jibala-1022
commited on
Commit
•
84a7b61
1
Parent(s):
6de183a
Upload local model
Browse files- config.json +27 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer_config.json +57 -0
- trainer_state.json +439 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./baseline_embedders/roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"Easyrec"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.46.1",
|
24 |
+
"type_vocab_size": 1,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 50265
|
27 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93585abd4ccfee4f2d2172711f8f42d1f8ff6c795de6349b635ec65ca5db70f2
|
3 |
+
size 655737594
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:513006ad8fa052431cb56b6f2c2ead54c64fdbd9b9a01dc5645c6845e76092d8
|
3 |
+
size 327853822
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5055fce62b22791dec01b4f36723ce996784d067b18ddc7fc7af0a8f9ac4ce31
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5b706c8e99f08314946f4320f89ca1b5e4b7d3ff15c61be602527aa36c0d1d7
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": false,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 512,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"padding_side": "right",
|
54 |
+
"sep_token": "</s>",
|
55 |
+
"tokenizer_class": "RobertaTokenizer",
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,439 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.019987082897612984,
|
3 |
+
"best_model_checkpoint": "./checkpoints/easyrec-roberta-base",
|
4 |
+
"epoch": 1.7954432887568101,
|
5 |
+
"eval_steps": 1000,
|
6 |
+
"global_step": 29000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.030955918771669144,
|
13 |
+
"grad_norm": 37.25,
|
14 |
+
"learning_rate": 4.9484068020472185e-05,
|
15 |
+
"loss": 2.3504,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.06191183754333829,
|
20 |
+
"grad_norm": 27.625,
|
21 |
+
"learning_rate": 4.896813604094436e-05,
|
22 |
+
"loss": 2.0019,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.09286775631500743,
|
27 |
+
"grad_norm": 43.75,
|
28 |
+
"learning_rate": 4.8452204061416544e-05,
|
29 |
+
"loss": 1.9156,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.12382367508667658,
|
34 |
+
"grad_norm": 36.75,
|
35 |
+
"learning_rate": 4.793627208188873e-05,
|
36 |
+
"loss": 1.8431,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.15477959385834572,
|
41 |
+
"grad_norm": 31.25,
|
42 |
+
"learning_rate": 4.74203401023609e-05,
|
43 |
+
"loss": 1.8579,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.18573551263001487,
|
48 |
+
"grad_norm": 27.375,
|
49 |
+
"learning_rate": 4.6904408122833086e-05,
|
50 |
+
"loss": 1.8486,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.216691431401684,
|
55 |
+
"grad_norm": 28.5,
|
56 |
+
"learning_rate": 4.638847614330527e-05,
|
57 |
+
"loss": 1.771,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.24764735017335315,
|
62 |
+
"grad_norm": 39.75,
|
63 |
+
"learning_rate": 4.587254416377745e-05,
|
64 |
+
"loss": 1.7856,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.2786032689450223,
|
69 |
+
"grad_norm": 31.0,
|
70 |
+
"learning_rate": 4.5356612184249634e-05,
|
71 |
+
"loss": 1.7762,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.30955918771669144,
|
76 |
+
"grad_norm": 50.75,
|
77 |
+
"learning_rate": 4.484068020472182e-05,
|
78 |
+
"loss": 1.7399,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.3405151064883606,
|
83 |
+
"grad_norm": 32.5,
|
84 |
