Ihor commited on
Commit
c0460c2
·
verified ·
1 Parent(s): 99867cf

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
gliner_config.json ADDED
@@ -0,0 +1,223 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class_token_index": -1,
3
+ "dropout": 0.3,
4
+ "embed_ent_token": true,
5
+ "encoder_config": {
6
+ "_attn_implementation_autoset": false,
7
+ "_name_or_path": "microsoft/deberta-v3-large",
8
+ "add_cross_attention": false,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bad_words_ids": null,
12
+ "begin_suppress_tokens": null,
13
+ "bos_token_id": null,
14
+ "chunk_size_feed_forward": 0,
15
+ "cross_attention_hidden_size": null,
16
+ "decoder_start_token_id": null,
17
+ "diversity_penalty": 0.0,
18
+ "do_sample": false,
19
+ "early_stopping": false,
20
+ "encoder_no_repeat_ngram_size": 0,
21
+ "eos_token_id": null,
22
+ "exponential_decay_length_penalty": null,
23
+ "finetuning_task": null,
24
+ "forced_bos_token_id": null,
25
+ "forced_eos_token_id": null,
26
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 1024,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 4096,
35
+ "is_decoder": false,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_eps": 1e-07,
42
+ "legacy": true,
43
+ "length_penalty": 1.0,
44
+ "max_length": 20,
45
+ "max_position_embeddings": 512,
46
+ "max_relative_positions": -1,
47
+ "min_length": 0,
48
+ "model_type": "deberta-v2",
49
+ "no_repeat_ngram_size": 0,
50
+ "norm_rel_ebd": "layer_norm",
51
+ "num_attention_heads": 16,
52
+ "num_beam_groups": 1,
53
+ "num_beams": 1,
54
+ "num_hidden_layers": 24,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": 0,
60
+ "pooler_dropout": 0,
61
+ "pooler_hidden_act": "gelu",
62
+ "pooler_hidden_size": 1024,
63
+ "pos_att_type": [
64
+ "p2c",
65
+ "c2p"
66
+ ],
67
+ "position_biased_input": false,
68
+ "position_buckets": 256,
69
+ "prefix": null,
70
+ "problem_type": null,
71
+ "pruned_heads": {},
72
+ "relative_attention": true,
73
+ "remove_invalid_values": false,
74
+ "repetition_penalty": 1.0,
75
+ "return_dict": true,
76
+ "return_dict_in_generate": false,
77
+ "sep_token_id": null,
78
+ "share_att_key": true,
79
+ "suppress_tokens": null,
80
+ "task_specific_params": null,
81
+ "temperature": 1.0,
82
+ "tf_legacy_loss": false,
83
+ "tie_encoder_decoder": false,
84
+ "tie_word_embeddings": true,
85
+ "tokenizer_class": null,
86
+ "top_k": 50,
87
+ "top_p": 1.0,
88
+ "torch_dtype": null,
89
+ "torchscript": false,
90
+ "type_vocab_size": 0,
91
+ "typical_p": 1.0,
92
+ "use_bfloat16": false,
93
+ "vocab_size": 128100
94
+ },
95
+ "ent_token": "<<ENT>>",
96
+ "eval_every": 10000,
97
+ "fine_tune": true,
98
+ "freeze_token_rep": false,
99
+ "fuse_layers": false,
100
+ "has_rnn": true,
101
+ "hidden_size": 768,
102
+ "label_smoothing": 0,
103
+ "labels_encoder": "BAAI/bge-base-en-v1.5",
104
+ "labels_encoder_config": {
105
+ "_attn_implementation_autoset": false,
106
+ "_name_or_path": "BAAI/bge-base-en-v1.5",
107
+ "add_cross_attention": false,
108
+ "architectures": [
109
+ "BertModel"
110
+ ],
111
+ "attention_probs_dropout_prob": 0.1,
112
+ "bad_words_ids": null,
113
+ "begin_suppress_tokens": null,
114
+ "bos_token_id": null,
115
