zabir735 commited on
Commit
0101d3d
1 Parent(s): 0893c93

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 11.0,
3
+ "train_loss": 1.5172127248242269,
4
+ "train_runtime": 9372.6529,
5
+ "train_samples_per_second": 2.056,
6
+ "train_steps_per_second": 0.257
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ }
27
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "49406": {
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49407": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": "<|startoftext|>",
22
+ "clean_up_tokenization_spaces": true,
23
+ "do_lower_case": true,
24
+ "eos_token": "<|endoftext|>",
25
+ "errors": "replace",
26
+ "model_max_length": 77,
27
+ "pad_token": "<|endoftext|>",
28
+ "tokenizer_class": "CLIPTokenizer",
29
+ "unk_token": "<|endoftext|>"
30
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 11.0,
3
+ "train_loss": 1.5172127248242269,
4
+ "train_runtime": 9372.6529,
5
+ "train_samples_per_second": 2.056,
6
+ "train_steps_per_second": 0.257
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 11.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2409,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 2.28,
13
+ "learning_rate": 3.9622249896222504e-05,
14
+ "loss": 1.9626,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 4.57,
19
+ "learning_rate": 2.9244499792445003e-05,
20
+ "loss": 1.7347,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 6.85,
25
+ "learning_rate": 1.8866749688667497e-05,
26
+ "loss": 1.4932,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 9.13,
31
+ "learning_rate": 8.488999584889996e-06,
32
+ "loss": 1.2625,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 11.0,
37
+ "step": 2409,
38
+ "total_flos": 1105239600655344.0,
39
+ "train_loss": 1.5172127248242269,
40
+ "train_runtime": 9372.6529,
41
+ "train_samples_per_second": 2.056,
42
+ "train_steps_per_second": 0.257
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 2409,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 11,
49
+ "save_steps": 500,
50
+ "total_flos": 1105239600655344.0,
51
+ "train_batch_size": 8,
52
+ "trial_name": null,
53
+ "trial_params": null
54
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff