Riyagarg01
commited on
Commit
•
2d7e769
1
Parent(s):
c7fc65a
Disease Model
Browse files- checkpoint-5500/config.json +74 -0
- checkpoint-5500/merges.txt +0 -0
- checkpoint-5500/optimizer.pt +3 -0
- checkpoint-5500/pytorch_model.bin +3 -0
- checkpoint-5500/rng_state.pth +3 -0
- checkpoint-5500/scheduler.pt +3 -0
- checkpoint-5500/special_tokens_map.json +1 -0
- checkpoint-5500/tokenizer.json +0 -0
- checkpoint-5500/tokenizer_config.json +1 -0
- checkpoint-5500/trainer_state.json +676 -0
- checkpoint-5500/training_args.bin +3 -0
- checkpoint-5500/vocab.json +0 -0
checkpoint-5500/config.json
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mse30/bart-base-finetuned-pubmed",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 768,
|
15 |
+
"decoder_attention_heads": 12,
|
16 |
+
"decoder_ffn_dim": 3072,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
+
"encoder_attention_heads": 12,
|
23 |
+
"encoder_ffn_dim": 3072,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 6,
|
26 |
+
"eos_token_id": 2,
|
27 |
+
"forced_eos_token_id": 2,
|
28 |
+
"gradient_checkpointing": false,
|
29 |
+
"id2label": {
|
30 |
+
"0": "LABEL_0",
|
31 |
+
"1": "LABEL_1",
|
32 |
+
"2": "LABEL_2"
|
33 |
+
},
|
34 |
+
"init_std": 0.02,
|
35 |
+
"is_encoder_decoder": true,
|
36 |
+
"label2id": {
|
37 |
+
"LABEL_0": 0,
|
38 |
+
"LABEL_1": 1,
|
39 |
+
"LABEL_2": 2
|
40 |
+
},
|
41 |
+
"max_position_embeddings": 1024,
|
42 |
+
"model_type": "bart",
|
43 |
+
"no_repeat_ngram_size": 3,
|
44 |
+
"normalize_before": false,
|
45 |
+
"normalize_embedding": true,
|
46 |
+
"num_beams": 4,
|
47 |
+
"num_hidden_layers": 6,
|
48 |
+
"pad_token_id": 1,
|
49 |
+
"scale_embedding": false,
|
50 |
+
"task_specific_params": {
|
51 |
+
"summarization": {
|
52 |
+
"length_penalty": 1.0,
|
53 |
+
"max_length": 128,
|
54 |
+
"min_length": 12,
|
55 |
+
"num_beams": 4
|
56 |
+
},
|
57 |
+
"summarization_cnn": {
|
58 |
+
"length_penalty": 2.0,
|
59 |
+
"max_length": 142,
|
60 |
+
"min_length": 56,
|
61 |
+
"num_beams": 4
|
62 |
+
},
|
63 |
+
"summarization_xsum": {
|
64 |
+
"length_penalty": 1.0,
|
65 |
+
"max_length": 62,
|
66 |
+
"min_length": 11,
|
67 |
+
"num_beams": 6
|
68 |
+
}
|
69 |
+
},
|
70 |
+
"torch_dtype": "float32",
|
71 |
+
"transformers_version": "4.18.0",
|
72 |
+
"use_cache": true,
|
73 |
+
"vocab_size": 50265
|
74 |
+
}
|
checkpoint-5500/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-5500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a988750469ec9c4185517464d72e2482ef26ffe535670773e2bc2977a7a7f3a3
|
3 |
+
size 1115513717
|
checkpoint-5500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:560d12357b54abe52f4a519def012ddd4b15818d39eaaeebd1c673ad80cc9d6b
|
3 |
+
size 557969145
|
checkpoint-5500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:caefd0c4694b22128170fa4faccd1a87847208418a2aaf835a5e693d6129cd41
|
3 |
+
size 14439
|
checkpoint-5500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:580deaed40a80e8c76d2eceda5b97f3273ea4fc39a1547344947afd55cd0f9c2
|
3 |
+
size 623
|
checkpoint-5500/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
checkpoint-5500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-5500/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "mse30/bart-base-finetuned-pubmed", "tokenizer_class": "BartTokenizer"}
|
checkpoint-5500/trainer_state.json
ADDED
@@ -0,0 +1,676 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 100.0,
|
5 |
+
"global_step": 5500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.91,
|
12 |
+
"learning_rate": 3e-06,
|
13 |
+
"loss": 5.7103,
|
14 |
+
"step": 50
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.82,
|
18 |
+
"learning_rate": 6e-06,
|
19 |
+
"loss": 3.639,
|
20 |
+
"step": 100
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.73,
|
24 |
+
"learning_rate": 9e-06,
|
25 |
+
"loss": 2.7117,
|
26 |
+
"step": 150
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 3.64,
|
30 |
+
"learning_rate": 1.2e-05,
|
31 |
+
"loss": 2.4133,
|
32 |
+
"step": 200
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 4.55,
|
36 |
+
