. training_args.bin +1 -1
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
- "epoch": 2.7272727272727275,
3
- "eval_accuracy": 1.0,
4
- "eval_loss": 1.0586352348327637,
5
- "eval_runtime": 0.2553,
6
- "eval_samples_per_second": 301.55,
7
- "eval_steps_per_second": 11.749,
8
- "total_flos": 1.912117618678579e+16,
9
- "train_loss": 1.0821615219116212,
10
- "train_runtime": 13.5983,
11
- "train_samples_per_second": 152.445,
12
- "train_steps_per_second": 1.103
13
  }
 
1
  {
2
+ "epoch": 8.88888888888889,
3
+ "eval_accuracy": 0.28125,
4
+ "eval_loss": 3.446418982515507e+16,
5
+ "eval_runtime": 0.4826,
6
+ "eval_samples_per_second": 198.94,
7
+ "eval_steps_per_second": 6.217,
8
+ "total_flos": 7.753465317556224e+16,
9
+ "train_loss": 3.2698800068537004e+16,
10
+ "train_runtime": 59.4328,
11
+ "train_samples_per_second": 145.374,
12
+ "train_steps_per_second": 1.01
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 2.7272727272727275,
3
- "eval_accuracy": 1.0,
4
- "eval_loss": 1.0586352348327637,
5
- "eval_runtime": 0.2553,
6
- "eval_samples_per_second": 301.55,
7
- "eval_steps_per_second": 11.749
8
  }
 
1
  {
2
+ "epoch": 8.88888888888889,
3
+ "eval_accuracy": 0.28125,
4
+ "eval_loss": 3.446418982515507e+16,
5
+ "eval_runtime": 0.4826,
6
+ "eval_samples_per_second": 198.94,
7
+ "eval_steps_per_second": 6.217
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e98a11465b7c0fb2b32eca1d73d02300a06192be747c2332586360ddb3816d06
3
  size 44766388
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfc22f97324aeb50510d88121abf39b7bc8ec2dce1a4e7f96d09d926e2633f49
3
  size 44766388
runs/Jun06_03-20-45_d5995827060b/events.out.tfevents.1717644130.d5995827060b.459.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eec2a94e7963c6e7bcfcaa48e871a42ed2b65ead8be2ae05a022af130065d5d
3
+ size 405
runs/Jun06_03-22-28_d5995827060b/events.out.tfevents.1717644157.d5995827060b.459.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cf482178ee4b38e9374bfe01567b083e05ad33fdf4bc7afafff47271a2d3312
3
+ size 5332
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 2.7272727272727275,
3
- "total_flos": 1.912117618678579e+16,
4
- "train_loss": 1.0821615219116212,
5
- "train_runtime": 13.5983,
6
- "train_samples_per_second": 152.445,
7
- "train_steps_per_second": 1.103
8
  }
 
