freesky commited on
Commit
043d099
·
1 Parent(s): a7fef25
added_tokens.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 92552,
3
+ "</img>": 92545,
4
+ "</quad>": 92548,
5
+ "</ref>": 92550,
6
+ "<IMG_CONTEXT>": 92546,
7
+ "<box>": 92551,
8
+ "<img>": 92544,
9
+ "<quad>": 92547,
10
+ "<ref>": 92549
11
+ }
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 0.8767247783765196,
4
+ "train_runtime": 2128.2481,
5
+ "train_samples": 400,
6
+ "train_samples_per_second": 0.376,
7
+ "train_steps_per_second": 0.094
8
+ }
config.json ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/dss/dssmcmlfs01/pn34sa/pn34sa-dss-0000/haowei/HF_models/InternVL-Chat-V1-5",
4
+ "architectures": [
5
+ "InternVLChatModel"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
9
+ "AutoModel": "modeling_internvl_chat.InternVLChatModel",
10
+ "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
11
+ },
12
+ "downsample_ratio": 0.5,
13
+ "dynamic_image_size": true,
14
+ "force_image_size": 448,
15
+ "llm_config": {
16
+ "_name_or_path": "pretrained/internlm2-chat-20b/",
17
+ "add_cross_attention": false,
18
+ "architectures": [
19
+ "InternLM2ForCausalLM"
20
+ ],
21
+ "attn_implementation": "flash_attention_2",
22
+ "auto_map": {
23
+ "AutoConfig": "configuration_internlm2.InternLM2Config",
24
+ "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
25
+ "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM"
26
+ },
27
+ "bad_words_ids": null,
28
+ "begin_suppress_tokens": null,
29
+ "bias": false,
30
+ "bos_token_id": 1,
31
+ "chunk_size_feed_forward": 0,
32
+ "cross_attention_hidden_size": null,
33
+ "decoder_start_token_id": null,
34
+ "diversity_penalty": 0.0,
35
+ "do_sample": false,
36
+ "early_stopping": false,
37
+ "encoder_no_repeat_ngram_size": 0,
38
+ "eos_token_id": 2,
39
+ "exponential_decay_length_penalty": null,
40
+ "finetuning_task": null,
41
+ "forced_bos_token_id": null,
42
+ "forced_eos_token_id": null,
43
+ "hidden_act": "silu",
44
+ "hidden_size": 6144,
45
+ "id2label": {
46
+ "0": "LABEL_0",
47
+ "1": "LABEL_1"
48
+ },
49
+ "initializer_range": 0.02,
50
+ "intermediate_size": 16384,
51
+ "is_decoder": false,
52
+ "is_encoder_decoder": false,
53
+ "label2id": {
54
+ "LABEL_0": 0,
55
+ "LABEL_1": 1
56
+ },
57
+ "length_penalty": 1.0,
58
+ "max_length": 20,
59
+ "max_position_embeddings": 32768,
60
+ "min_length": 0,
61
+ "model_type": "internlm2",
62
+ "no_repeat_ngram_size": 0,
63
+ "num_attention_heads": 48,
64
+ "num_beam_groups": 1,
65
+ "num_beams": 1,
66
+ "num_hidden_layers": 48,
67
+ "num_key_value_heads": 8,
68
+ "num_return_sequences": 1,
69
+ "output_attentions": false,
70
+ "output_hidden_states": false,
71
+ "output_scores": false,
72
+ "pad_token_id": 2,
73
+ "prefix": null,
74
+ "problem_type": null,
75
+ "pruned_heads": {},
76
+ "remove_invalid_values": false,
77
+ "repetition_penalty": 1.0,
78
+ "return_dict": true,
79
+ "return_dict_in_generate": false,
80
+ "rms_norm_eps": 1e-05,
81
+ "rope_scaling": {
82
+ "factor": 3.0,
83
+ "type": "dynamic"
84
+ },
85
+ "rope_theta": 1000000,
86
+ "sep_token_id": null,
87
+ "suppress_tokens": null,
88
+ "task_specific_params": null,
89
+ "temperature": 1.0,
90
+ "tf_legacy_loss": false,
91
+ "tie_encoder_decoder": false,
92
+ "tie_word_embeddings": false,
93
+ "tokenizer_class": null,
94
+ "top_k": 50,
95
+ "top_p": 1.0,
96
+ "torch_dtype": "bfloat16",
97
+ "torchscript": false,
98
+ "transformers_version": "4.37.2",
99
+ "typical_p": 1.0,
100
+ "use_bfloat16": false,
101
+ "use_cache": false,
102
+ "vocab_size": 92553
103
+ },
104
+ "max_dynamic_patch": 6,
105
+ "min_dynamic_patch": 1,
106
+ "model_type": "internvl_chat",
107
+ "pad2square": false,
108
+ "ps_version": "v2",
109
+ "select_layer": -1,
110
+ "template": "internlm2-chat",
111
+ "torch_dtype": "bfloat16",
112
+ "transformers_version": null,
113
+ "use_backbone_lora": 0,
114
+ "use_llm_lora": 16,
115
+ "use_thumbnail": true,
116
+ "vision_config": {
117
+ "_name_or_path": "OpenGVLab/InternViT-6B-448px-V1-5",
118
+ "add_cross_attention": false,
119
+ "architectures": [
120
+ "InternVisionModel"
121
+ ],
122
+ "attention_dropout": 0.0,
123
+ "auto_map": {
124
+ "AutoConfig": "configuration_intern_vit.InternVisionConfig",
125
+ "AutoModel": "modeling_intern_vit.InternVisionModel"
126
+ },
127
+ "bad_words_ids": null,
128
+ "begin_suppress_tokens": null,
129
+ "bos_token_id": null,
130
+ "chunk_size_feed_forward": 0,
131
+ "cross_attention_hidden_size": null,
132
+ "decoder_start_token_id": null,