"learning_rate": 1.5e-05,
|
37 |
+
"loss": 2.2296,
|
38 |
+
"step": 250
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 5.45,
|
42 |
+
"learning_rate": 1.8e-05,
|
43 |
+
"loss": 2.107,
|
44 |
+
"step": 300
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 6.36,
|
48 |
+
"learning_rate": 2.1e-05,
|
49 |
+
"loss": 2.0333,
|
50 |
+
"step": 350
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 7.27,
|
54 |
+
"learning_rate": 2.4e-05,
|
55 |
+
"loss": 1.9731,
|
56 |
+
"step": 400
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 8.18,
|
60 |
+
"learning_rate": 2.7000000000000002e-05,
|
61 |
+
"loss": 1.8658,
|
62 |
+
"step": 450
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 9.09,
|
66 |
+
"learning_rate": 3e-05,
|
67 |
+
"loss": 1.8214,
|
68 |
+
"step": 500
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 10.0,
|
72 |
+
"learning_rate": 2.97e-05,
|
73 |
+
"loss": 1.7787,
|
74 |
+
"step": 550
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 10.91,
|
78 |
+
"learning_rate": 2.94e-05,
|
79 |
+
"loss": 1.7357,
|
80 |
+
"step": 600
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 11.82,
|
84 |
+
"learning_rate": 2.91e-05,
|
85 |
+
"loss": 1.6861,
|
86 |
+
"step": 650
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 12.73,
|
90 |
+
"learning_rate": 2.88e-05,
|
91 |
+
"loss": 1.6649,
|
92 |
+
"step": 700
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 13.64,
|
96 |
+
"learning_rate": 2.8499999999999998e-05,
|
97 |
+
"loss": 1.6325,
|
98 |
+
"step": 750
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 14.55,
|
102 |
+
"learning_rate": 2.8199999999999998e-05,
|
103 |
+
"loss": 1.6259,
|
104 |
+
"step": 800
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 15.45,
|
108 |
+
"learning_rate": 2.79e-05,
|
109 |
+
"loss": 1.6039,
|
110 |
+
"step": 850
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 16.36,
|
114 |
+
"learning_rate": 2.7600000000000003e-05,
|
115 |
+
"loss": 1.5857,
|
116 |
+
"step": 900
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 17.27,
|
120 |
+
"learning_rate": 2.7300000000000003e-05,
|
121 |
+
"loss": 1.5742,
|
122 |
+
"step": 950
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 18.18,
|
126 |
+
"learning_rate": 2.7000000000000002e-05,
|
127 |
+
"loss": 1.5558,
|
128 |
+
"step": 1000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 19.09,
|
132 |
+
"learning_rate": 2.6700000000000002e-05,
|
133 |
+
"loss": 1.5472,
|
134 |
+
"step": 1050
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 20.0,
|
138 |
+
"learning_rate": 2.64e-05,
|
139 |
+
"loss": 1.5427,
|
140 |
+
"step": 1100
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 20.91,
|
144 |
+
"learning_rate": 2.61e-05,
|
145 |
+
"loss": 1.5299,
|
146 |
+
"step": 1150
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 21.82,
|
150 |
+
"learning_rate": 2.58e-05,
|
151 |
+
"loss": 1.5232,
|
152 |
+
"step": 1200
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 22.73,
|
156 |
+
"learning_rate": 2.55e-05,
|
157 |
+
"loss": 1.5215,
|
158 |
+
"step": 1250
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 23.64,
|
162 |
+
"learning_rate": 2.52e-05,
|
163 |
+
"loss": 1.5097,
|
164 |
+
"step": 1300
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 24.55,
|
168 |
+
"learning_rate": 2.49e-05,
|
169 |
+
"loss": 1.5066,
|
170 |
+
"step": 1350
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 25.45,
|
174 |
+
"learning_rate": 2.4599999999999998e-05,
|
175 |
+
"loss": 1.502,
|
176 |
+
"step": 1400
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 26.36,
|
180 |
+
"learning_rate": 2.43e-05,
|
181 |
+
"loss": 1.4968,
|
182 |
+
"step": 1450
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 27.27,
|
186 |
+
"learning_rate": 2.4e-05,
|
187 |
+
"loss": 1.4971,
|
188 |
+
"step": 1500
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 28.18,
|
192 |
+
"learning_rate": 2.37e-05,
|
193 |
+
"loss": 1.4914,
|
194 |
+
"step": 1550
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 29.09,
|
198 |
+
"learning_rate": 2.3400000000000003e-05,
|
199 |
+
