Hugging Face's logo

ydshieh
/
vit-gpt2-coco-en-ckpts

Image Classification
PyTorch
JAX
TensorBoard
generic
vision-encoder-decoder
Model card Files
xet
 Metrics Community
4
ydshieh HF Staff commited on
Commit
3143a0f
·
1 Parent(s): 14a752b

Saving weights and logs of epoch 2 - step 3000

Browse files
Files changed (10) hide show
  1. ckpt_epoch_2_step_3000/config.json +169 -0
  2. ckpt_epoch_2_step_3000/flax_model.msgpack +3 -0
  3. ckpt_epoch_2_step_3000/generation_eval.json +0 -0
  4. ckpt_epoch_2_step_3000/merges.txt +0 -0
  5. ckpt_epoch_2_step_3000/special_tokens_map.json +1 -0
  6. ckpt_epoch_2_step_3000/tokenizer.json +0 -0
  7. ckpt_epoch_2_step_3000/tokenizer_config.json +1 -0
  8. ckpt_epoch_2_step_3000/vocab.json +0 -0
  9. events.out.tfevents.1633443513.t1v-n-bb5dfd23-w-0.8655.0.v2 +2 -2
  10. report.txt +32 -0
ckpt_epoch_2_step_3000/config.json ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "VisionEncoderDecoderModel"
4
+ ],
5
+ "bos_token_id": 50256,
6
+ "decoder": {
7
+ "_name_or_path": "",
8
+ "activation_function": "gelu_new",
9
+ "add_cross_attention": true,
10
+ "architectures": [
11
+ "GPT2LMHeadModel"
12
+ ],
13
+ "attn_pdrop": 0.1,
14
+ "bad_words_ids": null,
15
+ "bos_token_id": 50256,
16
+ "chunk_size_feed_forward": 0,
17
+ "decoder_start_token_id": 50256,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "embd_pdrop": 0.1,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": 50256,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "id2label": {
28
+ "0": "LABEL_0",
29
+ "1": "LABEL_1"
30
+ },
31
+ "initializer_range": 0.02,
32
+ "is_decoder": true,
33
+ "is_encoder_decoder": false,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1
37
+ },
38
+ "layer_norm_epsilon": 1e-05,
39
+ "length_penalty": 1.0,
40
+ "max_length": 20,
41
+ "min_length": 0,
42
+ "model_type": "gpt2",
43
+ "n_ctx": 1024,
44
+ "n_embd": 768,
45
+ "n_head": 12,
46
+ "n_inner": null,
47
+ "n_layer": 12,
48
+ "n_positions": 1024,
49
+ "no_repeat_ngram_size": 0,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_scores": false,
56
+ "pad_token_id": 50256,
57
+ "prefix": null,
58
+ "problem_type": null,
59
+ "pruned_heads": {},
60
+ "remove_invalid_values": false,
61
+ "repetition_penalty": 1.0,
62
+ "resid_pdrop": 0.1,
63
+ "return_dict": true,
64
+ "return_dict_in_generate": false,
65
+ "scale_attn_weights": true,
66
+ "sep_token_id": null,
67
+ "summary_activation": null,
68
+ "summary_first_dropout": 0.1,
69
+ "summary_proj_to_labels": true,
70
+ "summary_type": "cls_index",
71
+ "summary_use_proj": true,
72
+ "task_specific_params": {
73
+ "text-generation": {
74
+ "do_sample": true,
75
+ "max_length": 50
76
+ }
77
+ },
78
+ "temperature": 1.0,
79
+ "tie_encoder_decoder": false,
80
+ "tie_word_embeddings": true,