133
+ "diversity_penalty": 0.0,
134
+ "do_sample": false,
135
+ "drop_path_rate": 0.4,
136
+ "dropout": 0.0,
137
+ "early_stopping": false,
138
+ "encoder_no_repeat_ngram_size": 0,
139
+ "eos_token_id": null,
140
+ "exponential_decay_length_penalty": null,
141
+ "finetuning_task": null,
142
+ "forced_bos_token_id": null,
143
+ "forced_eos_token_id": null,
144
+ "hidden_act": "gelu",
145
+ "hidden_size": 3200,
146
+ "id2label": {
147
+ "0": "LABEL_0",
148
+ "1": "LABEL_1"
149
+ },
150
+ "image_size": 448,
151
+ "initializer_factor": 0.1,
152
+ "initializer_range": 1e-10,
153
+ "intermediate_size": 12800,
154
+ "is_decoder": false,
155
+ "is_encoder_decoder": false,
156
+ "label2id": {
157
+ "LABEL_0": 0,
158
+ "LABEL_1": 1
159
+ },
160
+ "layer_norm_eps": 1e-06,
161
+ "length_penalty": 1.0,
162
+ "max_length": 20,
163
+ "min_length": 0,
164
+ "model_type": "intern_vit_6b",
165
+ "no_repeat_ngram_size": 0,
166
+ "norm_type": "rms_norm",
167
+ "num_attention_heads": 25,
168
+ "num_beam_groups": 1,
169
+ "num_beams": 1,
170
+ "num_channels": 3,
171
+ "num_hidden_layers": 45,
172
+ "num_return_sequences": 1,
173
+ "output_attentions": false,
174
+ "output_hidden_states": false,
175
+ "output_scores": false,
176
+ "pad_token_id": null,
177
+ "patch_size": 14,
178
+ "prefix": null,
179
+ "problem_type": null,
180
+ "pruned_heads": {},
181
+ "qk_normalization": true,
182
+ "qkv_bias": false,
183
+ "remove_invalid_values": false,
184
+ "repetition_penalty": 1.0,
185
+ "return_dict": true,
186
+ "return_dict_in_generate": false,
187
+ "sep_token_id": null,
188
+ "suppress_tokens": null,
189
+ "task_specific_params": null,
190
+ "temperature": 1.0,
191
+ "tf_legacy_loss": false,
192
+ "tie_encoder_decoder": false,
193
+ "tie_word_embeddings": true,
194
+ "tokenizer_class": null,
195
+ "top_k": 50,
196
+ "top_p": 1.0,
197
+ "torch_dtype": "bfloat16",
198
+ "torchscript": false,
199
+ "transformers_version": "4.37.2",
200
+ "typical_p": 1.0,
201
+ "use_bfloat16": true,
202
+ "use_flash_attn": true
203
+ }
204
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.37.2"
4
+ }
model-00001-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71da14ff2afb6a4d98042027f17e541edc57aad359b59597b1f5848934f5e609
3
+ size 4988569440
model-00002-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:291ea6a5037584d76aa28d97f941ce4ca3a6f48b6ac01101d6468d8248fd31cf
3
+ size 4937253584
model-00003-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb11d9d546ccf10ed1947029b485506d0cb9da93954941e1a184776785cc3679
3
+ size 4803026136
model-00004-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d25d07744d8e15942bb6934eccd9231b07d921d45852388e4f56760276ffbf83
3
+ size 4885078064
model-00005-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c376da0966e8488d86c196fd6c719eaf6db1b05ef39f8965572c2f6929e9270a
3
+ size 4885078120
model-00006-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eb842e48a685a2b25cb65d395a0ca13b8fbcb6f08f648da52ecc4bbd30ef507
3
+ size 4986225504
model-00007-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27c8100681a433c3e67a9a64ce8f683c6619237b40140e4161bc97d2b47ae5fc
3
+ size 4960575744
model-00008-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc9ca1d276a9612de6e8a6b44b1f5bc086259b1b8c395aa9aa88c2bc8474b15
3
+ size 4885078120
model-00009-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bdcd0e1f5461cf8fc47949931d68fe57a33dfc783a128f471016531855a3ac8
3
+ size 4986225504
model-00010-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b7cd33f33063c12bcfa36b32dcc05a8044d6bdc663b529815f2c5b5ef1b7465
3
+ size 4960575744
model-00011-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71131fdb9740ffa7a7150d6ef6d0ef9370162cfabe1ea222f20ed36a11cbe821
3
+ size 1772842336
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<img>",
4
+ "</img>",
5
+ "<IMG_CONTEXT>",
6
+ "<quad>",
7
+ "</quad>",
8
+ "<ref>",
9
+ "</ref>",
10
+ "<box>",
11
+ "</box>"
12
+ ],
13
+ "bos_token": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "pad_token": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "unk_token": {
35
+ "content": "<unk>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ }
41
+ }
tokenization_internlm2.py ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
2
+ #
3
+ # This code is based on transformers/src/transformers/models/llama/tokenization_llama.py
4
+ #
5
+ # Licensed under the Apache License, Version 2.0 (the "License");
6
+ # you may not use this file except in compliance with the License.