1
  {
2
+ "epoch": 8.88888888888889,
3
+ "total_flos": 7.753465317556224e+16,
4
+ "train_loss": 3.2698800068537004e+16,
5
+ "train_runtime": 59.4328,
6
+ "train_samples_per_second": 145.374,
7
+ "train_steps_per_second": 1.01
8
  }
trainer_state.json CHANGED
@@ -1,61 +1,150 @@
1
  {
2
- "best_metric": 1.0,
3
- "best_model_checkpoint": "resnet-18-finetuned-resnet/checkpoint-11",
4
- "epoch": 2.7272727272727275,
5
  "eval_steps": 500,
6
- "global_step": 15,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.9090909090909091,
13
- "eval_accuracy": 0.4805194805194805,
14
- "eval_loss": 1.0896967649459839,
15
- "eval_runtime": 0.2491,
16
- "eval_samples_per_second": 309.111,
17
- "eval_steps_per_second": 12.043,
18
- "step": 5
19
  },
20
  {
21
- "epoch": 1.8181818181818183,
22
- "grad_norm": 3.7016072273254395,
23
- "learning_rate": 1.923076923076923e-05,
24
- "loss": 1.0892,
25
  "step": 10
26
  },
27
  {
28
- "epoch": 2.0,
29
- "eval_accuracy": 1.0,
30
- "eval_loss": 1.0586352348327637,
31
- "eval_runtime": 0.2873,
32
- "eval_samples_per_second": 267.995,
33
- "eval_steps_per_second": 10.441,
34
- "step": 11
35
  },
36
  {
37
- "epoch": 2.7272727272727275,
38
- "eval_accuracy": 1.0,
39
- "eval_loss": 1.0516302585601807,
40
- "eval_runtime": 0.2316,
41
- "eval_samples_per_second": 332.499,
42
- "eval_steps_per_second": 12.955,
43
- "step": 15
44
  },
45
  {
46
- "epoch": 2.7272727272727275,
47
- "step": 15,
48
- "total_flos": 1.912117618678579e+16,
49
- "train_loss": 1.0821615219116212,
50
- "train_runtime": 13.5983,
51
- "train_samples_per_second": 152.445,
52
- "train_steps_per_second": 1.103
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
  }
54
  ],
55
  "logging_steps": 10,
56
- "max_steps": 15,
57
  "num_input_tokens_seen": 0,
58
- "num_train_epochs": 3,
59
  "save_steps": 500,
60
  "stateful_callbacks": {
61
  "TrainerControl": {
@@ -69,7 +158,7 @@
69
  "attributes": {}
70
  }
71
  },
72
- "total_flos": 1.912117618678579e+16,
73
  "train_batch_size": 32,
74
  "trial_name": null,
75
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.28125,
3
+ "best_model_checkpoint": "resnet-18-finetuned-resnet/checkpoint-6",
4
+ "epoch": 8.88888888888889,
5
  "eval_steps": 500,
6
+ "global_step": 60,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.8888888888888888,
13
+ "eval_accuracy": 0.28125,
14
+ "eval_loss": 3.446418982515507e+16,
15
+ "eval_runtime": 0.3799,
16
+ "eval_samples_per_second": 252.73,
17
+ "eval_steps_per_second": 7.898,
18
+ "step": 6
19
  },
20
  {
21
+ "epoch": 1.4814814814814814,
22
+ "grad_norm": 135589920768.0,
23
+ "learning_rate": 4.62962962962963e-05,
24
+ "loss": 4.868262966643917e+16,
25
  "step": 10
26
  },
27
  {
28
+ "epoch": 1.925925925925926,
29
+ "eval_accuracy": 0.28125,
30
+ "eval_loss": 3.1846918359351296e+16,
31
+ "eval_runtime": 0.3175,
32
+ "eval_samples_per_second": 302.406,
33
+ "eval_steps_per_second": 9.45,
34
+ "step": 13
35
  },
36
  {
37
+ "epoch": 2.962962962962963,
38
+ "grad_norm": 103599328.0,
39
+ "learning_rate": 3.7037037037037037e-05,
40
+ "loss": 2.955574185599959e+16,
41
+ "step": 20
 