+
"learning_rate": 4.432474822519399e-05,
|
85 |
+
"loss": 1.7679,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.37147102526002973,
|
90 |
+
"grad_norm": 31.625,
|
91 |
+
"learning_rate": 4.3808816245666175e-05,
|
92 |
+
"loss": 1.7481,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.4024269440316989,
|
97 |
+
"grad_norm": 54.0,
|
98 |
+
"learning_rate": 4.329288426613836e-05,
|
99 |
+
"loss": 1.7463,
|
100 |
+
"step": 6500
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.433382862803368,
|
104 |
+
"grad_norm": 40.75,
|
105 |
+
"learning_rate": 4.2776952286610534e-05,
|
106 |
+
"loss": 1.7458,
|
107 |
+
"step": 7000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.46433878157503716,
|
111 |
+
"grad_norm": 46.5,
|
112 |
+
"learning_rate": 4.226102030708272e-05,
|
113 |
+
"loss": 1.7173,
|
114 |
+
"step": 7500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.4952947003467063,
|
118 |
+
"grad_norm": 68.5,
|
119 |
+
"learning_rate": 4.17450883275549e-05,
|
120 |
+
"loss": 1.7502,
|
121 |
+
"step": 8000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.5262506191183755,
|
125 |
+
"grad_norm": 41.25,
|
126 |
+
"learning_rate": 4.1229156348027076e-05,
|
127 |
+
"loss": 1.7286,
|
128 |
+
"step": 8500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.5572065378900446,
|
132 |
+
"grad_norm": 30.25,
|
133 |
+
"learning_rate": 4.071322436849926e-05,
|
134 |
+
"loss": 1.7159,
|
135 |
+
"step": 9000
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.5881624566617137,
|
139 |
+
"grad_norm": 35.5,
|
140 |
+
"learning_rate": 4.019729238897144e-05,
|
141 |
+
"loss": 1.6927,
|
142 |
+
"step": 9500
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.6191183754333829,
|
146 |
+
"grad_norm": 29.75,
|
147 |
+
"learning_rate": 3.968136040944362e-05,
|
148 |
+
"loss": 1.7077,
|
149 |
+
"step": 10000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.650074294205052,
|
153 |
+
"grad_norm": 40.5,
|
154 |
+
"learning_rate": 3.91654284299158e-05,
|
155 |
+
"loss": 1.6932,
|
156 |
+
"step": 10500
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.6810302129767212,
|
160 |
+
"grad_norm": 30.25,
|
161 |
+
"learning_rate": 3.864949645038798e-05,
|
162 |
+
"loss": 1.7078,
|
163 |
+
"step": 11000
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.7119861317483903,
|
167 |
+
"grad_norm": 31.25,
|
168 |
+
"learning_rate": 3.813356447086016e-05,
|
169 |
+
"loss": 1.7004,
|
170 |
+
"step": 11500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.7429420505200595,
|
174 |
+
"grad_norm": 28.75,
|
175 |
+
"learning_rate": 3.761763249133234e-05,
|
176 |
+
"loss": 1.6726,
|
177 |
+
"step": 12000
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.7738979692917286,
|
181 |
+
"grad_norm": 52.0,
|
182 |
+
"learning_rate": 3.7101700511804524e-05,
|
183 |
+
"loss": 1.7026,
|
184 |
+
"step": 12500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.8048538880633977,
|
188 |
+
"grad_norm": 30.375,
|
189 |
+
"learning_rate": 3.658576853227671e-05,
|
190 |
+
"loss": 1.6645,
|
191 |
+
"step": 13000
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.8358098068350669,
|
195 |
+
"grad_norm": 33.75,
|
196 |
+
"learning_rate": 3.606983655274889e-05,
|
197 |
+
"loss": 1.6833,
|
198 |
+
"step": 13500
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.866765725606736,
|
202 |
+
"grad_norm": 32.75,
|
203 |
+
"learning_rate": 3.555390457322107e-05,
|
204 |
+
"loss": 1.6909,
|
205 |
+
"step": 14000