7
+ # You may obtain a copy of the License at
8
+ #
9
+ # http://www.apache.org/licenses/LICENSE-2.0
10
+ #
11
+ # Unless required by applicable law or agreed to in writing, software
12
+ # distributed under the License is distributed on an "AS IS" BASIS,
13
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
+ # See the License for the specific language governing permissions and
15
+ # limitations under the License.
16
+
17
+ """Tokenization classes for InternLM."""
18
+ import os
19
+ from shutil import copyfile
20
+ from typing import Any, Dict, List, Optional, Tuple
21
+
22
+ import sentencepiece as spm
23
+ from transformers.tokenization_utils import PreTrainedTokenizer
24
+ from transformers.utils import logging
25
+
26
+ logger = logging.get_logger(__name__)
27
+
28
+ VOCAB_FILES_NAMES = {'vocab_file': './tokenizer.model'}
29
+
30
+ PRETRAINED_VOCAB_FILES_MAP = {}
31
+
32
+
33
+ # Modified from transformers.model.llama.tokenization_llama.LlamaTokenizer
34
+ class InternLM2Tokenizer(PreTrainedTokenizer):
35
+ """
36
+ Construct a InternLM2 tokenizer. Based on byte-level Byte-Pair-Encoding.
37
+
38
+ Args:
39
+ vocab_file (`str`):
40
+ Path to the vocabulary file.
41
+ """
42
+
43
+ vocab_files_names = VOCAB_FILES_NAMES
44
+ pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
45
+ model_input_names = ['input_ids', 'attention_mask']
46
+ _auto_class = 'AutoTokenizer'
47
+
48
+ def __init__(
49
+ self,
50
+ vocab_file,
51
+ unk_token='<unk>',
52
+ bos_token='<s>',
53
+ eos_token='</s>',
54
+ pad_token='</s>',
55
+ sp_model_kwargs: Optional[Dict[str, Any]] = None,
56
+ add_bos_token=True,
57
+ add_eos_token=False,
58
+ decode_with_prefix_space=False,
59
+ clean_up_tokenization_spaces=False,
60
+ **kwargs,
61
+ ):
62
+ self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
63
+ self.vocab_file = vocab_file
64
+ self.add_bos_token = add_bos_token
65
+ self.add_eos_token = add_eos_token
66
+ self.decode_with_prefix_space = decode_with_prefix_space
67
+ self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
68
+ self.sp_model.Load(vocab_file)
69
+ self._no_prefix_space_tokens = None
70
+ super().__init__(
71
+ bos_token=bos_token,
72
+ eos_token=eos_token,
73
+ unk_token=unk_token,
74
+ pad_token=pad_token,
75
+ clean_up_tokenization_spaces=clean_up_tokenization_spaces,
76
+ **kwargs,
77
+ )
78
+
79
+ @property
80
+ def no_prefix_space_tokens(self):
81
+ if self._no_prefix_space_tokens is None:
82
+ vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
83
+ self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith('▁')}
84
+ return self._no_prefix_space_tokens
85
+
86
+ @property
87
+ def vocab_size(self):
88
+ """Returns vocab size"""
89
+ return self.sp_model.get_piece_size()
90
+
91
+ @property
92
+ def bos_token_id(self) -> Optional[int]:
93
+ return self.sp_model.bos_id()
94
+
95
+ @property
96
+ def eos_token_id(self) -> Optional[int]:
97
+ return self.sp_model.eos_id()
98
+
99
+ def get_vocab(self):
100
+ """Returns vocab as a dict"""
101
+ vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
102
+ vocab.update(self.added_tokens_encoder)
103
+ return vocab
104
+
105
+ def _tokenize(self, text):
106
+ """Returns a tokenized string."""
107
+ return self.sp_model.encode(text, out_type=str)
108
+
109
+ def _convert_token_to_id(self, token):
110
+ """Converts a token (str) in an id using the vocab."""
111
+ return self.sp_model.piece_to_id(token)
112
+
113
+ def _convert_id_to_token(self, index):
114
+ """Converts an index (integer) in a token (str) using the vocab."""
115
+ token = self.sp_model.IdToPiece(index)
116
+ return token
117
+
118
+ def _maybe_add_prefix_space(self, tokens, decoded):
119
+ if tokens and tokens[0] not in self.no_prefix_space_tokens:
120
+ return ' ' + decoded
121
+ else:
122
+ return decoded
123
+
124
+ def convert_tokens_to_string(self, tokens):
125
+ """Converts a sequence of tokens (string) in a single string."""
126
+ current_sub_tokens = []
127
+ out_string = ''
128
+ prev_is_special = False
129
+ for token in tokens:
130
+ # make sure that special tokens are not decoded using sentencepiece model
131
+ if token in self.all_special_tokens:
132
+ if not prev_is_special:
133
+ out_string += ' '
134
+ out_string += self.sp_model.decode(current_sub_tokens) + token
135
+ prev_is_special = True
136
+ current_sub_tokens = []
137
+ else:
138
+ current_sub_tokens.append(token)
139
+ prev_is_special = False
140
+ out_string += self.sp_model.decode(current_sub_tokens)
141
+ out_string = self.clean_up_tokenization(out_string)
142
+ out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
143
+ return out_string[1:]
144
+
145
+ def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
146
+ """
147
+ Save the vocabulary and special tokens file to a directory.
148
+
149
+ Args:
150
+ save_directory (`str`):
151
+ The directory in which to save the vocabulary.
152
+
153
+ Returns:
154
+ `Tuple(str)`: Paths to the files saved.