+ "chunk_size_feed_forward": 0,
116
+ "classifier_dropout": null,
117
+ "cross_attention_hidden_size": null,
118
+ "decoder_start_token_id": null,
119
+ "diversity_penalty": 0.0,
120
+ "do_sample": false,
121
+ "early_stopping": false,
122
+ "encoder_no_repeat_ngram_size": 0,
123
+ "eos_token_id": null,
124
+ "exponential_decay_length_penalty": null,
125
+ "finetuning_task": null,
126
+ "forced_bos_token_id": null,
127
+ "forced_eos_token_id": null,
128
+ "gradient_checkpointing": false,
129
+ "hidden_act": "gelu",
130
+ "hidden_dropout_prob": 0.1,
131
+ "hidden_size": 768,
132
+ "id2label": {
133
+ "0": "LABEL_0"
134
+ },
135
+ "initializer_range": 0.02,
136
+ "intermediate_size": 3072,
137
+ "is_decoder": false,
138
+ "is_encoder_decoder": false,
139
+ "label2id": {
140
+ "LABEL_0": 0
141
+ },
142
+ "layer_norm_eps": 1e-12,
143
+ "length_penalty": 1.0,
144
+ "max_length": 20,
145
+ "max_position_embeddings": 512,
146
+ "min_length": 0,
147
+ "model_type": "bert",
148
+ "no_repeat_ngram_size": 0,
149
+ "num_attention_heads": 12,
150
+ "num_beam_groups": 1,
151
+ "num_beams": 1,
152
+ "num_hidden_layers": 12,
153
+ "num_return_sequences": 1,
154
+ "output_attentions": false,
155
+ "output_hidden_states": false,
156
+ "output_scores": false,
157
+ "pad_token_id": 0,
158
+ "position_embedding_type": "absolute",
159
+ "prefix": null,
160
+ "problem_type": null,
161
+ "pruned_heads": {},
162
+ "remove_invalid_values": false,
163
+ "repetition_penalty": 1.0,
164
+ "return_dict": true,
165
+ "return_dict_in_generate": false,
166
+ "sep_token_id": null,
167
+ "suppress_tokens": null,
168
+ "task_specific_params": null,
169
+ "temperature": 1.0,
170
+ "tf_legacy_loss": false,
171
+ "tie_encoder_decoder": false,
172
+ "tie_word_embeddings": true,
173
+ "tokenizer_class": null,
174
+ "top_k": 50,
175
+ "top_p": 1.0,
176
+ "torch_dtype": "float32",
177
+ "torchscript": false,
178
+ "type_vocab_size": 2,
179
+ "typical_p": 1.0,
180
+ "use_bfloat16": false,
181
+ "use_cache": true,
182
+ "vocab_size": 30522
183
+ },
184
+ "labels_fusion_schema": "",
185
+ "log_dir": "deberta/",
186
+ "loss_alpha": 0.8,
187
+ "loss_gamma": 2,
188
+ "loss_reduction": "sum",
189
+ "lr_encoder": "1e-5",
190
+ "lr_others": "3e-5",
191
+ "max_grad_norm": 10.0,
192
+ "max_len": 2048,
193
+ "max_neg_type_ratio": 1,
194
+ "max_types": 100,
195
+ "max_width": 12,
196
+ "model_name": "microsoft/deberta-v3-large",
197
+ "model_type": "gliner",
198
+ "name": "span level gliner",
199
+ "num_post_fusion_layers": 1,
200
+ "num_rnns": 1,
201
+ "num_steps": 100000,
202
+ "post_fusion_schema": "",
203
+ "pre_fusion": false,
204
+ "prev_path": null,
205
+ "random_drop": true,
206
+ "root_dir": "gliner_logs",
207
+ "save_total_limit": 3,
208
+ "scheduler_type": "cosine",
209
+ "sep_token": "<<SEP>>",
210
+ "shuffle_types": true,
211
+ "size_sup": -1,
212
+ "span_mode": "markerV0",
213
+ "subtoken_pooling": "first",
214
+ "train_batch_size": 8,
215
+ "train_data": "data/nuner_train.json",
216
+ "transformers_version": "4.48.0.dev0",
217
+ "val_data_dir": "none",
218
+ "vocab_size": -1,
219
+ "warmup_ratio": 0.05,
220
+ "weight_decay_encoder": 0.1,
221
+ "weight_decay_other": 0.01,
222
