Hugging Face's logo

doulujiyao
/
repo_name

TensorBoard
Safetensors
internvl_chat
custom_code
Model card Files Metrics Community
doulujiyao commited on
Commit
55f1d12
•
1 Parent(s): 1292b16

7b model

Browse files
Files changed (19) hide show
  1. added_tokens.json +11 -0
  2. all_results.json +8 -0
  3. config.json +201 -0
  4. generation_config.json +8 -0
  5. model-00001-of-00004.safetensors +3 -0
  6. model-00002-of-00004.safetensors +3 -0
  7. model-00003-of-00004.safetensors +3 -0
  8. model-00004-of-00004.safetensors +3 -0
  9. model.safetensors.index.json +900 -0
  10. runs/Aug28_13-26-01_SH-IDC1-10-198-35-71/events.out.tfevents.1724822802.SH-IDC1-10-198-35-71.211533.0 +3 -0
  11. runs/Aug28_13-28-32_SH-IDC1-10-198-35-71/events.out.tfevents.1724822926.SH-IDC1-10-198-35-71.216189.0 +3 -0
  12. special_tokens_map.json +47 -0
  13. tokenization_internlm2.py +235 -0
  14. tokenizer.model +3 -0
  15. tokenizer_config.json +179 -0
  16. train_results.json +8 -0
  17. trainer_state.json +850 -0
  18. training_args.bin +3 -0
  19. training_log.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 92552,
3
+ "</img>": 92545,
4
+ "</quad>": 92548,
5
+ "</ref>": 92550,
6
+ "<IMG_CONTEXT>": 92546,
7
+ "<box>": 92551,
8
+ "<img>": 92544,
9
+ "<quad>": 92547,
10
+ "<ref>": 92549
11
+ }
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 1.008507801936223,
4
+ "train_runtime": 556.8684,
5
+ "train_samples": 416,
6
+ "train_samples_per_second": 3.735,
7
+ "train_steps_per_second": 0.233
8
+ }
config.json ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "./pretrained/InternVL2-8B",
4
+ "architectures": [
5
+ "InternVLChatModel"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
9
+ "AutoModel": "modeling_internvl_chat.InternVLChatModel",
10
+ "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
11
+ },
12
+ "downsample_ratio": 0.5,
13
+ "dynamic_image_size": true,
14
+ "force_image_size": 448,
15
+ "llm_config": {
16
+ "_name_or_path": "internlm/internlm2_5-7b-chat",
17
+ "add_cross_attention": false,
18
+ "architectures": [
19
+ "InternLM2ForCausalLM"
20
+ ],
21
+ "attn_implementation": "flash_attention_2",
22
+ "auto_map": {
23
+ "AutoConfig": "configuration_internlm2.InternLM2Config",
24
+ "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
25
+ "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM"
26
+ },
27
+ "bad_words_ids": null,
28
+ "begin_suppress_tokens": null,
29
+ "bias": false,
30
+ "bos_token_id": 1,
31
+ "chunk_size_feed_forward": 0,
32
+ "cross_attention_hidden_size": null,
33
+ "decoder_start_token_id": null,
34
+ "diversity_penalty": 0.0,
35
+ "do_sample": false,
36
+ "early_stopping": false,
37
+ "encoder_no_repeat_ngram_size": 0,
38
+ "eos_token_id": 2,
39
+ "exponential_decay_length_penalty": null,
40
+ "finetuning_task": null,
41
+ "forced_bos_token_id": null,
42
+ "forced_eos_token_id": null,
43
+ "hidden_act": "silu",
44
+ "hidden_size": 4096,
45
+ "id2label": {
46
+ "0": "LABEL_0",
47
+ "1": "LABEL_1"
48
+ },
49
+ "initializer_range": 0.02,
50
+ "intermediate_size": 14336,
51
+ "is_decoder": false,
52
+ "is_encoder_decoder": false,
53
+ "label2id": {
54
+ "LABEL_0": 0,
55
+ "LABEL_1": 1
56
+ },
57
+ "length_penalty": 1.0,
58
+ "max_length": 20,
59
+ "max_position_embeddings": 32768,
60
+ "min_length": 0,
61
+ "model_type": "internlm2",
62
+ "no_repeat_ngram_size": 0,
63
+ "num_attention_heads": 32,
64
+ "num_beam_groups": 1,
65
+ "num_beams": 1,
66
+ "num_hidden_layers": 32,
67
+ "num_key_value_heads": 8,
68
+ "num_return_sequences": 1,
69
+ "output_attentions": false,
70
+ "output_hidden_states": false,
71
+ "output_scores": false,
72
+ "pad_token_id": 2,
73
+ "prefix": null,
74
+ "pretraining_tp": 1,
75
+ "problem_type": null,
76
+ "pruned_heads": {},
77
+ "remove_invalid_values": false,
78
+ "repetition_penalty": 1.0,
79
+ "return_dict": true,
80
+ "return_dict_in_generate": false,
81
+ "rms_norm_eps": 1e-05,
82
+ "rope_scaling": {
83
+ "factor": 2.0,
84
+ "type": "dynamic"
85
+ },
86
+ "rope_theta": 1000000,
87
+ "sep_token_id": null,
88
+ "suppress_tokens": null,
89
+ "task_specific_params": null,
90
+ "temperature": 1.0,
91
+ "tf_legacy_loss": false,
92
+ "tie_encoder_decoder": false,
93
+ "tie_word_embeddings": false,
94
+ "tokenizer_class": null,
95
+ "top_k": 50,
96
+ "top_p": 1.0,
97
+ "torch_dtype": "bfloat16",
98
+ "torchscript": false,
99
+ "transformers_version": "4.37.2",
100
+ "typical_p": 1.0,
101
+ "use_bfloat16": true,
102
+ "use_cache": false,
103
+ "vocab_size": 92553
104
+ },
105
+ "max_dynamic_patch": 6,
106
+ "min_dynamic_patch": 1,
107
+ "model_type": "internvl_chat",
108
+ "pad2square": false,
109
+ "ps_version": "v2",
110
+ "select_layer": -1,
111
+ "template": "internlm2-chat",
112
+ "torch_dtype": "bfloat16",
113
+ "transformers_version": null,
114
+ "use_backbone_lora": 0,
115
+ "use_llm_lora": 16,
116
+ "use_thumbnail": true,
117
+ "vision_config": {
118
+ "_name_or_path": "",
119
+ "add_cross_attention": false,
120
+ "architectures": [
121
+ "InternVisionModel"
122
+ ],
123
+ "attention_dropout": 0.0,
124
+ "bad_words_ids": null,
125
+ "begin_suppress_tokens": null,
126
+ "bos_token_id": null,
127
+ "chunk_size_feed_forward": 0,
128
+ "cross_attention_hidden_size": null,
129
+ "decoder_start_token_id": null,
130
+ "diversity_penalty": 0.0,
131
+ "do_sample": false,
132
+ "drop_path_rate": 0.0,
133
+ "dropout": 0.0,
134
+ "early_stopping": false,
135
+ "encoder_no_repeat_ngram_size": 0,
136
+ "eos_token_id": null,
137
+ "exponential_decay_length_penalty": null,
138
+ "finetuning_task": null,
139
+ "forced_bos_token_id": null,
140
+ "forced_eos_token_id": null,
141
+ "hidden_act": "gelu",
142
+ "hidden_size": 1024,
143
+ "id2label": {
144
+ "0": "LABEL_0",
145
+ "1": "LABEL_1"
146
+ },
147
+ "image_size": 448,
148
+ "initializer_factor": 1.0,
149
+ "initializer_range": 0.02,
150
+ "intermediate_size": 4096,
151
+ "is_decoder": false,
152
+ "is_encoder_decoder": false,
153
+ "label2id": {
154
+ "LABEL_0": 0,
155
+ "LABEL_1": 1
156
+ },
157
+ "layer_norm_eps": 1e-06,
158
+ "length_penalty": 1.0,
159
+ "max_length": 20,
160
+ "min_length": 0,
161
+ "model_type": "intern_vit_6b",
162
+ "no_repeat_ngram_size": 0,
163
+ "norm_type": "layer_norm",
164
+ "num_attention_heads": 16,
165
+ "num_beam_groups": 1,
166
+ "num_beams": 1,
167
+ "num_channels": 3,
168
+ "num_hidden_layers": 24,
169
+ "num_return_sequences": 1,
170
+ "output_attentions": false,
171
+ "output_hidden_states": false,
172
+ "output_scores": false,
173
+ "pad_token_id": null,
174
+ "patch_size": 14,
175
+ "prefix": null,
176
+ "problem_type": null,
177
+ "pruned_heads": {},
178
+ "qk_normalization": false,
179
+ "qkv_bias": true,
180
+ "remove_invalid_values": false,
181
+ "repetition_penalty": 1.0,
182
+ "return_dict": true,
183
+ "return_dict_in_generate": false,
184
+ "sep_token_id": null,
185
+ "suppress_tokens": null,
186
+ "task_specific_params": null,
187
+ "temperature": 1.0,
188
+ "tf_legacy_loss": false,
189
+ "tie_encoder_decoder": false,
190
+ "tie_word_embeddings": true,
191
+ "tokenizer_class": null,
192
+ "top_k": 50,
193
+ "top_p": 1.0,
194
+ "torch_dtype": "bfloat16",
195
+ "torchscript": false,
196
+ "transformers_version": "4.37.2",
197
+ "typical_p": 1.0,
198
+ "use_bfloat16": true,
199
+ "use_flash_attn": true
200
+ }
201
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 92542,
5
+ 92543
6
+ ],
7
+ "transformers_version": "4.37.2"
8
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b3732a20fbace0aa8df501f75eab9f1ad079f216b7a165aecd315d4b098e4bd
3
+ size 4959423416
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f2fb9766ed850eb3ac94065daf2291e7a3a480d25fd5e36ea4fae4215be011a
3
+ size 4942476624
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81cd52fdb784c2e910ff59bc3e5b20781b90dabff09f43a500e8e7a120b13d26
3
+ size 4942476664
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c6996208a6cf2eb380e61fec763aa183d53caf262c6fd9e4123cf5d5c3e2465
3
+ size 1381978232
model.safetensors.index.json ADDED
@@ -0,0 +1,900 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16226228224
4
+ },
5
+ "weight_map": {
6
+ "language_model.base_model.model.model.layers.0.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
7
+ "language_model.base_model.model.model.layers.0.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
8
+ "language_model.base_model.model.model.layers.0.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.base_model.model.model.layers.0.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.base_model.model.model.layers.0.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.base_model.model.model.layers.0.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.base_model.model.model.layers.0.attention_norm.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.base_model.model.model.layers.0.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
14
+ "language_model.base_model.model.model.layers.0.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
15
+ "language_model.base_model.model.model.layers.0.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.base_model.model.model.layers.0.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
17
+ "language_model.base_model.model.model.layers.0.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
18
+ "language_model.base_model.model.model.layers.0.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
19
+ "language_model.base_model.model.model.layers.0.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
20
+ "language_model.base_model.model.model.layers.0.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
21
+ "language_model.base_model.model.model.layers.0.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
22
+ "language_model.base_model.model.model.layers.0.ffn_norm.weight": "model-00001-of-00004.safetensors",
23
+ "language_model.base_model.model.model.layers.1.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
24
+ "language_model.base_model.model.model.layers.1.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
25
+ "language_model.base_model.model.model.layers.1.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
26
+ "language_model.base_model.model.model.layers.1.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
27
+ "language_model.base_model.model.model.layers.1.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
28
+ "language_model.base_model.model.model.layers.1.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
29
+ "language_model.base_model.model.model.layers.1.attention_norm.weight": "model-00001-of-00004.safetensors",
30
+ "language_model.base_model.model.model.layers.1.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
31
+ "language_model.base_model.model.model.layers.1.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
32
+ "language_model.base_model.model.model.layers.1.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
33
+ "language_model.base_model.model.model.layers.1.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
34
+ "language_model.base_model.model.model.layers.1.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
35
+ "language_model.base_model.model.model.layers.1.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
36
+ "language_model.base_model.model.model.layers.1.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
37
+ "language_model.base_model.model.model.layers.1.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
38
+ "language_model.base_model.model.model.layers.1.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
39
+ "language_model.base_model.model.model.layers.1.ffn_norm.weight": "model-00001-of-00004.safetensors",
40
+ "language_model.base_model.model.model.layers.10.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
41
+ "language_model.base_model.model.model.layers.10.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
42
+ "language_model.base_model.model.model.layers.10.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
43
+ "language_model.base_model.model.model.layers.10.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
44
+ "language_model.base_model.model.model.layers.10.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.base_model.model.model.layers.10.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.base_model.model.model.layers.10.attention_norm.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.base_model.model.model.layers.10.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.base_model.model.model.layers.10.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.base_model.model.model.layers.10.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
50
+ "language_model.base_model.model.model.layers.10.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
51
+ "language_model.base_model.model.model.layers.10.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.base_model.model.model.layers.10.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
53
+ "language_model.base_model.model.model.layers.10.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
54
+ "language_model.base_model.model.model.layers.10.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
55
+ "language_model.base_model.model.model.layers.10.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
56
+ "language_model.base_model.model.model.layers.10.ffn_norm.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.base_model.model.model.layers.11.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.base_model.model.model.layers.11.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.base_model.model.model.layers.11.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.base_model.model.model.layers.11.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.base_model.model.model.layers.11.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
62
+ "language_model.base_model.model.model.layers.11.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
63
+ "language_model.base_model.model.model.layers.11.attention_norm.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.base_model.model.model.layers.11.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
65
+ "language_model.base_model.model.model.layers.11.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
66
+ "language_model.base_model.model.model.layers.11.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
67
+ "language_model.base_model.model.model.layers.11.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
68
+ "language_model.base_model.model.model.layers.11.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.base_model.model.model.layers.11.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.base_model.model.model.layers.11.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.base_model.model.model.layers.11.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.base_model.model.model.layers.11.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.base_model.model.model.layers.11.ffn_norm.weight": "model-00002-of-00004.safetensors",
74
+ "language_model.base_model.model.model.layers.12.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
75
+ "language_model.base_model.model.model.layers.12.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.base_model.model.model.layers.12.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
77
+ "language_model.base_model.model.model.layers.12.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
78
+ "language_model.base_model.model.model.layers.12.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
79
+ "language_model.base_model.model.model.layers.12.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.base_model.model.model.layers.12.attention_norm.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.base_model.model.model.layers.12.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.base_model.model.model.layers.12.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.base_model.model.model.layers.12.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.base_model.model.model.layers.12.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.base_model.model.model.layers.12.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