155
+ """
156
+ if not os.path.isdir(save_directory):
157
+ logger.error(f'Vocabulary path ({save_directory}) should be a directory')
158
+ return
159
+ out_vocab_file = os.path.join(
160
+ save_directory, (filename_prefix + '-' if filename_prefix else '') + VOCAB_FILES_NAMES['vocab_file']
161
+ )
162
+
163
+ if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
164
+ copyfile(self.vocab_file, out_vocab_file)
165
+ elif not os.path.isfile(self.vocab_file):
166
+ with open(out_vocab_file, 'wb') as fi:
167
+ content_spiece_model = self.sp_model.serialized_model_proto()
168
+ fi.write(content_spiece_model)
169
+
170
+ return (out_vocab_file,)
171
+
172
+ def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
173
+ if self.add_bos_token:
174
+ bos_token_ids = [self.bos_token_id]
175
+ else:
176
+ bos_token_ids = []
177
+
178
+ output = bos_token_ids + token_ids_0
179
+
180
+ if token_ids_1 is not None:
181
+ output = output + token_ids_1
182
+
183
+ if self.add_eos_token:
184
+ output = output + [self.eos_token_id]
185
+
186
+ return output
187
+
188
+ def get_special_tokens_mask(
189
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
190
+ ) -> List[int]:
191
+ """
192
+ Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
193
+ special tokens using the tokenizer `prepare_for_model` method.
194
+
195
+ Args:
196
+ token_ids_0 (`List[int]`):
197
+ List of IDs.
198
+ token_ids_1 (`List[int]`, *optional*):
199
+ Optional second list of IDs for sequence pairs.
200
+ already_has_special_tokens (`bool`, *optional*, defaults to `False`):
201
+ Whether or not the token list is already formatted with special tokens for the model.
202
+
203
+ Returns:
204
+ `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
205
+ """
206
+ if already_has_special_tokens:
207
+ return super().get_special_tokens_mask(
208
+ token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
209
+ )
210
+
211
+ if token_ids_1 is None:
212
+ return [1] + ([0] * len(token_ids_0)) + [1]
213
+ return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
214
+
215
+ def create_token_type_ids_from_sequences(
216
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
217
+ ) -> List[int]:
218
+ """
219
+ Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
220
+ use of token type ids, therefore a list of zeros is returned.
221
+
222
+ Args:
223
+ token_ids_0 (`List[int]`):
224
+ List of IDs.
225
+ token_ids_1 (`List[int]`, *optional*):
226
+ Optional second list of IDs for sequence pairs.
227
+
228
+ Returns:
229
+ `List[int]`: List of zeros.
230
+ """
231
+ eos = [self.eos_token_id]
232
+
233
+ if token_ids_1 is None:
234
+ return len(token_ids_0 + eos) * [0]
235
+ return len(token_ids_0 + eos + token_ids_1 + eos) * [0]
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
3
+ size 1477754
tokenizer_config.json ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "92538": {
28
+ "content": "<|plugin|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "92539": {
36
+ "content": "<|interpreter|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "92540": {
44
+ "content": "<|action_end|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "92541": {
52
+ "content": "<|action_start|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "92542": {
60
+ "content": "<|im_end|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "92543": {
68
+ "content": "<|im_start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "92544": {
76
+ "content": "<img>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "92545": {
84
+ "content": "</img>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "92546": {
92
+ "content": "<IMG_CONTEXT>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "92547": {
100
+ "content": "<quad>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "92548": {
108
+ "content": "</quad>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "92549": {
116
+ "content": "<ref>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "92550": {
124
+ "content": "</ref>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "92551": {
132
+ "content": "<box>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "92552": {
140
+ "content": "</box>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ }
147
+ },
148
+ "additional_special_tokens": [
149
+ "<img>",
150
+ "</img>",
151
+ "<IMG_CONTEXT>",
152
+ "<quad>",
153
+ "</quad>",
154
+ "<ref>",
155
+ "</ref>",
156
+ "<box>",
157
+ "</box>"
158
+ ],
159
+ "auto_map": {
160
+ "AutoTokenizer": [
161
+ "tokenization_internlm2.InternLM2Tokenizer",
162
+ null
163
+ ]
164
+ },
165
+ "bos_token": "<s>",
166
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
167
+ "clean_up_tokenization_spaces": false,
168
+ "eos_token": "</s>",
169
+ "model_max_length": 4096,
170
+ "pad_token": "</s>",
171
+ "tokenizer_class": "InternLM2Tokenizer",
172
+ "unk_token": "<unk>"
173
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 0.8767247783765196,
4
+ "train_runtime": 2128.2481,
5
+ "train_samples": 400,
6
+ "train_samples_per_second": 0.376,
7
+ "train_steps_per_second": 0.094
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1230 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 1.6666666666666667e-05,
14
+ "loss": 1.3711,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.02,
19
+ "learning_rate": 3.3333333333333335e-05,
20
+ "loss": 1.334,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.03,
25
+ "learning_rate": 5e-05,
26
+ "loss": 1.3864,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.04,
31
+ "learning_rate": 6.666666666666667e-05,
32
+ "loss": 2.248,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.05,
37
+ "learning_rate": 8.333333333333334e-05,
38
+ "loss": 1.9428,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.06,
43
+ "learning_rate": 0.0001,
44
+ "loss": 1.5513,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.07,
49
+ "learning_rate": 9.999344418328162e-05,
50
+ "loss": 1.3746,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.08,
55
+ "learning_rate": 9.997377845227576e-05,
56
+ "loss": 1.2993,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.09,
61
+ "learning_rate": 9.994100796397954e-05,
62
+ "loss": 2.3052,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.1,