"loss": 1.4906,
|
200 |
+
"step": 1600
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 30.0,
|
204 |
+
"learning_rate": 2.3100000000000002e-05,
|
205 |
+
"loss": 1.4842,
|
206 |
+
"step": 1650
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 30.91,
|
210 |
+
"learning_rate": 2.2800000000000002e-05,
|
211 |
+
"loss": 1.4828,
|
212 |
+
"step": 1700
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 31.82,
|
216 |
+
"learning_rate": 2.25e-05,
|
217 |
+
"loss": 1.482,
|
218 |
+
"step": 1750
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 32.73,
|
222 |
+
"learning_rate": 2.22e-05,
|
223 |
+
"loss": 1.4768,
|
224 |
+
"step": 1800
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 33.64,
|
228 |
+
"learning_rate": 2.19e-05,
|
229 |
+
"loss": 1.4833,
|
230 |
+
"step": 1850
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 34.55,
|
234 |
+
"learning_rate": 2.16e-05,
|
235 |
+
"loss": 1.4731,
|
236 |
+
"step": 1900
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 35.45,
|
240 |
+
"learning_rate": 2.13e-05,
|
241 |
+
"loss": 1.4725,
|
242 |
+
"step": 1950
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 36.36,
|
246 |
+
"learning_rate": 2.1e-05,
|
247 |
+
"loss": 1.4685,
|
248 |
+
"step": 2000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 37.27,
|
252 |
+
"learning_rate": 2.07e-05,
|
253 |
+
"loss": 1.4706,
|
254 |
+
"step": 2050
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 38.18,
|
258 |
+
"learning_rate": 2.04e-05,
|
259 |
+
"loss": 1.4653,
|
260 |
+
"step": 2100
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 39.09,
|
264 |
+
"learning_rate": 2.01e-05,
|
265 |
+
"loss": 1.4649,
|
266 |
+
"step": 2150
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 40.0,
|
270 |
+
"learning_rate": 1.98e-05,
|
271 |
+
"loss": 1.464,
|
272 |
+
"step": 2200
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 40.91,
|
276 |
+
"learning_rate": 1.95e-05,
|
277 |
+
"loss": 1.4627,
|
278 |
+
"step": 2250
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 41.82,
|
282 |
+
"learning_rate": 1.9200000000000003e-05,
|
283 |
+
"loss": 1.4615,
|
284 |
+
"step": 2300
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 42.73,
|
288 |
+
"learning_rate": 1.8900000000000002e-05,
|
289 |
+
"loss": 1.4593,
|
290 |
+
"step": 2350
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 43.64,
|
294 |
+
"learning_rate": 1.86e-05,
|
295 |
+
"loss": 1.4593,
|
296 |
+
"step": 2400
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 44.55,
|
300 |
+
"learning_rate": 1.83e-05,
|
301 |
+
"loss": 1.4595,
|
302 |
+
"step": 2450
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 45.45,
|
306 |
+
"learning_rate": 1.8e-05,
|
307 |
+
"loss": 1.4573,
|
308 |
+
"step": 2500
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 46.36,
|
312 |
+
"learning_rate": 1.77e-05,
|
313 |
+
"loss": 1.456,
|
314 |
+
"step": 2550
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 47.27,
|
318 |
+
"learning_rate": 1.74e-05,
|
319 |
+
"loss": 1.4578,
|
320 |
+
"step": 2600
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 48.18,
|
324 |
+
"learning_rate": 1.71e-05,
|
325 |
+
"loss": 1.4589,
|
326 |
+
"step": 2650
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 49.09,
|
330 |
+
"learning_rate": 1.6800000000000002e-05,
|
331 |
+
"loss": 1.4552,
|
332 |
+
"step": 2700
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 50.0,
|
336 |
+
"learning_rate": 1.65e-05,
|
337 |
+
"loss": 1.4546,
|
338 |
+
"step": 2750
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 50.91,
|
342 |
+
"learning_rate": 1.62e-05,
|
343 |
+
"loss": 1.453,
|
344 |
+
"step": 2800
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 51.82,
|
348 |
+
"learning_rate": 1.59e-05,
|
349 |
+
"loss": 1.4516,
|
350 |
+
"step": 2850
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 52.73,
|
354 |
+
"learning_rate": 1.56e-05,
|
355 |
+
"loss": 1.4519,
|
356 |
+
"step": 2900
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 53.64,
|
360 |
+
"learning_rate": 1.53e-05,
|
361 |
+
"loss": 1.4529,
|
362 |
+