+ "words_splitter_type": "whitespace"
223
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:672f0996795ccb20c4bc49e52c783cbe1d6405dd566612c610e80f7f508d49a0
3
+ size 2276530250
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6171ab284eb17652bf32183834fcbba270c07bdf182c366c1d5df2dc5de61711
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e115debc88a308ec6141837d91ce27474371bbc4ba1ac15e0c651b86a69e4cd3
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
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
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }
trainer_state.json ADDED
@@ -0,0 +1,741 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.7711654268508679,
5
+ "eval_steps": 500,
6
+ "global_step": 10000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.017711654268508677,
13
+ "grad_norm": 5928.86572265625,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 167.7101,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.035423308537017355,
20
+ "grad_norm": 1039.6475830078125,
21
+ "learning_rate": 2.0000000000000003e-06,
22
+ "loss": 150.4972,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.053134962805526036,
27
+ "grad_norm": 2417.1572265625,
28
+ "learning_rate": 3e-06,
29
+ "loss": 118.4022,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.07084661707403471,
34
+ "grad_norm": 658.3015747070312,
35
+ "learning_rate": 4.000000000000001e-06,
36
+ "loss": 81.2197,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.08855827134254339,
41
+ "grad_norm": 11006.369140625,
42
+ "learning_rate": 5e-06,
43
+ "loss": 191.8971,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.10626992561105207,
48
+ "grad_norm": 387.76507568359375,
49
+ "learning_rate": 6e-06,
50
+ "loss": 238.5224,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.12398157987956075,
55
+ "grad_norm": 520.3596801757812,
56
+ "learning_rate": 7e-06,
57
+ "loss": 140.7788,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.14169323414806942,
62
+ "grad_norm": 711.9447631835938,
63
+ "learning_rate": 8.000000000000001e-06,
64
+ "loss": 240.6655,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.1594048884165781,
69
+ "grad_norm": 685.3497314453125,
70
+ "learning_rate": 9e-06,
71
+ "loss": 142.9791,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.17711654268508678,
76
+ "grad_norm": 0.0,
77
+ "learning_rate": 1e-05,
78
+ "loss": 98.8305,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.19482819695359546,
83
+ "grad_norm": 672.6516723632812,
84
+ "learning_rate": 9.99695413509548e-06,
85
+ "loss": 93.7172,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.21253985122210414,
90
+ "grad_norm": 670.732666015625,
91
+ "learning_rate": 9.987820251299121e-06,
92
+ "loss": 108.1393,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.23025150549061282,
97
+ "grad_norm": 2993.84228515625,
98
+ "learning_rate": 9.972609476841368e-06,
99
+ "loss": 112.0507,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.2479631597591215,
104
+ "grad_norm": 494.7082214355469,
105
+ "learning_rate": 9.951340343707852e-06,
106
+ "loss": 87.2083,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.26567481402763016,
111
+ "grad_norm": 9774.228515625,