67
+ "learning_rate": 9.989514131188559e-05,
68
+ "loss": 1.2252,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.11,
73
+ "learning_rate": 9.983619052372848e-05,
74
+ "loss": 1.1473,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.12,
79
+ "learning_rate": 9.97641710583307e-05,
80
+ "loss": 1.474,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.13,
85
+ "learning_rate": 9.967910180154889e-05,
86
+ "loss": 1.5391,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.14,
91
+ "learning_rate": 9.958100506132127e-05,
92
+ "loss": 1.0238,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.15,
97
+ "learning_rate": 9.946990656181781e-05,
98
+ "loss": 0.6343,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.16,
103
+ "learning_rate": 9.934583543669453e-05,
104
+ "loss": 1.375,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.17,
109
+ "learning_rate": 9.920882422145372e-05,
110
+ "loss": 0.9674,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.18,
115
+ "learning_rate": 9.905890884491195e-05,
116
+ "loss": 0.6452,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.19,
121
+ "learning_rate": 9.889612861977853e-05,
122
+ "loss": 0.5237,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.2,
127
+ "learning_rate": 9.872052623234632e-05,
128
+ "loss": 1.2983,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.21,
133
+ "learning_rate": 9.853214773129796e-05,
134
+ "loss": 0.8931,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.22,
139
+ "learning_rate": 9.833104251563056e-05,
140
+ "loss": 1.1171,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.23,
145
+ "learning_rate": 9.811726332170153e-05,
146
+ "loss": 1.3356,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.24,
151
+ "learning_rate": 9.789086620939936e-05,
152
+ "loss": 0.9511,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.25,
157
+ "learning_rate": 9.765191054744305e-05,
158
+ "loss": 1.0608,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.26,
163
+ "learning_rate": 9.740045899781352e-05,
164
+ "loss": 1.0137,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.27,
169
+ "learning_rate": 9.713657749932172e-05,
170
+ "loss": 1.0402,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.28,
175
+ "learning_rate": 9.686033525031719e-05,
176
+ "loss": 0.5888,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.29,
181
+ "learning_rate": 9.657180469054213e-05,
182
+ "loss": 1.0759,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.3,
187
+ "learning_rate": 9.627106148213522e-05,
188
+ "loss": 1.1284,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.31,
193
+ "learning_rate": 9.595818448979061e-05,
194
+ "loss": 0.5581,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.32,
199
+ "learning_rate": 9.563325576007701e-05,
200
+ "loss": 0.1291,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.33,
205
+ "learning_rate": 9.529636049992234e-05,
206
+ "loss": 0.5968,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.34,
211
+ "learning_rate": 9.494758705426978e-05,
212
+ "loss": 0.0704,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.35,
217
+ "learning_rate": 9.458702688291073e-05,
218
+ "loss": 0.567,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.36,
223
+ "learning_rate": 9.421477453650118e-05,
224
+ "loss": 0.4475,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.37,
229
+ "learning_rate": 9.38309276317674e-05,
230
+ "loss": 1.4415,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.38,
235
+ "learning_rate": 9.343558682590756e-05,
236
+ "loss": 0.7743,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.39,
241
+ "learning_rate": 9.302885579019627e-05,
242
+ "loss": 0.6328,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.4,
247
+ "learning_rate": 9.261084118279847e-05,
248
+ "loss": 0.2475,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.41,
253
+ "learning_rate": 9.218165262080023e-05,
254
+ "loss": 1.2443,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.42,
259
+ "learning_rate": 9.174140265146356e-05,
260
+ "loss": 0.8085,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.43,
265
+ "learning_rate": 9.129020672271283e-05,
266
+ "loss": 0.7764,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.44,
271
+ "learning_rate": 9.082818315286055e-05,
272
+ "loss": 0.5008,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.45,
277
+ "learning_rate": 9.035545309958046e-05,
278
+ "loss": 0.5582,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.46,
283
+ "learning_rate": 8.987214052813604e-05,
284
+ "loss": 1.2532,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.47,
289
+ "learning_rate": 8.937837217887273e-05,
290
+ "loss": 0.5482,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.48,
295
+ "learning_rate": 8.887427753398248e-05,
296
+ "loss": 1.1794,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.49,
301
+ "learning_rate": 8.835998878354931e-05,
302
+ "loss": 1.0944,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.5,
307
+ "learning_rate": 8.783564079088477e-05,
308
+ "loss": 0.9639,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.51,
313
+ "learning_rate": 8.73013710571623e-05,
314
+ "loss": 0.6401,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.52,
319
+ "learning_rate": 8.675731968536002e-05,
320
+ "loss": 1.1377,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.53,
325
+ "learning_rate": 8.620362934352109e-05,
326
+ "loss": 0.5624,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.54,
331
+ "learning_rate": 8.564044522734147e-05,
332
+ "loss": 1.1549,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.55,
337
+ "learning_rate": 8.506791502209496e-05,
338
+ "loss": 0.7098,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.56,
343
+ "learning_rate": 8.448618886390522e-05,
344
+ "loss": 0.6059,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.57,
349
+ "learning_rate": 8.389541930037516e-05,
350
+ "loss": 0.6728,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.58,
355
+ "learning_rate": 8.329576125058406e-05,
356
+ "loss": 1.0251,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.59,
361
+ "learning_rate": 8.268737196446264e-05,
362
+ "loss": 0.7898,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.6,
