Hugging Face's logo

Jinghao-Guo
/
llavaov_sft6

Safetensors
llavaonevision1_5
custom_code
Model card Files
xet
 Community
Jinghao-Guo commited on
Commit
3f039a6
·
verified ·
1 Parent(s): 490b0a1

Upload folder using huggingface_hub

Browse files
Files changed (27) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +24 -0
  3. chat_template.jinja +7 -0
  4. config.json +97 -0
  5. configuration_llavaonevision1_5.py +288 -0
  6. generation_config.json +4 -0
  7. model-00001-of-00002.safetensors +3 -0
  8. model-00002-of-00002.safetensors +3 -0
  9. model.safetensors.index.json +706 -0
  10. modeling_llavaonevision1_5.py +0 -0
  11. optimizer.pt +3 -0
  12. preprocessor_config.json +29 -0
  13. rng_state_0.pth +3 -0
  14. rng_state_1.pth +3 -0
  15. rng_state_2.pth +3 -0
  16. rng_state_3.pth +3 -0
  17. rng_state_4.pth +3 -0
  18. rng_state_5.pth +3 -0
  19. rng_state_6.pth +3 -0
  20. rng_state_7.pth +3 -0
  21. scheduler.pt +3 -0
  22. special_tokens_map.json +31 -0
  23. tokenizer.json +3 -0
  24. tokenizer_config.json +208 -0
  25. trainer_state.json +2484 -0
  26. training_args.bin +3 -0
  27. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LLaVAOneVision1_5_ForConditionalGeneration"
4
+ ],
5
+ "auto_map": {
6
+ "AutoConfig": "configuration_llavaonevision1_5.Llavaonevision1_5Config",
7
+ "AutoModel": "modeling_llavaonevision1_5.LLaVAOneVision1_5_ForConditionalGeneration",
8
+ "AutoModelForCausalLM": "modeling_llavaonevision1_5.LLaVAOneVision1_5_ForConditionalGeneration"
9
+ },
10
+ "dtype": "bfloat16",
11
+ "image_token_id": 151655,
12
+ "model_type": "llavaonevision1_5",
13
+ "text_config": {
14
+ "attention_bias": false,
15
+ "attention_dropout": 0.0,
16
+ "dtype": "bfloat16",
17
+ "head_dim": 128,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 2560,
20
+ "image_token_id": null,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 9728,
23
+ "layer_types": [
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention"
60
+ ],
61
+ "max_position_embeddings": 262144,
62
+ "max_window_layers": 36,
63
+ "model_type": "LLaVAOneVision1_5_text",
64
+ "num_attention_heads": 32,
65
+ "num_hidden_layers": 36,
66
+ "num_key_value_heads": 8,
67
+ "rms_norm_eps": 1e-06,
68
+ "rope_scaling": null,
69
+ "rope_theta": 5000000.0,
70
+ "sliding_window": null,
71
+ "use_cache": true,
72
+ "use_sliding_window": false,
73
+ "video_token_id": null,
74
+ "vocab_size": 151936
75
+ },
76
+ "transformers_version": "4.57.3",
77
+ "use_cache": false,
78
+ "video_token_id": 151656,
79
+ "vision_config": {
80
+ "depth": 24,
81
+ "dtype": "bfloat16",
82
+ "embed_dim": 1024,
83
+ "hidden_act": "gelu",
84
+ "hidden_size": 1024,
85
+ "in_channels": 3,
86
+ "initializer_range": 0.02,
87
+ "intermediate_size": 4096,
88
+ "layer_norm_eps": 1e-05,
89
+ "model_type": "rice_vit",
90
+ "num_heads": 16,
91
+ "patch_size": 14,
92
+ "spatial_merge_size": 2,
93
+ "temporal_patch_size": 1,
94
+ "text_hidden_size": 2560
95
+ },
96
+ "vocab_size": 152064
97
+ }
configuration_llavaonevision1_5.py ADDED
@@ -0,0 +1,288 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # coding=utf-8
2
+ #
3
+ # Licensed under the Apache License, Version 2.0 (the "License");
4
+ # you may not use this file except in compliance with the License.
5
+ # You may obtain a copy of the License at
6
+ #
7
+ # http://www.apache.org/licenses/LICENSE-2.0
8
+ #
9
+ # Unless required by applicable law or agreed to in writing, software
10
+ # distributed under the License is distributed on an "AS IS" BASIS,
11
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12
+ # See the License for the specific language governing permissions and
13
+ # limitations under the License.
14
+
15
+ from transformers.configuration_utils import PretrainedConfig, layer_type_validation
16
+ from transformers.modeling_rope_utils import rope_config_validation
17
+ from transformers.utils import logging
18
+
19
+ logger = logging.get_logger(__name__)
20
+
21
+ class RiceConfig(PretrainedConfig):
22
+ model_type = "rice_vit"
23
+ base_config_key = "vision_config"
24
+
25
+ def __init__(
26
+ self,
27
+ depth=24,
28
+ embed_dim=1024,
29
+ hidden_size=1024,
30
+ hidden_act="gelu",
31
+ intermediate_size=4096,
32
+ num_heads=16,
33
+ in_channels=3,
34
+ patch_size=14,
35
+ spatial_merge_size=2,
36
+ temporal_patch_size=1,
37
+ initializer_range=0.02,
38
+ layer_norm_eps=1e-05,
39
+ text_hidden_size=2560,
40
+ **kwargs,
41
+ ):
42
+ super().__init__(**kwargs)
43
+
44
+ self.depth = depth
45
+ self.embed_dim = embed_dim
46
+ self.hidden_size = hidden_size
47
+ self.hidden_act = hidden_act
48
+ self.intermediate_size = intermediate_size
49
+ self.num_heads = num_heads
50
+ self.in_channels = in_channels
51
+ self.patch_size = patch_size
52
+ self.spatial_merge_size = spatial_merge_size
53
+ self.temporal_patch_size = temporal_patch_size
54
+ self.initializer_range = initializer_range
55
+ self.layer_norm_eps = layer_norm_eps
56
+ self.text_hidden_size = text_hidden_size
57
+
58
+
59
+ class LLaVAOneVision1_5_TextConfig(PretrainedConfig):
60
+ r"""
61
+ Args:
62
+ vocab_size (`int`, *optional*, defaults to 152064):
63
+ Vocabulary size of the Qwen2VL model. Defines the number of different tokens that can be represented by the
64
+ `inputs_ids` passed when calling [`Qwen2VLModel`]
65
+ hidden_size (`int`, *optional*, defaults to 8192):
66
+ Dimension of the hidden representations.
67
+ intermediate_size (`int`, *optional*, defaults to 29568):
68
+ Dimension of the MLP representations.
69
+ num_hidden_layers (`int`, *optional*, defaults to 80):
70
+ Number of hidden layers in the Transformer encoder.
71
+ num_attention_heads (`int`, *optional*, defaults to 64):
72
+ Number of attention heads for each attention layer in the Transformer encoder.
73
+ num_key_value_heads (`int`, *optional*, defaults to 8):
74
+ This is the number of key_value heads that should be used to implement Grouped Query Attention. If
75
+ `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
76
+ `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When
77
+ converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
78
+ by meanpooling all the original heads within that group. For more details checkout [this
79
+ paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `32`.
80
+ hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
81
+ The non-linear activation function (function or string) in the decoder.
82
+ max_position_embeddings (`int`, *optional*, defaults to 32768):
83
+ The maximum sequence length that this model might ever be used with.
84
+ initializer_range (`float`, *optional*, defaults to 0.02):
85
+ The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
86
+ rms_norm_eps (`float`, *optional*, defaults to 1e-05):
87
+ The epsilon used by the rms normalization layers.
88
+ use_cache (`bool`, *optional*, defaults to `True`):
89
+ Whether or not the model should return the last key/values attentions (not used by all models). Only
90
+ relevant if `config.is_decoder=True`.
91
+ tie_word_embeddings (`bool`, *optional*, defaults to `False`):
92
+ Whether the model's input and output word embeddings should be tied.
93
+ rope_theta (`float`, *optional*, defaults to 1000000.0):
94
+ The base period of the RoPE embeddings.
95
+ use_sliding_window (`bool`, *optional*, defaults to `False`):
96
+ Whether to use sliding window attention.
97
+ sliding_window (`int`, *optional*, defaults to 4096):
98
+ Sliding window attention (SWA) window size. If not specified, will default to `4096`.
99
+ max_window_layers (`int`, *optional*, defaults to 80):
100
+ The number of layers that use SWA (Sliding Window Attention). The bottom layers use SWA while the top use full attention.
101
+ attention_dropout (`float`, *optional*, defaults to 0.0):
102
+ The dropout ratio for the attention probabilities.
103
+ rope_scaling (`Dict`, *optional*):
104
+ Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
105
+ and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
106
+ accordingly.
107
+ Expected contents:
108
+ `rope_type` (`str`):
109
+ The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
110
+ 'llama3'], with 'default' being the original RoPE implementation.
111
+ `factor` (`float`, *optional*):
112
+ Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
113
+ most scaling types, a `factor` of x will enable the model to handle sequences of length x *
114
+ original maximum pre-trained length.
115
+ `original_max_position_embeddings` (`int`, *optional*):
116
+ Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
117
+ pretraining.
118
+ `attention_factor` (`float`, *optional*):
119
+ Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
120
+ computation. If unspecified, it defaults to value recommended by the implementation, using the
121
+ `factor` field to infer the suggested value.
122
+ `beta_fast` (`float`, *optional*):
123
+ Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
124
+ ramp function. If unspecified, it defaults to 32.
125
+ `beta_slow` (`float`, *optional*):
126
+ Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
127
+ ramp function. If unspecified, it defaults to 1.
128
+ `short_factor` (`List[float]`, *optional*):
129
+ Only used with 'longrope'. The scaling factor to be applied to short contexts (<
130
+ `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
131
+ size divided by the number of attention heads divided by 2
132
+ `long_factor` (`List[float]`, *optional*):
133
+ Only used with 'longrope'. The scaling factor to be applied to long contexts (<
134
+ `original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
135
+ size divided by the number of attention heads divided by 2
136
+ `low_freq_factor` (`float`, *optional*):
137
+ Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
138
+ `high_freq_factor` (`float`, *optional*):
139
+ Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
140
+ image_token_id (`int`, *optional*):
141
+ Token index used as placeholder for image embeddings.
142
+ video_token_id (`int`, *optional*):
143
+ Token index used as placeholder for video embeddings.