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.8977216443784052,
|
209 |
+
"grad_norm": 49.0,
|
210 |
+
"learning_rate": 3.503797259369325e-05,
|
211 |
+
"loss": 1.684,
|
212 |
+
"step": 14500
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.9286775631500743,
|
216 |
+
"grad_norm": 52.0,
|
217 |
+
"learning_rate": 3.452204061416543e-05,
|
218 |
+
"loss": 1.681,
|
219 |
+
"step": 15000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.9596334819217435,
|
223 |
+
"grad_norm": 38.0,
|
224 |
+
"learning_rate": 3.4006108634637614e-05,
|
225 |
+
"loss": 1.672,
|
226 |
+
"step": 15500
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.9905894006934126,
|
230 |
+
"grad_norm": 32.75,
|
231 |
+
"learning_rate": 3.349017665510979e-05,
|
232 |
+
"loss": 1.6553,
|
233 |
+
"step": 16000
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.0215453194650816,
|
237 |
+
"grad_norm": 35.75,
|
238 |
+
"learning_rate": 3.297424467558197e-05,
|
239 |
+
"loss": 1.6618,
|
240 |
+
"step": 16500
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 1.052501238236751,
|
244 |
+
"grad_norm": 37.5,
|
245 |
+
"learning_rate": 3.2458312696054156e-05,
|
246 |
+
"loss": 1.657,
|
247 |
+
"step": 17000
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 1.08345715700842,
|
251 |
+
"grad_norm": 30.25,
|
252 |
+
"learning_rate": 3.194238071652633e-05,
|
253 |
+
"loss": 1.6701,
|
254 |
+
"step": 17500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.1144130757800892,
|
258 |
+
"grad_norm": 32.25,
|
259 |
+
"learning_rate": 3.1426448736998515e-05,
|
260 |
+
"loss": 1.6779,
|
261 |
+
"step": 18000
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.1453689945517582,
|
265 |
+
"grad_norm": 37.5,
|
266 |
+
"learning_rate": 3.09105167574707e-05,
|
267 |
+
"loss": 1.6635,
|
268 |
+
"step": 18500
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 1.1763249133234275,
|
272 |
+
"grad_norm": 30.75,
|
273 |
+
"learning_rate": 3.0394584777942874e-05,
|
274 |
+
"loss": 1.664,
|
275 |
+
"step": 19000
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.2072808320950965,
|
279 |
+
"grad_norm": 55.75,
|
280 |
+
"learning_rate": 2.9878652798415056e-05,
|
281 |
+
"loss": 1.6398,
|
282 |
+
"step": 19500
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 1.2382367508667658,
|
286 |
+
"grad_norm": 51.0,
|
287 |
+
"learning_rate": 2.936272081888724e-05,
|
288 |
+
"loss": 1.6424,
|
289 |
+
"step": 20000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 1.2691926696384348,
|
293 |
+
"grad_norm": 32.0,
|
294 |
+
"learning_rate": 2.884678883935942e-05,
|
295 |
+
"loss": 1.6251,
|
296 |
+
"step": 20500
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.300148588410104,
|
300 |
+
"grad_norm": 31.5,
|
301 |
+
"learning_rate": 2.83308568598316e-05,
|
302 |
+
"loss": 1.6295,
|
303 |
+
"step": 21000
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.331104507181773,
|
307 |
+
"grad_norm": 38.75,
|
308 |
+
"learning_rate": 2.7814924880303784e-05,
|
309 |
+
"loss": 1.6628,
|
310 |
+
"step": 21500
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.3620604259534423,
|
314 |
+
"grad_norm": 54.5,
|
315 |
+
"learning_rate": 2.729899290077596e-05,
|
316 |
+
"loss": 1.6579,
|
317 |
+
"step": 22000
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.3930163447251114,
|
321 |
+
"grad_norm": 64.5,
|
322 |
+
"learning_rate": 2.6783060921248143e-05,
|
323 |
+
"loss": 1.6185,
|
324 |
+
"step": 22500
