Ihor commited on
Commit
1b280b2
·
verified ·
1 Parent(s): 9bddbf4

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<<ENT>>": 128001,
3
+ "<<SEP>>": 128002,
4
+ "[MASK]": 128000
5
+ }
gliner_config.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class_token_index": 128001,
3
+ "dropout": 0.4,
4
+ "embed_ent_token": true,
5
+ "encoder_config": {
6
+ "_attn_implementation_autoset": false,
7
+ "_name_or_path": "microsoft/deberta-v3-base",
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": 768,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
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": 12,
52
+ "num_beam_groups": 1,
53
+ "num_beams": 1,
54
+ "num_hidden_layers": 12,
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": 768,
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": 128003
94
+ },
95
+ "ent_token": "<<ENT>>",
96
+ "fine_tune": true,
97
+ "fuse_layers": false,
98
+ "has_rnn": true,
99
+ "hidden_size": 768,
100
+ "label_smoothing": 0.0,
101
+ "labels_encoder": null,
102
+ "labels_encoder_config": null,
103
+ "labels_fusion_schema": "",
104
+ "loss_alpha": 0.8,
105
+ "loss_gamma": 0,
106
+ "loss_reduction": "sum",
107
+ "max_len": 1024,
108
+ "max_neg_type_ratio": 1,
109
+ "max_types": 30,
110
+ "max_width": 12,
111
+ "model_name": "microsoft/deberta-v3-base",
112
+ "model_type": "gliner",
113
+ "name": "span level gliner",
114
+ "num_post_fusion_layers": 1,
115
+ "num_rnns": 1,
116
+ "post_fusion_schema": "",
117
+ "pre_fusion": false,
118
+ "random_drop": true,
119
+ "sep_token": "<<SEP>>",
120
+ "shuffle_types": true,
121
+ "span_mode": "markerV0",
122
+ "subtoken_pooling": "first",
123
+ "transformers_version": "4.49.0",
124
+ "vocab_size": 128003,
125
+ "words_splitter_type": "whitespace"
126
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57ec000ab651592040dae3543b96de16462bbcc3bb5c97deda9bb479194cecaa
3
+ size 834285094
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 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "128001": {
44
+ "content": "<<ENT>>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "128002": {
52
+ "content": "<<SEP>>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ }
59
+ },
60
+ "bos_token": "[CLS]",
61
+ "clean_up_tokenization_spaces": true,
62
+ "cls_token": "[CLS]",
63
+ "do_lower_case": false,
64
+ "eos_token": "[SEP]",
65
+ "extra_special_tokens": {},
66
+ "mask_token": "[MASK]",
67
+ "model_max_length": 1000000000000000019884624838656,
68
+ "pad_token": "[PAD]",
69
+ "sep_token": "[SEP]",
70
+ "sp_model_kwargs": {},
71
+ "split_by_punct": false,
72
+ "tokenizer_class": "DebertaV2Tokenizer",
73
+ "unk_token": "[UNK]",
74
+ "vocab_type": "spm"
75
+ }
trainer_state.json ADDED
@@ -0,0 +1,741 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.1060723371308483,
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": 0.011060723371308484,
13
+ "grad_norm": 538.04736328125,
14
+ "learning_rate": 1.0000000000000002e-06,
15
+ "loss": 78.145,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.022121446742616967,
20
+ "grad_norm": 219.34432983398438,
21
+ "learning_rate": 2.0000000000000003e-06,
22
+ "loss": 92.9586,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.03318217011392545,
27
+ "grad_norm": 726.5635986328125,
28
+ "learning_rate": 3e-06,
29
+ "loss": 53.8293,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.044242893485233935,
34
+ "grad_norm": 125.79649353027344,
35
+ "learning_rate": 4.000000000000001e-06,
