Saving weights and logs of epoch 4 - step 8700
Browse files- ckpt_epoch_4_step_8700/config.json +169 -0
- ckpt_epoch_4_step_8700/flax_model.msgpack +3 -0
- ckpt_epoch_4_step_8700/generation_eval.json +0 -0
- ckpt_epoch_4_step_8700/merges.txt +0 -0
- ckpt_epoch_4_step_8700/special_tokens_map.json +1 -0
- ckpt_epoch_4_step_8700/tokenizer.json +0 -0
- ckpt_epoch_4_step_8700/tokenizer_config.json +1 -0
- ckpt_epoch_4_step_8700/vocab.json +0 -0
- events.out.tfevents.1633443513.t1v-n-bb5dfd23-w-0.8655.0.v2 +2 -2
- report.txt +32 -0
ckpt_epoch_4_step_8700/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_4_step_8700/flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ff36b431c23e7bce105a6846f384c34dd429dc31142684483746910741d9e73
|
3 |
+
size 956799284
|
ckpt_epoch_4_step_8700/generation_eval.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
ckpt_epoch_4_step_8700/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
ckpt_epoch_4_step_8700/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}
|
ckpt_epoch_4_step_8700/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
ckpt_epoch_4_step_8700/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_4_step_8700/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:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25e990b0be71c86218c052fd96d52e84fc543525670ee97a9419c3c00374452f
|
3 |
+
size 5971189
|
report.txt
CHANGED
@@ -900,3 +900,35 @@ Epoch... (4/30 | Step: 8390 | Loss: 1.7176601886749268, Learning Rate: 2.6363675
|
|
900 |
Epoch... (4/30 | Step: 8400 | Loss: 1.7720857858657837, Learning Rate: 2.635934106365312e-05)
|
901 |
Epoch... (4/30 | Step: 8400 | Loss: 1.7720857858657837, Learning Rate: 2.635934106365312e-05)
|
902 |
Epoch... (4/30 | Step: 8400 | Eval Loss: 1.899088978767395 | Eval rouge1: 41.3427 | Eval rouge2: 15.713 | Eval rougeL: 37.6044 | Eval rougeLsum: 37.602 | Eval gen_len: 11.2508 |)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
900 |
Epoch... (4/30 | Step: 8400 | Loss: 1.7720857858657837, Learning Rate: 2.635934106365312e-05)
|
901 |
Epoch... (4/30 | Step: 8400 | Loss: 1.7720857858657837, Learning Rate: 2.635934106365312e-05)
|
902 |
Epoch... (4/30 | Step: 8400 | Eval Loss: 1.899088978767395 | Eval rouge1: 41.3427 | Eval rouge2: 15.713 | Eval rougeL: 37.6044 | Eval rougeLsum: 37.602 | Eval gen_len: 11.2508 |)
|
903 |
+
Epoch... (4/30 | Step: 8410 | Loss: 1.7903679609298706, Learning Rate: 2.635500641190447e-05)
|
904 |
+
Epoch... (4/30 | Step: 8420 | Loss: 1.7643471956253052, Learning Rate: 2.635067176015582e-05)
|
905 |
+
Epoch... (4/30 | Step: 8430 | Loss: 1.7884368896484375, Learning Rate: 2.634633710840717e-05)
|
906 |
+
Epoch... (4/30 | Step: 8440 | Loss: 1.7901930809020996, Learning Rate: 2.634200245665852e-05)
|
907 |
+
Epoch... (4/30 | Step: 8450 | Loss: 1.8174161911010742, Learning Rate: 2.6337665985920466e-05)
|
908 |
+