86
+ "language_model.base_model.model.model.layers.12.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
87
+ "language_model.base_model.model.model.layers.12.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
88
+ "language_model.base_model.model.model.layers.12.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
89
+ "language_model.base_model.model.model.layers.12.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
90
+ "language_model.base_model.model.model.layers.12.ffn_norm.weight": "model-00002-of-00004.safetensors",
91
+ "language_model.base_model.model.model.layers.13.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
92
+ "language_model.base_model.model.model.layers.13.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
93
+ "language_model.base_model.model.model.layers.13.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
94
+ "language_model.base_model.model.model.layers.13.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
95
+ "language_model.base_model.model.model.layers.13.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
96
+ "language_model.base_model.model.model.layers.13.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
97
+ "language_model.base_model.model.model.layers.13.attention_norm.weight": "model-00002-of-00004.safetensors",
98
+ "language_model.base_model.model.model.layers.13.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
99
+ "language_model.base_model.model.model.layers.13.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
100
+ "language_model.base_model.model.model.layers.13.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
101
+ "language_model.base_model.model.model.layers.13.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
102
+ "language_model.base_model.model.model.layers.13.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
103
+ "language_model.base_model.model.model.layers.13.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
104
+ "language_model.base_model.model.model.layers.13.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
105
+ "language_model.base_model.model.model.layers.13.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
106
+ "language_model.base_model.model.model.layers.13.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
107
+ "language_model.base_model.model.model.layers.13.ffn_norm.weight": "model-00002-of-00004.safetensors",
108
+ "language_model.base_model.model.model.layers.14.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
109
+ "language_model.base_model.model.model.layers.14.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
110
+ "language_model.base_model.model.model.layers.14.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
111
+ "language_model.base_model.model.model.layers.14.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
112
+ "language_model.base_model.model.model.layers.14.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
113
+ "language_model.base_model.model.model.layers.14.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
114
+ "language_model.base_model.model.model.layers.14.attention_norm.weight": "model-00002-of-00004.safetensors",
115
+ "language_model.base_model.model.model.layers.14.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
116
+ "language_model.base_model.model.model.layers.14.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
117
+ "language_model.base_model.model.model.layers.14.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
118
+ "language_model.base_model.model.model.layers.14.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
119
+ "language_model.base_model.model.model.layers.14.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
120
+ "language_model.base_model.model.model.layers.14.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
121
+ "language_model.base_model.model.model.layers.14.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
122
+ "language_model.base_model.model.model.layers.14.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
123
+ "language_model.base_model.model.model.layers.14.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
124
+ "language_model.base_model.model.model.layers.14.ffn_norm.weight": "model-00002-of-00004.safetensors",
125
+ "language_model.base_model.model.model.layers.15.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
126
+ "language_model.base_model.model.model.layers.15.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
127
+ "language_model.base_model.model.model.layers.15.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
128
+ "language_model.base_model.model.model.layers.15.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
129
+ "language_model.base_model.model.model.layers.15.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
130
+ "language_model.base_model.model.model.layers.15.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
131
+ "language_model.base_model.model.model.layers.15.attention_norm.weight": "model-00002-of-00004.safetensors",
132
+ "language_model.base_model.model.model.layers.15.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
133
+ "language_model.base_model.model.model.layers.15.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
134
+ "language_model.base_model.model.model.layers.15.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
135
+ "language_model.base_model.model.model.layers.15.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
136
+ "language_model.base_model.model.model.layers.15.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
137
+ "language_model.base_model.model.model.layers.15.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
138
+ "language_model.base_model.model.model.layers.15.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
139
+ "language_model.base_model.model.model.layers.15.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
140
+ "language_model.base_model.model.model.layers.15.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
141
+ "language_model.base_model.model.model.layers.15.ffn_norm.weight": "model-00002-of-00004.safetensors",
142
+ "language_model.base_model.model.model.layers.16.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
143
+ "language_model.base_model.model.model.layers.16.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
144
+ "language_model.base_model.model.model.layers.16.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
145
+ "language_model.base_model.model.model.layers.16.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
146
+ "language_model.base_model.model.model.layers.16.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
147
+ "language_model.base_model.model.model.layers.16.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
148
+ "language_model.base_model.model.model.layers.16.attention_norm.weight": "model-00002-of-00004.safetensors",
149
+ "language_model.base_model.model.model.layers.16.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
150
+ "language_model.base_model.model.model.layers.16.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
151
+ "language_model.base_model.model.model.layers.16.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
152
+ "language_model.base_model.model.model.layers.16.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
153
+ "language_model.base_model.model.model.layers.16.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
154
+ "language_model.base_model.model.model.layers.16.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
155
+ "language_model.base_model.model.model.layers.16.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
156
+ "language_model.base_model.model.model.layers.16.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
157
+ "language_model.base_model.model.model.layers.16.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
158
+ "language_model.base_model.model.model.layers.16.ffn_norm.weight": "model-00002-of-00004.safetensors",
159
+ "language_model.base_model.model.model.layers.17.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
160
+ "language_model.base_model.model.model.layers.17.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
161
+ "language_model.base_model.model.model.layers.17.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
162
+ "language_model.base_model.model.model.layers.17.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
163
+ "language_model.base_model.model.model.layers.17.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
164
+ "language_model.base_model.model.model.layers.17.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
165
+ "language_model.base_model.model.model.layers.17.attention_norm.weight": "model-00002-of-00004.safetensors",
166
+ "language_model.base_model.model.model.layers.17.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
167
+ "language_model.base_model.model.model.layers.17.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
168
+ "language_model.base_model.model.model.layers.17.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
169
+ "language_model.base_model.model.model.layers.17.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
170
+ "language_model.base_model.model.model.layers.17.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
171
+ "language_model.base_model.model.model.layers.17.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
172
+ "language_model.base_model.model.model.layers.17.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
173
+ "language_model.base_model.model.model.layers.17.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
174
+ "language_model.base_model.model.model.layers.17.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
175
+ "language_model.base_model.model.model.layers.17.ffn_norm.weight": "model-00002-of-00004.safetensors",
176
+ "language_model.base_model.model.model.layers.18.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
177
+ "language_model.base_model.model.model.layers.18.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
178
+ "language_model.base_model.model.model.layers.18.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
179
+ "language_model.base_model.model.model.layers.18.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
180
+ "language_model.base_model.model.model.layers.18.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
181
+ "language_model.base_model.model.model.layers.18.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
182
+ "language_model.base_model.model.model.layers.18.attention_norm.weight": "model-00002-of-00004.safetensors",
183
+ "language_model.base_model.model.model.layers.18.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
184
+ "language_model.base_model.model.model.layers.18.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
185
+ "language_model.base_model.model.model.layers.18.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
186
+ "language_model.base_model.model.model.layers.18.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
187
+ "language_model.base_model.model.model.layers.18.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
188
+ "language_model.base_model.model.model.layers.18.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
189
+ "language_model.base_model.model.model.layers.18.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
190
+ "language_model.base_model.model.model.layers.18.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
191
+ "language_model.base_model.model.model.layers.18.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
192
+ "language_model.base_model.model.model.layers.18.ffn_norm.weight": "model-00002-of-00004.safetensors",
193
+ "language_model.base_model.model.model.layers.19.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
194
+ "language_model.base_model.model.model.layers.19.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
195
+ "language_model.base_model.model.model.layers.19.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
196
+ "language_model.base_model.model.model.layers.19.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
197
+ "language_model.base_model.model.model.layers.19.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
198
+ "language_model.base_model.model.model.layers.19.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
199
+ "language_model.base_model.model.model.layers.19.attention_norm.weight": "model-00003-of-00004.safetensors",
200
+ "language_model.base_model.model.model.layers.19.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
201
+ "language_model.base_model.model.model.layers.19.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
202
+ "language_model.base_model.model.model.layers.19.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
203
+ "language_model.base_model.model.model.layers.19.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
204
+ "language_model.base_model.model.model.layers.19.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
205
+ "language_model.base_model.model.model.layers.19.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
206
+ "language_model.base_model.model.model.layers.19.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
207
+ "language_model.base_model.model.model.layers.19.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
208
+ "language_model.base_model.model.model.layers.19.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
209
+ "language_model.base_model.model.model.layers.19.ffn_norm.weight": "model-00003-of-00004.safetensors",
210
+ "language_model.base_model.model.model.layers.2.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
211
+ "language_model.base_model.model.model.layers.2.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
212
+ "language_model.base_model.model.model.layers.2.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
213
+ "language_model.base_model.model.model.layers.2.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
214
+ "language_model.base_model.model.model.layers.2.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
215
+ "language_model.base_model.model.model.layers.2.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
216
+ "language_model.base_model.model.model.layers.2.attention_norm.weight": "model-00001-of-00004.safetensors",
217
+ "language_model.base_model.model.model.layers.2.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
218
+ "language_model.base_model.model.model.layers.2.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
219
+ "language_model.base_model.model.model.layers.2.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
220
+ "language_model.base_model.model.model.layers.2.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
221
+ "language_model.base_model.model.model.layers.2.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
222
+ "language_model.base_model.model.model.layers.2.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
223
+ "language_model.base_model.model.model.layers.2.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
224
+ "language_model.base_model.model.model.layers.2.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
225
+ "language_model.base_model.model.model.layers.2.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
226
+ "language_model.base_model.model.model.layers.2.ffn_norm.weight": "model-00001-of-00004.safetensors",
227
+ "language_model.base_model.model.model.layers.20.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
228
+ "language_model.base_model.model.model.layers.20.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
229
+ "language_model.base_model.model.model.layers.20.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
230
+ "language_model.base_model.model.model.layers.20.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