 
42
  },
43
  {
44
+ "epoch": 2.962962962962963,
45
+ "eval_accuracy": 0.28125,
46
+ "eval_loss": 3.1846918359351296e+16,
47
+ "eval_runtime": 0.4078,
48
+ "eval_samples_per_second": 235.429,
49
+ "eval_steps_per_second": 7.357,
50
+ "step": 20
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "eval_accuracy": 0.28125,
55
+ "eval_loss": 3.1846918359351296e+16,
56
+ "eval_runtime": 0.3459,
57
+ "eval_samples_per_second": 277.522,
58
+ "eval_steps_per_second": 8.673,
59
+ "step": 27
60
+ },
61
+ {
62
+ "epoch": 4.444444444444445,
63
+ "grad_norm": 19.70957374572754,
64
+ "learning_rate": 2.777777777777778e-05,
65
+ "loss": 2.895491716297523e+16,
66
+ "step": 30
67
+ },
68
+ {
69
+ "epoch": 4.888888888888889,
70
+ "eval_accuracy": 0.28125,
71
+ "eval_loss": 3.1846918359351296e+16,
72
+ "eval_runtime": 0.7223,
73
+ "eval_samples_per_second": 132.905,
74
+ "eval_steps_per_second": 4.153,
75
+ "step": 33
76
+ },
77
+ {
78
+ "epoch": 5.925925925925926,
79
+ "grad_norm": 21.029253005981445,
80
+ "learning_rate": 1.8518518518518518e-05,
81
+ "loss": 2.987389241744425e+16,
82
+ "step": 40
83
+ },
84
+ {
85
+ "epoch": 5.925925925925926,
86
+ "eval_accuracy": 0.28125,
87
+ "eval_loss": 3.1846918359351296e+16,
88
+ "eval_runtime": 0.4428,
89
+ "eval_samples_per_second": 216.799,
90
+ "eval_steps_per_second": 6.775,
91
+ "step": 40
92
+ },
93
+ {
94
+ "epoch": 6.962962962962963,
95
+ "eval_accuracy": 0.28125,
96
+ "eval_loss": 3.1846918359351296e+16,
97
+ "eval_runtime": 0.4296,
98
+ "eval_samples_per_second": 223.44,
99
+ "eval_steps_per_second": 6.983,
100
+ "step": 47
101
+ },
102
+ {
103
+ "epoch": 7.407407407407407,
104
+ "grad_norm": 21.59038543701172,
105
+ "learning_rate": 9.259259259259259e-06,
106
+ "loss": 2.957511044051763e+16,
107
+ "step": 50
108
+ },
109
+ {
110
+ "epoch": 8.0,
111
+ "eval_accuracy": 0.28125,
112
+ "eval_loss": 3.1846918359351296e+16,
113
+ "eval_runtime": 0.312,
114
+ "eval_samples_per_second": 307.663,
115
+ "eval_steps_per_second": 9.614,
116
+ "step": 54
117
+ },
118
+ {
119
+ "epoch": 8.88888888888889,
120
+ "grad_norm": 21.067672729492188,
121
+ "learning_rate": 0.0,
122
+ "loss": 2.9550508867846144e+16,
123
+ "step": 60
124
+ },
125
+ {
126
+ "epoch": 8.88888888888889,
127
+ "eval_accuracy": 0.28125,
128
+ "eval_loss": 3.1846918359351296e+16,
129
+ "eval_runtime": 0.5513,
130
+ "eval_samples_per_second": 174.136,
131
+ "eval_steps_per_second": 5.442,
132
+ "step": 60
133
+ },
134
+ {
135
+ "epoch": 8.88888888888889,
136
+ "step": 60,
137
+ "total_flos": 7.753465317556224e+16,
138
+ "train_loss": 3.2698800068537004e+16,
139
+ "train_runtime": 59.4328,
140
+ "train_samples_per_second": 145.374,
141
+ "train_steps_per_second": 1.01
142
  }
143
  ],
144
  "logging_steps": 10,
145
+ "max_steps": 60,
146
  "num_input_tokens_seen": 0,
147
+ "num_train_epochs": 10,
148
  "save_steps": 500,
149
  "stateful_callbacks": {
150
  "TrainerControl": {
 
158
  "attributes": {}
159
  }
160
  },
161
+ "total_flos": 7.753465317556224e+16,
162
  "train_batch_size": 32,
163
  "trial_name": null,
164
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ba227fe52ab42f1eb7551ecd405f08a8884fc5db4a00e2f66ed096fd565f757
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b4df92a5e5ff98f7bea34009aa7b914416f28e019091f9a9913feefc18b5fd2
3
  size 5112