144
+
145
+ """
146
+
147
+ model_type = "LLaVAOneVision1_5_text"
148
+ base_config_key = "text_config"
149
+ keys_to_ignore_at_inference = ["past_key_values"]
150
+ # Default tensor parallel plan for base model `Qwen2VL`
151
+ base_model_tp_plan = {
152
+ "layers.*.self_attn.q_proj": "colwise",
153
+ "layers.*.self_attn.k_proj": "colwise",
154
+ "layers.*.self_attn.v_proj": "colwise",
155
+ "layers.*.self_attn.o_proj": "rowwise",
156
+ "layers.*.mlp.gate_proj": "colwise",
157
+ "layers.*.mlp.up_proj": "colwise",
158
+ "layers.*.mlp.down_proj": "rowwise",
159
+ }
160
+ base_model_pp_plan = {
161
+ "embed_tokens": (["input_ids"], ["inputs_embeds"]),
162
+ "layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
163
+ "norm": (["hidden_states"], ["hidden_states"]),
164
+ }
165
+
166
+ def __init__(
167
+ self,
168
+ vocab_size=151936,
169
+ hidden_size=4096,
170
+ intermediate_size=12288,
171
+ num_hidden_layers=36,
172
+ num_attention_heads=32,
173
+ num_key_value_heads=8,
174
+ head_dim=128,
175
+ hidden_act="silu",
176
+ max_position_embeddings=32768,
177
+ initializer_range=0.02,
178
+ rms_norm_eps=1e-06,
179
+ use_cache=True,
180
+ tie_word_embeddings=False,
181
+ rope_theta=1000000.0,
182
+ attention_bias=False,
183
+ use_sliding_window=False,
184
+ sliding_window=None,
185
+ max_window_layers=36,
186
+ attention_dropout=0.0,
187
+ rope_scaling=None,
188
+ layer_types=None,
189
+ image_token_id=None,
190
+ video_token_id=None,
191
+ **kwargs,
192
+ ):
193
+ self.vocab_size = vocab_size
194
+ self.max_position_embeddings = max_position_embeddings
195
+ self.hidden_size = hidden_size
196
+ self.intermediate_size = intermediate_size
197
+ self.num_hidden_layers = num_hidden_layers
198
+ self.num_attention_heads = num_attention_heads
199
+ self.use_sliding_window = use_sliding_window
200
+ self.sliding_window = sliding_window
201
+ self.max_window_layers = max_window_layers
202
+
203
+ # for backward compatibility
204
+ if num_key_value_heads is None:
205
+ num_key_value_heads = num_attention_heads
206
+
207
+ self.num_key_value_heads = num_key_value_heads
208
+ self.head_dim = head_dim
209
+ self.hidden_act = hidden_act
210
+ self.initializer_range = initializer_range
211
+ self.rms_norm_eps = rms_norm_eps
212
+ self.use_cache = use_cache
213
+ self.rope_theta = rope_theta
214
+ self.attention_dropout = attention_dropout
215
+ self.rope_scaling = rope_scaling
216
+ self.attention_bias = attention_bias
217
+ self.tie_word_embeddings = tie_word_embeddings
218
+
219
+ # Validate the correctness of rotary position embeddings parameters
220
+ # BC: if there is a 'type' field, move it to 'rope_type'.
221
+ # and change type from 'mrope' to 'default' because `mrope` does default RoPE calculations
222
+ # one can set it to "linear"/"dynamic" etc. to have scaled RoPE
223
+ # TODO: @raushan update config in the hub
224
+ if self.rope_scaling is not None and "type" in self.rope_scaling:
225
+ if self.rope_scaling["type"] == "mrope":
226
+ self.rope_scaling["type"] = "default"
227
+ self.rope_scaling["rope_type"] = self.rope_scaling["type"]
228
+ rope_config_validation(self, ignore_keys={"mrope_section"})
229
+ self.image_token_id = image_token_id
230
+ self.video_token_id = video_token_id
231
+
232
+ self.layer_types = layer_types
233
+ if self.layer_types is None:
234
+ self.layer_types = [
235
+ "sliding_attention"
236
+ if self.sliding_window is not None and i >= self.max_window_layers
237
+ else "full_attention"
238
+ for i in range(self.num_hidden_layers)
239
+ ]
240
+ layer_type_validation(self.layer_types)
241
+
242
+ super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs)
243
+
244
+
245
+ class Llavaonevision1_5Config(PretrainedConfig):
246
+ r"""
247
+ Args:
248
+ text_config (`Union[PreTrainedConfig, dict]`, *optional*, defaults to `LLaVAOneVision1_5_TextConfig`):
249
+ The config object or dictionary of the text backbone.
250
+ vision_config (`Union[PreTrainedConfig, dict]`, *optional*, defaults to `LLaVAOneVision1_5_VisionConfig`):
251
+ The config object or dictionary of the vision backbone.
252
+ image_token_id (`int`, *optional*, defaults to 151655):
253
+ The image token index to encode the image prompt.
254
+ video_token_id (`int`, *optional*, defaults to 151656):
255
+ The video token index to encode the image prompt.
256
+ """
257
+
258
+ model_type = "llavaonevision1_5"
259
+ sub_configs = {"vision_config": RiceConfig, "text_config": LLaVAOneVision1_5_TextConfig}
260
+ keys_to_ignore_at_inference = ["past_key_values"]
261
+
262
+ def __init__(
263
+ self,
264
+ text_config=None,
265
+ vision_config=None,
266
+ image_token_id=151655,
267
+ video_token_id=151656,
268
+ vocab_size=152064,
269
+ **kwargs,
270
+ ):
271
+ if isinstance(vision_config, dict):
272
+ self.vision_config = self.sub_configs["vision_config"](**vision_config)
273
+ elif vision_config is None:
274
+ self.vision_config = self.sub_configs["vision_config"]()
275
+
276
+ if isinstance(text_config, dict):
277
+ self.text_config = self.sub_configs["text_config"](**text_config)
278
+ elif text_config is None:
279
+ # For BC use all kwargs to init `TextConfig`
280
+ self.text_config = self.sub_configs["text_config"](**kwargs)
281
+
282
+ self.image_token_id = image_token_id
283
+ self.video_token_id = video_token_id
284
+ self.vocab_size = vocab_size
285
+
286
+ super().__init__(**kwargs)
287
+
288
+ __all__ = ["Llavaonevision1_5Config", "LLaVAOneVision1_5_TextConfig"]
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.57.3"
4
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57eed509f4a2e5df39b04d27e58df0a5cfc31bd5f37e543ef312643cf8b57abd
3
+ size 4972223088
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2b04081166b3dc41e824818f8ff3b82399f35a76759a6ac9b3cff8231ef4d26
3
+ size 4511075336
model.safetensors.index.json ADDED
@@ -0,0 +1,706 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4741610528,
4
+ "total_size": 9483221056
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00002-of-00002.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
109
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
110
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
112
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
113
+ "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
120
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
121
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
122
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
123
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
124
+ "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
125
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
126
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
127
+ "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
128
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
129
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
130
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
131
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
132
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
133
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
134
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
135
+ "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
136
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
138
+ "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
139
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
156
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
157
+ "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
158
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
160
+ "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
161
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
217
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
218
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
221
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
222
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
223
+ "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
243
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
244
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
245
+ "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
246
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
248
+ "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
254
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
257
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
259
+ "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
262
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
277
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
278
+ "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
281
+ "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
282
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
283
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
284
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
285
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
286
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
287
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
288
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
289
+ "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
290
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
291
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
292
+ "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
293
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
294
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
295
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
296
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
300
+ "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
301
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
302
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
304
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
305
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
306
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
307
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
313
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
314
+ "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
316
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
317
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
318
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
319
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
325
+ "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
326
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
328
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
329
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
331
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
332
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
334
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
337
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
338
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
339
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
340
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
342
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
344
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
345
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
346
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
347
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
348
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
349
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
350
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
351
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
352
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
353
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
354
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
355
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
356
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
357
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
358
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
359
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
360
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
361
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
362
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
363
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
364
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
365
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
366
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
367
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
368
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
369
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
370
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
373
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
374
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
376
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
378
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
382
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
386
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
388
+ "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
390
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
394
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
396
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
398
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
400
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
402
+ "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
404
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
405
+ "model.norm.weight": "model-00002-of-00002.safetensors",
406
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
407