"step": 2950
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 54.55,
|
366 |
+
"learning_rate": 1.5e-05,
|
367 |
+
"loss": 1.4508,
|
368 |
+
"step": 3000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 55.45,
|
372 |
+
"learning_rate": 1.47e-05,
|
373 |
+
"loss": 1.4495,
|
374 |
+
"step": 3050
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 56.36,
|
378 |
+
"learning_rate": 1.44e-05,
|
379 |
+
"loss": 1.4491,
|
380 |
+
"step": 3100
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 57.27,
|
384 |
+
"learning_rate": 1.4099999999999999e-05,
|
385 |
+
"loss": 1.4501,
|
386 |
+
"step": 3150
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 58.18,
|
390 |
+
"learning_rate": 1.3800000000000002e-05,
|
391 |
+
"loss": 1.4485,
|
392 |
+
"step": 3200
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 59.09,
|
396 |
+
"learning_rate": 1.3500000000000001e-05,
|
397 |
+
"loss": 1.447,
|
398 |
+
"step": 3250
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 60.0,
|
402 |
+
"learning_rate": 1.32e-05,
|
403 |
+
"loss": 1.4466,
|
404 |
+
"step": 3300
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 60.91,
|
408 |
+
"learning_rate": 1.29e-05,
|
409 |
+
"loss": 1.4464,
|
410 |
+
"step": 3350
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 61.82,
|
414 |
+
"learning_rate": 1.26e-05,
|
415 |
+
"loss": 1.4467,
|
416 |
+
"step": 3400
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 62.73,
|
420 |
+
"learning_rate": 1.2299999999999999e-05,
|
421 |
+
"loss": 1.4463,
|
422 |
+
"step": 3450
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 63.64,
|
426 |
+
"learning_rate": 1.2e-05,
|
427 |
+
"loss": 1.445,
|
428 |
+
"step": 3500
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 64.55,
|
432 |
+
"learning_rate": 1.1700000000000001e-05,
|
433 |
+
"loss": 1.4457,
|
434 |
+
"step": 3550
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 65.45,
|
438 |
+
"learning_rate": 1.1400000000000001e-05,
|
439 |
+
"loss": 1.4455,
|
440 |
+
"step": 3600
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 66.36,
|
444 |
+
"learning_rate": 1.11e-05,
|
445 |
+
"loss": 1.4439,
|
446 |
+
"step": 3650
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 67.27,
|
450 |
+
"learning_rate": 1.08e-05,
|
451 |
+
"loss": 1.444,
|
452 |
+
"step": 3700
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 68.18,
|
456 |
+
"learning_rate": 1.05e-05,
|
457 |
+
"loss": 1.444,
|
458 |
+
"step": 3750
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 69.09,
|
462 |
+
"learning_rate": 1.02e-05,
|
463 |
+
"loss": 1.4442,
|
464 |
+
"step": 3800
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 70.0,
|
468 |
+
"learning_rate": 9.9e-06,
|
469 |
+
"loss": 1.4428,
|
470 |
+
"step": 3850
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 70.91,
|
474 |
+
"learning_rate": 9.600000000000001e-06,
|
475 |
+
"loss": 1.4443,
|
476 |
+
"step": 3900
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 71.82,
|
480 |
+
"learning_rate": 9.3e-06,
|
481 |
+
"loss": 1.4436,
|
482 |
+
"step": 3950
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 72.73,
|
486 |
+
"learning_rate": 9e-06,
|
487 |
+
"loss": 1.4429,
|
488 |
+
"step": 4000
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 73.64,
|
492 |
+
"learning_rate": 8.7e-06,
|
493 |
+
"loss": 1.4419,
|
494 |
+
"step": 4050
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 74.55,
|
498 |
+
"learning_rate": 8.400000000000001e-06,
|
499 |
+
"loss": 1.4415,
|
500 |
+
"step": 4100
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 75.45,
|
504 |
+
"learning_rate": 8.1e-06,
|
505 |
+
"loss": 1.4406,
|
506 |
+
"step": 4150
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 76.36,
|
510 |
+
"learning_rate": 7.8e-06,
|
511 |
+
"loss": 1.443,
|
512 |
+
"step": 4200
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 77.27,
|
516 |
+
"learning_rate": 7.5e-06,
|
517 |
+
"loss": 1.4402,
|
518 |
+
"step": 4250
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 78.18,
|
522 |
+
"learning_rate": 7.2e-06,
|
523 |
+
"loss": 1.441,
|
524 |
+