36
+ "loss": 46.7007,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.05530361685654242,
41
+ "grad_norm": 1567.8216552734375,
42
+ "learning_rate": 5e-06,
43
+ "loss": 45.0472,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.0663643402278509,
48
+ "grad_norm": 1465.835205078125,
49
+ "learning_rate": 6e-06,
50
+ "loss": 77.118,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.07742506359915939,
55
+ "grad_norm": 879.969482421875,
56
+ "learning_rate": 7e-06,
57
+ "loss": 39.1988,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.08848578697046787,
62
+ "grad_norm": 271.9729309082031,
63
+ "learning_rate": 8.000000000000001e-06,
64
+ "loss": 79.6761,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.09954651034177635,
69
+ "grad_norm": 273.8168029785156,
70
+ "learning_rate": 9e-06,
71
+ "loss": 59.4896,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.11060723371308484,
76
+ "grad_norm": 226.001220703125,
77
+ "learning_rate": 1e-05,
78
+ "loss": 58.7963,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.12166795708439332,
83
+ "grad_norm": 281.18731689453125,
84
+ "learning_rate": 9.88888888888889e-06,
85
+ "loss": 36.1047,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.1327286804557018,
90
+ "grad_norm": 483.055908203125,
91
+ "learning_rate": 9.777777777777779e-06,
92
+ "loss": 47.9512,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.14378940382701028,
97
+ "grad_norm": 308.240966796875,
98
+ "learning_rate": 9.666666666666667e-06,
99
+ "loss": 28.3554,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.15485012719831878,
104
+ "grad_norm": 4638.63232421875,
105
+ "learning_rate": 9.555555555555556e-06,
106
+ "loss": 74.364,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.16591085056962726,
111
+ "grad_norm": 287.8631896972656,
112
+ "learning_rate": 9.444444444444445e-06,
113
+ "loss": 66.8505,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.17697157394093574,
118
+ "grad_norm": 63.01036071777344,
119
+ "learning_rate": 9.333333333333334e-06,
120
+ "loss": 66.0975,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.18803229731224422,
125
+ "grad_norm": 794.6065063476562,
126
+ "learning_rate": 9.222222222222224e-06,
127
+ "loss": 39.9113,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.1990930206835527,
132
+ "grad_norm": 597.668701171875,
133
+ "learning_rate": 9.111111111111112e-06,
134
+ "loss": 40.9694,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.21015374405486117,
139
+ "grad_norm": 627.0382080078125,
140
+ "learning_rate": 9e-06,
141
+ "loss": 70.5725,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.22121446742616968,
146
+ "grad_norm": 246.689697265625,
147
+ "learning_rate": 8.888888888888888e-06,
148
+ "loss": 63.1588,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.23227519079747816,
153
+ "grad_norm": 109.21578979492188,
154
+ "learning_rate": 8.777777777777778e-06,
155
+ "loss": 46.5431,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.24333591416878664,
160
+ "grad_norm": 740.5646362304688,
161
+ "learning_rate": 8.666666666666668e-06,
162
+ "loss": 43.8307,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.2543966375400951,
167
+ "grad_norm": 295.5723876953125,
168
+ "learning_rate": 8.555555555555556e-06,
169
+ "loss": 80.948,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.2654573609114036,
174
+ "grad_norm": 221.36172485351562,
175
+ "learning_rate": 8.444444444444446e-06,
176