112
+ "learning_rate": 9.924038765061042e-06,
113
+ "loss": 83.2371,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.28338646829613884,
118
+ "grad_norm": 1228.3587646484375,
119
+ "learning_rate": 9.890738003669029e-06,
120
+ "loss": 132.57,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.3010981225646475,
125
+ "grad_norm": 1199.085693359375,
126
+ "learning_rate": 9.851478631379982e-06,
127
+ "loss": 84.5867,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.3188097768331562,
132
+ "grad_norm": 4537.9521484375,
133
+ "learning_rate": 9.806308479691595e-06,
134
+ "loss": 96.3146,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.3365214311016649,
139
+ "grad_norm": 1682.6268310546875,
140
+ "learning_rate": 9.755282581475769e-06,
141
+ "loss": 122.0458,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.35423308537017356,
146
+ "grad_norm": 474.109619140625,
147
+ "learning_rate": 9.698463103929542e-06,
148
+ "loss": 82.0088,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.37194473963868224,
153
+ "grad_norm": 550.49072265625,
154
+ "learning_rate": 9.635919272833938e-06,
155
+ "loss": 102.8292,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.3896563939071909,
160
+ "grad_norm": 5476.99560546875,
161
+ "learning_rate": 9.567727288213005e-06,
162
+ "loss": 146.4771,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.4073680481756996,
167
+ "grad_norm": 962.66064453125,
168
+ "learning_rate": 9.493970231495836e-06,
169
+ "loss": 113.7458,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.4250797024442083,
174
+ "grad_norm": 176.8959197998047,
175
+ "learning_rate": 9.414737964294636e-06,
176
+ "loss": 79.8068,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 0.44279135671271697,
181
+ "grad_norm": 0.0,
182
+ "learning_rate": 9.330127018922195e-06,
183
+ "loss": 95.6945,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 0.46050301098122565,
188
+ "grad_norm": 739.9681396484375,
189
+ "learning_rate": 9.24024048078213e-06,
190
+ "loss": 127.2645,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 0.4782146652497343,
195
+ "grad_norm": 892.9599609375,
196
+ "learning_rate": 9.145187862775208e-06,
197
+ "loss": 67.8974,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 0.495926319518243,
202
+ "grad_norm": 478.8652038574219,
203
+ "learning_rate": 9.045084971874738e-06,
204
+ "loss": 125.3699,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 0.5136379737867517,
209
+ "grad_norm": 176.39854431152344,
210
+ "learning_rate": 8.94005376803361e-06,
211
+ "loss": 145.9999,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 0.5313496280552603,
216
+ "grad_norm": 738.6134643554688,
217
+ "learning_rate": 8.83022221559489e-06,
218
+ "loss": 161.4359,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 0.549061282323769,
223
+ "grad_norm": 389.0908203125,
224
+ "learning_rate": 8.715724127386971e-06,
225
+ "loss": 63.7037,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 0.5667729365922777,
230
+ "grad_norm": 622.670654296875,
231
+ "learning_rate": 8.596699001693257e-06,
232
+ "loss": 66.3127,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 0.5844845908607864,
237
+ "grad_norm": 332.5394592285156,