Epoch... (4/30 | Step: 8460 | Loss: 1.7797125577926636, Learning Rate: 2.6333331334171817e-05)
|
909 |
+
Epoch... (4/30 | Step: 8470 | Loss: 1.743789553642273, Learning Rate: 2.6328996682423167e-05)
|
910 |
+
Epoch... (4/30 | Step: 8480 | Loss: 1.7208518981933594, Learning Rate: 2.632466384966392e-05)
|
911 |
+
Epoch... (4/30 | Step: 8490 | Loss: 1.7644871473312378, Learning Rate: 2.632032919791527e-05)
|
912 |
+
Epoch... (4/30 | Step: 8500 | Loss: 1.8212189674377441, Learning Rate: 2.631599454616662e-05)
|
913 |
+
Epoch... (4/30 | Step: 8510 | Loss: 1.7835339307785034, Learning Rate: 2.631165989441797e-05)
|
914 |
+
Epoch... (4/30 | Step: 8520 | Loss: 1.768432378768921, Learning Rate: 2.630732524266932e-05)
|
915 |
+
Epoch... (4/30 | Step: 8530 | Loss: 1.7398850917816162, Learning Rate: 2.6302990590920672e-05)
|
916 |
+
Epoch... (4/30 | Step: 8540 | Loss: 1.7920219898223877, Learning Rate: 2.629865412018262e-05)
|
917 |
+
Epoch... (4/30 | Step: 8550 | Loss: 1.8058758974075317, Learning Rate: 2.629431946843397e-05)
|
918 |
+
Epoch... (4/30 | Step: 8560 | Loss: 1.8054993152618408, Learning Rate: 2.628998481668532e-05)
|
919 |
+
Epoch... (4/30 | Step: 8570 | Loss: 1.7596275806427002, Learning Rate: 2.6285651983926073e-05)
|
920 |
+
Epoch... (4/30 | Step: 8580 | Loss: 1.7128454446792603, Learning Rate: 2.6281317332177423e-05)
|
921 |
+
Epoch... (4/30 | Step: 8590 | Loss: 1.8160572052001953, Learning Rate: 2.6276982680428773e-05)
|
922 |
+
Epoch... (4/30 | Step: 8600 | Loss: 1.7876338958740234, Learning Rate: 2.6272648028680123e-05)
|
923 |
+
Epoch... (4/30 | Step: 8610 | Loss: 1.7162377834320068, Learning Rate: 2.6268313376931474e-05)
|
924 |
+
Epoch... (4/30 | Step: 8620 | Loss: 1.7962429523468018, Learning Rate: 2.6263978725182824e-05)
|
925 |
+
Epoch... (4/30 | Step: 8630 | Loss: 1.7868194580078125, Learning Rate: 2.6259644073434174e-05)
|
926 |
+
Epoch... (4/30 | Step: 8640 | Loss: 1.778346061706543, Learning Rate: 2.6255309421685524e-05)
|
927 |
+
Epoch... (4/30 | Step: 8650 | Loss: 1.7848930358886719, Learning Rate: 2.6250974769936875e-05)
|
928 |
+
Epoch... (4/30 | Step: 8660 | Loss: 1.7496588230133057, Learning Rate: 2.6246640118188225e-05)
|
929 |
+
Epoch... (4/30 | Step: 8670 | Loss: 1.7488641738891602, Learning Rate: 2.6242305466439575e-05)
|
930 |
+
Epoch... (4/30 | Step: 8680 | Loss: 1.7910881042480469, Learning Rate: 2.6237970814690925e-05)
|
931 |
+
Epoch... (4/30 | Step: 8690 | Loss: 1.7799428701400757, Learning Rate: 2.6233636162942275e-05)
|
932 |
+
Epoch... (4/30 | Step: 8700 | Loss: 1.7098944187164307, Learning Rate: 2.6229301511193626e-05)
|
933 |
+
Epoch... (4/30 | Step: 8700 | Loss: 1.7098944187164307, Learning Rate: 2.6229301511193626e-05)
|
934 |
+
Epoch... (4/30 | Step: 8700 | Eval Loss: 1.9023772478103638 | Eval rouge1: 41.0716 | Eval rouge2: 15.5551 | Eval rougeL: 37.3622 | Eval rougeLsum: 37.3627 | Eval gen_len: 11.3028 |)
|