231
+ "language_model.base_model.model.model.layers.20.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
232
+ "language_model.base_model.model.model.layers.20.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
233
+ "language_model.base_model.model.model.layers.20.attention_norm.weight": "model-00003-of-00004.safetensors",
234
+ "language_model.base_model.model.model.layers.20.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
235
+ "language_model.base_model.model.model.layers.20.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
236
+ "language_model.base_model.model.model.layers.20.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
237
+ "language_model.base_model.model.model.layers.20.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
238
+ "language_model.base_model.model.model.layers.20.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
239
+ "language_model.base_model.model.model.layers.20.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
240
+ "language_model.base_model.model.model.layers.20.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
241
+ "language_model.base_model.model.model.layers.20.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
242
+ "language_model.base_model.model.model.layers.20.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
243
+ "language_model.base_model.model.model.layers.20.ffn_norm.weight": "model-00003-of-00004.safetensors",
244
+ "language_model.base_model.model.model.layers.21.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
245
+ "language_model.base_model.model.model.layers.21.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
246
+ "language_model.base_model.model.model.layers.21.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
247
+ "language_model.base_model.model.model.layers.21.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
248
+ "language_model.base_model.model.model.layers.21.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
249
+ "language_model.base_model.model.model.layers.21.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
250
+ "language_model.base_model.model.model.layers.21.attention_norm.weight": "model-00003-of-00004.safetensors",
251
+ "language_model.base_model.model.model.layers.21.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
252
+ "language_model.base_model.model.model.layers.21.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
253
+ "language_model.base_model.model.model.layers.21.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
254
+ "language_model.base_model.model.model.layers.21.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
255
+ "language_model.base_model.model.model.layers.21.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
256
+ "language_model.base_model.model.model.layers.21.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
257
+ "language_model.base_model.model.model.layers.21.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
258
+ "language_model.base_model.model.model.layers.21.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
259
+ "language_model.base_model.model.model.layers.21.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
260
+ "language_model.base_model.model.model.layers.21.ffn_norm.weight": "model-00003-of-00004.safetensors",
261
+ "language_model.base_model.model.model.layers.22.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
262
+ "language_model.base_model.model.model.layers.22.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
263
+ "language_model.base_model.model.model.layers.22.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
264
+ "language_model.base_model.model.model.layers.22.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
265
+ "language_model.base_model.model.model.layers.22.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
266
+ "language_model.base_model.model.model.layers.22.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
267
+ "language_model.base_model.model.model.layers.22.attention_norm.weight": "model-00003-of-00004.safetensors",
268
+ "language_model.base_model.model.model.layers.22.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
269
+ "language_model.base_model.model.model.layers.22.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
270
+ "language_model.base_model.model.model.layers.22.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
271
+ "language_model.base_model.model.model.layers.22.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
272
+ "language_model.base_model.model.model.layers.22.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
273
+ "language_model.base_model.model.model.layers.22.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
274
+ "language_model.base_model.model.model.layers.22.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
275
+ "language_model.base_model.model.model.layers.22.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
276
+ "language_model.base_model.model.model.layers.22.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
277
+ "language_model.base_model.model.model.layers.22.ffn_norm.weight": "model-00003-of-00004.safetensors",
278
+ "language_model.base_model.model.model.layers.23.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
279
+ "language_model.base_model.model.model.layers.23.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
280
+ "language_model.base_model.model.model.layers.23.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
281
+ "language_model.base_model.model.model.layers.23.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
282
+ "language_model.base_model.model.model.layers.23.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
283
+ "language_model.base_model.model.model.layers.23.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
284
+ "language_model.base_model.model.model.layers.23.attention_norm.weight": "model-00003-of-00004.safetensors",
285
+ "language_model.base_model.model.model.layers.23.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
286
+ "language_model.base_model.model.model.layers.23.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
287
+ "language_model.base_model.model.model.layers.23.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
288
+ "language_model.base_model.model.model.layers.23.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
289
+ "language_model.base_model.model.model.layers.23.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
290
+ "language_model.base_model.model.model.layers.23.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
291
+ "language_model.base_model.model.model.layers.23.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
292
+ "language_model.base_model.model.model.layers.23.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
293
+ "language_model.base_model.model.model.layers.23.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
294
+ "language_model.base_model.model.model.layers.23.ffn_norm.weight": "model-00003-of-00004.safetensors",
295
+ "language_model.base_model.model.model.layers.24.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
296
+ "language_model.base_model.model.model.layers.24.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
297
+ "language_model.base_model.model.model.layers.24.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
298
+ "language_model.base_model.model.model.layers.24.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
299
+ "language_model.base_model.model.model.layers.24.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
300
+ "language_model.base_model.model.model.layers.24.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
301
+ "language_model.base_model.model.model.layers.24.attention_norm.weight": "model-00003-of-00004.safetensors",
302
+ "language_model.base_model.model.model.layers.24.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
303
+ "language_model.base_model.model.model.layers.24.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
304
+ "language_model.base_model.model.model.layers.24.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
305
+ "language_model.base_model.model.model.layers.24.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
306
+ "language_model.base_model.model.model.layers.24.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
307
+ "language_model.base_model.model.model.layers.24.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
308
+ "language_model.base_model.model.model.layers.24.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
309
+ "language_model.base_model.model.model.layers.24.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
310
+ "language_model.base_model.model.model.layers.24.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
311
+ "language_model.base_model.model.model.layers.24.ffn_norm.weight": "model-00003-of-00004.safetensors",
312
+ "language_model.base_model.model.model.layers.25.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
313
+ "language_model.base_model.model.model.layers.25.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
314
+ "language_model.base_model.model.model.layers.25.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
315
+ "language_model.base_model.model.model.layers.25.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
316
+ "language_model.base_model.model.model.layers.25.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
317
+ "language_model.base_model.model.model.layers.25.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
318
+ "language_model.base_model.model.model.layers.25.attention_norm.weight": "model-00003-of-00004.safetensors",
319
+ "language_model.base_model.model.model.layers.25.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
320
+ "language_model.base_model.model.model.layers.25.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
321
+ "language_model.base_model.model.model.layers.25.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
322
+ "language_model.base_model.model.model.layers.25.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
323
+ "language_model.base_model.model.model.layers.25.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
324
+ "language_model.base_model.model.model.layers.25.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
325
+ "language_model.base_model.model.model.layers.25.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
326
+ "language_model.base_model.model.model.layers.25.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
327
+ "language_model.base_model.model.model.layers.25.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
328
+ "language_model.base_model.model.model.layers.25.ffn_norm.weight": "model-00003-of-00004.safetensors",
329
+ "language_model.base_model.model.model.layers.26.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
330
+ "language_model.base_model.model.model.layers.26.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
331
+ "language_model.base_model.model.model.layers.26.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
332
+ "language_model.base_model.model.model.layers.26.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
333
+ "language_model.base_model.model.model.layers.26.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
334
+ "language_model.base_model.model.model.layers.26.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
335
+ "language_model.base_model.model.model.layers.26.attention_norm.weight": "model-00003-of-00004.safetensors",
336
+ "language_model.base_model.model.model.layers.26.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
337
+ "language_model.base_model.model.model.layers.26.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
338
+ "language_model.base_model.model.model.layers.26.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
339
+ "language_model.base_model.model.model.layers.26.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
340
+ "language_model.base_model.model.model.layers.26.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
341
+ "language_model.base_model.model.model.layers.26.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
342
+ "language_model.base_model.model.model.layers.26.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
343
+ "language_model.base_model.model.model.layers.26.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
344
+ "language_model.base_model.model.model.layers.26.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
345
+ "language_model.base_model.model.model.layers.26.ffn_norm.weight": "model-00003-of-00004.safetensors",
346
+ "language_model.base_model.model.model.layers.27.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
347
+ "language_model.base_model.model.model.layers.27.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
348
+ "language_model.base_model.model.model.layers.27.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
349
+ "language_model.base_model.model.model.layers.27.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
350
+ "language_model.base_model.model.model.layers.27.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
351
+ "language_model.base_model.model.model.layers.27.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
352
+ "language_model.base_model.model.model.layers.27.attention_norm.weight": "model-00003-of-00004.safetensors",
353
+ "language_model.base_model.model.model.layers.27.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
354
+ "language_model.base_model.model.model.layers.27.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
355
+ "language_model.base_model.model.model.layers.27.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
356
+ "language_model.base_model.model.model.layers.27.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
357
+ "language_model.base_model.model.model.layers.27.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
358
+ "language_model.base_model.model.model.layers.27.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
359
+ "language_model.base_model.model.model.layers.27.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
360
+ "language_model.base_model.model.model.layers.27.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
361
+ "language_model.base_model.model.model.layers.27.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
362
+ "language_model.base_model.model.model.layers.27.ffn_norm.weight": "model-00003-of-00004.safetensors",
363
+ "language_model.base_model.model.model.layers.28.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
364
+ "language_model.base_model.model.model.layers.28.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
365
+ "language_model.base_model.model.model.layers.28.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
366
+ "language_model.base_model.model.model.layers.28.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
367
+ "language_model.base_model.model.model.layers.28.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
368
+ "language_model.base_model.model.model.layers.28.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
369
+ "language_model.base_model.model.model.layers.28.attention_norm.weight": "model-00003-of-00004.safetensors",
370
+ "language_model.base_model.model.model.layers.28.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
371
+ "language_model.base_model.model.model.layers.28.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
372
+ "language_model.base_model.model.model.layers.28.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
373
+ "language_model.base_model.model.model.layers.28.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
374
+ "language_model.base_model.model.model.layers.28.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
375
+ "language_model.base_model.model.model.layers.28.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
376
+ "language_model.base_model.model.model.layers.28.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
377