238
+ "learning_rate": 8.473291852294986e-06,
239
+ "loss": 78.8835,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 0.602196245129295,
244
+ "grad_norm": 334.5383605957031,
245
+ "learning_rate": 8.345653031794292e-06,
246
+ "loss": 74.8007,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 0.6199078993978038,
251
+ "grad_norm": 2048.822021484375,
252
+ "learning_rate": 8.213938048432697e-06,
253
+ "loss": 105.3306,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 0.6376195536663124,
258
+ "grad_norm": 418.65618896484375,
259
+ "learning_rate": 8.078307376628292e-06,
260
+ "loss": 92.522,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 0.6553312079348211,
265
+ "grad_norm": 588.8889770507812,
266
+ "learning_rate": 7.938926261462366e-06,
267
+ "loss": 93.5883,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 0.6730428622033298,
272
+ "grad_norm": 213.2515411376953,
273
+ "learning_rate": 7.795964517353734e-06,
274
+ "loss": 81.18,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 0.6907545164718385,
279
+ "grad_norm": 502.90399169921875,
280
+ "learning_rate": 7.649596321166024e-06,
281
+ "loss": 91.3637,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 0.7084661707403471,
286
+ "grad_norm": 37754.41015625,
287
+ "learning_rate": 7.500000000000001e-06,
288
+ "loss": 84.6845,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 0.7261778250088559,
293
+ "grad_norm": 620.5169677734375,
294
+ "learning_rate": 7.347357813929455e-06,
295
+ "loss": 76.8845,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 0.7438894792773645,
300
+ "grad_norm": 607.29541015625,
301
+ "learning_rate": 7.191855733945388e-06,
302
+ "loss": 136.6091,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 0.7616011335458732,
307
+ "grad_norm": 1504.0474853515625,
308
+ "learning_rate": 7.033683215379002e-06,
309
+ "loss": 87.2499,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 0.7793127878143818,
314
+ "grad_norm": 351.63482666015625,
315
+ "learning_rate": 6.873032967079562e-06,
316
+ "loss": 70.2709,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 0.7970244420828906,
321
+ "grad_norm": 608.7922973632812,
322
+ "learning_rate": 6.710100716628345e-06,
323
+ "loss": 60.6958,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 0.8147360963513992,
328
+ "grad_norm": 501.0238037109375,
329
+ "learning_rate": 6.545084971874738e-06,
330
+ "loss": 78.5794,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 0.832447750619908,
335
+ "grad_norm": 667.3199462890625,
336
+ "learning_rate": 6.378186779084996e-06,
337
+ "loss": 71.3733,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 0.8501594048884166,
342
+ "grad_norm": 280.9075927734375,
343
+ "learning_rate": 6.209609477998339e-06,
344
+ "loss": 62.0313,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 0.8678710591569253,
349
+ "grad_norm": 257.11114501953125,
350
+ "learning_rate": 6.039558454088796e-06,
351
+ "loss": 61.1799,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 0.8855827134254339,
356
+ "grad_norm": 878.3767700195312,
357
+ "learning_rate": 5.8682408883346535e-06,
358
+ "loss": 91.728,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 0.9032943676939427,