"step": 4300
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 79.09,
|
528 |
+
"learning_rate": 6.900000000000001e-06,
|
529 |
+
"loss": 1.4403,
|
530 |
+
"step": 4350
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 80.0,
|
534 |
+
"learning_rate": 6.6e-06,
|
535 |
+
"loss": 1.4407,
|
536 |
+
"step": 4400
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 80.91,
|
540 |
+
"learning_rate": 6.3e-06,
|
541 |
+
"loss": 1.44,
|
542 |
+
"step": 4450
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 81.82,
|
546 |
+
"learning_rate": 6e-06,
|
547 |
+
"loss": 1.4401,
|
548 |
+
"step": 4500
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 82.73,
|
552 |
+
"learning_rate": 5.7000000000000005e-06,
|
553 |
+
"loss": 1.4391,
|
554 |
+
"step": 4550
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 83.64,
|
558 |
+
"learning_rate": 5.4e-06,
|
559 |
+
"loss": 1.4399,
|
560 |
+
"step": 4600
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 84.55,
|
564 |
+
"learning_rate": 5.1e-06,
|
565 |
+
"loss": 1.4403,
|
566 |
+
"step": 4650
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 85.45,
|
570 |
+
"learning_rate": 4.800000000000001e-06,
|
571 |
+
"loss": 1.4389,
|
572 |
+
"step": 4700
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 86.36,
|
576 |
+
"learning_rate": 4.5e-06,
|
577 |
+
"loss": 1.4394,
|
578 |
+
"step": 4750
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 87.27,
|
582 |
+
"learning_rate": 4.2000000000000004e-06,
|
583 |
+
"loss": 1.4394,
|
584 |
+
"step": 4800
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 88.18,
|
588 |
+
"learning_rate": 3.9e-06,
|
589 |
+
"loss": 1.4386,
|
590 |
+
"step": 4850
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 89.09,
|
594 |
+
"learning_rate": 3.6e-06,
|
595 |
+
"loss": 1.4388,
|
596 |
+
"step": 4900
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 90.0,
|
600 |
+
"learning_rate": 3.3e-06,
|
601 |
+
"loss": 1.4394,
|
602 |
+
"step": 4950
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 90.91,
|
606 |
+
"learning_rate": 3e-06,
|
607 |
+
"loss": 1.439,
|
608 |
+
"step": 5000
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 91.82,
|
612 |
+
"learning_rate": 2.7e-06,
|
613 |
+
"loss": 1.4387,
|
614 |
+
"step": 5050
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 92.73,
|
618 |
+
"learning_rate": 2.4000000000000003e-06,
|
619 |
+
"loss": 1.4396,
|
620 |
+
"step": 5100
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 93.64,
|
624 |
+
"learning_rate": 2.1000000000000002e-06,
|
625 |
+
"loss": 1.4377,
|
626 |
+
"step": 5150
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 94.55,
|
630 |
+
"learning_rate": 1.8e-06,
|
631 |
+
"loss": 1.4383,
|
632 |
+
"step": 5200
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 95.45,
|
636 |
+
"learning_rate": 1.5e-06,
|
637 |
+
"loss": 1.4378,
|
638 |
+
"step": 5250
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 96.36,
|
642 |
+
"learning_rate": 1.2000000000000002e-06,
|
643 |
+
"loss": 1.4383,
|
644 |
+
"step": 5300
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 97.27,
|
648 |
+
"learning_rate": 9e-07,
|
649 |
+
"loss": 1.4379,
|
650 |
+
"step": 5350
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 98.18,
|
654 |
+
"learning_rate": 6.000000000000001e-07,
|
655 |
+
"loss": 1.4374,
|
656 |
+
"step": 5400
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 99.09,
|
660 |
+
"learning_rate": 3.0000000000000004e-07,
|
661 |
+
"loss": 1.4375,
|
662 |
+
"step": 5450
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 100.0,
|
666 |
+
"learning_rate": 0.0,
|
667 |
+
"loss": 1.4379,
|
668 |
+
"step": 5500
|
669 |
+
}
|
670 |
+
],
|
671 |
+
"max_steps": 5500,
|
672 |
+
"num_train_epochs": 100,
|
673 |
+
"total_flos": 1.3353228435456e+16,
|
674 |
+
"trial_name": null,
|
675 |
+
"trial_params": null
|
676 |
+
}
|
checkpoint-5500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5d6d75854a1d3a8362f0fc3ffb557477622f5f795ebe7f99e10487c2aae36d6
|
3 |
+
size 3119
|
checkpoint-5500/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|