367
+ "learning_rate": 8.2070410981557e-05,
368
+ "loss": 0.8504,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.61,
373
+ "learning_rate": 8.144504008919222e-05,
374
+ "loss": 0.5914,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.62,
379
+ "learning_rate": 8.081142328004637e-05,
380
+ "loss": 1.1653,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.63,
385
+ "learning_rate": 8.016972670914624e-05,
386
+ "loss": 1.1441,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.64,
391
+ "learning_rate": 7.952011865029614e-05,
392
+ "loss": 1.1371,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.65,
397
+ "learning_rate": 7.886276945195099e-05,
398
+ "loss": 0.7263,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.66,
403
+ "learning_rate": 7.819785149254532e-05,
404
+ "loss": 0.6626,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.67,
409
+ "learning_rate": 7.752553913529018e-05,
410
+ "loss": 1.0817,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.68,
415
+ "learning_rate": 7.68460086824492e-05,
416
+ "loss": 0.6464,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.69,
421
+ "learning_rate": 7.61594383291065e-05,
422
+ "loss": 0.6011,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.7,
427
+ "learning_rate": 7.546600811643816e-05,
428
+ "loss": 1.0604,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.71,
433
+ "learning_rate": 7.476589988449939e-05,
434
+ "loss": 0.5161,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.72,
439
+ "learning_rate": 7.405929722454026e-05,
440
+ "loss": 0.8083,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.73,
445
+ "learning_rate": 7.334638543086203e-05,
446
+ "loss": 1.0716,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.74,
451
+ "learning_rate": 7.262735145222696e-05,
452
+ "loss": 0.5927,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.75,
457
+ "learning_rate": 7.190238384283412e-05,
458
+ "loss": 1.2094,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.76,
463
+ "learning_rate": 7.117167271287453e-05,
464
+ "loss": 0.5113,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.77,
469
+ "learning_rate": 7.043540967867782e-05,
470
+ "loss": 0.9976,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.78,
475
+ "learning_rate": 6.969378781246436e-05,
476
+ "loss": 1.0694,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.79,
481
+ "learning_rate": 6.894700159171534e-05,
482
+ "loss": 0.0773,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.8,
487
+ "learning_rate": 6.819524684817438e-05,
488
+ "loss": 1.2459,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.81,
493
+ "learning_rate": 6.743872071649411e-05,
494
+ "loss": 1.2277,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.82,
499
+ "learning_rate": 6.667762158254104e-05,
500
+ "loss": 0.7503,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.83,
505
+ "learning_rate": 6.59121490313722e-05,
506
+ "loss": 0.8949,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.84,
511
+ "learning_rate": 6.514250379489753e-05,
512
+ "loss": 1.0714,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.85,
517
+ "learning_rate": 6.436888769924142e-05,
518
+ "loss": 0.764,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.86,
523
+ "learning_rate": 6.359150361181715e-05,
524
+ "loss": 1.0263,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.87,
529
+ "learning_rate": 6.281055538812861e-05,
530
+ "loss": 1.0915,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.88,
535
+ "learning_rate": 6.202624781831268e-05,
536
+ "loss": 1.1416,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.89,
541
+ "learning_rate": 6.123878657343648e-05,
542
+ "loss": 1.0471,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.9,
547
+ "learning_rate": 6.044837815156377e-05,
548
+ "loss": 0.7535,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.91,
553
+ "learning_rate": 5.9655229823604406e-05,
554
+ "loss": 1.1383,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.92,
559
+ "learning_rate": 5.885954957896115e-05,
560
+ "loss": 1.1546,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.93,
565
+ "learning_rate": 5.8061546070987994e-05,
566
+ "loss": 0.6833,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.94,
571
+ "learning_rate": 5.726142856227452e-05,
572
+ "loss": 0.7396,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.95,
577
+ "learning_rate": 5.645940686977033e-05,
578
+ "loss": 1.0028,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.96,
583
+ "learning_rate": 5.565569130976422e-05,
584
+ "loss": 0.7586,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.97,
589
+ "learning_rate": 5.4850492642732406e-05,
590
+ "loss": 1.0252,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.98,
595
+ "learning_rate": 5.4044022018070214e-05,
596
+ "loss": 0.8318,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.99,
601
+ "learning_rate": 5.3236490918721794e-05,
602
+ "loss": 1.4927,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 1.0,
607
+ "learning_rate": 5.242811110572242e-05,
608
+ "loss": 1.0549,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 1.01,
613
+ "learning_rate": 5.1619094562667804e-05,
614
+ "loss": 1.1034,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 1.02,
619
+ "learning_rate": 5.080965344012508e-05,
620
+ "loss": 1.1269,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 1.03,
625
+ "learning_rate": 5e-05,
626
+ "loss": 0.5282,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 1.04,
631
+ "learning_rate": 4.919034655987493e-05,
632
+ "loss": 0.5633,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 1.05,
637
+ "learning_rate": 4.838090543733222e-05,
638
+ "loss": 0.508,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 1.06,
643
+ "learning_rate": 4.7571888894277604e-05,
644
+ "loss": 1.0521,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 1.07,
649
+ "learning_rate": 4.676350908127822e-05,
650
+ "loss": 0.6679,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 1.08,
655
+ "learning_rate": 4.59559779819298e-05,
656
+ "loss": 0.5803,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 1.09,
661
+ "learning_rate": 4.51495073572676e-05,
662