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
408
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
409
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
410
+ "visual.blocks.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
411
+ "visual.blocks.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
412
+ "visual.blocks.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
413
+ "visual.blocks.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
414
+ "visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
415
+ "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
416
+ "visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
417
+ "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
418
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
419
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
420
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
421
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
422
+ "visual.blocks.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
423
+ "visual.blocks.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
424
+ "visual.blocks.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
425
+ "visual.blocks.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
426
+ "visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
427
+ "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
428
+ "visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
429
+ "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
430
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
431
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
432
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
433
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
434
+ "visual.blocks.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
435
+ "visual.blocks.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
436
+ "visual.blocks.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
437
+ "visual.blocks.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
438
+ "visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
439
+ "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
440
+ "visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
441
+ "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
442
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
443
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
444
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
445
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
446
+ "visual.blocks.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
447
+ "visual.blocks.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
448
+ "visual.blocks.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
449
+ "visual.blocks.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
450
+ "visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
451
+ "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
452
+ "visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
453
+ "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
454
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
455
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
456
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
457
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
458
+ "visual.blocks.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
459
+ "visual.blocks.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
460
+ "visual.blocks.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
461
+ "visual.blocks.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
462
+ "visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
463
+ "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
464
+ "visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
465
+ "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
466
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
467
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
468
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
469
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
470
+ "visual.blocks.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
471
+ "visual.blocks.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
472
+ "visual.blocks.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
473
+ "visual.blocks.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
474
+ "visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
475
+ "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
476
+ "visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
477
+ "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
478
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
479
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
480
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
481
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
482
+ "visual.blocks.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
483
+ "visual.blocks.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
484
+ "visual.blocks.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
485
+ "visual.blocks.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
486
+ "visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
487
+ "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
488
+ "visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
489
+ "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
490
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
491
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
492
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
493
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
494
+ "visual.blocks.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
495
+ "visual.blocks.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
496
+ "visual.blocks.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
497
+ "visual.blocks.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
498
+ "visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
499
+ "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
500
+ "visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
501
+ "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
502
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
503
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
504
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
505
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
506
+ "visual.blocks.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
507
+ "visual.blocks.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
508
+ "visual.blocks.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
509
+ "visual.blocks.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
510
+ "visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
511
+ "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
512
+ "visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
513
+ "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
514
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
515
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
516
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
517
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
518
+ "visual.blocks.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
519
+ "visual.blocks.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
520
+ "visual.blocks.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
521
+ "visual.blocks.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
522
+ "visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
523
+ "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
524
+ "visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
525
+ "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
526
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
527
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
528
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
529
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
530
+ "visual.blocks.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
531
+ "visual.blocks.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
532
+ "visual.blocks.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
533
+ "visual.blocks.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
534
+ "visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
535
+ "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
536
+ "visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
537
+ "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
538
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
539
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
540
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
541
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
542
+ "visual.blocks.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
543
+ "visual.blocks.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
544
+ "visual.blocks.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
545
+ "visual.blocks.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
546
+ "visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
547
+ "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
548
+ "visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
549
+ "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
550
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
551
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
552
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
553
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
554
+ "visual.blocks.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
555
+ "visual.blocks.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
556
+ "visual.blocks.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
557
+ "visual.blocks.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
558
+ "visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
559
+ "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
560
+ "visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
561
+ "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
562
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
563
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
564
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
565
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
566
+ "visual.blocks.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
567
+ "visual.blocks.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
568
+ "visual.blocks.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
569
+ "visual.blocks.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
570
+ "visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
571
+ "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
572
+ "visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
573
+ "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
574
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
575
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
576
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
577
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
578
+ "visual.blocks.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
579
+ "visual.blocks.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
580
+ "visual.blocks.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
581
+ "visual.blocks.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
582
+ "visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
583
+ "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
584
+ "visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
585
+ "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
586
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
587
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
588
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
589
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
590
+ "visual.blocks.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
591
+ "visual.blocks.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
592
+ "visual.blocks.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
593
+ "visual.blocks.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
594
+ "visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
595
+ "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
596
+ "visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
597
+ "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
598
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
599
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
600
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
601
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
602
+ "visual.blocks.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
603
+ "visual.blocks.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
604
+ "visual.blocks.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
605
+ "visual.blocks.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
606
+ "visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
607
+ "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
608
+ "visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
609
+ "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
610
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
611
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
612
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
613
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
614
+ "visual.blocks.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
615