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 1.4239722634967806,
|
328 |
+
"grad_norm": 30.875,
|
329 |
+
"learning_rate": 2.6267128941720326e-05,
|
330 |
+
"loss": 1.6521,
|
331 |
+
"step": 23000
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 1.4549281822684497,
|
335 |
+
"grad_norm": 34.75,
|
336 |
+
"learning_rate": 2.57511969621925e-05,
|
337 |
+
"loss": 1.6372,
|
338 |
+
"step": 23500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.485884101040119,
|
342 |
+
"grad_norm": 48.5,
|
343 |
+
"learning_rate": 2.5235264982664684e-05,
|
344 |
+
"loss": 1.6597,
|
345 |
+
"step": 24000
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 1.516840019811788,
|
349 |
+
"grad_norm": 31.75,
|
350 |
+
"learning_rate": 2.4719333003136867e-05,
|
351 |
+
"loss": 1.6437,
|
352 |
+
"step": 24500
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 1.5477959385834572,
|
356 |
+
"grad_norm": 18.75,
|
357 |
+
"learning_rate": 2.420340102360905e-05,
|
358 |
+
"loss": 1.6191,
|
359 |
+
"step": 25000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 1.5787518573551265,
|
363 |
+
"grad_norm": 26.5,
|
364 |
+
"learning_rate": 2.368746904408123e-05,
|
365 |
+
"loss": 1.6564,
|
366 |
+
"step": 25500
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 1.6097077761267955,
|
370 |
+
"grad_norm": 37.5,
|
371 |
+
"learning_rate": 2.3171537064553412e-05,
|
372 |
+
"loss": 1.6498,
|
373 |
+
"step": 26000
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 1.6406636948984645,
|
377 |
+
"grad_norm": 42.75,
|
378 |
+
"learning_rate": 2.265560508502559e-05,
|
379 |
+
"loss": 1.6201,
|
380 |
+
"step": 26500
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.6716196136701336,
|
384 |
+
"grad_norm": 35.5,
|
385 |
+
"learning_rate": 2.213967310549777e-05,
|
386 |
+
"loss": 1.6459,
|
387 |
+
"step": 27000
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.7025755324418028,
|
391 |
+
"grad_norm": 27.875,
|
392 |
+
"learning_rate": 2.1623741125969954e-05,
|
393 |
+
"loss": 1.6636,
|
394 |
+
"step": 27500
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 1.733531451213472,
|
398 |
+
"grad_norm": 33.75,
|
399 |
+
"learning_rate": 2.1107809146442133e-05,
|
400 |
+
"loss": 1.6359,
|
401 |
+
"step": 28000
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 1.764487369985141,
|
405 |
+
"grad_norm": 34.75,
|
406 |
+
"learning_rate": 2.0591877166914312e-05,
|
407 |
+
"loss": 1.6679,
|
408 |
+
"step": 28500
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 1.7954432887568101,
|
412 |
+
"grad_norm": 27.0,
|
413 |
+
"learning_rate": 2.0075945187386495e-05,
|
414 |
+
"loss": 1.6409,
|
415 |
+
"step": 29000
|
416 |
+
}
|
417 |
+
],
|
418 |
+
"logging_steps": 500,
|
419 |
+
"max_steps": 48456,
|
420 |
+
"num_input_tokens_seen": 0,
|
421 |
+
"num_train_epochs": 3,
|
422 |
+
"save_steps": 1000,
|
423 |
+
"stateful_callbacks": {
|
424 |
+
"TrainerControl": {
|
425 |
+
"args": {
|
426 |
+
"should_epoch_stop": false,
|
427 |
+
"should_evaluate": false,
|
428 |
+
"should_log": false,
|
429 |
+
"should_save": false,
|
430 |
+
"should_training_stop": false
|
431 |
+
},
|
432 |
+
"attributes": {}
|
433 |
+
}
|
434 |
+
},
|
435 |
+
"total_flos": 0.0,
|
436 |
+
"train_batch_size": 8,
|
437 |
+
"trial_name": null,
|
438 |
+
"trial_params": null
|
439 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a131b90005464f760954c8f646b08f16b14e045225ce9fabe0591fbc1756762
|
3 |
+
size 5240
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|