Saving weights and logs of epoch 3 - step 6900
Browse files- ckpt_epoch_3_step_6900/config.json +169 -0
- ckpt_epoch_3_step_6900/flax_model.msgpack +3 -0
- ckpt_epoch_3_step_6900/generation_eval.json +0 -0
- ckpt_epoch_3_step_6900/merges.txt +0 -0
- ckpt_epoch_3_step_6900/special_tokens_map.json +1 -0
- ckpt_epoch_3_step_6900/tokenizer.json +0 -0
- ckpt_epoch_3_step_6900/tokenizer_config.json +1 -0
- ckpt_epoch_3_step_6900/vocab.json +0 -0
- events.out.tfevents.1633443513.t1v-n-bb5dfd23-w-0.8655.0.v2 +2 -2
- report.txt +32 -0
ckpt_epoch_3_step_6900/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_3_step_6900/flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df01c05234220e7fea4e92598162988c48315bb6fa2475b5d66f002875710be9
|
3 |
+
size 956799284
|
ckpt_epoch_3_step_6900/generation_eval.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
ckpt_epoch_3_step_6900/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
ckpt_epoch_3_step_6900/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}
|
ckpt_epoch_3_step_6900/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
ckpt_epoch_3_step_6900/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_3_step_6900/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 sha256:22f21a2c86dfa4ac032800a3a00b2b032aca84a755debf64cf5043610e598bc6
|
3 |
+
size 4721045
|
report.txt
CHANGED
@@ -706,3 +706,35 @@ Epoch... (3/30 | Step: 6590 | Loss: 1.836090326309204, Learning Rate: 2.71439093
|
|
706 |
Epoch... (3/30 | Step: 6600 | Loss: 1.8392951488494873, Learning Rate: 2.7139572921441868e-05)
|
707 |
Epoch... (3/30 | Step: 6600 | Loss: 1.8392951488494873, Learning Rate: 2.7139572921441868e-05)
|
708 |
Epoch... (3/30 | Step: 6600 | Eval Loss: 1.9147193431854248 | Eval rouge1: 41.1766 | Eval rouge2: 15.6082 | Eval rougeL: 37.5075 | Eval rougeLsum: 37.5043 | Eval gen_len: 11.1454 |)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
706 |
Epoch... (3/30 | Step: 6600 | Loss: 1.8392951488494873, Learning Rate: 2.7139572921441868e-05)
|
707 |
Epoch... (3/30 | Step: 6600 | Loss: 1.8392951488494873, Learning Rate: 2.7139572921441868e-05)
|
708 |
Epoch... (3/30 | Step: 6600 | Eval Loss: 1.9147193431854248 | Eval rouge1: 41.1766 | Eval rouge2: 15.6082 | Eval rougeL: 37.5075 | Eval rougeLsum: 37.5043 | Eval gen_len: 11.1454 |)
|
709 |
+
Epoch... (3/30 | Step: 6610 | Loss: 1.8817616701126099, Learning Rate: 2.7135238269693218e-05)
|
710 |
+
Epoch... (3/30 | Step: 6620 | Loss: 1.8995423316955566, Learning Rate: 2.7130905436933972e-05)
|
711 |
+
Epoch... (3/30 | Step: 6630 | Loss: 1.7520475387573242, Learning Rate: 2.7126570785185322e-05)
|
712 |
+
Epoch... (3/30 | Step: 6640 | Loss: 1.841223955154419, Learning Rate: 2.7122236133436672e-05)
|
713 |
+
Epoch... (3/30 | Step: 6650 | Loss: 1.7794084548950195, Learning Rate: 2.7117901481688023e-05)
|
714 |
+