+ "loss": 31.6573,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 0.2765180842827121,
181
+ "grad_norm": 237.7281494140625,
182
+ "learning_rate": 8.333333333333334e-06,
183
+ "loss": 68.8744,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 0.28757880765402055,
188
+ "grad_norm": 1603.667724609375,
189
+ "learning_rate": 8.222222222222222e-06,
190
+ "loss": 61.5703,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 0.29863953102532903,
195
+ "grad_norm": 2168.47607421875,
196
+ "learning_rate": 8.111111111111112e-06,
197
+ "loss": 57.0335,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 0.30970025439663756,
202
+ "grad_norm": 1646.4892578125,
203
+ "learning_rate": 8.000000000000001e-06,
204
+ "loss": 29.541,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 0.32076097776794604,
209
+ "grad_norm": 410.48150634765625,
210
+ "learning_rate": 7.88888888888889e-06,
211
+ "loss": 58.4033,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 0.3318217011392545,
216
+ "grad_norm": 457.2492370605469,
217
+ "learning_rate": 7.77777777777778e-06,
218
+ "loss": 77.6572,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 0.342882424510563,
223
+ "grad_norm": 222.49844360351562,
224
+ "learning_rate": 7.666666666666667e-06,
225
+ "loss": 86.4192,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 0.3539431478818715,
230
+ "grad_norm": 218.73208618164062,
231
+ "learning_rate": 7.555555555555556e-06,
232
+ "loss": 28.7311,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 0.36500387125317996,
237
+ "grad_norm": 514.8499755859375,
238
+ "learning_rate": 7.444444444444445e-06,
239
+ "loss": 61.9305,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 0.37606459462448844,
244
+ "grad_norm": 471.7864074707031,
245
+ "learning_rate": 7.333333333333333e-06,
246
+ "loss": 52.1054,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 0.3871253179957969,
251
+ "grad_norm": 26.25701904296875,
252
+ "learning_rate": 7.222222222222223e-06,
253
+ "loss": 41.1312,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 0.3981860413671054,
258
+ "grad_norm": 158.19760131835938,
259
+ "learning_rate": 7.111111111111112e-06,
260
+ "loss": 31.3393,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 0.40924676473841387,
265
+ "grad_norm": 426.075927734375,
266
+ "learning_rate": 7e-06,
267
+ "loss": 53.1371,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 0.42030748810972235,
272
+ "grad_norm": 235.6551513671875,
273
+ "learning_rate": 6.88888888888889e-06,
274
+ "loss": 74.3628,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 0.4313682114810309,
279
+ "grad_norm": 847.091796875,
280
+ "learning_rate": 6.777777777777779e-06,
281
+ "loss": 66.8835,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 0.44242893485233936,
286
+ "grad_norm": 462.72064208984375,
287
+ "learning_rate": 6.666666666666667e-06,
288
+ "loss": 21.3985,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 0.45348965822364784,
293
+ "grad_norm": 84.74278259277344,
294
+ "learning_rate": 6.555555555555556e-06,
295
+ "loss": 46.6882,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 0.4645503815949563,
300
+ "grad_norm": 307.1804504394531,
301
+ "learning_rate": 6.444444444444445e-06,
302
+ "loss": 40.7358,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 0.4756111049662648,
307
+ "grad_norm": 135.82408142089844,
308
+ "learning_rate": 6.333333333333333e-06,
309
+ "loss": 34.787,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 0.4866718283375733,