+ "visual.blocks.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
616
+ "visual.blocks.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
617
+ "visual.blocks.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
618
+ "visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
619
+ "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
620
+ "visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
621
+ "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
622
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
623
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
624
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
625
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
626
+ "visual.blocks.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
627
+ "visual.blocks.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
628
+ "visual.blocks.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
629
+ "visual.blocks.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
630
+ "visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
631
+ "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
632
+ "visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
633
+ "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
634
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
635
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
636
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
637
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
638
+ "visual.blocks.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
639
+ "visual.blocks.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
640
+ "visual.blocks.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
641
+ "visual.blocks.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
642
+ "visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
643
+ "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
644
+ "visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
645
+ "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
646
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
647
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
648
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
649
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
650
+ "visual.blocks.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
651
+ "visual.blocks.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
652
+ "visual.blocks.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
653
+ "visual.blocks.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
654
+ "visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
655
+ "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
656
+ "visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
657
+ "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
658
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
659
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
660
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
661
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
662
+ "visual.blocks.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
663
+ "visual.blocks.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
664
+ "visual.blocks.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
665
+ "visual.blocks.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
666
+ "visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
667
+ "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
668
+ "visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
669
+ "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
670
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
671
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
672
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
673
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
674
+ "visual.blocks.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
675
+ "visual.blocks.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
676
+ "visual.blocks.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
677
+ "visual.blocks.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
678
+ "visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
679
+ "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
680
+ "visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
681
+ "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
682
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
683
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
684
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
685
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
686
+ "visual.blocks.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
687
+ "visual.blocks.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
688
+ "visual.blocks.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
689
+ "visual.blocks.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
690
+ "visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
691
+ "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
692
+ "visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
693
+ "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
694
+ "visual.class_embedding": "model-00001-of-00002.safetensors",
695
+ "visual.class_pos_emb": "model-00001-of-00002.safetensors",
696
+ "visual.merger.ln_q.bias": "model-00001-of-00002.safetensors",
697
+ "visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
698
+ "visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
699
+ "visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
700
+ "visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
701
+ "visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
702
+ "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
703
+ "visual.pre_layernorm.bias": "model-00001-of-00002.safetensors",
704
+ "visual.pre_layernorm.weight": "model-00001-of-00002.safetensors"
705
+ }
706
+ }
modeling_llavaonevision1_5.py ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5558e17fc70940e21f6069073d3bd7a196f2c5caac6ab7df329195a2699bec6c
3
+ size 18967059777
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 2560000,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2_5_VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 12845056,
26
+ "shortest_edge": 3136
27
+ },
28
+ "temporal_patch_size": 1
29
+ }
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8f92cf63e0989759370d24108b469c492c12202403f036015307ce49f12cedc
3
+ size 16389
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ed40a0a4e9f365d2c6cc004d97e6705894eba46c8be4c160c1455bc3062dee1
3
+ size 16389
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d688b304d19c260b5cfa471535ed51d7e1d60b3a0d0159dfd1a04b87904a9f42
3
+ size 16389
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9967425ebcaee80d9b518fa0244d52f739b1b983d87cda71d5fede0c073e9d3b
3
+ size 16389
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:469900fd39c667ffbd49c3c407c0ba317a1e9f5f9339a99b5d38423b7d0ce6d4
3
+ size 16389
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:124688471ff2a6e80f2fcefedbf741fb18d08dd539d5bd07a52e81be545142a5
3
+ size 16389
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e69f1ced9f992a72c948698e5eb06088610788988cdb2fdbdd624e064319d60
3
+ size 16389
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a376268a55d6ee10c371c06aa952334c4c6a1af9ea2d71b1951a57367a0c6722
3
+ size 16389
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b4205f29dfdbd4d55145ab073922abdb3f07ab48587909c01e834833ff66cd3
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "processor_class": "Qwen2_5_VLProcessor",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
trainer_state.json ADDED
@@ -0,0 +1,2484 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.002857142857142857,
14
+ "grad_norm": 8.25,
15
+ "learning_rate": 9.999991910858043e-06,
16
+ "loss": 2.0631,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.005714285714285714,
21
+ "grad_norm": 2.84375,
22
+ "learning_rate": 9.999708793637737e-06,
23
+ "loss": 1.5602,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.008571428571428572,
28
+ "grad_norm": 1.890625,
29
+ "learning_rate": 9.999021245492833e-06,
30
+ "loss": 1.4412,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.011428571428571429,
35
+ "grad_norm": 1.7421875,
36
+ "learning_rate": 9.997929322039716e-06,
37
+ "loss": 1.4112,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.014285714285714285,
42
+ "grad_norm": 1.7109375,
43
+ "learning_rate": 9.996433111605053e-06,
44
+ "loss": 1.4083,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.017142857142857144,
49
+ "grad_norm": 1.625,
50
+ "learning_rate": 9.994532735218647e-06,
51
+ "loss": 1.3948,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.02,
56
+ "grad_norm": 1.6875,
57
+ "learning_rate": 9.992228346603645e-06,
58
+ "loss": 1.3753,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.022857142857142857,
63
+ "grad_norm": 1.6171875,
64
+ "learning_rate": 9.98952013216411e-06,
65
+ "loss": 1.3471,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.025714285714285714,
70
+ "grad_norm": 1.703125,
71
+ "learning_rate": 9.986408310969932e-06,
72
+ "loss": 1.3213,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.02857142857142857,
77
+ "grad_norm": 1.5234375,
78
+ "learning_rate": 9.982893134739118e-06,
79
+ "loss": 1.319,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.03142857142857143,
84
+ "grad_norm": 1.6328125,
85
+ "learning_rate": 9.978974887817424e-06,
86
+ "loss": 1.3487,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.03428571428571429,
91
+ "grad_norm": 1.5703125,
92
+ "learning_rate": 9.97465388715535e-06,
93
+ "loss": 1.3334,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.037142857142857144,
98
+ "grad_norm": 1.6328125,
99
+ "learning_rate": 9.969930482282518e-06,
100
+ "loss": 1.286,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.04,
105
+ "grad_norm": 1.5078125,
106
+ "learning_rate": 9.964805055279374e-06,
107
+ "loss": 1.2842,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.04285714285714286,
112
+ "grad_norm": 1.5703125,
113
+ "learning_rate": 9.959278020746308e-06,
114
+ "loss": 1.3026,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.045714285714285714,
119
+ "grad_norm": 1.546875,
120
+ "learning_rate": 9.953349825770093e-06,
121
+ "loss": 1.3521,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.04857142857142857,
126
+ "grad_norm": 1.4921875,
127
+ "learning_rate": 9.947020949887732e-06,
128
+ "loss": 1.284,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.05142857142857143,
133
+ "grad_norm": 1.5625,
134
+ "learning_rate": 9.940291905047668e-06,
135
+ "loss": 1.2834,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.054285714285714284,
140
+ "grad_norm": 1.6484375,
141
+ "learning_rate": 9.933163235568369e-06,
142
+ "loss": 1.312,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.05714285714285714,
147
+ "grad_norm": 1.5,
148
+ "learning_rate": 9.925635518094295e-06,
149
+ "loss": 1.2968,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.06,
154
+ "grad_norm": 1.609375,
155
+ "learning_rate": 9.917709361549257e-06,
156
+ "loss": 1.3068,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.06285714285714286,
161
+ "grad_norm": 1.625,
162
+ "learning_rate": 9.909385407087164e-06,
163
+ "loss": 1.2879,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.06571428571428571,
168
+ "grad_norm": 1.53125,
169
+ "learning_rate": 9.900664328040151e-06,
170
+ "loss": 1.2828,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.06857142857142857,
175
+ "grad_norm": 1.5078125,
176
+ "learning_rate": 9.891546829864115e-06,
177
+ "loss": 1.2977,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.07142857142857142,
182
+ "grad_norm": 1.671875,
183
+ "learning_rate": 9.882033650081656e-06,
184
+ "loss": 1.3454,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.07428571428571429,
189
+ "grad_norm": 1.4609375,
190
+ "learning_rate": 9.87212555822241e-06,
191
+ "loss": 1.2249,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.07714285714285714,
196
+ "grad_norm": 1.5390625,
197
+ "learning_rate": 9.861823355760806e-06,
198
+ "loss": 1.2945,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.08,
203
+ "grad_norm": 1.4296875,
204
+ "learning_rate": 9.851127876051236e-06,
205
+ "loss": 1.3094,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.08285714285714285,
210
+ "grad_norm": 1.5625,
211
+ "learning_rate": 9.840039984260634e-06,
212
+ "loss": 1.3061,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.08571428571428572,
217
+ "grad_norm": 1.484375,
218
+ "learning_rate": 9.828560577298505e-06,
219
+ "loss": 1.2716,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.08857142857142856,
224
+ "grad_norm": 1.6015625,
225
+ "learning_rate": 9.816690583744366e-06,
226
+ "loss": 1.27,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.09142857142857143,
231
+ "grad_norm": 1.71875,
232
+ "learning_rate": 9.804430963772632e-06,
233
+ "loss": 1.2911,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.09428571428571429,
238
+ "grad_norm": 1.484375,
239
+ "learning_rate": 9.791782709074944e-06,
240
+ "loss": 1.2916,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.09714285714285714,
245
+ "grad_norm": 1.4453125,
246
+ "learning_rate": 9.778746842779962e-06,
247
+ "loss": 1.2836,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.1,
252
+ "grad_norm": 2.046875,
253
+ "learning_rate": 9.765324419370595e-06,
254
+ "loss": 1.2619,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.10285714285714286,
259