Epoch... (3/30 | Step: 6660 | Loss: 1.8177577257156372, Learning Rate: 2.7113566829939373e-05)
|
715 |
+
Epoch... (3/30 | Step: 6670 | Loss: 1.844765543937683, Learning Rate: 2.7109232178190723e-05)
|
716 |
+
Epoch... (3/30 | Step: 6680 | Loss: 1.87111496925354, Learning Rate: 2.7104897526442073e-05)
|
717 |
+
Epoch... (3/30 | Step: 6690 | Loss: 1.8403642177581787, Learning Rate: 2.7100562874693424e-05)
|
718 |
+
Epoch... (3/30 | Step: 6700 | Loss: 1.819663643836975, Learning Rate: 2.7096228222944774e-05)
|
719 |
+
Epoch... (3/30 | Step: 6710 | Loss: 1.8723413944244385, Learning Rate: 2.7091893571196124e-05)
|
720 |
+
Epoch... (3/30 | Step: 6720 | Loss: 1.789346694946289, Learning Rate: 2.7087558919447474e-05)
|
721 |
+
Epoch... (3/30 | Step: 6730 | Loss: 1.864307165145874, Learning Rate: 2.7083224267698824e-05)
|
722 |
+
Epoch... (3/30 | Step: 6740 | Loss: 1.8256621360778809, Learning Rate: 2.7078889615950175e-05)
|
723 |
+
Epoch... (3/30 | Step: 6750 | Loss: 1.8974370956420898, Learning Rate: 2.7074554964201525e-05)
|
724 |
+
Epoch... (3/30 | Step: 6760 | Loss: 1.7825756072998047, Learning Rate: 2.7070220312452875e-05)
|
725 |
+
Epoch... (3/30 | Step: 6770 | Loss: 1.768592357635498, Learning Rate: 2.7065885660704225e-05)
|
726 |
+
Epoch... (3/30 | Step: 6780 | Loss: 1.8202202320098877, Learning Rate: 2.7061551008955576e-05)
|
727 |
+
Epoch... (3/30 | Step: 6790 | Loss: 1.8324875831604004, Learning Rate: 2.7057216357206926e-05)
|
728 |
+
Epoch... (3/30 | Step: 6800 | Loss: 1.862152099609375, Learning Rate: 2.7052881705458276e-05)
|
729 |
+
Epoch... (3/30 | Step: 6810 | Loss: 1.855210781097412, Learning Rate: 2.7048547053709626e-05)
|
730 |
+
Epoch... (3/30 | Step: 6820 | Loss: 1.8279563188552856, Learning Rate: 2.7044212401960976e-05)
|
731 |
+
Epoch... (3/30 | Step: 6830 | Loss: 1.7613282203674316, Learning Rate: 2.7039877750212327e-05)
|
732 |
+
Epoch... (3/30 | Step: 6840 | Loss: 1.8263907432556152, Learning Rate: 2.7035543098463677e-05)
|
733 |
+
Epoch... (3/30 | Step: 6850 | Loss: 1.8450121879577637, Learning Rate: 2.7031208446715027e-05)
|
734 |
+
Epoch... (3/30 | Step: 6860 | Loss: 1.8444921970367432, Learning Rate: 2.7026873794966377e-05)
|
735 |
+
Epoch... (3/30 | Step: 6870 | Loss: 1.7890636920928955, Learning Rate: 2.7022539143217728e-05)
|
736 |
+
Epoch... (3/30 | Step: 6880 | Loss: 1.8365561962127686, Learning Rate: 2.701820631045848e-05)
|
737 |
+
Epoch... (3/30 | Step: 6890 | Loss: 1.871873378753662, Learning Rate: 2.701387165870983e-05)
|
738 |
+
Epoch... (3/30 | Step: 6900 | Loss: 1.7828240394592285, Learning Rate: 2.7009535187971778e-05)
|
739 |
+
Epoch... (3/30 | Step: 6900 | Loss: 1.7828240394592285, Learning Rate: 2.7009535187971778e-05)
|
740 |
+
Epoch... (3/30 | Step: 6900 | Eval Loss: 1.9094223976135254 | Eval rouge1: 41.6785 | Eval rouge2: 15.9564 | Eval rougeL: 37.9578 | Eval rougeLsum: 37.96 | Eval gen_len: 11.0899 |)
|