+ "language_model.base_model.model.model.layers.28.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
378
+ "language_model.base_model.model.model.layers.28.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
379
+ "language_model.base_model.model.model.layers.28.ffn_norm.weight": "model-00003-of-00004.safetensors",
380
+ "language_model.base_model.model.model.layers.29.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
381
+ "language_model.base_model.model.model.layers.29.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
382
+ "language_model.base_model.model.model.layers.29.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
383
+ "language_model.base_model.model.model.layers.29.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
384
+ "language_model.base_model.model.model.layers.29.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
385
+ "language_model.base_model.model.model.layers.29.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
386
+ "language_model.base_model.model.model.layers.29.attention_norm.weight": "model-00003-of-00004.safetensors",
387
+ "language_model.base_model.model.model.layers.29.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
388
+ "language_model.base_model.model.model.layers.29.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
389
+ "language_model.base_model.model.model.layers.29.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
390
+ "language_model.base_model.model.model.layers.29.feed_forward.w2.base_layer.weight": "model-00003-of-00004.safetensors",
391
+ "language_model.base_model.model.model.layers.29.feed_forward.w2.lora_A.default.weight": "model-00003-of-00004.safetensors",
392
+ "language_model.base_model.model.model.layers.29.feed_forward.w2.lora_B.default.weight": "model-00003-of-00004.safetensors",
393
+ "language_model.base_model.model.model.layers.29.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
394
+ "language_model.base_model.model.model.layers.29.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
395
+ "language_model.base_model.model.model.layers.29.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
396
+ "language_model.base_model.model.model.layers.29.ffn_norm.weight": "model-00003-of-00004.safetensors",
397
+ "language_model.base_model.model.model.layers.3.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
398
+ "language_model.base_model.model.model.layers.3.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
399
+ "language_model.base_model.model.model.layers.3.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
400
+ "language_model.base_model.model.model.layers.3.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
401
+ "language_model.base_model.model.model.layers.3.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
402
+ "language_model.base_model.model.model.layers.3.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
403
+ "language_model.base_model.model.model.layers.3.attention_norm.weight": "model-00001-of-00004.safetensors",
404
+ "language_model.base_model.model.model.layers.3.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
405
+ "language_model.base_model.model.model.layers.3.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
406
+ "language_model.base_model.model.model.layers.3.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
407
+ "language_model.base_model.model.model.layers.3.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
408
+ "language_model.base_model.model.model.layers.3.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
409
+ "language_model.base_model.model.model.layers.3.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
410
+ "language_model.base_model.model.model.layers.3.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
411
+ "language_model.base_model.model.model.layers.3.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
412
+ "language_model.base_model.model.model.layers.3.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
413
+ "language_model.base_model.model.model.layers.3.ffn_norm.weight": "model-00001-of-00004.safetensors",
414
+ "language_model.base_model.model.model.layers.30.attention.wo.base_layer.weight": "model-00003-of-00004.safetensors",
415
+ "language_model.base_model.model.model.layers.30.attention.wo.lora_A.default.weight": "model-00003-of-00004.safetensors",
416
+ "language_model.base_model.model.model.layers.30.attention.wo.lora_B.default.weight": "model-00003-of-00004.safetensors",
417
+ "language_model.base_model.model.model.layers.30.attention.wqkv.base_layer.weight": "model-00003-of-00004.safetensors",
418
+ "language_model.base_model.model.model.layers.30.attention.wqkv.lora_A.default.weight": "model-00003-of-00004.safetensors",
419
+ "language_model.base_model.model.model.layers.30.attention.wqkv.lora_B.default.weight": "model-00003-of-00004.safetensors",
420
+ "language_model.base_model.model.model.layers.30.attention_norm.weight": "model-00004-of-00004.safetensors",
421
+ "language_model.base_model.model.model.layers.30.feed_forward.w1.base_layer.weight": "model-00003-of-00004.safetensors",
422
+ "language_model.base_model.model.model.layers.30.feed_forward.w1.lora_A.default.weight": "model-00003-of-00004.safetensors",
423
+ "language_model.base_model.model.model.layers.30.feed_forward.w1.lora_B.default.weight": "model-00003-of-00004.safetensors",
424
+ "language_model.base_model.model.model.layers.30.feed_forward.w2.base_layer.weight": "model-00004-of-00004.safetensors",
425
+ "language_model.base_model.model.model.layers.30.feed_forward.w2.lora_A.default.weight": "model-00004-of-00004.safetensors",
426
+ "language_model.base_model.model.model.layers.30.feed_forward.w2.lora_B.default.weight": "model-00004-of-00004.safetensors",
427
+ "language_model.base_model.model.model.layers.30.feed_forward.w3.base_layer.weight": "model-00003-of-00004.safetensors",
428
+ "language_model.base_model.model.model.layers.30.feed_forward.w3.lora_A.default.weight": "model-00003-of-00004.safetensors",
429
+ "language_model.base_model.model.model.layers.30.feed_forward.w3.lora_B.default.weight": "model-00003-of-00004.safetensors",
430
+ "language_model.base_model.model.model.layers.30.ffn_norm.weight": "model-00004-of-00004.safetensors",
431
+ "language_model.base_model.model.model.layers.31.attention.wo.base_layer.weight": "model-00004-of-00004.safetensors",
432
+ "language_model.base_model.model.model.layers.31.attention.wo.lora_A.default.weight": "model-00004-of-00004.safetensors",
433
+ "language_model.base_model.model.model.layers.31.attention.wo.lora_B.default.weight": "model-00004-of-00004.safetensors",
434
+ "language_model.base_model.model.model.layers.31.attention.wqkv.base_layer.weight": "model-00004-of-00004.safetensors",
435
+ "language_model.base_model.model.model.layers.31.attention.wqkv.lora_A.default.weight": "model-00004-of-00004.safetensors",
436
+ "language_model.base_model.model.model.layers.31.attention.wqkv.lora_B.default.weight": "model-00004-of-00004.safetensors",
437
+ "language_model.base_model.model.model.layers.31.attention_norm.weight": "model-00004-of-00004.safetensors",
438
+ "language_model.base_model.model.model.layers.31.feed_forward.w1.base_layer.weight": "model-00004-of-00004.safetensors",
439
+ "language_model.base_model.model.model.layers.31.feed_forward.w1.lora_A.default.weight": "model-00004-of-00004.safetensors",
440
+ "language_model.base_model.model.model.layers.31.feed_forward.w1.lora_B.default.weight": "model-00004-of-00004.safetensors",
441
+ "language_model.base_model.model.model.layers.31.feed_forward.w2.base_layer.weight": "model-00004-of-00004.safetensors",
442
+ "language_model.base_model.model.model.layers.31.feed_forward.w2.lora_A.default.weight": "model-00004-of-00004.safetensors",
443
+ "language_model.base_model.model.model.layers.31.feed_forward.w2.lora_B.default.weight": "model-00004-of-00004.safetensors",
444
+ "language_model.base_model.model.model.layers.31.feed_forward.w3.base_layer.weight": "model-00004-of-00004.safetensors",
445
+ "language_model.base_model.model.model.layers.31.feed_forward.w3.lora_A.default.weight": "model-00004-of-00004.safetensors",
446
+ "language_model.base_model.model.model.layers.31.feed_forward.w3.lora_B.default.weight": "model-00004-of-00004.safetensors",
447
+ "language_model.base_model.model.model.layers.31.ffn_norm.weight": "model-00004-of-00004.safetensors",
448
+ "language_model.base_model.model.model.layers.4.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
449
+ "language_model.base_model.model.model.layers.4.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
450
+ "language_model.base_model.model.model.layers.4.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
451
+ "language_model.base_model.model.model.layers.4.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
452
+ "language_model.base_model.model.model.layers.4.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
453
+ "language_model.base_model.model.model.layers.4.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
454
+ "language_model.base_model.model.model.layers.4.attention_norm.weight": "model-00001-of-00004.safetensors",
455
+ "language_model.base_model.model.model.layers.4.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
456
+ "language_model.base_model.model.model.layers.4.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
457
+ "language_model.base_model.model.model.layers.4.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
458
+ "language_model.base_model.model.model.layers.4.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
459
+ "language_model.base_model.model.model.layers.4.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
460
+ "language_model.base_model.model.model.layers.4.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
461
+ "language_model.base_model.model.model.layers.4.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
462
+ "language_model.base_model.model.model.layers.4.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
463
+ "language_model.base_model.model.model.layers.4.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
464
+ "language_model.base_model.model.model.layers.4.ffn_norm.weight": "model-00001-of-00004.safetensors",
465
+ "language_model.base_model.model.model.layers.5.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
466
+ "language_model.base_model.model.model.layers.5.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
467
+ "language_model.base_model.model.model.layers.5.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
468
+ "language_model.base_model.model.model.layers.5.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
469
+ "language_model.base_model.model.model.layers.5.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
470
+ "language_model.base_model.model.model.layers.5.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
471
+ "language_model.base_model.model.model.layers.5.attention_norm.weight": "model-00001-of-00004.safetensors",
472
+ "language_model.base_model.model.model.layers.5.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
473
+ "language_model.base_model.model.model.layers.5.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
474
+ "language_model.base_model.model.model.layers.5.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
475
+ "language_model.base_model.model.model.layers.5.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
476
+ "language_model.base_model.model.model.layers.5.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
477
+ "language_model.base_model.model.model.layers.5.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
478
+ "language_model.base_model.model.model.layers.5.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
479
+ "language_model.base_model.model.model.layers.5.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
480
+ "language_model.base_model.model.model.layers.5.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
481
+ "language_model.base_model.model.model.layers.5.ffn_norm.weight": "model-00001-of-00004.safetensors",
482
+ "language_model.base_model.model.model.layers.6.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
483
+ "language_model.base_model.model.model.layers.6.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
484
+ "language_model.base_model.model.model.layers.6.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
485
+ "language_model.base_model.model.model.layers.6.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
486
+ "language_model.base_model.model.model.layers.6.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
487
+ "language_model.base_model.model.model.layers.6.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
488
+ "language_model.base_model.model.model.layers.6.attention_norm.weight": "model-00001-of-00004.safetensors",
489
+ "language_model.base_model.model.model.layers.6.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
490
+ "language_model.base_model.model.model.layers.6.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
491
+ "language_model.base_model.model.model.layers.6.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
492
+ "language_model.base_model.model.model.layers.6.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
493
+ "language_model.base_model.model.model.layers.6.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
494
+ "language_model.base_model.model.model.layers.6.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
495
+ "language_model.base_model.model.model.layers.6.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
496
+ "language_model.base_model.model.model.layers.6.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
497
+ "language_model.base_model.model.model.layers.6.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
498
+ "language_model.base_model.model.model.layers.6.ffn_norm.weight": "model-00001-of-00004.safetensors",
499
+ "language_model.base_model.model.model.layers.7.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
500
+ "language_model.base_model.model.model.layers.7.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
501
+ "language_model.base_model.model.model.layers.7.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
502
+ "language_model.base_model.model.model.layers.7.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
503
+ "language_model.base_model.model.model.layers.7.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
504
+ "language_model.base_model.model.model.layers.7.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
505
+ "language_model.base_model.model.model.layers.7.attention_norm.weight": "model-00001-of-00004.safetensors",
506
+ "language_model.base_model.model.model.layers.7.feed_forward.w1.base_layer.weight": "model-00001-of-00004.safetensors",
507
+ "language_model.base_model.model.model.layers.7.feed_forward.w1.lora_A.default.weight": "model-00001-of-00004.safetensors",
508
+ "language_model.base_model.model.model.layers.7.feed_forward.w1.lora_B.default.weight": "model-00001-of-00004.safetensors",
509
+ "language_model.base_model.model.model.layers.7.feed_forward.w2.base_layer.weight": "model-00001-of-00004.safetensors",
510
+ "language_model.base_model.model.model.layers.7.feed_forward.w2.lora_A.default.weight": "model-00001-of-00004.safetensors",
511
+ "language_model.base_model.model.model.layers.7.feed_forward.w2.lora_B.default.weight": "model-00001-of-00004.safetensors",
512
+ "language_model.base_model.model.model.layers.7.feed_forward.w3.base_layer.weight": "model-00001-of-00004.safetensors",
513
+ "language_model.base_model.model.model.layers.7.feed_forward.w3.lora_A.default.weight": "model-00001-of-00004.safetensors",
514
+ "language_model.base_model.model.model.layers.7.feed_forward.w3.lora_B.default.weight": "model-00001-of-00004.safetensors",
515
+ "language_model.base_model.model.model.layers.7.ffn_norm.weight": "model-00001-of-00004.safetensors",
516