314
+ "grad_norm": 349.708984375,
315
+ "learning_rate": 6.222222222222223e-06,
316
+ "loss": 65.6245,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 0.49773255170888175,
321
+ "grad_norm": 226.45968627929688,
322
+ "learning_rate": 6.111111111111112e-06,
323
+ "loss": 41.7902,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 0.5087932750801902,
328
+ "grad_norm": 626.4755859375,
329
+ "learning_rate": 6e-06,
330
+ "loss": 41.5158,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 0.5198539984514987,
335
+ "grad_norm": 1342.0029296875,
336
+ "learning_rate": 5.88888888888889e-06,
337
+ "loss": 36.3761,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 0.5309147218228072,
342
+ "grad_norm": 246.92034912109375,
343
+ "learning_rate": 5.777777777777778e-06,
344
+ "loss": 65.2225,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 0.5419754451941157,
349
+ "grad_norm": 935.7799682617188,
350
+ "learning_rate": 5.666666666666667e-06,
351
+ "loss": 28.8935,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 0.5530361685654241,
356
+ "grad_norm": 96.46562957763672,
357
+ "learning_rate": 5.555555555555557e-06,
358
+ "loss": 23.2736,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 0.5640968919367326,
363
+ "grad_norm": 331.4699401855469,
364
+ "learning_rate": 5.444444444444445e-06,
365
+ "loss": 37.549,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 0.5751576153080411,
370
+ "grad_norm": 828.3701782226562,
371
+ "learning_rate": 5.333333333333334e-06,
372
+ "loss": 39.8081,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 0.5862183386793496,
377
+ "grad_norm": 493.2457275390625,
378
+ "learning_rate": 5.2222222222222226e-06,
379
+ "loss": 71.5602,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 0.5972790620506581,
384
+ "grad_norm": 142.9763946533203,
385
+ "learning_rate": 5.1111111111111115e-06,
386
+ "loss": 35.0131,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 0.6083397854219667,
391
+ "grad_norm": 2258.4990234375,
392
+ "learning_rate": 5e-06,
393
+ "loss": 53.0131,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 0.6194005087932751,
398
+ "grad_norm": 452.21826171875,
399
+ "learning_rate": 4.888888888888889e-06,
400
+ "loss": 52.5697,
401
+ "step": 5600
402
+ },
403
+ {
404
+ "epoch": 0.6304612321645836,
405
+ "grad_norm": 285.1300048828125,
406
+ "learning_rate": 4.777777777777778e-06,
407
+ "loss": 27.8757,
408
+ "step": 5700
409
+ },
410
+ {
411
+ "epoch": 0.6415219555358921,
412
+ "grad_norm": 531.2687377929688,
413
+ "learning_rate": 4.666666666666667e-06,
414
+ "loss": 50.0262,
415
+ "step": 5800
416
+ },
417
+ {
418
+ "epoch": 0.6525826789072006,
419
+ "grad_norm": 634.396240234375,
420
+ "learning_rate": 4.555555555555556e-06,
421
+ "loss": 26.5551,
422
+ "step": 5900
423
+ },
424
+ {
425
+ "epoch": 0.663643402278509,
426
+ "grad_norm": 202.63027954101562,
427
+ "learning_rate": 4.444444444444444e-06,
428
+ "loss": 47.3534,
429
+ "step": 6000
430
+ },
431
+ {
432
+ "epoch": 0.6747041256498175,
433
+ "grad_norm": 135.98355102539062,
434
+ "learning_rate": 4.333333333333334e-06,
435
+ "loss": 56.0106,
436
+ "step": 6100
437
+ },
438
+ {
439
+ "epoch": 0.685764849021126,
440
+ "grad_norm": 172.3655242919922,
441
+ "learning_rate": 4.222222222222223e-06,
442
+ "loss": 87.5618,
443
+ "step": 6200
444
+ },
445
+ {
446
+ "epoch": 0.6968255723924345,
447
+ "grad_norm": 312.11932373046875,
448
+ "learning_rate": 4.111111111111111e-06,