363
+ "grad_norm": 1279.4716796875,
364
+ "learning_rate": 5.695865504800328e-06,
365
+ "loss": 78.0071,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 0.9210060219624513,
370
+ "grad_norm": 360.426025390625,
371
+ "learning_rate": 5.522642316338268e-06,
372
+ "loss": 63.6748,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 0.9387176762309599,
377
+ "grad_norm": 670.2398071289062,
378
+ "learning_rate": 5.348782368720627e-06,
379
+ "loss": 87.3999,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 0.9564293304994687,
384
+ "grad_norm": 642.230712890625,
385
+ "learning_rate": 5.174497483512506e-06,
386
+ "loss": 100.3238,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 0.9741409847679773,
391
+ "grad_norm": 462.1632080078125,
392
+ "learning_rate": 5e-06,
393
+ "loss": 95.8226,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 0.991852639036486,
398
+ "grad_norm": 1005.881591796875,
399
+ "learning_rate": 4.825502516487497e-06,
400
+ "loss": 67.1857,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 1.0,
405
+ "eval_loss": 292.22265625,
406
+ "eval_runtime": 58.4771,
407
+ "eval_samples_per_second": 42.923,
408
+ "eval_steps_per_second": 10.739,
409
+ "step": 5646
410
+ },
411
+ {
412
+ "epoch": 1.0095642933049946,
413
+ "grad_norm": 342.584716796875,
414
+ "learning_rate": 4.651217631279374e-06,
415
+ "loss": 61.0431,
416
+ "step": 5700
417
+ },
418
+ {
419
+ "epoch": 1.0272759475735034,
420
+ "grad_norm": 10458.5888671875,
421
+ "learning_rate": 4.477357683661734e-06,
422
+ "loss": 100.5392,
423
+ "step": 5800
424
+ },
425
+ {
426
+ "epoch": 1.0449876018420121,
427
+ "grad_norm": 266.7583923339844,
428
+ "learning_rate": 4.304134495199675e-06,
429
+ "loss": 40.7089,
430
+ "step": 5900
431
+ },
432
+ {
433
+ "epoch": 1.0626992561105206,
434
+ "grad_norm": 156.3075408935547,
435
+ "learning_rate": 4.131759111665349e-06,
436
+ "loss": 49.5499,
437
+ "step": 6000
438
+ },
439
+ {
440
+ "epoch": 1.0804109103790294,
441
+ "grad_norm": 255.9273223876953,
442
+ "learning_rate": 3.960441545911205e-06,
443
+ "loss": 70.7226,
444
+ "step": 6100
445
+ },
446
+ {
447
+ "epoch": 1.098122564647538,
448
+ "grad_norm": 571.5280151367188,
449
+ "learning_rate": 3.790390522001662e-06,
450
+ "loss": 91.4461,
451
+ "step": 6200
452
+ },
453
+ {
454
+ "epoch": 1.1158342189160468,
455
+ "grad_norm": 947.069091796875,
456
+ "learning_rate": 3.6218132209150047e-06,
457
+ "loss": 83.3039,
458
+ "step": 6300
459
+ },
460
+ {
461
+ "epoch": 1.1335458731845554,
462
+ "grad_norm": 182.46408081054688,
463
+ "learning_rate": 3.4549150281252635e-06,
464
+ "loss": 53.0065,
465
+ "step": 6400
466
+ },
467
+ {
468
+ "epoch": 1.151257527453064,
469
+ "grad_norm": 3747.530517578125,
470
+ "learning_rate": 3.289899283371657e-06,
471
+ "loss": 55.4958,
472
+ "step": 6500
473
+ },
474
+ {
475
+ "epoch": 1.1689691817215728,
476
+ "grad_norm": 186.1503448486328,
477
+ "learning_rate": 3.12696703292044e-06,
478
+ "loss": 76.359,
479
+ "step": 6600
480
+ },
481
+ {
482
+ "epoch": 1.1866808359900816,
483
+ "grad_norm": 213.66128540039062,
484
+ "learning_rate": 2.966316784621e-06,
485
+ "loss": 45.9871,
486
+ "step": 6700
487
+ },
488
+ {