+ "language_model.base_model.model.model.layers.8.attention.wo.base_layer.weight": "model-00001-of-00004.safetensors",
517
+ "language_model.base_model.model.model.layers.8.attention.wo.lora_A.default.weight": "model-00001-of-00004.safetensors",
518
+ "language_model.base_model.model.model.layers.8.attention.wo.lora_B.default.weight": "model-00001-of-00004.safetensors",
519
+ "language_model.base_model.model.model.layers.8.attention.wqkv.base_layer.weight": "model-00001-of-00004.safetensors",
520
+ "language_model.base_model.model.model.layers.8.attention.wqkv.lora_A.default.weight": "model-00001-of-00004.safetensors",
521
+ "language_model.base_model.model.model.layers.8.attention.wqkv.lora_B.default.weight": "model-00001-of-00004.safetensors",
522
+ "language_model.base_model.model.model.layers.8.attention_norm.weight": "model-00002-of-00004.safetensors",
523
+ "language_model.base_model.model.model.layers.8.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
524
+ "language_model.base_model.model.model.layers.8.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
525
+ "language_model.base_model.model.model.layers.8.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
526
+ "language_model.base_model.model.model.layers.8.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
527
+ "language_model.base_model.model.model.layers.8.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
528
+ "language_model.base_model.model.model.layers.8.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
529
+ "language_model.base_model.model.model.layers.8.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
530
+ "language_model.base_model.model.model.layers.8.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
531
+ "language_model.base_model.model.model.layers.8.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
532
+ "language_model.base_model.model.model.layers.8.ffn_norm.weight": "model-00002-of-00004.safetensors",
533
+ "language_model.base_model.model.model.layers.9.attention.wo.base_layer.weight": "model-00002-of-00004.safetensors",
534
+ "language_model.base_model.model.model.layers.9.attention.wo.lora_A.default.weight": "model-00002-of-00004.safetensors",
535
+ "language_model.base_model.model.model.layers.9.attention.wo.lora_B.default.weight": "model-00002-of-00004.safetensors",
536
+ "language_model.base_model.model.model.layers.9.attention.wqkv.base_layer.weight": "model-00002-of-00004.safetensors",
537
+ "language_model.base_model.model.model.layers.9.attention.wqkv.lora_A.default.weight": "model-00002-of-00004.safetensors",
538
+ "language_model.base_model.model.model.layers.9.attention.wqkv.lora_B.default.weight": "model-00002-of-00004.safetensors",
539
+ "language_model.base_model.model.model.layers.9.attention_norm.weight": "model-00002-of-00004.safetensors",
540
+ "language_model.base_model.model.model.layers.9.feed_forward.w1.base_layer.weight": "model-00002-of-00004.safetensors",
541
+ "language_model.base_model.model.model.layers.9.feed_forward.w1.lora_A.default.weight": "model-00002-of-00004.safetensors",
542
+ "language_model.base_model.model.model.layers.9.feed_forward.w1.lora_B.default.weight": "model-00002-of-00004.safetensors",
543
+ "language_model.base_model.model.model.layers.9.feed_forward.w2.base_layer.weight": "model-00002-of-00004.safetensors",
544
+ "language_model.base_model.model.model.layers.9.feed_forward.w2.lora_A.default.weight": "model-00002-of-00004.safetensors",
545
+ "language_model.base_model.model.model.layers.9.feed_forward.w2.lora_B.default.weight": "model-00002-of-00004.safetensors",
546
+ "language_model.base_model.model.model.layers.9.feed_forward.w3.base_layer.weight": "model-00002-of-00004.safetensors",
547
+ "language_model.base_model.model.model.layers.9.feed_forward.w3.lora_A.default.weight": "model-00002-of-00004.safetensors",
548
+ "language_model.base_model.model.model.layers.9.feed_forward.w3.lora_B.default.weight": "model-00002-of-00004.safetensors",
549
+ "language_model.base_model.model.model.layers.9.ffn_norm.weight": "model-00002-of-00004.safetensors",
550
+ "language_model.base_model.model.model.norm.weight": "model-00004-of-00004.safetensors",
551
+ "language_model.base_model.model.model.tok_embeddings.weight": "model-00001-of-00004.safetensors",
552
+ "language_model.base_model.model.output.weight": "model-00004-of-00004.safetensors",
553
+ "mlp1.0.bias": "model-00004-of-00004.safetensors",
554
+ "mlp1.0.weight": "model-00004-of-00004.safetensors",
555
+ "mlp1.1.bias": "model-00004-of-00004.safetensors",
556
+ "mlp1.1.weight": "model-00004-of-00004.safetensors",
557
+ "mlp1.3.bias": "model-00004-of-00004.safetensors",
558
+ "mlp1.3.weight": "model-00004-of-00004.safetensors",
559
+ "vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
560
+ "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
561
+ "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
562
+ "vision_model.embeddings.position_embedding": "model-00001-of-00004.safetensors",
563
+ "vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00004.safetensors",
564
+ "vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00004.safetensors",
565
+ "vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
566
+ "vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
567
+ "vision_model.encoder.layers.0.ls1": "model-00001-of-00004.safetensors",
568
+ "vision_model.encoder.layers.0.ls2": "model-00001-of-00004.safetensors",
569
+ "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
570
+ "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
571
+ "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
572
+ "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
573
+ "vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00004.safetensors",
574
+ "vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00004.safetensors",
575
+ "vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00004.safetensors",
576
+ "vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00004.safetensors",
577
+ "vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00004.safetensors",
578
+ "vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00004.safetensors",
579
+ "vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
580
+ "vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
581
+ "vision_model.encoder.layers.1.ls1": "model-00001-of-00004.safetensors",
582
+ "vision_model.encoder.layers.1.ls2": "model-00001-of-00004.safetensors",
583
+ "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
584
+ "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
585
+ "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
586
+ "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
587
+ "vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00004.safetensors",
588
+ "vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00004.safetensors",
589
+ "vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00004.safetensors",
590
+ "vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00004.safetensors",
591
+ "vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00004.safetensors",
592
+ "vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00004.safetensors",
593
+ "vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
594
+ "vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
595
+ "vision_model.encoder.layers.10.ls1": "model-00001-of-00004.safetensors",
596
+ "vision_model.encoder.layers.10.ls2": "model-00001-of-00004.safetensors",
597
+ "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
598
+ "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
599
+ "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
600
+ "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
601
+ "vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00004.safetensors",
602
+ "vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00004.safetensors",
603
+ "vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00004.safetensors",
604
+ "vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00004.safetensors",
605
+ "vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00004.safetensors",
606
+ "vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00004.safetensors",
607
+ "vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
608
+ "vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
609
+ "vision_model.encoder.layers.11.ls1": "model-00001-of-00004.safetensors",
610
+ "vision_model.encoder.layers.11.ls2": "model-00001-of-00004.safetensors",
611
+ "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
612
+ "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
613
+ "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
614
+ "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
615
+ "vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00004.safetensors",
616
+ "vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00004.safetensors",
617
+ "vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00004.safetensors",
618
+ "vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00004.safetensors",
619
+ "vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00004.safetensors",
620
+ "vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00004.safetensors",
621
+ "vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
622
+ "vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
623
+ "vision_model.encoder.layers.12.ls1": "model-00001-of-00004.safetensors",
624
+ "vision_model.encoder.layers.12.ls2": "model-00001-of-00004.safetensors",
625
+ "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
626
+ "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
627
+ "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
628
+ "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
629
+ "vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00004.safetensors",
630
+ "vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00004.safetensors",
631
+ "vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00004.safetensors",
632
+ "vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00004.safetensors",
633
+ "vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00004.safetensors",
634
+ "vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00004.safetensors",
635
+ "vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
636
+ "vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
637
+ "vision_model.encoder.layers.13.ls1": "model-00001-of-00004.safetensors",
638
+ "vision_model.encoder.layers.13.ls2": "model-00001-of-00004.safetensors",
639
+ "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
640
+ "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
641
+ "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
642
+ "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
643
+ "vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00004.safetensors",
644
+ "vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00004.safetensors",
645
+ "vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00004.safetensors",
646
+ "vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00004.safetensors",
647
+ "vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00004.safetensors",
648
+ "vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00004.safetensors",
649
+ "vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
650
+ "vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
651
+ "vision_model.encoder.layers.14.ls1": "model-00001-of-00004.safetensors",
652
+ "vision_model.encoder.layers.14.ls2": "model-00001-of-00004.safetensors",
653
+ "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
654
+ "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
655
+ "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
656
+ "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
657
+ "vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00004.safetensors",
658
+ "vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00004.safetensors",
659
+ "vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00004.safetensors",
660
+ "vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00004.safetensors",
661
+ "vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00004.safetensors",
662
+ "vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00004.safetensors",
663
+ "vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
664
+ "vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
665
+ "vision_model.encoder.layers.15.ls1": "model-00001-of-00004.safetensors",
666
+ "vision_model.encoder.layers.15.ls2": "model-00001-of-00004.safetensors",
667
+ "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
668
+ "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
669
+ "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
670
+ "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
671
+ "vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00004.safetensors",
672
+ "vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00004.safetensors",
673
+ "vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00004.safetensors",
674
+ "vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00004.safetensors",
675
+ "vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00004.safetensors",
676
+ "vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00004.safetensors",
677
+ "vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
678
+ "vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
679
+ "vision_model.encoder.layers.16.ls1": "model-00001-of-00004.safetensors",
680
+ "vision_model.encoder.layers.16.ls2": "model-00001-of-00004.safetensors",
681
+ "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
682
+ "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
683
+ "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
684
+ "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
685
+ "vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00004.safetensors",
686
+ "vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00004.safetensors",
687
+ "vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00004.safetensors",
688
+ "vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00004.safetensors",
689
+ "vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00004.safetensors",
690
+ "vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00004.safetensors",
691
+ "vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
692
+ "vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
693
+ "vision_model.encoder.layers.17.ls1": "model-00001-of-00004.safetensors",
694
+ "vision_model.encoder.layers.17.ls2": "model-00001-of-00004.safetensors",
695
+ "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
696
+ "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
697
+ "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
698
+ "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
699
+ "vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00004.safetensors",
700
+ "vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00004.safetensors",
701
+ "vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00004.safetensors",
702
+ "vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00004.safetensors",
703
+ "vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00004.safetensors",
704
+ "vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00004.safetensors",
705
+ "vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
706
+ "vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
707
+ "vision_model.encoder.layers.18.ls1": "model-00001-of-00004.safetensors",
708
+ "vision_model.encoder.layers.18.ls2": "model-00001-of-00004.safetensors",
709
+ "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
710
+ "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
711
+ "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
712
+ "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
713
+ "vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00004.safetensors",
714
+ "vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00004.safetensors",
715