449
+ "loss": 38.6178,
450
+ "step": 6300
451
+ },
452
+ {
453
+ "epoch": 0.707886295763743,
454
+ "grad_norm": 313.05389404296875,
455
+ "learning_rate": 4.000000000000001e-06,
456
+ "loss": 67.4866,
457
+ "step": 6400
458
+ },
459
+ {
460
+ "epoch": 0.7189470191350514,
461
+ "grad_norm": 220.42941284179688,
462
+ "learning_rate": 3.88888888888889e-06,
463
+ "loss": 51.0776,
464
+ "step": 6500
465
+ },
466
+ {
467
+ "epoch": 0.7300077425063599,
468
+ "grad_norm": 255.8204803466797,
469
+ "learning_rate": 3.777777777777778e-06,
470
+ "loss": 46.7792,
471
+ "step": 6600
472
+ },
473
+ {
474
+ "epoch": 0.7410684658776684,
475
+ "grad_norm": 303.4053649902344,
476
+ "learning_rate": 3.6666666666666666e-06,
477
+ "loss": 43.976,
478
+ "step": 6700
479
+ },
480
+ {
481
+ "epoch": 0.7521291892489769,
482
+ "grad_norm": 65.36351776123047,
483
+ "learning_rate": 3.555555555555556e-06,
484
+ "loss": 32.331,
485
+ "step": 6800
486
+ },
487
+ {
488
+ "epoch": 0.7631899126202853,
489
+ "grad_norm": 226.184814453125,
490
+ "learning_rate": 3.444444444444445e-06,
491
+ "loss": 39.1361,
492
+ "step": 6900
493
+ },
494
+ {
495
+ "epoch": 0.7742506359915938,
496
+ "grad_norm": 242.291015625,
497
+ "learning_rate": 3.3333333333333333e-06,
498
+ "loss": 23.3194,
499
+ "step": 7000
500
+ },
501
+ {
502
+ "epoch": 0.7853113593629023,
503
+ "grad_norm": 390.12750244140625,
504
+ "learning_rate": 3.2222222222222227e-06,
505
+ "loss": 39.4668,
506
+ "step": 7100
507
+ },
508
+ {
509
+ "epoch": 0.7963720827342108,
510
+ "grad_norm": 365.88909912109375,
511
+ "learning_rate": 3.1111111111111116e-06,
512
+ "loss": 47.7755,
513
+ "step": 7200
514
+ },
515
+ {
516
+ "epoch": 0.8074328061055193,
517
+ "grad_norm": 1790.1258544921875,
518
+ "learning_rate": 3e-06,
519
+ "loss": 45.9991,
520
+ "step": 7300
521
+ },
522
+ {
523
+ "epoch": 0.8184935294768277,
524
+ "grad_norm": 199.19326782226562,
525
+ "learning_rate": 2.888888888888889e-06,
526
+ "loss": 29.6907,
527
+ "step": 7400
528
+ },
529
+ {
530
+ "epoch": 0.8295542528481362,
531
+ "grad_norm": 399.6342468261719,
532
+ "learning_rate": 2.7777777777777783e-06,
533
+ "loss": 42.3841,
534
+ "step": 7500
535
+ },
536
+ {
537
+ "epoch": 0.8406149762194447,
538
+ "grad_norm": 331.04315185546875,
539
+ "learning_rate": 2.666666666666667e-06,
540
+ "loss": 65.6187,
541
+ "step": 7600
542
+ },
543
+ {
544
+ "epoch": 0.8516756995907533,
545
+ "grad_norm": 2146.183349609375,
546
+ "learning_rate": 2.5555555555555557e-06,
547
+ "loss": 43.9393,
548
+ "step": 7700
549
+ },
550
+ {
551
+ "epoch": 0.8627364229620618,
552
+ "grad_norm": 204.7069549560547,
553
+ "learning_rate": 2.4444444444444447e-06,
554
+ "loss": 41.5145,
555
+ "step": 7800
556
+ },
557
+ {
558
+ "epoch": 0.8737971463333702,
559
+ "grad_norm": 118.2260971069336,
560
+ "learning_rate": 2.3333333333333336e-06,
561
+ "loss": 23.4009,
562
+ "step": 7900
563
+ },
564
+ {
565
+ "epoch": 0.8848578697046787,
566
+ "grad_norm": 808.902587890625,
567
+ "learning_rate": 2.222222222222222e-06,
568
+ "loss": 28.5469,
569
+ "step": 8000
570
+ },
571
+ {
572
+ "epoch": 0.8959185930759872,
573
+ "grad_norm": 514.1236572265625,
574
+ "learning_rate": 2.1111111111111114e-06,
575
+ "loss": 32.4101,
576
+ "step": 8100
577
+ },
578
+ {
579
+ "epoch": 0.9069793164472957,
580
+ "grad_norm": 256.0317077636719,
581
+ "learning_rate": 2.0000000000000003e-06,
582
+ "loss": 49.2802,
583
+ "step": 8200
584
+ },
585
+ {
586