81
+ "tokenizer_class": null,
82
+ "top_k": 50,
83
+ "top_p": 1.0,
84
+ "torch_dtype": null,
85
+ "torchscript": false,
86
+ "transformers_version": "4.11.0.dev0",
87
+ "use_bfloat16": false,
88
+ "use_cache": true,
89
+ "vocab_size": 50257
90
+ },
91
+ "decoder_start_token_id": 50256,
92
+ "encoder": {
93
+ "_name_or_path": "",
94
+ "add_cross_attention": false,
95
+ "architectures": [
96
+ "ViTModel"
97
+ ],
98
+ "attention_probs_dropout_prob": 0.0,
99
+ "bad_words_ids": null,
100
+ "bos_token_id": null,
101
+ "chunk_size_feed_forward": 0,
102
+ "decoder_start_token_id": null,
103
+ "diversity_penalty": 0.0,
104
+ "do_sample": false,
105
+ "early_stopping": false,
106
+ "encoder_no_repeat_ngram_size": 0,
107
+ "eos_token_id": null,
108
+ "finetuning_task": null,
109
+ "forced_bos_token_id": null,
110
+ "forced_eos_token_id": null,
111
+ "hidden_act": "gelu",
112
+ "hidden_dropout_prob": 0.0,
113
+ "hidden_size": 768,
114
+ "id2label": {
115
+ "0": "LABEL_0",
116
+ "1": "LABEL_1"
117
+ },
118
+ "image_size": 224,
119
+ "initializer_range": 0.02,
120
+ "intermediate_size": 3072,
121
+ "is_decoder": false,
122
+ "is_encoder_decoder": false,
123
+ "label2id": {
124
+ "LABEL_0": 0,
125
+ "LABEL_1": 1
126
+ },
127
+ "layer_norm_eps": 1e-12,
128
+ "length_penalty": 1.0,
129
+ "max_length": 20,
130
+ "min_length": 0,
131
+ "model_type": "vit",
132
+ "no_repeat_ngram_size": 0,
133
+ "num_attention_heads": 12,
134
+ "num_beam_groups": 1,
135
+ "num_beams": 1,
136
+ "num_channels": 3,
137
+ "num_hidden_layers": 12,
138
+ "num_return_sequences": 1,
139
+ "output_attentions": false,
140
+ "output_hidden_states": false,
141
+ "output_scores": false,
142
+ "pad_token_id": null,
143
+ "patch_size": 16,
144
+ "prefix": null,
145
+ "problem_type": null,
146
+ "pruned_heads": {},
147
+ "remove_invalid_values": false,
148
+ "repetition_penalty": 1.0,
149
+ "return_dict": true,
150
+ "return_dict_in_generate": false,
151
+ "sep_token_id": null,
152
+ "task_specific_params": null,
153
+ "temperature": 1.0,
154
+ "tie_encoder_decoder": false,
155
+ "tie_word_embeddings": true,
156
+ "tokenizer_class": null,
157
+ "top_k": 50,
158
+ "top_p": 1.0,
159
+ "torch_dtype": null,
160
+ "torchscript": false,
161
+ "transformers_version": "4.11.0.dev0",
162
+ "use_bfloat16": false
163
+ },
164
+ "eos_token_id": 50256,
165
+ "is_encoder_decoder": true,
166
+ "model_type": "vision-encoder-decoder",
167
+ "pad_token_id": 50256,
168
+ "transformers_version": null
169
+ }
ckpt_epoch_2_step_3000/flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66b22ea5a0b2a4c77b9c6592a1f9ba764b26e744ab61944e1d6ec81178e75184
3
+ size 956799284
ckpt_epoch_2_step_3000/generation_eval.json ADDED
The diff for this file is too large to render. See raw diff
 