+ "vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00004.safetensors",
716
+ "vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00004.safetensors",
717
+ "vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00004.safetensors",
718
+ "vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00004.safetensors",
719
+ "vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
720
+ "vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
721
+ "vision_model.encoder.layers.19.ls1": "model-00001-of-00004.safetensors",
722
+ "vision_model.encoder.layers.19.ls2": "model-00001-of-00004.safetensors",
723
+ "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
724
+ "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
725
+ "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
726
+ "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
727
+ "vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00004.safetensors",
728
+ "vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00004.safetensors",
729
+ "vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00004.safetensors",
730
+ "vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00004.safetensors",
731
+ "vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00004.safetensors",
732
+ "vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00004.safetensors",
733
+ "vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
734
+ "vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
735
+ "vision_model.encoder.layers.2.ls1": "model-00001-of-00004.safetensors",
736
+ "vision_model.encoder.layers.2.ls2": "model-00001-of-00004.safetensors",
737
+ "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
738
+ "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
739
+ "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
740
+ "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
741
+ "vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00004.safetensors",
742
+ "vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00004.safetensors",
743
+ "vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00004.safetensors",
744
+ "vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00004.safetensors",
745
+ "vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00004.safetensors",
746
+ "vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00004.safetensors",
747
+ "vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
748
+ "vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
749
+ "vision_model.encoder.layers.20.ls1": "model-00001-of-00004.safetensors",
750
+ "vision_model.encoder.layers.20.ls2": "model-00001-of-00004.safetensors",
751
+ "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
752
+ "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
753
+ "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
754
+ "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
755
+ "vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00004.safetensors",
756
+ "vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00004.safetensors",
757
+ "vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00004.safetensors",
758
+ "vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00004.safetensors",
759
+ "vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00004.safetensors",
760
+ "vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00004.safetensors",
761
+ "vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
762
+ "vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
763
+ "vision_model.encoder.layers.21.ls1": "model-00001-of-00004.safetensors",
764
+ "vision_model.encoder.layers.21.ls2": "model-00001-of-00004.safetensors",
765
+ "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
766
+ "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
767
+ "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
768
+ "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
769
+ "vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00004.safetensors",
770
+ "vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00004.safetensors",
771
+ "vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00004.safetensors",
772
+ "vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00004.safetensors",
773
+ "vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00004.safetensors",
774
+ "vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00004.safetensors",
775
+ "vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
776
+ "vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
777
+ "vision_model.encoder.layers.22.ls1": "model-00001-of-00004.safetensors",
778
+ "vision_model.encoder.layers.22.ls2": "model-00001-of-00004.safetensors",
779
+ "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
780
+ "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
781
+ "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
782
+ "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
783
+ "vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00004.safetensors",
784
+ "vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00004.safetensors",
785
+ "vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00004.safetensors",
786
+ "vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00004.safetensors",
787
+ "vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00004.safetensors",
788
+ "vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00004.safetensors",
789
+ "vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
790
+ "vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
791
+ "vision_model.encoder.layers.23.ls1": "model-00001-of-00004.safetensors",
792
+ "vision_model.encoder.layers.23.ls2": "model-00001-of-00004.safetensors",
793
+ "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
794
+ "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
795
+ "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
796
+ "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
797
+ "vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00004.safetensors",
798
+ "vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00004.safetensors",
799
+ "vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00004.safetensors",
800
+ "vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00004.safetensors",
801
+ "vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00004.safetensors",
802
+ "vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00004.safetensors",
803
+ "vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
804
+ "vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
805
+ "vision_model.encoder.layers.3.ls1": "model-00001-of-00004.safetensors",
806
+ "vision_model.encoder.layers.3.ls2": "model-00001-of-00004.safetensors",
807
+ "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
808
+ "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
809
+ "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
810
+ "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
811
+ "vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00004.safetensors",
812
+ "vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00004.safetensors",
813
+ "vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00004.safetensors",
814
+ "vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00004.safetensors",
815
+ "vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00004.safetensors",
816
+ "vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00004.safetensors",
817
+ "vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
818
+ "vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
819
+ "vision_model.encoder.layers.4.ls1": "model-00001-of-00004.safetensors",
820
+ "vision_model.encoder.layers.4.ls2": "model-00001-of-00004.safetensors",
821
+ "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
822
+ "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
823
+ "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
824
+ "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
825
+ "vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00004.safetensors",
826
+ "vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00004.safetensors",
827
+ "vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00004.safetensors",
828
+ "vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00004.safetensors",
829
+ "vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00004.safetensors",
830
+ "vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00004.safetensors",
831
+ "vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
832
+ "vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
833
+ "vision_model.encoder.layers.5.ls1": "model-00001-of-00004.safetensors",
834
+ "vision_model.encoder.layers.5.ls2": "model-00001-of-00004.safetensors",
835
+ "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
836
+ "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
837
+ "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
838
+ "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
839
+ "vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00004.safetensors",
840
+ "vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00004.safetensors",
841
+ "vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00004.safetensors",
842
+ "vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00004.safetensors",
843
+ "vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00004.safetensors",
844
+ "vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00004.safetensors",
845
+ "vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
846
+ "vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
847
+ "vision_model.encoder.layers.6.ls1": "model-00001-of-00004.safetensors",
848
+ "vision_model.encoder.layers.6.ls2": "model-00001-of-00004.safetensors",
849
+ "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
850
+ "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
851
+ "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
852
+ "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
853
+ "vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00004.safetensors",
854
+ "vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00004.safetensors",
855
+ "vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00004.safetensors",
856
+ "vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00004.safetensors",
857
+ "vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00004.safetensors",
858
+ "vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00004.safetensors",
859
+ "vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
860
+ "vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
861
+ "vision_model.encoder.layers.7.ls1": "model-00001-of-00004.safetensors",
862
+ "vision_model.encoder.layers.7.ls2": "model-00001-of-00004.safetensors",
863
+ "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
864
+ "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
865
+ "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
866
+ "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
867
+ "vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00004.safetensors",
868
+ "vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00004.safetensors",
869
+ "vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00004.safetensors",
870
+ "vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00004.safetensors",
871
+ "vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00004.safetensors",
872
+ "vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00004.safetensors",
873
+ "vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
874
+ "vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
875
+ "vision_model.encoder.layers.8.ls1": "model-00001-of-00004.safetensors",
876
+ "vision_model.encoder.layers.8.ls2": "model-00001-of-00004.safetensors",
877
+ "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
878
+ "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
879
+ "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
880
+ "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
881
+ "vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00004.safetensors",
882
+ "vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00004.safetensors",
883
+ "vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00004.safetensors",
884
+ "vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00004.safetensors",
885
+ "vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00004.safetensors",
886
+ "vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00004.safetensors",
887
+ "vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
888
+ "vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
889
+ "vision_model.encoder.layers.9.ls1": "model-00001-of-00004.safetensors",
890
+ "vision_model.encoder.layers.9.ls2": "model-00001-of-00004.safetensors",
891
+ "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
892
+ "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
893
+ "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
894
+ "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
895
+ "vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00004.safetensors",
896
+ "vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00004.safetensors",
897
+ "vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00004.safetensors",
898
+ "vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00004.safetensors"
899
+ }
900
+ }
runs/Aug28_13-26-01_SH-IDC1-10-198-35-71/events.out.tfevents.1724822802.SH-IDC1-10-198-35-71.211533.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f6dc601c60435fd0ad02b3b7e071b6a2aef52740754693dc143bd5f5f983fee
3
+ size 9776
runs/Aug28_13-28-32_SH-IDC1-10-198-35-71/events.out.tfevents.1724822926.SH-IDC1-10-198-35-71.216189.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4596a37b6fbc3389b4706041d3d4ed8a3cacb3cf4c324c50beaa48a1389cbaff
3
+ size 31186
special_tokens_map.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|action_start|>",
6
+ "<|action_end|>",
7
+ "<|interpreter|>",
8
+ "<|plugin|>",
9
+ "<img>",
10
+ "</img>",
11
+ "<IMG_CONTEXT>",
12
+ "<quad>",
13
+ "</quad>",
14
+ "<ref>",
15
+ "</ref>",
16
+ "<box>",
17
+ "</box>"
18
+ ],
19
+ "bos_token": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "eos_token": {
27
+ "content": "</s>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "pad_token": {
34
+ "content": "</s>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ "unk_token": {
41
+ "content": "<unk>",
42
+ "lstrip": false,
43
+ "normalized": false,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ }
47
+ }
tokenization_internlm2.py ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
2
+ #
3
+ # This code is based on transformers/src/transformers/models/llama/tokenization_llama.py
4
+ #
5
+ # Licensed under the Apache License, Version 2.0 (the "License");
6
+ # you may not use this file except in compliance with the License.
7
+ # You may obtain a copy of the License at
8
+ #
9
+ # http://www.apache.org/licenses/LICENSE-2.0
10
+ #
11
+ # Unless required by applicable law or agreed to in writing, software
12
+ # distributed under the License is distributed on an "AS IS" BASIS,
13
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
+ # See the License for the specific language governing permissions and
15
+ # limitations under the License.
16
+
17
+ """Tokenization classes for InternLM."""
18
+ import os
19
+ from shutil import copyfile
20
+ from typing import Any, Dict, List, Optional, Tuple
21
+
22
+ import sentencepiece as spm
23
+ from transformers.tokenization_utils import PreTrainedTokenizer
24
+ from transformers.utils import logging
25
+
26
+ logger = logging.get_logger(__name__)
27
+
28
+ VOCAB_FILES_NAMES = {'vocab_file': './tokenizer.model'}
29
+
30
+ PRETRAINED_VOCAB_FILES_MAP = {}
31
+
32
+
33
+ # Modified from transformers.model.llama.tokenization_llama.LlamaTokenizer
34
+ class InternLM2Tokenizer(PreTrainedTokenizer):
35
+ """
36
+ Construct a InternLM2 tokenizer. Based on byte-level Byte-Pair-Encoding.
37
+
38
+ Args:
39
+ vocab_file (`str`):
40
+ Path to the vocabulary file.