+ "epoch": 0.9180400398186042,
587
+ "grad_norm": 248.129150390625,
588
+ "learning_rate": 1.888888888888889e-06,
589
+ "loss": 40.7159,
590
+ "step": 8300
591
+ },
592
+ {
593
+ "epoch": 0.9291007631899126,
594
+ "grad_norm": 207.14627075195312,
595
+ "learning_rate": 1.777777777777778e-06,
596
+ "loss": 36.8628,
597
+ "step": 8400
598
+ },
599
+ {
600
+ "epoch": 0.9401614865612211,
601
+ "grad_norm": 492.2493591308594,
602
+ "learning_rate": 1.6666666666666667e-06,
603
+ "loss": 50.4246,
604
+ "step": 8500
605
+ },
606
+ {
607
+ "epoch": 0.9512222099325296,
608
+ "grad_norm": 237.53575134277344,
609
+ "learning_rate": 1.5555555555555558e-06,
610
+ "loss": 45.3869,
611
+ "step": 8600
612
+ },
613
+ {
614
+ "epoch": 0.9622829333038381,
615
+ "grad_norm": 446.43524169921875,
616
+ "learning_rate": 1.4444444444444445e-06,
617
+ "loss": 54.2354,
618
+ "step": 8700
619
+ },
620
+ {
621
+ "epoch": 0.9733436566751466,
622
+ "grad_norm": 301.3879699707031,
623
+ "learning_rate": 1.3333333333333334e-06,
624
+ "loss": 53.4569,
625
+ "step": 8800
626
+ },
627
+ {
628
+ "epoch": 0.984404380046455,
629
+ "grad_norm": 378.23992919921875,
630
+ "learning_rate": 1.2222222222222223e-06,
631
+ "loss": 74.1828,
632
+ "step": 8900
633
+ },
634
+ {
635
+ "epoch": 0.9954651034177635,
636
+ "grad_norm": 244.3396453857422,
637
+ "learning_rate": 1.111111111111111e-06,
638
+ "loss": 38.1764,
639
+ "step": 9000
640
+ },
641
+ {
642
+ "epoch": 1.0,
643
+ "eval_loss": 91.81082153320312,
644
+ "eval_runtime": 31.8798,
645
+ "eval_samples_per_second": 63.049,
646
+ "eval_steps_per_second": 31.525,
647
+ "step": 9041
648
+ },
649
+ {
650
+ "epoch": 1.006525826789072,
651
+ "grad_norm": 69.61438751220703,
652
+ "learning_rate": 1.0000000000000002e-06,
653
+ "loss": 39.4874,
654
+ "step": 9100
655
+ },
656
+ {
657
+ "epoch": 1.0175865501603805,
658
+ "grad_norm": 204.00283813476562,
659
+ "learning_rate": 8.88888888888889e-07,
660
+ "loss": 30.213,
661
+ "step": 9200
662
+ },
663
+ {
664
+ "epoch": 1.028647273531689,
665
+ "grad_norm": 1114.0423583984375,
666
+ "learning_rate": 7.777777777777779e-07,
667
+ "loss": 19.251,
668
+ "step": 9300
669
+ },
670
+ {
671
+ "epoch": 1.0397079969029974,
672
+ "grad_norm": 592.7640380859375,
673
+ "learning_rate": 6.666666666666667e-07,
674
+ "loss": 31.6648,
675
+ "step": 9400
676
+ },
677
+ {
678
+ "epoch": 1.050768720274306,
679
+ "grad_norm": 258.1551818847656,
680
+ "learning_rate": 5.555555555555555e-07,
681
+ "loss": 55.9748,
682
+ "step": 9500
683
+ },
684
+ {
685
+ "epoch": 1.0618294436456144,
686
+ "grad_norm": 12517.9658203125,
687
+ "learning_rate": 4.444444444444445e-07,
688
+ "loss": 38.2583,
689
+ "step": 9600
690
+ },
691
+ {
692
+ "epoch": 1.0728901670169229,
693
+ "grad_norm": 101.80846405029297,
694
+ "learning_rate": 3.3333333333333335e-07,
695
+ "loss": 34.3433,
696
+ "step": 9700
697
+ },
698
+ {
699
+ "epoch": 1.0839508903882313,
700
+ "grad_norm": 529.3522338867188,
701
+ "learning_rate": 2.2222222222222224e-07,
702
+ "loss": 35.9397,
703
+ "step": 9800
704
+ },
705
+ {
706
+ "epoch": 1.0950116137595398,
707
+ "grad_norm": 64.61666870117188,
708
+ "learning_rate": 1.1111111111111112e-07,
709
+ "loss": 20.6341,
710
+ "step": 9900
711
+ },
712
+ {
713
+ "epoch": 1.1060723371308483,
714
+ "grad_norm": 143.1585235595703,
715
+ "learning_rate": 0.0,
716
+ "loss": 34.9678,
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": 2,
739
+ "trial_name": null,
740
+ "trial_params": null
741
+ }