+ "grad_norm": 1.390625,
260
+ "learning_rate": 9.751516524598697e-06,
261
+ "loss": 1.2661,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.10571428571428572,
266
+ "grad_norm": 1.59375,
267
+ "learning_rate": 9.73732427539725e-06,
268
+ "loss": 1.2996,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.10857142857142857,
273
+ "grad_norm": 1.3515625,
274
+ "learning_rate": 9.722748819790012e-06,
275
+ "loss": 1.2307,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.11142857142857143,
280
+ "grad_norm": 2.65625,
281
+ "learning_rate": 9.707791336798642e-06,
282
+ "loss": 1.3046,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.11428571428571428,
287
+ "grad_norm": 1.5390625,
288
+ "learning_rate": 9.692453036347352e-06,
289
+ "loss": 1.3182,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.11714285714285715,
294
+ "grad_norm": 1.5546875,
295
+ "learning_rate": 9.676735159165001e-06,
296
+ "loss": 1.2765,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.12,
301
+ "grad_norm": 1.609375,
302
+ "learning_rate": 9.660638976684766e-06,
303
+ "loss": 1.3235,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.12285714285714286,
308
+ "grad_norm": 1.65625,
309
+ "learning_rate": 9.64416579094127e-06,
310
+ "loss": 1.2747,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.12571428571428572,
315
+ "grad_norm": 1.6171875,
316
+ "learning_rate": 9.627316934465266e-06,
317
+ "loss": 1.275,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.12857142857142856,
322
+ "grad_norm": 1.40625,
323
+ "learning_rate": 9.610093770175856e-06,
324
+ "loss": 1.2651,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.13142857142857142,
329
+ "grad_norm": 1.6171875,
330
+ "learning_rate": 9.592497691270234e-06,
331
+ "loss": 1.2993,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.13428571428571429,
336
+ "grad_norm": 1.515625,
337
+ "learning_rate": 9.57453012111099e-06,
338
+ "loss": 1.2805,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.13714285714285715,
343
+ "grad_norm": 1.59375,
344
+ "learning_rate": 9.556192513110974e-06,
345
+ "loss": 1.2978,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.14,
350
+ "grad_norm": 2.171875,
351
+ "learning_rate": 9.537486350615727e-06,
352
+ "loss": 1.2951,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.14285714285714285,
357
+ "grad_norm": 1.859375,
358
+ "learning_rate": 9.518413146783502e-06,
359
+ "loss": 1.275,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.1457142857142857,
364
+ "grad_norm": 1.4921875,
365
+ "learning_rate": 9.498974444462847e-06,
366
+ "loss": 1.2869,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.14857142857142858,
371
+ "grad_norm": 1.34375,
372
+ "learning_rate": 9.479171816067808e-06,
373
+ "loss": 1.2968,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.15142857142857144,
378
+ "grad_norm": 1.40625,
379
+ "learning_rate": 9.459006863450745e-06,
380
+ "loss": 1.2781,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.15428571428571428,
385
+ "grad_norm": 1.75,
386
+ "learning_rate": 9.438481217772744e-06,
387
+ "loss": 1.238,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.15714285714285714,
392
+ "grad_norm": 1.40625,
393
+ "learning_rate": 9.417596539371677e-06,
394
+ "loss": 1.2414,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.16,
399
+ "grad_norm": 1.6953125,
400
+ "learning_rate": 9.396354517627893e-06,
401
+ "loss": 1.2428,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.16285714285714287,
406
+ "grad_norm": 1.4921875,
407
+ "learning_rate": 9.37475687082757e-06,
408
+ "loss": 1.2304,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.1657142857142857,
413
+ "grad_norm": 1.453125,
414
+ "learning_rate": 9.35280534602371e-06,
415
+ "loss": 1.2377,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.16857142857142857,
420
+ "grad_norm": 1.6171875,
421
+ "learning_rate": 9.330501718894822e-06,
422
+ "loss": 1.2865,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.17142857142857143,
427
+ "grad_norm": 1.484375,
428
+ "learning_rate": 9.307847793601295e-06,
429
+ "loss": 1.2753,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.1742857142857143,
434
+ "grad_norm": 2.078125,
435
+ "learning_rate": 9.284845402639447e-06,
436
+ "loss": 1.2317,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.17714285714285713,
441
+ "grad_norm": 1.546875,
442
+ "learning_rate": 9.261496406693291e-06,
443
+ "loss": 1.2473,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.18,
448
+ "grad_norm": 1.375,
449
+ "learning_rate": 9.237802694484035e-06,
450
+ "loss": 1.2379,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.18285714285714286,
455
+ "grad_norm": 1.4375,
456
+ "learning_rate": 9.213766182617291e-06,
457
+ "loss": 1.2274,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.18571428571428572,
462
+ "grad_norm": 1.3828125,
463
+ "learning_rate": 9.189388815428047e-06,
464
+ "loss": 1.2372,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.18857142857142858,
469
+ "grad_norm": 1.5390625,
470
+ "learning_rate": 9.164672564823374e-06,
471
+ "loss": 1.2541,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.19142857142857142,
476
+ "grad_norm": 1.828125,
477
+ "learning_rate": 9.139619430122934e-06,
478
+ "loss": 1.2972,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.19428571428571428,
483
+ "grad_norm": 1.4375,
484
+ "learning_rate": 9.114231437897245e-06,
485
+ "loss": 1.2356,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.19714285714285715,
490
+ "grad_norm": 1.90625,
491
+ "learning_rate": 9.088510641803747e-06,
492
+ "loss": 1.2966,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.2,
497
+ "grad_norm": 1.4140625,
498
+ "learning_rate": 9.062459122420684e-06,
499
+ "loss": 1.231,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.20285714285714285,
504
+ "grad_norm": 1.453125,
505
+ "learning_rate": 9.036078987078804e-06,
506
+ "loss": 1.2295,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.2057142857142857,
511
+ "grad_norm": 1.5078125,
512
+ "learning_rate": 9.009372369690897e-06,
513
+ "loss": 1.2599,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.20857142857142857,
518
+ "grad_norm": 1.546875,
519
+ "learning_rate": 8.982341430579174e-06,
520
+ "loss": 1.2406,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.21142857142857144,
525
+ "grad_norm": 1.75,
526
+ "learning_rate": 8.954988356300518e-06,
527
+ "loss": 1.2162,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.21428571428571427,
532
+ "grad_norm": 1.6171875,
533
+ "learning_rate": 8.927315359469627e-06,
534
+ "loss": 1.2414,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.21714285714285714,
539
+ "grad_norm": 1.2890625,
540
+ "learning_rate": 8.899324678580005e-06,
541
+ "loss": 1.2257,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.22,
546
+ "grad_norm": 1.5703125,
547
+ "learning_rate": 8.871018577822916e-06,
548
+ "loss": 1.2735,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.22285714285714286,
553
+ "grad_norm": 1.421875,
554
+ "learning_rate": 8.842399346904215e-06,
555
+ "loss": 1.2487,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.2257142857142857,
560
+ "grad_norm": 1.5,
561
+ "learning_rate": 8.813469300859135e-06,
562
+ "loss": 1.2696,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.22857142857142856,
567
+ "grad_norm": 1.2890625,
568
+ "learning_rate": 8.784230779865029e-06,
569
+ "loss": 1.2262,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.23142857142857143,
574
+ "grad_norm": 1.59375,
575
+ "learning_rate": 8.754686149052057e-06,
576
+ "loss": 1.2514,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.2342857142857143,
581
+ "grad_norm": 1.46875,
582
+ "learning_rate": 8.724837798311883e-06,
583
+ "loss": 1.2419,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.23714285714285716,
588
+ "grad_norm": 1.4453125,
589
+ "learning_rate": 8.694688142104346e-06,
590
+ "loss": 1.2941,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.24,
595
+ "grad_norm": 1.4765625,
596
+ "learning_rate": 8.664239619262151e-06,
597
+ "loss": 1.2273,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.24285714285714285,
602
+ "grad_norm": 1.4296875,
603
+ "learning_rate": 8.6334946927936e-06,
604
+ "loss": 1.249,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.24571428571428572,
609
+ "grad_norm": 1.4921875,
610
+ "learning_rate": 8.602455849683343e-06,
611
+ "loss": 1.2663,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.24857142857142858,
616
+ "grad_norm": 1.640625,
617
+ "learning_rate": 8.571125600691214e-06,
618
+ "loss": 1.2835,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.25142857142857145,
623
+ "grad_norm": 1.6796875,
624
+ "learning_rate": 8.53950648014913e-06,
625
+ "loss": 1.2804,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.2542857142857143,
630
+ "grad_norm": 1.5,
631
+ "learning_rate": 8.507601045756085e-06,
632
+ "loss": 1.2981,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.2571428571428571,
637
+ "grad_norm": 1.71875,
638
+ "learning_rate": 8.475411878371257e-06,
639
+ "loss": 1.1956,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.26,
644
+ "grad_norm": 1.5625,
645
+ "learning_rate": 8.442941581805245e-06,
646
+ "loss": 1.2578,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.26285714285714284,
651
+ "grad_norm": 1.46875,
652
+ "learning_rate": 8.410192782609428e-06,
653
+ "loss": 1.2073,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.26571428571428574,
658
+ "grad_norm": 1.59375,
659
+ "learning_rate": 8.377168129863526e-06,
660
+ "loss": 1.2343,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.26857142857142857,
665
+ "grad_norm": 1.5,
666
+ "learning_rate": 8.34387029496129e-06,
667
+ "loss": 1.2565,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.2714285714285714,
672
+ "grad_norm": 2.265625,
673
+ "learning_rate": 8.310301971394423e-06,
674
+ "loss": 1.2424,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.2742857142857143,
679
+ "grad_norm": 1.546875,
680
+ "learning_rate": 8.276465874534701e-06,
681
+ "loss": 1.2834,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.27714285714285714,
686
+ "grad_norm": 1.5859375,
687
+ "learning_rate": 8.242364741414321e-06,
688
+ "loss": 1.2526,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.28,
693
+ "grad_norm": 1.703125,
694
+ "learning_rate": 8.208001330504497e-06,
695
+ "loss": 1.2253,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.28285714285714286,
700
+ "grad_norm": 1.6171875,
701
+ "learning_rate": 8.17337842149233e-06,
702
+ "loss": 1.2526,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.2857142857142857,
707
+ "grad_norm": 1.9609375,
708
+ "learning_rate": 8.138498815055959e-06,
709
+ "loss": 1.2918,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.2885714285714286,
714
+ "grad_norm": 1.453125,
715
+ "learning_rate": 8.103365332638e-06,
716
+ "loss": 1.2428,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.2914285714285714,
721
+ "grad_norm": 1.3984375,
722
+ "learning_rate": 8.067980816217336e-06,
723
+ "loss": 1.2538,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.29428571428571426,
728
+ "grad_norm": 1.5859375,
729
+ "learning_rate": 8.032348128079204e-06,
730
+ "loss": 1.253,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.29714285714285715,
735
+ "grad_norm": 1.390625,
736
+ "learning_rate": 7.996470150583678e-06,
737
+ "loss": 1.2471,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.3,
742
+ "grad_norm": 1.4765625,
743
+ "learning_rate": 7.96034978593251e-06,
744
+ "loss": 1.2314,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.3028571428571429,
749
+ "grad_norm": 1.4375,
750
+ "learning_rate": 7.923989955934363e-06,
751
+ "loss": 1.2425,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.3057142857142857,
756
+ "grad_norm": 1.4296875,
757
+ "learning_rate": 7.887393601768468e-06,
758
+ "loss": 1.2446,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.30857142857142855,
763
+ "grad_norm": 1.9921875,
764
+ "learning_rate": 7.85056368374671e-06,
765
+ "loss": 1.2594,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.31142857142857144,
770
+ "grad_norm": 1.65625,
771
+ "learning_rate": 7.813503181074157e-06,
772
+ "loss": 1.2098,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.3142857142857143,
777
+ "grad_norm": 1.59375,
778
+ "learning_rate": 7.776215091608087e-06,
779
+ "loss": 1.2196,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.3171428571428571,
784
+ "grad_norm": 1.4921875,
785
+ "learning_rate": 7.738702431615464e-06,
786
+ "loss": 1.2226,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.32,
791
+ "grad_norm": 1.6484375,
792
+ "learning_rate": 7.700968235528973e-06,
793
+ "loss": 1.2617,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.32285714285714284,
798
+ "grad_norm": 1.8828125,
799
+ "learning_rate": 7.663015555701552e-06,
800
+ "loss": 1.2693,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.32571428571428573,
805
+ "grad_norm": 2.875,
806
+ "learning_rate": 7.624847462159479e-06,
807
+ "loss": 1.258,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.32857142857142857,
812
+ "grad_norm": 1.5,
813
+ "learning_rate": 7.586467042354044e-06,
814
+ "loss": 1.24,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.3314285714285714,
819
+ "grad_norm": 1.5625,
820
+ "learning_rate": 7.547877400911798e-06,
821
+ "loss": 1.2413,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.3342857142857143,
826
+ "grad_norm": 1.4609375,
827
+ "learning_rate": 7.509081659383417e-06,
828