41
+ """
42
+
43
+ vocab_files_names = VOCAB_FILES_NAMES
44
+ pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
45
+ model_input_names = ['input_ids', 'attention_mask']
46
+ _auto_class = 'AutoTokenizer'
47
+
48
+ def __init__(
49
+ self,
50
+ vocab_file,
51
+ unk_token='<unk>',
52
+ bos_token='<s>',
53
+ eos_token='</s>',
54
+ pad_token='</s>',
55
+ sp_model_kwargs: Optional[Dict[str, Any]] = None,
56
+ add_bos_token=True,
57
+ add_eos_token=False,
58
+ decode_with_prefix_space=False,
59
+ clean_up_tokenization_spaces=False,
60
+ **kwargs,
61
+ ):
62
+ self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
63
+ self.vocab_file = vocab_file
64
+ self.add_bos_token = add_bos_token
65
+ self.add_eos_token = add_eos_token
66
+ self.decode_with_prefix_space = decode_with_prefix_space
67
+ self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
68
+ self.sp_model.Load(vocab_file)
69
+ self._no_prefix_space_tokens = None
70
+ super().__init__(
71
+ bos_token=bos_token,
72
+ eos_token=eos_token,
73
+ unk_token=unk_token,
74
+ pad_token=pad_token,
75
+ clean_up_tokenization_spaces=clean_up_tokenization_spaces,
76
+ **kwargs,
77
+ )
78
+
79
+ @property
80
+ def no_prefix_space_tokens(self):
81
+ if self._no_prefix_space_tokens is None:
82
+ vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
83
+ self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith('▁')}
84
+ return self._no_prefix_space_tokens
85
+
86
+ @property
87
+ def vocab_size(self):
88
+ """Returns vocab size"""
89
+ return self.sp_model.get_piece_size()
90
+
91
+ @property
92
+ def bos_token_id(self) -> Optional[int]:
93
+ return self.sp_model.bos_id()
94
+
95
+ @property
96
+ def eos_token_id(self) -> Optional[int]:
97
+ return self.sp_model.eos_id()
98
+
99
+ def get_vocab(self):
100
+ """Returns vocab as a dict"""
101
+ vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
102
+ vocab.update(self.added_tokens_encoder)
103
+ return vocab
104
+
105
+ def _tokenize(self, text):
106
+ """Returns a tokenized string."""
107
+ return self.sp_model.encode(text, out_type=str)
108
+
109
+ def _convert_token_to_id(self, token):
110
+ """Converts a token (str) in an id using the vocab."""
111
+ return self.sp_model.piece_to_id(token)
112
+
113
+ def _convert_id_to_token(self, index):
114
+ """Converts an index (integer) in a token (str) using the vocab."""
115
+ token = self.sp_model.IdToPiece(index)
116
+ return token
117
+
118
+ def _maybe_add_prefix_space(self, tokens, decoded):
119
+ if tokens and tokens[0] not in self.no_prefix_space_tokens:
120
+ return ' ' + decoded
121
+ else:
122
+ return decoded
123
+
124
+ def convert_tokens_to_string(self, tokens):
125
+ """Converts a sequence of tokens (string) in a single string."""
126
+ current_sub_tokens = []
127
+ out_string = ''
128
+ prev_is_special = False
129
+ for token in tokens:
130
+ # make sure that special tokens are not decoded using sentencepiece model
131
+ if token in self.all_special_tokens:
132
+ if not prev_is_special:
133
+ out_string += ' '
134
+ out_string += self.sp_model.decode(current_sub_tokens) + token
135
+ prev_is_special = True
136
+ current_sub_tokens = []
137
+ else:
138
+ current_sub_tokens.append(token)
139
+ prev_is_special = False
140
+ out_string += self.sp_model.decode(current_sub_tokens)
141
+ out_string = self.clean_up_tokenization(out_string)
142
+ out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
143
+ return out_string[1:]
144
+
145
+ def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
146
+ """
147
+ Save the vocabulary and special tokens file to a directory.
148
+
149
+ Args:
150
+ save_directory (`str`):
151
+ The directory in which to save the vocabulary.
152
+
153
+ Returns:
154
+ `Tuple(str)`: Paths to the files saved.
155
+ """
156
+ if not os.path.isdir(save_directory):
157
+ logger.error(f'Vocabulary path ({save_directory}) should be a directory')
158
+ return
159
+ out_vocab_file = os.path.join(
160
+ save_directory, (filename_prefix + '-' if filename_prefix else '') + VOCAB_FILES_NAMES['vocab_file']
161
+ )
162
+
163
+ if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
164
+ copyfile(self.vocab_file, out_vocab_file)
165
+ elif not os.path.isfile(self.vocab_file):
166
+ with open(out_vocab_file, 'wb') as fi:
167
+ content_spiece_model = self.sp_model.serialized_model_proto()
168
+ fi.write(content_spiece_model)
169
+
170
+ return (out_vocab_file,)
171
+
172
+ def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
173
+ if self.add_bos_token:
174
+ bos_token_ids = [self.bos_token_id]
175
+ else:
176
+ bos_token_ids = []
177
+
178
+ output = bos_token_ids + token_ids_0
179
+
180
+ if token_ids_1 is not None:
181
+ output = output + token_ids_1
182
+
183
+ if self.add_eos_token:
184
+ output = output + [self.eos_token_id]
185
+
186
+ return output
187
+
188
+ def get_special_tokens_mask(
189
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
190
+ ) -> List[int]:
191
+ """
192
+ Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
193
+ special tokens using the tokenizer `prepare_for_model` method.
194
+
195
+ Args:
196
+ token_ids_0 (`List[int]`):
197
+ List of IDs.
198
+ token_ids_1 (`List[int]`, *optional*):
199
+ Optional second list of IDs for sequence pairs.
200
+ already_has_special_tokens (`bool`, *optional*, defaults to `False`):
201
+ Whether or not the token list is already formatted with special tokens for the model.
202
+
203
+ Returns:
204
+ `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
205
+ """
206
+ if already_has_special_tokens:
207
+ return super().get_special_tokens_mask(
208
+ token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
209
+ )
210
+
211
+ if token_ids_1 is None:
212
+ return [1] + ([0] * len(token_ids_0)) + [1]
213
+ return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
214
+
215
+ def create_token_type_ids_from_sequences(
216
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
217
+ ) -> List[int]:
218
+ """
219
+ Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
220
+ use of token type ids, therefore a list of zeros is returned.
221
+
222
+ Args:
223
+ token_ids_0 (`List[int]`):
224
+ List of IDs.
225
+ token_ids_1 (`List[int]`, *optional*):
226
+ Optional second list of IDs for sequence pairs.
227
+
228
+ Returns:
229
+ `List[int]`: List of zeros.
230
+ """
231
+ eos = [self.eos_token_id]
232
+
233
+ if token_ids_1 is None:
234
+ return len(token_ids_0 + eos) * [0]
235
+ return len(token_ids_0 + eos + token_ids_1 + eos) * [0]
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
3
+ size 1477754
tokenizer_config.json ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "92538": {
28
+ "content": "<|plugin|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "92539": {
36
+ "content": "<|interpreter|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "92540": {
44
+ "content": "<|action_end|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "92541": {
52
+ "content": "<|action_start|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "92542": {
60
+ "content": "<|im_end|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "92543": {
68
+ "content": "<|im_start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "92544": {
76
+ "content": "<img>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "92545": {
84
+ "content": "</img>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "92546": {
92
+ "content": "<IMG_CONTEXT>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "92547": {
100
+ "content": "<quad>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "92548": {
108
+ "content": "</quad>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "92549": {
116
+ "content": "<ref>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "92550": {
124
+ "content": "</ref>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "92551": {
132
+ "content": "<box>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "92552": {
140
+ "content": "</box>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ }
147
+ },
148
+ "additional_special_tokens": [
149
+ "<|im_start|>",
150
+ "<|im_end|>",
151
+ "<|action_start|>",
152
+ "<|action_end|>",
153
+ "<|interpreter|>",
154
+ "<|plugin|>",
155
+ "<img>",
156
+ "</img>",
157
+ "<IMG_CONTEXT>",
158
+ "<quad>",
159
+ "</quad>",
160
+ "<ref>",
161
+ "</ref>",
162
+ "<box>",
163
+ "</box>"
164
+ ],
165
+ "auto_map": {
166
+ "AutoTokenizer": [
167
+ "tokenization_internlm2.InternLM2Tokenizer",
168
+ null
169
+ ]
170
+ },
171
+ "bos_token": "<s>",
172
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
173
+ "clean_up_tokenization_spaces": false,
174
+ "eos_token": "</s>",
175
+ "model_max_length": 4096,
176
+ "pad_token": "</s>",
177
+ "tokenizer_class": "InternLM2Tokenizer",
178
+ "unk_token": "<unk>"
179
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 1.008507801936223,
4
+ "train_runtime": 556.8684,
5
+ "train_samples": 416,
6
+ "train_samples_per_second": 3.735,
7
+ "train_steps_per_second": 0.233
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,850 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 130,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04,
13
+ "learning_rate": 1e-05,
14
+ "loss": 3.9642,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.08,
19
+ "learning_rate": 2e-05,
20
+ "loss": 4.071,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.12,
25
+ "learning_rate": 3.0000000000000004e-05,
26
+ "loss": 3.8538,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.15,
31
+ "learning_rate": 4e-05,
32
+ "loss": 3.9502,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.19,
37
+ "learning_rate": 3.999378364001633e-05,
38
+ "loss": 3.7881,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.23,
43
+ "learning_rate": 3.997513842437845e-05,
44
+ "loss": 3.4548,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.27,