+ "loss": 0.6257,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 1.1,
667
+ "learning_rate": 4.434430869023579e-05,
668
+ "loss": 1.1256,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 1.11,
673
+ "learning_rate": 4.35405931302297e-05,
674
+ "loss": 1.0836,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 1.12,
679
+ "learning_rate": 4.27385714377255e-05,
680
+ "loss": 1.0069,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 1.13,
685
+ "learning_rate": 4.193845392901201e-05,
686
+ "loss": 0.0824,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 1.14,
691
+ "learning_rate": 4.114045042103887e-05,
692
+ "loss": 0.887,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 1.15,
697
+ "learning_rate": 4.0344770176395606e-05,
698
+ "loss": 0.9928,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 1.16,
703
+ "learning_rate": 3.955162184843625e-05,
704
+ "loss": 0.6192,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 1.17,
709
+ "learning_rate": 3.876121342656355e-05,
710
+ "loss": 0.9845,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 1.18,
715
+ "learning_rate": 3.7973752181687335e-05,
716
+ "loss": 1.0146,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 1.19,
721
+ "learning_rate": 3.718944461187138e-05,
722
+ "loss": 0.6376,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 1.2,
727
+ "learning_rate": 3.640849638818286e-05,
728
+ "loss": 1.1646,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 1.21,
733
+ "learning_rate": 3.5631112300758595e-05,
734
+ "loss": 0.6622,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 1.22,
739
+ "learning_rate": 3.4857496205102474e-05,
740
+ "loss": 0.1604,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 1.23,
745
+ "learning_rate": 3.408785096862782e-05,
746
+ "loss": 0.5158,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 1.24,
751
+ "learning_rate": 3.332237841745898e-05,
752
+ "loss": 0.6361,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 1.25,
757
+ "learning_rate": 3.2561279283505883e-05,
758
+ "loss": 1.1773,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 1.26,
763
+ "learning_rate": 3.180475315182563e-05,
764
+ "loss": 1.1003,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 1.27,
769
+ "learning_rate": 3.105299840828466e-05,
770
+ "loss": 0.5131,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 1.28,
775
+ "learning_rate": 3.0306212187535653e-05,
776
+ "loss": 0.9371,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 1.29,
781
+ "learning_rate": 2.9564590321322207e-05,
782
+ "loss": 0.4125,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 1.3,
787
+ "learning_rate": 2.882832728712551e-05,
788
+ "loss": 1.034,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 1.31,
793
+ "learning_rate": 2.8097616157165883e-05,
794
+ "loss": 0.5951,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 1.32,
799
+ "learning_rate": 2.737264854777306e-05,
800
+ "loss": 0.3212,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 1.33,
805
+ "learning_rate": 2.6653614569137968e-05,
806
+ "loss": 0.6433,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 1.34,
811
+ "learning_rate": 2.5940702775459747e-05,
812
+ "loss": 0.7006,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 1.35,
817
+ "learning_rate": 2.5234100115500643e-05,
818
+ "loss": 1.091,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 1.36,
823
+ "learning_rate": 2.4533991883561868e-05,
824
+ "loss": 0.4494,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 1.37,
829
+ "learning_rate": 2.3840561670893496e-05,
830
+ "loss": 0.4309,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 1.38,
835
+ "learning_rate": 2.315399131755081e-05,
836
+ "loss": 0.9503,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 1.39,
841
+ "learning_rate": 2.2474460864709824e-05,
842
+ "loss": 1.1667,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 1.4,
847
+ "learning_rate": 2.180214850745467e-05,
848
+ "loss": 1.1528,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 1.41,
853
+ "learning_rate": 2.1137230548049043e-05,
854
+ "loss": 0.5514,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 1.42,
859
+ "learning_rate": 2.0479881349703883e-05,
860
+ "loss": 1.0104,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 1.43,
865
+ "learning_rate": 1.983027329085377e-05,
866
+ "loss": 1.2217,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 1.44,
871
+ "learning_rate": 1.9188576719953633e-05,
872
+ "loss": 1.1916,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 1.45,
877
+ "learning_rate": 1.8554959910807775e-05,
878
+ "loss": 0.5268,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 1.46,
883
+ "learning_rate": 1.7929589018443016e-05,
884
+ "loss": 0.6524,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 1.47,
889
+ "learning_rate": 1.7312628035537387e-05,
890
+ "loss": 0.5125,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 1.48,
895
+ "learning_rate": 1.6704238749415957e-05,
896
+ "loss": 0.577,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 1.49,
901
+ "learning_rate": 1.6104580699624837e-05,
902
+ "loss": 1.098,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 1.5,
907
+ "learning_rate": 1.5513811136094787e-05,
908
+ "loss": 0.9055,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 1.51,
913
+ "learning_rate": 1.4932084977905042e-05,
914
+ "loss": 0.8727,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 1.52,
919
+ "learning_rate": 1.4359554772658552e-05,
920
+ "loss": 0.9075,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 1.53,
925
+ "learning_rate": 1.3796370656478935e-05,
926
+ "loss": 1.1641,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 1.54,
931
+ "learning_rate": 1.3242680314639993e-05,
932
+ "loss": 0.5507,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 1.55,
937
+ "learning_rate": 1.2698628942837699e-05,
938
+ "loss": 0.5801,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 1.56,
943
+ "learning_rate": 1.2164359209115234e-05,
944
+ "loss": 1.1929,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 1.57,
949
+ "learning_rate": 1.1640011216450691e-05,
950
+ "loss": 1.2133,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 1.58,
955
+ "learning_rate": 1.1125722466017547e-05,