+ "loss": 1.232,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.33714285714285713,
833
+ "grad_norm": 1.4140625,
834
+ "learning_rate": 7.4700829559912005e-06,
835
+ "loss": 1.2422,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.34,
840
+ "grad_norm": 1.4921875,
841
+ "learning_rate": 7.430884445375212e-06,
842
+ "loss": 1.2341,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.34285714285714286,
847
+ "grad_norm": 1.59375,
848
+ "learning_rate": 7.391489298338099e-06,
849
+ "loss": 1.2236,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.3457142857142857,
854
+ "grad_norm": 1.65625,
855
+ "learning_rate": 7.351900701588612e-06,
856
+ "loss": 1.2481,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.3485714285714286,
861
+ "grad_norm": 1.765625,
862
+ "learning_rate": 7.312121857483816e-06,
863
+ "loss": 1.2099,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.3514285714285714,
868
+ "grad_norm": 1.53125,
869
+ "learning_rate": 7.272155983770055e-06,
870
+ "loss": 1.2585,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.35428571428571426,
875
+ "grad_norm": 1.640625,
876
+ "learning_rate": 7.232006313322668e-06,
877
+ "loss": 1.2337,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.35714285714285715,
882
+ "grad_norm": 1.34375,
883
+ "learning_rate": 7.191676093884479e-06,
884
+ "loss": 1.2221,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.36,
889
+ "grad_norm": 2.15625,
890
+ "learning_rate": 7.151168587803074e-06,
891
+ "loss": 1.2662,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.3628571428571429,
896
+ "grad_norm": 1.5078125,
897
+ "learning_rate": 7.110487071766924e-06,
898
+ "loss": 1.2171,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.3657142857142857,
903
+ "grad_norm": 1.65625,
904
+ "learning_rate": 7.069634836540311e-06,
905
+ "loss": 1.221,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.36857142857142855,
910
+ "grad_norm": 1.4375,
911
+ "learning_rate": 7.0286151866971544e-06,
912
+ "loss": 1.2431,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.37142857142857144,
917
+ "grad_norm": 1.5546875,
918
+ "learning_rate": 6.987431440353687e-06,
919
+ "loss": 1.2335,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.3742857142857143,
924
+ "grad_norm": 1.640625,
925
+ "learning_rate": 6.946086928900054e-06,
926
+ "loss": 1.1925,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.37714285714285717,
931
+ "grad_norm": 1.53125,
932
+ "learning_rate": 6.904584996730839e-06,
933
+ "loss": 1.2303,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.38,
938
+ "grad_norm": 1.6875,
939
+ "learning_rate": 6.862929000974523e-06,
940
+ "loss": 1.2511,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.38285714285714284,
945
+ "grad_norm": 1.328125,
946
+ "learning_rate": 6.821122311221932e-06,
947
+ "loss": 1.2166,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.38571428571428573,
952
+ "grad_norm": 1.4453125,
953
+ "learning_rate": 6.779168309253663e-06,
954
+ "loss": 1.2181,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.38857142857142857,
959
+ "grad_norm": 1.53125,
960
+ "learning_rate": 6.73707038876653e-06,
961
+ "loss": 1.2358,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.3914285714285714,
966
+ "grad_norm": 1.7578125,
967
+ "learning_rate": 6.6948319550990485e-06,
968
+ "loss": 1.2176,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.3942857142857143,
973
+ "grad_norm": 1.3828125,
974
+ "learning_rate": 6.6524564249559645e-06,
975
+ "loss": 1.2317,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.39714285714285713,
980
+ "grad_norm": 1.609375,
981
+ "learning_rate": 6.6099472261318864e-06,
982
+ "loss": 1.306,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.4,
987
+ "grad_norm": 1.5703125,
988
+ "learning_rate": 6.567307797233997e-06,
989
+ "loss": 1.253,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.40285714285714286,
994
+ "grad_norm": 2.75,
995
+ "learning_rate": 6.524541587403915e-06,
996
+ "loss": 1.2285,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.4057142857142857,
1001
+ "grad_norm": 1.40625,
1002
+ "learning_rate": 6.481652056038672e-06,
1003
+ "loss": 1.2117,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.4085714285714286,
1008
+ "grad_norm": 1.65625,
1009
+ "learning_rate": 6.438642672510894e-06,
1010
+ "loss": 1.2791,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.4114285714285714,
1015
+ "grad_norm": 1.9296875,
1016
+ "learning_rate": 6.395516915888158e-06,
1017
+ "loss": 1.2448,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.4142857142857143,
1022
+ "grad_norm": 1.328125,
1023
+ "learning_rate": 6.352278274651562e-06,
1024
+ "loss": 1.2291,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.41714285714285715,
1029
+ "grad_norm": 1.546875,
1030
+ "learning_rate": 6.308930246413541e-06,
1031
+ "loss": 1.2544,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.42,
1036
+ "grad_norm": 1.7890625,
1037
+ "learning_rate": 6.265476337634942e-06,
1038
+ "loss": 1.2402,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.4228571428571429,
1043
+ "grad_norm": 1.4296875,
1044
+ "learning_rate": 6.22192006334139e-06,
1045
+ "loss": 1.2525,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.4257142857142857,
1050
+ "grad_norm": 1.7265625,
1051
+ "learning_rate": 6.178264946838942e-06,
1052
+ "loss": 1.2481,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.42857142857142855,
1057
+ "grad_norm": 1.484375,
1058
+ "learning_rate": 6.13451451942909e-06,
1059
+ "loss": 1.2281,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.43142857142857144,
1064
+ "grad_norm": 1.6015625,
1065
+ "learning_rate": 6.090672320123113e-06,
1066
+ "loss": 1.2064,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.4342857142857143,
1071
+ "grad_norm": 1.5546875,
1072
+ "learning_rate": 6.046741895355802e-06,
1073
+ "loss": 1.2248,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.43714285714285717,
1078
+ "grad_norm": 1.484375,
1079
+ "learning_rate": 6.00272679869858e-06,
1080
+ "loss": 1.2337,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.44,
1085
+ "grad_norm": 1.53125,
1086
+ "learning_rate": 5.958630590572061e-06,
1087
+ "loss": 1.241,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.44285714285714284,
1092
+ "grad_norm": 1.4140625,
1093
+ "learning_rate": 5.914456837958032e-06,
1094
+ "loss": 1.222,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.44571428571428573,
1099
+ "grad_norm": 1.3515625,
1100
+ "learning_rate": 5.87020911411093e-06,
1101
+ "loss": 1.2441,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.44857142857142857,
1106
+ "grad_norm": 1.6171875,
1107
+ "learning_rate": 5.825890998268784e-06,
1108
+ "loss": 1.2635,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.4514285714285714,
1113
+ "grad_norm": 1.5,
1114
+ "learning_rate": 5.781506075363702e-06,
1115
+ "loss": 1.243,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.4542857142857143,
1120
+ "grad_norm": 1.5,
1121
+ "learning_rate": 5.737057935731868e-06,
1122
+ "loss": 1.2483,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.45714285714285713,
1127
+ "grad_norm": 1.4140625,
1128
+ "learning_rate": 5.692550174823129e-06,
1129
+ "loss": 1.2055,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.46,
1134
+ "grad_norm": 1.5078125,
1135
+ "learning_rate": 5.647986392910149e-06,
1136
+ "loss": 1.2177,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.46285714285714286,
1141
+ "grad_norm": 2.015625,
1142
+ "learning_rate": 5.6033701947971805e-06,
1143
+ "loss": 1.2275,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.4657142857142857,
1148
+ "grad_norm": 1.6328125,
1149
+ "learning_rate": 5.55870518952847e-06,
1150
+ "loss": 1.2497,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.4685714285714286,
1155
+ "grad_norm": 1.328125,
1156
+ "learning_rate": 5.513994990096318e-06,
1157
+ "loss": 1.2057,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.4714285714285714,
1162
+ "grad_norm": 2.421875,
1163
+ "learning_rate": 5.469243213148821e-06,
1164
+ "loss": 1.2558,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.4742857142857143,
1169
+ "grad_norm": 1.6953125,
1170
+ "learning_rate": 5.424453478697321e-06,
1171
+ "loss": 1.2452,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.47714285714285715,
1176
+ "grad_norm": 1.7578125,
1177
+ "learning_rate": 5.379629409823571e-06,
1178
+ "loss": 1.253,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.48,
1183
+ "grad_norm": 1.578125,
1184
+ "learning_rate": 5.334774632386672e-06,
1185
+ "loss": 1.2358,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.4828571428571429,
1190
+ "grad_norm": 1.828125,
1191
+ "learning_rate": 5.2898927747297665e-06,
1192
+ "loss": 1.2656,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.4857142857142857,
1197
+ "grad_norm": 1.6328125,
1198
+ "learning_rate": 5.244987467386536e-06,
1199
+ "loss": 1.2283,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.48857142857142855,
1204
+ "grad_norm": 1.6015625,
1205
+ "learning_rate": 5.200062342787534e-06,
1206
+ "loss": 1.217,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.49142857142857144,
1211
+ "grad_norm": 1.4921875,
1212
+ "learning_rate": 5.155121034966346e-06,
1213
+ "loss": 1.2441,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.4942857142857143,
1218
+ "grad_norm": 1.6171875,
1219
+ "learning_rate": 5.110167179265636e-06,
1220
+ "loss": 1.2197,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.49714285714285716,
1225
+ "grad_norm": 1.515625,
1226
+ "learning_rate": 5.065204412043071e-06,
1227
+ "loss": 1.2542,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.5,
1232
+ "grad_norm": 1.5546875,
1233
+ "learning_rate": 5.0202363703771866e-06,
1234
+ "loss": 1.2047,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.5028571428571429,
1239
+ "grad_norm": 1.65625,
1240
+ "learning_rate": 4.975266691773168e-06,
1241
+ "loss": 1.2221,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.5057142857142857,
1246
+ "grad_norm": 1.484375,
1247
+ "learning_rate": 4.930299013868616e-06,
1248
+ "loss": 1.2402,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.5085714285714286,
1253
+ "grad_norm": 1.453125,
1254
+ "learning_rate": 4.885336974139292e-06,
1255
+ "loss": 1.1988,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.5114285714285715,
1260
+ "grad_norm": 1.7421875,
1261
+ "learning_rate": 4.840384209604881e-06,
1262
+ "loss": 1.2282,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.5142857142857142,
1267
+ "grad_norm": 1.7265625,
1268
+ "learning_rate": 4.795444356534787e-06,
1269
+ "loss": 1.1957,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.5171428571428571,
1274
+ "grad_norm": 1.4453125,
1275
+ "learning_rate": 4.750521050153997e-06,
1276
+ "loss": 1.2562,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.52,
1281
+ "grad_norm": 1.4453125,
1282
+ "learning_rate": 4.7056179243490205e-06,
1283
+ "loss": 1.2339,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.5228571428571429,
1288
+ "grad_norm": 1.84375,
1289
+ "learning_rate": 4.660738611373942e-06,
1290
+ "loss": 1.2338,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.5257142857142857,
1295
+ "grad_norm": 1.546875,
1296
+ "learning_rate": 4.615886741556604e-06,
1297
+ "loss": 1.2672,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.5285714285714286,
1302
+ "grad_norm": 1.828125,
1303
+ "learning_rate": 4.5710659430049475e-06,
1304
+ "loss": 1.2383,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.5314285714285715,
1309
+ "grad_norm": 1.53125,
1310
+ "learning_rate": 4.5262798413135345e-06,
1311
+ "loss": 1.2147,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.5342857142857143,
1316
+ "grad_norm": 1.375,
1317
+ "learning_rate": 4.4815320592702625e-06,
1318
+ "loss": 1.1947,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.5371428571428571,
1323
+ "grad_norm": 1.5390625,
1324
+ "learning_rate": 4.436826216563318e-06,
1325
+ "loss": 1.2432,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.54,
1330
+ "grad_norm": 1.4296875,
1331
+ "learning_rate": 4.392165929488381e-06,
1332
+ "loss": 1.2544,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 0.5428571428571428,
1337
+ "grad_norm": 1.59375,
1338
+ "learning_rate": 4.347554810656093e-06,
1339
+ "loss": 1.2482,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 0.5457142857142857,
1344
+ "grad_norm": 1.6015625,
1345
+ "learning_rate": 4.3029964686998335e-06,
1346
+ "loss": 1.2396,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 0.5485714285714286,
1351
+ "grad_norm": 1.53125,
1352
+ "learning_rate": 4.25849450798381e-06,
1353
+ "loss": 1.2299,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 0.5514285714285714,
1358
+ "grad_norm": 1.515625,
1359
+ "learning_rate": 4.2140525283115054e-06,
1360
+ "loss": 1.2296,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 0.5542857142857143,
1365
+ "grad_norm": 4.0,
1366
+ "learning_rate": 4.169674124634482e-06,
1367
+ "loss": 1.2191,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 0.5571428571428572,
1372
+ "grad_norm": 1.578125,
1373
+ "learning_rate": 4.125362886761577e-06,
1374
+ "loss": 1.2496,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 0.56,
1379
+ "grad_norm": 1.609375,
1380
+ "learning_rate": 4.08112239906853e-06,
1381
+ "loss": 1.2369,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 0.5628571428571428,
1386
+ "grad_norm": 1.6328125,
1387
+ "learning_rate": 4.036956240208039e-06,
1388
+ "loss": 1.2569,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 0.5657142857142857,
1393
+ "grad_norm": 1.625,