ckpt_epoch_2_step_3000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
ckpt_epoch_2_step_3000/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}
ckpt_epoch_2_step_3000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
ckpt_epoch_2_step_3000/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
ckpt_epoch_2_step_3000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
events.out.tfevents.1633443513.t1v-n-bb5dfd23-w-0.8655.0.v2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11e55aaee55ba295b3206dd0ebc81a2a71d40030a982cc3b6be33bba5c0391c4
3
- size 1648289
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34d511f9ba292d071293ec42b1b0234544a3433795b853f55a2f74b28ba9af32
3
+ size 1750651
report.txt CHANGED
@@ -288,3 +288,35 @@ Epoch... (2/30 | Step: 2690 | Loss: 1.928293228149414, Learning Rate: 2.88344162
288
  Epoch... (2/30 | Step: 2700 | Loss: 2.0274925231933594, Learning Rate: 2.883008164644707e-05)
289
  Epoch... (2/30 | Step: 2700 | Loss: 2.0274925231933594, Learning Rate: 2.883008164644707e-05)
290
  Epoch... (2/30 | Step: 2700 | Eval Loss: 2.009991407394409 | Eval rouge1: 40.5888 | Eval rouge2: 15.0982 | Eval rougeL: 36.9127 | Eval rougeLsum: 36.9165 | Eval gen_len: 10.6976 |)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
288
  Epoch... (2/30 | Step: 2700 | Loss: 2.0274925231933594, Learning Rate: 2.883008164644707e-05)
289
  Epoch... (2/30 | Step: 2700 | Loss: 2.0274925231933594, Learning Rate: 2.883008164644707e-05)
290
  Epoch... (2/30 | Step: 2700 | Eval Loss: 2.009991407394409 | Eval rouge1: 40.5888 | Eval rouge2: 15.0982 | Eval rougeL: 36.9127 | Eval rougeLsum: 36.9165 | Eval gen_len: 10.6976 |)
291
+ Epoch... (2/30 | Step: 2710 | Loss: 1.939640760421753, Learning Rate: 2.8825745175709017e-05)
292
+ Epoch... (2/30 | Step: 2720 | Loss: 1.9807898998260498, Learning Rate: 2.882141234294977e-05)
293
+ Epoch... (2/30 | Step: 2730 | Loss: 1.9780454635620117, Learning Rate: 2.881707769120112e-05)
294
+ Epoch... (2/30 | Step: 2740 | Loss: 1.9607644081115723, Learning Rate: 2.881274303945247e-05)
295
+ Epoch... (2/30 | Step: 2750 | Loss: 1.9642720222473145, Learning Rate: 2.880840838770382e-05)
296
+ Epoch... (2/30 | Step: 2760 | Loss: 2.0490057468414307, Learning Rate: 2.880407373595517e-05)
297
+ Epoch... (2/30 | Step: 2770 | Loss: 1.982258915901184, Learning Rate: 2.879973908420652e-05)
298
+ Epoch... (2/30 | Step: 2780 | Loss: 1.9002817869186401, Learning Rate: 2.8795404432457872e-05)
299
+ Epoch... (2/30 | Step: 2790 | Loss: 1.9543405771255493, Learning Rate: 2.8791069780709222e-05)
300
+ Epoch... (2/30 | Step: 2800 | Loss: 1.924607753753662, Learning Rate: 2.8786735128960572e-05)
301
+ Epoch... (2/30 | Step: 2810 | Loss: 1.9794992208480835, Learning Rate: 2.8782402296201326e-05)
302
+ Epoch... (2/30 | Step: 2820 | Loss: 1.9884564876556396, Learning Rate: 2.8778065825463273e-05)
303
+ Epoch... (2/30 | Step: 2830 | Loss: 2.0604281425476074, Learning Rate: 2.8773731173714623e-05)
304
+ Epoch... (2/30 | Step: 2840 | Loss: 1.9901032447814941, Learning Rate: 2.8769396521965973e-05)
305
+ Epoch... (2/30 | Step: 2850 | Loss: 1.9847352504730225, Learning Rate: 2.8765061870217323e-05)
306
+ Epoch... (2/30 | Step: 2860 | Loss: 1.9160382747650146, Learning Rate: 2.8760727218468674e-05)
307
+ Epoch... (2/30 | Step: 2870 | Loss: 2.013071060180664, Learning Rate: 2.8756392566720024e-05)
308
+ Epoch... (2/30 | Step: 2880 | Loss: 2.004521369934082, Learning Rate: 2.8752057914971374e-05)
309
+ Epoch... (2/30 | Step: 2890 | Loss: 1.962958812713623, Learning Rate: 2.8747723263222724e-05)
310
+ Epoch... (2/30 | Step: 2900 | Loss: 2.002131223678589, Learning Rate: 2.8743390430463478e-05)
311
+ Epoch... (2/30 | Step: 2910 | Loss: 1.8968100547790527, Learning Rate: 2.8739053959725425e-05)
312
+ Epoch... (2/30 | Step: 2920 | Loss: 1.9270609617233276, Learning Rate: 2.8734719307976775e-05)
313
+ Epoch... (2/30 | Step: 2930 | Loss: 1.918048620223999, Learning Rate: 2.8730384656228125e-05)
314
+ Epoch... (2/30 | Step: 2940 | Loss: 2.055185317993164, Learning Rate: 2.8726050004479475e-05)
315
+ Epoch... (2/30 | Step: 2950 | Loss: 1.998548984527588, Learning Rate: 2.8721715352730826e-05)
316
+ Epoch... (2/30 | Step: 2960 | Loss: 1.9728754758834839, Learning Rate: 2.8717380700982176e-05)
317
+ Epoch... (2/30 | Step: 2970 | Loss: 2.0119190216064453, Learning Rate: 2.8713046049233526e-05)
318
+ Epoch... (2/30 | Step: 2980 | Loss: 1.9915521144866943, Learning Rate: 2.870871321647428e-05)
319
+ Epoch... (2/30 | Step: 2990 | Loss: 2.039159059524536, Learning Rate: 2.870437856472563e-05)
320
+ Epoch... (2/30 | Step: 3000 | Loss: 1.9609485864639282, Learning Rate: 2.870004391297698e-05)
321
+ Epoch... (2/30 | Step: 3000 | Loss: 1.9609485864639282, Learning Rate: 2.870004391297698e-05)
322
+ Epoch... (2/30 | Step: 3000 | Eval Loss: 1.9941604137420654 | Eval rouge1: 40.6226 | Eval rouge2: 15.1062 | Eval rougeL: 36.9129 | Eval rougeLsum: 36.9145 | Eval gen_len: 11.0414 |)