956
+ "loss": 0.6737,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 1.59,
961
+ "learning_rate": 1.0621627821127289e-05,
962
+ "loss": 1.0575,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 1.6,
967
+ "learning_rate": 1.012785947186397e-05,
968
+ "loss": 0.5367,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 1.61,
973
+ "learning_rate": 9.644546900419533e-06,
974
+ "loss": 0.876,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 1.62,
979
+ "learning_rate": 9.171816847139448e-06,
980
+ "loss": 0.8905,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 1.63,
985
+ "learning_rate": 8.70979327728718e-06,
986
+ "loss": 0.6048,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 1.64,
991
+ "learning_rate": 8.25859734853645e-06,
992
+ "loss": 0.4433,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 1.65,
997
+ "learning_rate": 7.81834737919978e-06,
998
+ "loss": 1.1322,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 1.66,
1003
+ "learning_rate": 7.389158817201542e-06,
1004
+ "loss": 1.1292,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 1.67,
1009
+ "learning_rate": 6.9711442098037375e-06,
1010
+ "loss": 0.5969,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 1.68,
1015
+ "learning_rate": 6.564413174092443e-06,
1016
+ "loss": 0.815,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 1.69,
1021
+ "learning_rate": 6.16907236823262e-06,
1022
+ "loss": 1.1361,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 1.7,
1027
+ "learning_rate": 5.785225463498828e-06,
1028
+ "loss": 0.3949,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 1.71,
1033
+ "learning_rate": 5.412973117089287e-06,
1034
+ "loss": 1.0599,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 1.72,
1039
+ "learning_rate": 5.05241294573024e-06,
1040
+ "loss": 0.177,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 1.73,
1045
+ "learning_rate": 4.703639500077656e-06,
1046
+ "loss": 1.0362,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 1.74,
1051
+ "learning_rate": 4.366744239922998e-06,
1052
+ "loss": 0.3497,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 1.75,
1057
+ "learning_rate": 4.041815510209396e-06,
1058
+ "loss": 0.9584,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 1.76,
1063
+ "learning_rate": 3.728938517864794e-06,
1064
+ "loss": 0.9382,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 1.77,
1069
+ "learning_rate": 3.4281953094578877e-06,
1070
+ "loss": 0.9351,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 1.78,
1075
+ "learning_rate": 3.1396647496828247e-06,
1076
+ "loss": 1.3268,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 1.79,
1081
+ "learning_rate": 2.8634225006782865e-06,
1082
+ "loss": 0.4768,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 1.8,
1087
+ "learning_rate": 2.5995410021864787e-06,
1088
+ "loss": 0.0659,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 1.81,
1093
+ "learning_rate": 2.3480894525569562e-06,
1094
+ "loss": 0.0854,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 1.82,
1099
+ "learning_rate": 2.1091337906006482e-06,
1100
+ "loss": 1.0339,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 1.83,
1105
+ "learning_rate": 1.8827366782984913e-06,
1106
+ "loss": 0.7292,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 1.84,
1111
+ "learning_rate": 1.6689574843694433e-06,
1112
+ "loss": 1.082,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 1.85,
1117
+ "learning_rate": 1.4678522687020413e-06,
1118
+ "loss": 1.2546,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 1.86,
1123
+ "learning_rate": 1.2794737676536994e-06,
1124
+ "loss": 1.0967,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 1.87,
1129
+ "learning_rate": 1.1038713802214717e-06,
1130
+ "loss": 0.5755,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 1.88,
1135
+ "learning_rate": 9.410911550880475e-07,
1136
+ "loss": 0.6927,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 1.89,
1141
+ "learning_rate": 7.911757785462881e-07,
1142
+ "loss": 1.0575,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 1.9,
1147
+ "learning_rate": 6.54164563305465e-07,
1148
+ "loss": 0.9652,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 1.91,
1153
+ "learning_rate": 5.300934381821998e-07,
1154
+ "loss": 0.7263,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 1.92,
1159
+ "learning_rate": 4.189949386787462e-07,
1160
+ "loss": 0.4148,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 1.93,
1165
+ "learning_rate": 3.208981984511195e-07,
1166
+ "loss": 0.9471,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 1.94,
1171
+ "learning_rate": 2.3582894166930268e-07,
1172
+ "loss": 1.0083,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 1.95,
1177
+ "learning_rate": 1.6380947627153143e-07,
1178
+ "loss": 0.1093,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 1.96,
1183
+ "learning_rate": 1.0485868811441757e-07,
1184
+ "loss": 0.8541,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 1.97,
1189
+ "learning_rate": 5.899203602046655e-08,
1190
+ "loss": 1.032,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 1.98,
1195
+ "learning_rate": 2.6221547724253337e-08,
1196
+ "loss": 1.1813,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 1.99,
1201
+ "learning_rate": 6.5558167183898955e-09,
1202
+ "loss": 0.0601,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 2.0,
1207
+ "learning_rate": 0.0,
1208
+ "loss": 1.1166,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 2.0,
1213
+ "step": 200,
1214
+ "total_flos": 3.406531187714294e+17,
1215
+ "train_loss": 0.8767247783765196,
1216
+ "train_runtime": 2128.2481,
1217
+ "train_samples_per_second": 0.376,
1218
+ "train_steps_per_second": 0.094
1219
+ }
1220
+ ],
1221
+ "logging_steps": 1.0,
1222
+ "max_steps": 200,
1223
+ "num_input_tokens_seen": 0,
1224
+ "num_train_epochs": 2,
1225
+ "save_steps": 10000,
1226
+ "total_flos": 3.406531187714294e+17,
1227
+ "train_batch_size": 2,
1228
+ "trial_name": null,
1229
+ "trial_params": null
1230
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcbf453a0230e0c1f2d2d7d3f3197746f1690760b3b6c5c6645305741c74c0c7
3
+ size 6267
training_log.txt ADDED
The diff for this file is too large to render. See raw diff