489
+ "epoch": 1.20439249025859,
490
+ "grad_norm": 817.01806640625,
491
+ "learning_rate": 2.8081442660546126e-06,
492
+ "loss": 50.9655,
493
+ "step": 6800
494
+ },
495
+ {
496
+ "epoch": 1.2221041445270988,
497
+ "grad_norm": 236.37423706054688,
498
+ "learning_rate": 2.6526421860705474e-06,
499
+ "loss": 65.4025,
500
+ "step": 6900
501
+ },
502
+ {
503
+ "epoch": 1.2398157987956075,
504
+ "grad_norm": 470.6351013183594,
505
+ "learning_rate": 2.5000000000000015e-06,
506
+ "loss": 53.6276,
507
+ "step": 7000
508
+ },
509
+ {
510
+ "epoch": 1.257527453064116,
511
+ "grad_norm": 839.293701171875,
512
+ "learning_rate": 2.3504036788339763e-06,
513
+ "loss": 50.0294,
514
+ "step": 7100
515
+ },
516
+ {
517
+ "epoch": 1.2752391073326248,
518
+ "grad_norm": 404.825927734375,
519
+ "learning_rate": 2.204035482646267e-06,
520
+ "loss": 113.8194,
521
+ "step": 7200
522
+ },
523
+ {
524
+ "epoch": 1.2929507616011335,
525
+ "grad_norm": 590.0635986328125,
526
+ "learning_rate": 2.061073738537635e-06,
527
+ "loss": 57.679,
528
+ "step": 7300
529
+ },
530
+ {
531
+ "epoch": 1.3106624158696423,
532
+ "grad_norm": 131.95318603515625,
533
+ "learning_rate": 1.9216926233717087e-06,
534
+ "loss": 53.4347,
535
+ "step": 7400
536
+ },
537
+ {
538
+ "epoch": 1.328374070138151,
539
+ "grad_norm": 245.02337646484375,
540
+ "learning_rate": 1.7860619515673034e-06,
541
+ "loss": 78.5544,
542
+ "step": 7500
543
+ },
544
+ {
545
+ "epoch": 1.3460857244066595,
546
+ "grad_norm": 321.28204345703125,
547
+ "learning_rate": 1.6543469682057105e-06,
548
+ "loss": 110.1398,
549
+ "step": 7600
550
+ },
551
+ {
552
+ "epoch": 1.3637973786751683,
553
+ "grad_norm": 367.9349365234375,
554
+ "learning_rate": 1.5267081477050132e-06,
555
+ "loss": 56.705,
556
+ "step": 7700
557
+ },
558
+ {
559
+ "epoch": 1.381509032943677,
560
+ "grad_norm": 278.4571533203125,
561
+ "learning_rate": 1.4033009983067454e-06,
562
+ "loss": 46.6718,
563
+ "step": 7800
564
+ },
565
+ {
566
+ "epoch": 1.3992206872121855,
567
+ "grad_norm": 1197.47265625,
568
+ "learning_rate": 1.2842758726130283e-06,
569
+ "loss": 88.5932,
570
+ "step": 7900
571
+ },
572
+ {
573
+ "epoch": 1.4169323414806942,
574
+ "grad_norm": 403.6693420410156,
575
+ "learning_rate": 1.1697777844051105e-06,
576
+ "loss": 56.4835,
577
+ "step": 8000
578
+ },
579
+ {
580
+ "epoch": 1.434643995749203,
581
+ "grad_norm": 774.799072265625,
582
+ "learning_rate": 1.0599462319663906e-06,
583
+ "loss": 80.3962,
584
+ "step": 8100
585
+ },
586
+ {
587
+ "epoch": 1.4523556500177117,
588
+ "grad_norm": 250.503662109375,
589
+ "learning_rate": 9.549150281252633e-07,
590
+ "loss": 67.517,
591
+ "step": 8200
592
+ },
593
+ {
594
+ "epoch": 1.4700673042862205,
595
+ "grad_norm": 750.6965942382812,
596
+ "learning_rate": 8.54812137224792e-07,
597
+ "loss": 49.6351,
598
+ "step": 8300
599
+ },
600
+ {
601
+ "epoch": 1.487778958554729,
602
+ "grad_norm": 292.1385498046875,
603
+ "learning_rate": 7.597595192178702e-07,
604
+ "loss": 43.521,
605
+ "step": 8400
606
+ },
607
+ {
608
+ "epoch": 1.5054906128232377,
609
+ "grad_norm": 148.10813903808594,
610
+ "learning_rate": 6.698729810778065e-07,
611
+ "loss": 75.3037,
612
+ "step": 8500
613
+ },