1394
+ "learning_rate": 3.992867982820268e-06,
1395
+ "loss": 1.2248,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 0.5685714285714286,
1400
+ "grad_norm": 1.484375,
1401
+ "learning_rate": 3.948861193243867e-06,
1402
+ "loss": 1.2002,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 0.5714285714285714,
1407
+ "grad_norm": 1.921875,
1408
+ "learning_rate": 3.904939431227477e-06,
1409
+ "loss": 1.23,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 0.5742857142857143,
1414
+ "grad_norm": 1.6796875,
1415
+ "learning_rate": 3.8611062496417895e-06,
1416
+ "loss": 1.2209,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 0.5771428571428572,
1421
+ "grad_norm": 1.5859375,
1422
+ "learning_rate": 3.81736519419214e-06,
1423
+ "loss": 1.271,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 0.58,
1428
+ "grad_norm": 1.4921875,
1429
+ "learning_rate": 3.7737198031317025e-06,
1430
+ "loss": 1.2471,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 0.5828571428571429,
1435
+ "grad_norm": 1.2109375,
1436
+ "learning_rate": 3.7301736069752683e-06,
1437
+ "loss": 1.2174,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 0.5857142857142857,
1442
+ "grad_norm": 1.7578125,
1443
+ "learning_rate": 3.686730128213668e-06,
1444
+ "loss": 1.2369,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 0.5885714285714285,
1449
+ "grad_norm": 1.5625,
1450
+ "learning_rate": 3.6433928810288292e-06,
1451
+ "loss": 1.2319,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 0.5914285714285714,
1456
+ "grad_norm": 1.9375,
1457
+ "learning_rate": 3.6001653710095115e-06,
1458
+ "loss": 1.3194,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 0.5942857142857143,
1463
+ "grad_norm": 1.65625,
1464
+ "learning_rate": 3.557051094867735e-06,
1465
+ "loss": 1.1943,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 0.5971428571428572,
1470
+ "grad_norm": 1.5546875,
1471
+ "learning_rate": 3.514053540155934e-06,
1472
+ "loss": 1.2375,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 0.6,
1477
+ "grad_norm": 1.78125,
1478
+ "learning_rate": 3.471176184984839e-06,
1479
+ "loss": 1.2498,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 0.6028571428571429,
1484
+ "grad_norm": 1.4609375,
1485
+ "learning_rate": 3.4284224977421333e-06,
1486
+ "loss": 1.2565,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 0.6057142857142858,
1491
+ "grad_norm": 1.5625,
1492
+ "learning_rate": 3.3857959368118874e-06,
1493
+ "loss": 1.1942,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 0.6085714285714285,
1498
+ "grad_norm": 1.40625,
1499
+ "learning_rate": 3.3432999502948156e-06,
1500
+ "loss": 1.2208,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 0.6114285714285714,
1505
+ "grad_norm": 1.6953125,
1506
+ "learning_rate": 3.300937975729347e-06,
1507
+ "loss": 1.2034,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 0.6142857142857143,
1512
+ "grad_norm": 1.7890625,
1513
+ "learning_rate": 3.2587134398135654e-06,
1514
+ "loss": 1.2471,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 0.6171428571428571,
1519
+ "grad_norm": 1.546875,
1520
+ "learning_rate": 3.216629758128018e-06,
1521
+ "loss": 1.2465,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 0.62,
1526
+ "grad_norm": 1.453125,
1527
+ "learning_rate": 3.1746903348594303e-06,
1528
+ "loss": 1.204,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 0.6228571428571429,
1533
+ "grad_norm": 1.453125,
1534
+ "learning_rate": 3.1328985625253304e-06,
1535
+ "loss": 1.2282,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 0.6257142857142857,
1540
+ "grad_norm": 1.5859375,
1541
+ "learning_rate": 3.0912578216996316e-06,
1542
+ "loss": 1.2622,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 0.6285714285714286,
1547
+ "grad_norm": 1.71875,
1548
+ "learning_rate": 3.0497714807391776e-06,
1549
+ "loss": 1.2507,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 0.6314285714285715,
1554
+ "grad_norm": 1.5,
1555
+ "learning_rate": 3.008442895511263e-06,
1556
+ "loss": 1.2277,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 0.6342857142857142,
1561
+ "grad_norm": 1.65625,
1562
+ "learning_rate": 2.9672754091221807e-06,
1563
+ "loss": 1.2164,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 0.6371428571428571,
1568
+ "grad_norm": 1.6171875,
1569
+ "learning_rate": 2.926272351646794e-06,
1570
+ "loss": 1.2358,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 0.64,
1575
+ "grad_norm": 1.5546875,
1576
+ "learning_rate": 2.88543703985917e-06,
1577
+ "loss": 1.2415,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 0.6428571428571429,
1582
+ "grad_norm": 1.53125,
1583
+ "learning_rate": 2.8447727769642697e-06,
1584
+ "loss": 1.2594,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 0.6457142857142857,
1589
+ "grad_norm": 1.78125,
1590
+ "learning_rate": 2.8042828523307562e-06,
1591
+ "loss": 1.2364,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 0.6485714285714286,
1596
+ "grad_norm": 1.5234375,
1597
+ "learning_rate": 2.7639705412249185e-06,
1598
+ "loss": 1.2227,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 0.6514285714285715,
1603
+ "grad_norm": 2.1875,
1604
+ "learning_rate": 2.7238391045457273e-06,
1605
+ "loss": 1.2627,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 0.6542857142857142,
1610
+ "grad_norm": 1.546875,
1611
+ "learning_rate": 2.683891788561055e-06,
1612
+ "loss": 1.2754,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 0.6571428571428571,
1617
+ "grad_norm": 1.3046875,
1618
+ "learning_rate": 2.644131824645092e-06,
1619
+ "loss": 1.2215,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 0.66,
1624
+ "grad_norm": 1.7890625,
1625
+ "learning_rate": 2.604562429016944e-06,
1626
+ "loss": 1.2072,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 0.6628571428571428,
1631
+ "grad_norm": 1.65625,
1632
+ "learning_rate": 2.5651868024804847e-06,
1633
+ "loss": 1.2342,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 0.6657142857142857,
1638
+ "grad_norm": 1.6171875,
1639
+ "learning_rate": 2.526008130165432e-06,
1640
+ "loss": 1.2508,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 0.6685714285714286,
1645
+ "grad_norm": 1.515625,
1646
+ "learning_rate": 2.4870295812696924e-06,
1647
+ "loss": 1.2335,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 0.6714285714285714,
1652
+ "grad_norm": 1.4921875,
1653
+ "learning_rate": 2.4482543088030188e-06,
1654
+ "loss": 1.2186,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 0.6742857142857143,
1659
+ "grad_norm": 1.453125,
1660
+ "learning_rate": 2.4096854493319476e-06,
1661
+ "loss": 1.2424,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 0.6771428571428572,
1666
+ "grad_norm": 1.6015625,
1667
+ "learning_rate": 2.3713261227260815e-06,
1668
+ "loss": 1.2232,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 0.68,
1673
+ "grad_norm": 1.5546875,
1674
+ "learning_rate": 2.333179431905726e-06,
1675
+ "loss": 1.1973,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 0.6828571428571428,
1680
+ "grad_norm": 1.671875,
1681
+ "learning_rate": 2.295248462590883e-06,
1682
+ "loss": 1.2461,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 0.6857142857142857,
1687
+ "grad_norm": 1.40625,
1688
+ "learning_rate": 2.257536283051651e-06,
1689
+ "loss": 1.17,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 0.6885714285714286,
1694
+ "grad_norm": 2.03125,
1695
+ "learning_rate": 2.2200459438600296e-06,
1696
+ "loss": 1.2275,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 0.6914285714285714,
1701
+ "grad_norm": 1.5703125,
1702
+ "learning_rate": 2.1827804776431478e-06,
1703
+ "loss": 1.2649,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 0.6942857142857143,
1708
+ "grad_norm": 1.5703125,
1709
+ "learning_rate": 2.145742898837964e-06,
1710
+ "loss": 1.2343,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 0.6971428571428572,
1715
+ "grad_norm": 1.5,
1716
+ "learning_rate": 2.1089362034474176e-06,
1717
+ "loss": 1.2209,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 0.7,
1722
+ "grad_norm": 1.5859375,
1723
+ "learning_rate": 2.07236336879808e-06,
1724
+ "loss": 1.2363,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 0.7028571428571428,
1729
+ "grad_norm": 1.640625,
1730
+ "learning_rate": 2.0360273532993195e-06,
1731
+ "loss": 1.2301,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 0.7057142857142857,
1736
+ "grad_norm": 1.4140625,
1737
+ "learning_rate": 1.9999310962039937e-06,
1738
+ "loss": 1.2704,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 0.7085714285714285,
1743
+ "grad_norm": 1.453125,
1744
+ "learning_rate": 1.964077517370681e-06,
1745
+ "loss": 1.1998,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 0.7114285714285714,
1750
+ "grad_norm": 1.671875,
1751
+ "learning_rate": 1.9284695170275054e-06,
1752
+ "loss": 1.2305,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 0.7142857142857143,
1757
+ "grad_norm": 1.59375,
1758
+ "learning_rate": 1.8931099755375203e-06,
1759
+ "loss": 1.21,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 0.7171428571428572,
1764
+ "grad_norm": 1.4609375,
1765
+ "learning_rate": 1.858001753165724e-06,
1766
+ "loss": 1.2015,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 0.72,
1771
+ "grad_norm": 1.4375,
1772
+ "learning_rate": 1.823147689847687e-06,
1773
+ "loss": 1.2115,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 0.7228571428571429,
1778
+ "grad_norm": 2.015625,
1779
+ "learning_rate": 1.7885506049598201e-06,
1780
+ "loss": 1.2317,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 0.7257142857142858,
1785
+ "grad_norm": 2.265625,
1786
+ "learning_rate": 1.7542132970913251e-06,
1787
+ "loss": 1.2063,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 0.7285714285714285,
1792
+ "grad_norm": 1.5,
1793
+ "learning_rate": 1.720138543817807e-06,
1794
+ "loss": 1.2621,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 0.7314285714285714,
1799
+ "grad_norm": 1.578125,
1800
+ "learning_rate": 1.6863291014765893e-06,
1801
+ "loss": 1.2355,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 0.7342857142857143,
1806
+ "grad_norm": 1.59375,
1807
+ "learning_rate": 1.6527877049437624e-06,
1808
+ "loss": 1.2525,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 0.7371428571428571,
1813
+ "grad_norm": 7.28125,
1814
+ "learning_rate": 1.6195170674129469e-06,
1815
+ "loss": 1.2434,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 0.74,
1820
+ "grad_norm": 1.6328125,
1821
+ "learning_rate": 1.586519880175827e-06,
1822
+ "loss": 1.2228,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 0.7428571428571429,
1827
+ "grad_norm": 1.3203125,
1828
+ "learning_rate": 1.5537988124044495e-06,
1829
+ "loss": 1.2388,
1830
+ "step": 2600
1831
+ },
1832
+ {
1833
+ "epoch": 0.7457142857142857,
1834
+ "grad_norm": 1.4609375,
1835
+ "learning_rate": 1.5213565109353045e-06,
1836
+ "loss": 1.2369,
1837
+ "step": 2610
1838
+ },
1839
+ {
1840
+ "epoch": 0.7485714285714286,
1841
+ "grad_norm": 4.09375,
1842
+ "learning_rate": 1.489195600055232e-06,
1843
+ "loss": 1.2123,
1844
+ "step": 2620
1845
+ },
1846
+ {
1847
+ "epoch": 0.7514285714285714,
1848
+ "grad_norm": 1.5234375,
1849
+ "learning_rate": 1.4573186812891344e-06,
1850
+ "loss": 1.2231,
1851
+ "step": 2630
1852
+ },
1853
+ {
1854
+ "epoch": 0.7542857142857143,
1855
+ "grad_norm": 1.4765625,
1856
+ "learning_rate": 1.4257283331895316e-06,
1857
+ "loss": 1.2269,
1858
+ "step": 2640
1859
+ },
1860
+ {
1861
+ "epoch": 0.7571428571428571,
1862
+ "grad_norm": 1.5,
1863
+ "learning_rate": 1.3944271111279938e-06,
1864
+ "loss": 1.2389,
1865
+ "step": 2650
1866
+ },
1867
+ {
1868
+ "epoch": 0.76,
1869
+ "grad_norm": 1.359375,
1870
+ "learning_rate": 1.3634175470884192e-06,
1871
+ "loss": 1.2535,
1872
+ "step": 2660
1873
+ },
1874
+ {
1875
+ "epoch": 0.7628571428571429,
1876
+ "grad_norm": 1.5703125,
1877
+ "learning_rate": 1.3327021494622327e-06,
1878
+ "loss": 1.2166,
1879
+ "step": 2670
1880
+ },
1881
+ {
1882
+ "epoch": 0.7657142857142857,
1883
+ "grad_norm": 1.46875,
1884
+ "learning_rate": 1.3022834028454746e-06,
1885
+ "loss": 1.2672,
1886
+ "step": 2680
1887
+ },
1888
+ {
1889
+ "epoch": 0.7685714285714286,
1890
+ "grad_norm": 1.6640625,
1891
+ "learning_rate": 1.2721637678378135e-06,
1892
+ "loss": 1.2109,
1893
+ "step": 2690
1894
+ },
1895
+ {
1896
+ "epoch": 0.7714285714285715,
1897
+ "grad_norm": 1.5859375,
1898
+ "learning_rate": 1.242345680843517e-06,
1899
+ "loss": 1.2273,
1900
+ "step": 2700
1901
+ },
1902
+ {
1903
+ "epoch": 0.7742857142857142,
1904
+ "grad_norm": 1.4453125,
1905
+ "learning_rate": 1.2128315538743646e-06,
1906
+ "loss": 1.2322,
1907
+ "step": 2710
1908
+ },
1909
+ {
1910
+ "epoch": 0.7771428571428571,
1911
+ "grad_norm": 1.4375,
1912
+ "learning_rate": 1.183623774354531e-06,
1913
+ "loss": 1.2197,
1914
+ "step": 2720
1915
+ },
1916
+ {
1917
+ "epoch": 0.78,
1918
+ "grad_norm": 1.890625,
1919
+ "learning_rate": 1.1547247049274767e-06,
1920
+ "loss": 1.2347,
1921
+ "step": 2730
1922
+ },
1923
+ {
1924
+ "epoch": 0.7828571428571428,
1925
+ "grad_norm": 1.640625,
1926
+ "learning_rate": 1.1261366832648258e-06,
1927
+ "loss": 1.2782,
1928
+ "step": 2740
1929
+ },
1930
+ {
1931
+ "epoch": 0.7857142857142857,
1932
+ "grad_norm": 1.5859375,
1933
+ "learning_rate": 1.0978620218772655e-06,
1934
+ "loss": 1.222,
1935
+ "step": 2750
1936
+ },
1937
+ {
1938
+ "epoch": 0.7885714285714286,
1939
+ "grad_norm": 1.625,
1940
+ "learning_rate": 1.0699030079274957e-06,
1941
+ "loss": 1.2103,
1942
+ "step": 2760
1943
+ },
1944
+ {
1945
+ "epoch": 0.7914285714285715,
1946
+ "grad_norm": 1.6875,