614
+ {
615
+ "epoch": 1.5232022670917464,
616
+ "grad_norm": 754.1968994140625,
617
+ "learning_rate": 5.852620357053651e-07,
618
+ "loss": 56.1155,
619
+ "step": 8600
620
+ },
621
+ {
622
+ "epoch": 1.540913921360255,
623
+ "grad_norm": 329.13482666015625,
624
+ "learning_rate": 5.06029768504166e-07,
625
+ "loss": 56.4271,
626
+ "step": 8700
627
+ },
628
+ {
629
+ "epoch": 1.5586255756287637,
630
+ "grad_norm": 142.98875427246094,
631
+ "learning_rate": 4.322727117869951e-07,
632
+ "loss": 55.9837,
633
+ "step": 8800
634
+ },
635
+ {
636
+ "epoch": 1.5763372298972724,
637
+ "grad_norm": 2218.41845703125,
638
+ "learning_rate": 3.6408072716606346e-07,
639
+ "loss": 55.8351,
640
+ "step": 8900
641
+ },
642
+ {
643
+ "epoch": 1.594048884165781,
644
+ "grad_norm": 483.5868225097656,
645
+ "learning_rate": 3.015368960704584e-07,
646
+ "loss": 78.6791,
647
+ "step": 9000
648
+ },
649
+ {
650
+ "epoch": 1.61176053843429,
651
+ "grad_norm": 507.6253356933594,
652
+ "learning_rate": 2.447174185242324e-07,
653
+ "loss": 52.5828,
654
+ "step": 9100
655
+ },
656
+ {
657
+ "epoch": 1.6294721927027984,
658
+ "grad_norm": 839.6124267578125,
659
+ "learning_rate": 1.9369152030840553e-07,
660
+ "loss": 60.3558,
661
+ "step": 9200
662
+ },
663
+ {
664
+ "epoch": 1.6471838469713072,
665
+ "grad_norm": 725.627685546875,
666
+ "learning_rate": 1.4852136862001766e-07,
667
+ "loss": 72.146,
668
+ "step": 9300
669
+ },
670
+ {
671
+ "epoch": 1.664895501239816,
672
+ "grad_norm": 287.16595458984375,
673
+ "learning_rate": 1.0926199633097156e-07,
674
+ "loss": 66.3919,
675
+ "step": 9400
676
+ },
677
+ {
678
+ "epoch": 1.6826071555083244,
679
+ "grad_norm": 305.81866455078125,
680
+ "learning_rate": 7.59612349389599e-08,
681
+ "loss": 38.9066,
682
+ "step": 9500
683
+ },
684
+ {
685
+ "epoch": 1.7003188097768331,
686
+ "grad_norm": 787.4326782226562,
687
+ "learning_rate": 4.865965629214819e-08,
688
+ "loss": 81.1311,
689
+ "step": 9600
690
+ },
691
+ {
692
+ "epoch": 1.7180304640453419,
693
+ "grad_norm": 564.6408081054688,
694
+ "learning_rate": 2.7390523158633552e-08,
695
+ "loss": 81.2833,
696
+ "step": 9700
697
+ },
698
+ {
699
+ "epoch": 1.7357421183138504,
700
+ "grad_norm": 750.64111328125,
701
+ "learning_rate": 1.2179748700879013e-08,
702
+ "loss": 36.9215,
703
+ "step": 9800
704
+ },
705
+ {
706
+ "epoch": 1.7534537725823593,
707
+ "grad_norm": 477.2333068847656,
708
+ "learning_rate": 3.0458649045211897e-09,
709
+ "loss": 74.1448,
710
+ "step": 9900
711
+ },
712
+ {
713
+ "epoch": 1.7711654268508679,
714
+ "grad_norm": 722.1519775390625,
715
+ "learning_rate": 0.0,
716
+ "loss": 60.6096,
717
+ "step": 10000
718
+ }
719
+ ],
720
+ "logging_steps": 100,
721
+ "max_steps": 10000,
722
+ "num_input_tokens_seen": 0,
723
+ "num_train_epochs": 2,
724
+ "save_steps": 5000,
725
+ "stateful_callbacks": {
726
+ "TrainerControl": {
727
+ "args": {
728
+ "should_epoch_stop": false,
729
+ "should_evaluate": false,
730
+ "should_log": false,
731
+ "should_save": true,
732
+ "should_training_stop": true
733
+ },
734
+ "attributes": {}
735
+ }
736
+ },
737
+ "total_flos": 0.0,
738
+ "train_batch_size": 4,
739
+ "trial_name": null,
740
+ "trial_params": null
741
+ }