1947
+ "learning_rate": 1.0422619030452063e-06,
1948
+ "loss": 1.2241,
1949
+ "step": 2770
1950
+ },
1951
+ {
1952
+ "epoch": 0.7942857142857143,
1953
+ "grad_norm": 1.546875,
1954
+ "learning_rate": 1.0149409431441421e-06,
1955
+ "loss": 1.24,
1956
+ "step": 2780
1957
+ },
1958
+ {
1959
+ "epoch": 0.7971428571428572,
1960
+ "grad_norm": 1.765625,
1961
+ "learning_rate": 9.879423382412328e-07,
1962
+ "loss": 1.2566,
1963
+ "step": 2790
1964
+ },
1965
+ {
1966
+ "epoch": 0.8,
1967
+ "grad_norm": 1.671875,
1968
+ "learning_rate": 9.612682722778206e-07,
1969
+ "loss": 1.2916,
1970
+ "step": 2800
1971
+ },
1972
+ {
1973
+ "epoch": 0.8028571428571428,
1974
+ "grad_norm": 1.40625,
1975
+ "learning_rate": 9.349209029430051e-07,
1976
+ "loss": 1.212,
1977
+ "step": 2810
1978
+ },
1979
+ {
1980
+ "epoch": 0.8057142857142857,
1981
+ "grad_norm": 1.3828125,
1982
+ "learning_rate": 9.089023614991032e-07,
1983
+ "loss": 1.2317,
1984
+ "step": 2820
1985
+ },
1986
+ {
1987
+ "epoch": 0.8085714285714286,
1988
+ "grad_norm": 1.5703125,
1989
+ "learning_rate": 8.83214752609246e-07,
1990
+ "loss": 1.2229,
1991
+ "step": 2830
1992
+ },
1993
+ {
1994
+ "epoch": 0.8114285714285714,
1995
+ "grad_norm": 1.609375,
1996
+ "learning_rate": 8.578601541671366e-07,
1997
+ "loss": 1.2755,
1998
+ "step": 2840
1999
+ },
2000
+ {
2001
+ "epoch": 0.8142857142857143,
2002
+ "grad_norm": 1.4140625,
2003
+ "learning_rate": 8.328406171289621e-07,
2004
+ "loss": 1.2019,
2005
+ "step": 2850
2006
+ },
2007
+ {
2008
+ "epoch": 0.8171428571428572,
2009
+ "grad_norm": 1.7734375,
2010
+ "learning_rate": 8.081581653474945e-07,
2011
+ "loss": 1.1962,
2012
+ "step": 2860
2013
+ },
2014
+ {
2015
+ "epoch": 0.82,
2016
+ "grad_norm": 1.78125,
2017
+ "learning_rate": 7.83814795408378e-07,
2018
+ "loss": 1.2464,
2019
+ "step": 2870
2020
+ },
2021
+ {
2022
+ "epoch": 0.8228571428571428,
2023
+ "grad_norm": 1.609375,
2024
+ "learning_rate": 7.598124764686182e-07,
2025
+ "loss": 1.1909,
2026
+ "step": 2880
2027
+ },
2028
+ {
2029
+ "epoch": 0.8257142857142857,
2030
+ "grad_norm": 1.53125,
2031
+ "learning_rate": 7.361531500973052e-07,
2032
+ "loss": 1.2326,
2033
+ "step": 2890
2034
+ },
2035
+ {
2036
+ "epoch": 0.8285714285714286,
2037
+ "grad_norm": 1.6796875,
2038
+ "learning_rate": 7.128387301185502e-07,
2039
+ "loss": 1.2443,
2040
+ "step": 2900
2041
+ },
2042
+ {
2043
+ "epoch": 0.8314285714285714,
2044
+ "grad_norm": 1.4296875,
2045
+ "learning_rate": 6.898711024566762e-07,
2046
+ "loss": 1.2719,
2047
+ "step": 2910
2048
+ },
2049
+ {
2050
+ "epoch": 0.8342857142857143,
2051
+ "grad_norm": 1.515625,
2052
+ "learning_rate": 6.672521249836689e-07,
2053
+ "loss": 1.2577,
2054
+ "step": 2920
2055
+ },
2056
+ {
2057
+ "epoch": 0.8371428571428572,
2058
+ "grad_norm": 1.7109375,
2059
+ "learning_rate": 6.44983627368882e-07,
2060
+ "loss": 1.2606,
2061
+ "step": 2930
2062
+ },
2063
+ {
2064
+ "epoch": 0.84,
2065
+ "grad_norm": 1.6875,
2066
+ "learning_rate": 6.230674109310436e-07,
2067
+ "loss": 1.2358,
2068
+ "step": 2940
2069
+ },
2070
+ {
2071
+ "epoch": 0.8428571428571429,
2072
+ "grad_norm": 1.6875,
2073
+ "learning_rate": 6.015052484925426e-07,
2074
+ "loss": 1.2674,
2075
+ "step": 2950
2076
+ },
2077
+ {
2078
+ "epoch": 0.8457142857142858,
2079
+ "grad_norm": 1.671875,
2080
+ "learning_rate": 5.802988842360169e-07,
2081
+ "loss": 1.2425,
2082
+ "step": 2960
2083
+ },
2084
+ {
2085
+ "epoch": 0.8485714285714285,
2086
+ "grad_norm": 1.546875,
2087
+ "learning_rate": 5.594500335632785e-07,
2088
+ "loss": 1.2456,
2089
+ "step": 2970
2090
+ },
2091
+ {
2092
+ "epoch": 0.8514285714285714,
2093
+ "grad_norm": 1.578125,
2094
+ "learning_rate": 5.389603829565393e-07,
2095
+ "loss": 1.2576,
2096
+ "step": 2980
2097
+ },
2098
+ {
2099
+ "epoch": 0.8542857142857143,
2100
+ "grad_norm": 1.65625,
2101
+ "learning_rate": 5.188315898419971e-07,
2102
+ "loss": 1.2568,
2103
+ "step": 2990
2104
+ },
2105
+ {
2106
+ "epoch": 0.8571428571428571,
2107
+ "grad_norm": 1.6484375,
2108
+ "learning_rate": 4.990652824557651e-07,
2109
+ "loss": 1.2363,
2110
+ "step": 3000
2111
+ },
2112
+ {
2113
+ "epoch": 0.86,
2114
+ "grad_norm": 1.46875,
2115
+ "learning_rate": 4.796630597121616e-07,
2116
+ "loss": 1.2239,
2117
+ "step": 3010
2118
+ },
2119
+ {
2120
+ "epoch": 0.8628571428571429,
2121
+ "grad_norm": 1.5859375,
2122
+ "learning_rate": 4.6062649107436906e-07,
2123
+ "loss": 1.265,
2124
+ "step": 3020
2125
+ },
2126
+ {
2127
+ "epoch": 0.8657142857142858,
2128
+ "grad_norm": 1.5,
2129
+ "learning_rate": 4.4195711642748497e-07,
2130
+ "loss": 1.2642,
2131
+ "step": 3030
2132
+ },
2133
+ {
2134
+ "epoch": 0.8685714285714285,
2135
+ "grad_norm": 1.5859375,
2136
+ "learning_rate": 4.2365644595395163e-07,
2137
+ "loss": 1.2409,
2138
+ "step": 3040
2139
+ },
2140
+ {
2141
+ "epoch": 0.8714285714285714,
2142
+ "grad_norm": 1.7890625,
2143
+ "learning_rate": 4.057259600114072e-07,
2144
+ "loss": 1.187,
2145
+ "step": 3050
2146
+ },
2147
+ {
2148
+ "epoch": 0.8742857142857143,
2149
+ "grad_norm": 1.6640625,
2150
+ "learning_rate": 3.8816710901292467e-07,
2151
+ "loss": 1.2412,
2152
+ "step": 3060
2153
+ },
2154
+ {
2155
+ "epoch": 0.8771428571428571,
2156
+ "grad_norm": 1.625,
2157
+ "learning_rate": 3.709813133096957e-07,
2158
+ "loss": 1.2396,
2159
+ "step": 3070
2160
+ },
2161
+ {
2162
+ "epoch": 0.88,
2163
+ "grad_norm": 1.5859375,
2164
+ "learning_rate": 3.5416996307613526e-07,
2165
+ "loss": 1.245,
2166
+ "step": 3080
2167
+ },
2168
+ {
2169
+ "epoch": 0.8828571428571429,
2170
+ "grad_norm": 1.3984375,
2171
+ "learning_rate": 3.377344181974301e-07,
2172
+ "loss": 1.1911,
2173
+ "step": 3090
2174
+ },
2175
+ {
2176
+ "epoch": 0.8857142857142857,
2177
+ "grad_norm": 1.6484375,
2178
+ "learning_rate": 3.2167600815953106e-07,
2179
+ "loss": 1.2691,
2180
+ "step": 3100
2181
+ },
2182
+ {
2183
+ "epoch": 0.8885714285714286,
2184
+ "grad_norm": 1.8203125,
2185
+ "learning_rate": 3.059960319416183e-07,
2186
+ "loss": 1.2316,
2187
+ "step": 3110
2188
+ },
2189
+ {
2190
+ "epoch": 0.8914285714285715,
2191
+ "grad_norm": 1.6171875,
2192
+ "learning_rate": 2.90695757911017e-07,
2193
+ "loss": 1.2343,
2194
+ "step": 3120
2195
+ },
2196
+ {
2197
+ "epoch": 0.8942857142857142,
2198
+ "grad_norm": 1.4765625,
2199
+ "learning_rate": 2.7577642372060676e-07,
2200
+ "loss": 1.2145,
2201
+ "step": 3130
2202
+ },
2203
+ {
2204
+ "epoch": 0.8971428571428571,
2205
+ "grad_norm": 1.5859375,
2206
+ "learning_rate": 2.6123923620869797e-07,
2207
+ "loss": 1.234,
2208
+ "step": 3140
2209
+ },
2210
+ {
2211
+ "epoch": 0.9,
2212
+ "grad_norm": 1.3515625,
2213
+ "learning_rate": 2.4708537130141484e-07,
2214
+ "loss": 1.2177,
2215
+ "step": 3150
2216
+ },
2217
+ {
2218
+ "epoch": 0.9028571428571428,
2219
+ "grad_norm": 1.7734375,
2220
+ "learning_rate": 2.3331597391757444e-07,
2221
+ "loss": 1.2631,
2222
+ "step": 3160
2223
+ },
2224
+ {
2225
+ "epoch": 0.9057142857142857,
2226
+ "grad_norm": 1.609375,
2227
+ "learning_rate": 2.1993215787606937e-07,
2228
+ "loss": 1.2564,
2229
+ "step": 3170
2230
+ },
2231
+ {
2232
+ "epoch": 0.9085714285714286,
2233
+ "grad_norm": 1.546875,
2234
+ "learning_rate": 2.0693500580577232e-07,
2235
+ "loss": 1.2415,
2236
+ "step": 3180
2237
+ },
2238
+ {
2239
+ "epoch": 0.9114285714285715,
2240
+ "grad_norm": 1.5390625,
2241
+ "learning_rate": 1.9432556905796153e-07,
2242
+ "loss": 1.2711,
2243
+ "step": 3190
2244
+ },
2245
+ {
2246
+ "epoch": 0.9142857142857143,
2247
+ "grad_norm": 1.5390625,
2248
+ "learning_rate": 1.82104867621275e-07,
2249
+ "loss": 1.2392,
2250
+ "step": 3200
2251
+ },
2252
+ {
2253
+ "epoch": 0.9171428571428571,
2254
+ "grad_norm": 2.015625,
2255
+ "learning_rate": 1.7027389003920315e-07,
2256
+ "loss": 1.2394,
2257
+ "step": 3210
2258
+ },
2259
+ {
2260
+ "epoch": 0.92,
2261
+ "grad_norm": 1.5625,
2262
+ "learning_rate": 1.5883359333012438e-07,
2263
+ "loss": 1.2219,
2264
+ "step": 3220
2265
+ },
2266
+ {
2267
+ "epoch": 0.9228571428571428,
2268
+ "grad_norm": 1.4609375,
2269
+ "learning_rate": 1.4778490290988934e-07,
2270
+ "loss": 1.2376,
2271
+ "step": 3230
2272
+ },
2273
+ {
2274
+ "epoch": 0.9257142857142857,
2275
+ "grad_norm": 1.6015625,
2276
+ "learning_rate": 1.3712871251697012e-07,
2277
+ "loss": 1.2682,
2278
+ "step": 3240
2279
+ },
2280
+ {
2281
+ "epoch": 0.9285714285714286,
2282
+ "grad_norm": 1.6796875,
2283
+ "learning_rate": 1.2686588414015544e-07,
2284
+ "loss": 1.2103,
2285
+ "step": 3250
2286
+ },
2287
+ {
2288
+ "epoch": 0.9314285714285714,
2289
+ "grad_norm": 1.7109375,
2290
+ "learning_rate": 1.169972479488285e-07,
2291
+ "loss": 1.2426,
2292
+ "step": 3260
2293
+ },
2294
+ {
2295
+ "epoch": 0.9342857142857143,
2296
+ "grad_norm": 1.6796875,
2297
+ "learning_rate": 1.0752360222581471e-07,
2298
+ "loss": 1.2023,
2299
+ "step": 3270
2300
+ },
2301
+ {
2302
+ "epoch": 0.9371428571428572,
2303
+ "grad_norm": 2.203125,
2304
+ "learning_rate": 9.84457133028055e-08,
2305
+ "loss": 1.2508,
2306
+ "step": 3280
2307
+ },
2308
+ {
2309
+ "epoch": 0.94,
2310
+ "grad_norm": 1.4765625,
2311
+ "learning_rate": 8.976431549837239e-08,
2312
+ "loss": 1.2167,
2313
+ "step": 3290
2314
+ },
2315
+ {
2316
+ "epoch": 0.9428571428571428,
2317
+ "grad_norm": 1.6953125,
2318
+ "learning_rate": 8.148011105856168e-08,
2319
+ "loss": 1.2454,
2320
+ "step": 3300
2321
+ },
2322
+ {
2323
+ "epoch": 0.9457142857142857,
2324
+ "grad_norm": 1.734375,
2325
+ "learning_rate": 7.359377010009383e-08,
2326
+ "loss": 1.2451,
2327
+ "step": 3310
2328
+ },
2329
+ {
2330
+ "epoch": 0.9485714285714286,
2331
+ "grad_norm": 1.4296875,
2332
+ "learning_rate": 6.610593055615733e-08,
2333
+ "loss": 1.2328,
2334
+ "step": 3320
2335
+ },
2336
+ {
2337
+ "epoch": 0.9514285714285714,
2338
+ "grad_norm": 1.84375,
2339
+ "learning_rate": 5.9017198124801664e-08,
2340
+ "loss": 1.2635,
2341
+ "step": 3330
2342
+ },
2343
+ {
2344
+ "epoch": 0.9542857142857143,
2345
+ "grad_norm": 1.5390625,
2346
+ "learning_rate": 5.232814621994597e-08,
2347
+ "loss": 1.2532,
2348
+ "step": 3340
2349
+ },
2350
+ {
2351
+ "epoch": 0.9571428571428572,
2352
+ "grad_norm": 1.671875,
2353
+ "learning_rate": 4.603931592499278e-08,
2354
+ "loss": 1.2491,
2355
+ "step": 3350
2356
+ },
2357
+ {
2358
+ "epoch": 0.96,
2359
+ "grad_norm": 1.5703125,
2360
+ "learning_rate": 4.015121594906024e-08,
2361
+ "loss": 1.2173,
2362
+ "step": 3360
2363
+ },
2364
+ {
2365
+ "epoch": 0.9628571428571429,
2366
+ "grad_norm": 1.4140625,
2367
+ "learning_rate": 3.4664322585831745e-08,
2368
+ "loss": 1.2187,
2369
+ "step": 3370
2370
+ },
2371
+ {
2372
+ "epoch": 0.9657142857142857,
2373
+ "grad_norm": 1.6875,
2374
+ "learning_rate": 2.9579079675028377e-08,
2375
+ "loss": 1.234,
2376
+ "step": 3380
2377
+ },
2378
+ {
2379
+ "epoch": 0.9685714285714285,
2380
+ "grad_norm": 1.609375,
2381
+ "learning_rate": 2.4895898566505982e-08,
2382
+ "loss": 1.2441,
2383
+ "step": 3390
2384
+ },
2385
+ {
2386
+ "epoch": 0.9714285714285714,
2387
+ "grad_norm": 1.4375,
2388
+ "learning_rate": 2.0615158086981225e-08,
2389
+ "loss": 1.2438,
2390
+ "step": 3400
2391
+ },
2392
+ {
2393
+ "epoch": 0.9742857142857143,
2394
+ "grad_norm": 1.46875,
2395
+ "learning_rate": 1.6737204509387206e-08,
2396
+ "loss": 1.1841,
2397
+ "step": 3410
2398
+ },
2399
+ {
2400
+ "epoch": 0.9771428571428571,
2401
+ "grad_norm": 1.5703125,
2402
+ "learning_rate": 1.3262351524864215e-08,
2403
+ "loss": 1.2387,
2404
+ "step": 3420
2405
+ },
2406
+ {
2407
+ "epoch": 0.98,
2408
+ "grad_norm": 1.921875,
2409
+ "learning_rate": 1.0190880217383348e-08,
2410
+ "loss": 1.2228,
2411
+ "step": 3430
2412
+ },
2413
+ {
2414
+ "epoch": 0.9828571428571429,
2415
+ "grad_norm": 1.4375,
2416
+ "learning_rate": 7.523039041012481e-09,
2417
+ "loss": 1.2125,
2418
+ "step": 3440
2419
+ },
2420
+ {
2421
+ "epoch": 0.9857142857142858,
2422
+ "grad_norm": 1.59375,
2423
+ "learning_rate": 5.259043799813457e-09,
2424
+ "loss": 1.2386,
2425
+ "step": 3450
2426
+ },
2427
+ {
2428
+ "epoch": 0.9885714285714285,
2429
+ "grad_norm": 1.546875,
2430
+ "learning_rate": 3.3990776303910457e-09,
2431
+ "loss": 1.2625,
2432
+ "step": 3460
2433
+ },
2434
+ {
2435
+ "epoch": 0.9914285714285714,
2436
+ "grad_norm": 1.5859375,
2437
+ "learning_rate": 1.9432909870747972e-09,
2438
+ "loss": 1.2377,
2439
+ "step": 3470
2440
+ },
2441
+ {
2442
+ "epoch": 0.9942857142857143,
2443
+ "grad_norm": 1.7421875,
2444
+ "learning_rate": 8.918016297515541e-10,
2445
+ "loss": 1.2364,
2446
+ "step": 3480
2447
+ },
2448
+ {
2449
+ "epoch": 0.9971428571428571,
2450
+ "grad_norm": 1.625,
2451
+ "learning_rate": 2.4469461433751507e-10,
2452
+ "loss": 1.2174,
2453
+ "step": 3490
2454
+ },
2455
+ {
2456
+ "epoch": 1.0,
2457
+ "grad_norm": 1.546875,
2458
+ "learning_rate": 2.02228589873954e-12,
2459
+ "loss": 1.2482,
2460
+ "step": 3500
2461
+ }
2462
+ ],
2463
+ "logging_steps": 10,
2464
+ "max_steps": 3500,
2465
+ "num_input_tokens_seen": 0,
2466
+ "num_train_epochs": 9223372036854775807,
2467
+ "save_steps": 500,
2468
+ "stateful_callbacks": {
2469
+ "TrainerControl": {
2470
+ "args": {
2471
+ "should_epoch_stop": false,
2472
+ "should_evaluate": false,
2473
+ "should_log": false,
2474
+ "should_save": true,
2475
+ "should_training_stop": true
2476
+ },
2477
+ "attributes": {}
2478
+ }
2479
+ },
2480
+ "total_flos": 1.412338023206486e+19,
2481
+ "train_batch_size": 28,
2482
+ "trial_name": null,
2483
+ "trial_params": null
2484
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c788dc8de97ffded3503dc2a768968b009c430b2014b30f1894637b8fe26fe88
3
+ size 5905
vocab.json ADDED
The diff for this file is too large to render. See raw diff