49
+ "learning_rate": 3.9944075943623605e-05,
50
+ "loss": 3.3921,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.31,
55
+ "learning_rate": 3.990061550730803e-05,
56
+ "loss": 3.0533,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.35,
61
+ "learning_rate": 3.984478413200345e-05,
62
+ "loss": 2.7676,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.38,
67
+ "learning_rate": 3.977661652450257e-05,
68
+ "loss": 2.6457,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.42,
73
+ "learning_rate": 3.9696155060244166e-05,
74
+ "loss": 2.3735,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.46,
79
+ "learning_rate": 3.9603449756970877e-05,
80
+ "loss": 2.4271,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.5,
85
+ "learning_rate": 3.949855824363647e-05,
86
+ "loss": 2.2207,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.54,
91
+ "learning_rate": 3.938154572458156e-05,
92
+ "loss": 2.1449,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.58,
97
+ "learning_rate": 3.925248493900024e-05,
98
+ "loss": 1.9469,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.62,
103
+ "learning_rate": 3.911145611572282e-05,
104
+ "loss": 1.8312,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.65,
109
+ "learning_rate": 3.895854692334264e-05,
110
+ "loss": 1.7768,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.69,
115
+ "learning_rate": 3.879385241571817e-05,
116
+ "loss": 1.6802,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.73,
121
+ "learning_rate": 3.861747497288409e-05,
122
+ "loss": 1.6101,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.77,
127
+ "learning_rate": 3.842952423740816e-05,
128
+ "loss": 1.5403,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.81,
133
+ "learning_rate": 3.823011704623347e-05,
134
+ "loss": 1.4114,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.85,
139
+ "learning_rate": 3.801937735804838e-05,
140
+ "loss": 1.4065,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.88,
145
+ "learning_rate": 3.7797436176229376e-05,
146
+ "loss": 1.3727,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.92,
151
+ "learning_rate": 3.756443146740457e-05,
152
+ "loss": 1.3538,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.96,
157
+ "learning_rate": 3.732050807568878e-05,
158
+ "loss": 1.4656,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 1.0,
163
+ "learning_rate": 3.7065817632643115e-05,
164
+ "loss": 1.3587,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 1.0,
169
+ "eval_loss": 1.2306509017944336,
170
+ "eval_runtime": 21.666,
171
+ "eval_samples_per_second": 2.123,
172
+ "eval_steps_per_second": 0.138,
173
+ "step": 26
174
+ },
175
+ {
176
+ "epoch": 1.04,
177
+ "learning_rate": 3.680051846301543e-05,
178
+ "loss": 1.2631,
179
+ "step": 27
180
+ },
181
+ {
182
+ "epoch": 1.08,
183
+ "learning_rate": 3.65247754863199e-05,
184
+ "loss": 1.2049,
185
+ "step": 28
186
+ },
187
+ {
188
+ "epoch": 1.12,
189
+ "learning_rate": 3.623876011431714e-05,
190
+ "loss": 1.2327,
191
+ "step": 29
192
+ },
193
+ {
194
+ "epoch": 1.15,
195
+ "learning_rate": 3.5942650144458454e-05,
196
+ "loss": 1.0479,
197
+ "step": 30
198
+ },
199
+ {
200
+ "epoch": 1.19,
201
+ "learning_rate": 3.56366296493606e-05,
202
+ "loss": 1.0442,
203
+ "step": 31
204
+ },
205
+ {
206
+ "epoch": 1.23,
207
+ "learning_rate": 3.532088886237956e-05,
208
+ "loss": 1.0004,
209
+ "step": 32
210
+ },
211
+ {
212
+ "epoch": 1.27,
213
+ "learning_rate": 3.499562405935469e-05,
214
+ "loss": 1.0744,
215
+ "step": 33
216
+ },
217
+ {
218
+ "epoch": 1.31,
219
+ "learning_rate": 3.4661037436596526e-05,
220
+ "loss": 0.8552,
221
+ "step": 34
222
+ },
223
+ {
224
+ "epoch": 1.35,
225
+ "learning_rate": 3.431733698519437e-05,
226
+ "loss": 1.0061,
227
+ "step": 35
228
+ },
229
+ {
230
+ "epoch": 1.38,
231
+ "learning_rate": 3.396473636172146e-05,
232
+ "loss": 0.8791,
233
+ "step": 36
234
+ },
235
+ {
236
+ "epoch": 1.42,
237
+ "learning_rate": 3.360345475541839e-05,
238
+ "loss": 0.8711,
239
+ "step": 37
240
+ },
241
+ {
242
+ "epoch": 1.46,
243
+ "learning_rate": 3.323371675193719e-05,
244
+ "loss": 1.1293,
245
+ "step": 38
246
+ },
247
+ {
248
+ "epoch": 1.5,
249
+ "learning_rate": 3.285575219373079e-05,
250
+ "loss": 0.7738,
251
+ "step": 39
252
+ },
253
+ {
254
+ "epoch": 1.54,
255
+ "learning_rate": 3.246979603717467e-05,
256
+ "loss": 0.7033,
257
+ "step": 40
258
+ },
259
+ {
260
+ "epoch": 1.58,
261
+ "learning_rate": 3.207608820650955e-05,
262
+ "loss": 0.8763,
263
+ "step": 41
264
+ },
265
+ {
266
+ "epoch": 1.62,
267
+ "learning_rate": 3.1674873444695804e-05,
268
+ "loss": 0.7544,
269
+ "step": 42
270
+ },
271
+ {
272
+ "epoch": 1.65,
273
+ "learning_rate": 3.126640116127244e-05,
274
+ "loss": 0.7928,
275
+ "step": 43
276
+ },
277
+ {
278
+ "epoch": 1.69,
279
+ "learning_rate": 3.0850925277315193e-05,
280
+ "loss": 0.8081,
281
+ "step": 44
282
+ },
283
+ {
284
+ "epoch": 1.73,
285
+ "learning_rate": 3.0428704067589963e-05,
286
+ "loss": 0.7112,
287
+ "step": 45
288
+ },
289
+ {
290
+ "epoch": 1.77,
291
+ "learning_rate": 3.0000000000000004e-05,
292
+ "loss": 0.7927,
293
+ "step": 46
294
+ },
295
+ {
296
+ "epoch": 1.81,
297
+ "learning_rate": 2.956507957242637e-05,
298
+ "loss": 0.6722,
299
+ "step": 47
300
+ },
301
+ {
302
+ "epoch": 1.85,
303
+ "learning_rate": 2.9124213147063263e-05,
304
+ "loss": 0.7657,
305
+ "step": 48
306
+ },
307
+ {
308
+ "epoch": 1.88,
309
+ "learning_rate": 2.8677674782351164e-05,
310
+ "loss": 0.7748,
311
+ "step": 49
312
+ },
313
+ {
314
+ "epoch": 1.92,
315
+ "learning_rate": 2.8225742062612236e-05,
316
+ "loss": 0.7922,
317
+ "step": 50
318
+ },
319
+ {
320
+ "epoch": 1.96,
321
+ "learning_rate": 2.7768695925493897e-05,
322
+ "loss": 0.8061,
323
+ "step": 51
324
+ },
325
+ {
326
+ "epoch": 2.0,
327
+ "learning_rate": 2.7306820487327906e-05,
328
+ "loss": 0.7763,
329
+ "step": 52
330
+ },
331
+ {
332
+ "epoch": 2.0,
333
+ "eval_loss": 0.6676424741744995,
334
+ "eval_runtime": 21.6655,
335
+ "eval_samples_per_second": 2.123,
336
+ "eval_steps_per_second": 0.138,
337
+ "step": 52
338
+ },
339
+ {
340
+ "epoch": 2.04,
341
+ "learning_rate": 2.684040286651338e-05,
342
+ "loss": 0.7045,
343
+ "step": 53
344
+ },
345
+ {
346
+ "epoch": 2.08,
347
+ "learning_rate": 2.6369733005033693e-05,
348
+ "loss": 0.7259,
349
+ "step": 54
350
+ },
351
+ {
352
+ "epoch": 2.12,
353
+ "learning_rate": 2.589510348821809e-05,
354
+ "loss": 0.684,
355
+ "step": 55
356
+ },
357
+ {
358
+ "epoch": 2.15,
359
+ "learning_rate": 2.5416809362860107e-05,
360
+ "loss": 0.6923,
361
+ "step": 56
362
+ },
363
+ {
364
+ "epoch": 2.19,
365
+ "learning_rate": 2.493514795380587e-05,
366
+ "loss": 0.6401,
367
+ "step": 57
368
+ },
369
+ {
370
+ "epoch": 2.23,
371
+ "learning_rate": 2.445041867912629e-05,
372
+ "loss": 0.7307,
373
+ "step": 58
374
+ },
375
+ {
376
+ "epoch": 2.27,
377
+ "learning_rate": 2.3962922863987956e-05,
378
+ "loss": 0.6738,
379
+ "step": 59
380
+ },
381
+ {
382
+ "epoch": 2.31,
383
+ "learning_rate": 2.3472963553338614e-05,
384
+ "loss": 0.6694,
385
+ "step": 60
386
+ },
387
+ {
388
+ "epoch": 2.35,
389
+ "learning_rate": 2.2980845323523487e-05,
390
+ "loss": 0.6664,
391
+ "step": 61
392
+ },
393
+ {
394
+ "epoch": 2.38,
395
+ "learning_rate": 2.2486874092949708e-05,
396
+ "loss": 0.6477,
397
+ "step": 62
398
+ },
399
+ {
400
+ "epoch": 2.42,
401
+ "learning_rate": 2.1991356931916335e-05,
402
+ "loss": 0.6324,
403
+ "step": 63
404
+ },
405
+ {
406
+ "epoch": 2.46,
407
+ "learning_rate": 2.149460187172849e-05,
408
+ "loss": 0.6167,
409
+ "step": 64
410
+ },
411
+ {
412
+ "epoch": 2.5,
413
+ "learning_rate": 2.0996917713213944e-05,
414
+ "loss": 0.6035,
415
+ "step": 65
416
+ },
417
+ {
418
+ "epoch": 2.54,
419
+ "learning_rate": 2.0498613834761462e-05,
420
+ "loss": 0.653,
421
+ "step": 66
422
+ },
423
+ {
424
+ "epoch": 2.58,
425
+ "learning_rate": 2e-05,
426
+ "loss": 0.6213,
427
+ "step": 67
428
+ },
429
+ {
430
+ "epoch": 2.62,
431
+ "learning_rate": 1.9501386165238548e-05,
432
+ "loss": 0.5961,
433
+ "step": 68
434
+ },
435
+ {
436
+ "epoch": 2.65,
437
+ "learning_rate": 1.9003082286786056e-05,
438
+ "loss": 0.6726,
439
+ "step": 69
440
+ },
441
+ {
442
+ "epoch": 2.69,
443
+ "learning_rate": 1.8505398128271517e-05,
444
+ "loss": 0.6147,
445
+ "step": 70
446
+ },
447
+ {
448
+ "epoch": 2.73,
449
+ "learning_rate": 1.800864306808367e-05,
450
+ "loss": 0.5905,
451
+ "step": 71
452
+ },
453
+ {
454
+ "epoch": 2.77,
455
+ "learning_rate": 1.7513125907050302e-05,
456
+ "loss": 0.671,
457
+ "step": 72
458
+ },
459
+ {
460
+ "epoch": 2.81,
461
+ "learning_rate": 1.701915467647651e-05,
462
+ "loss": 0.6069,
463
+ "step": 73
464
+ },
465
+ {
466
+ "epoch": 2.85,
467
+ "learning_rate": 1.6527036446661396e-05,
468
+ "loss": 0.6503,
469
+ "step": 74
470
+ },
471
+ {
472
+ "epoch": 2.88,
473
+ "learning_rate": 1.6037077136012054e-05,
474
+ "loss": 0.6333,
475
+ "step": 75
476
+ },
477
+ {
478
+ "epoch": 2.92,
479
+ "learning_rate": 1.5549581320873715e-05,
480
+ "loss": 0.6213,
481
+ "step": 76
482
+ },
483
+ {
484
+ "epoch": 2.96,
485
+ "learning_rate": 1.5064852046194127e-05,
486
+ "loss": 0.6124,
487
+ "step": 77
488
+ },
489
+ {
490
+ "epoch": 3.0,
491
+ "learning_rate": 1.4583190637139901e-05,
492
+ "loss": 0.6404,
493
+ "step": 78
494
+ },
495
+ {
496
+ "epoch": 3.0,
497
+ "eval_loss": 0.5793539881706238,
498
+ "eval_runtime": 21.5979,
499
+ "eval_samples_per_second": 2.13,
500
+ "eval_steps_per_second": 0.139,
501
+ "step": 78
502
+ },
503
+ {
504
+ "epoch": 3.04,
505
+ "learning_rate": 1.4104896511781916e-05,
506
+ "loss": 0.6378,
507
+ "step": 79
508
+ },
509
+ {
510
+ "epoch": 3.08,
511
+ "learning_rate": 1.3630266994966314e-05,
512
+ "loss": 0.629,
513
+ "step": 80
514
+ },
515
+ {
516
+ "epoch": 3.12,
517
+ "learning_rate": 1.3159597133486628e-05,
518
+ "loss": 0.5703,
519
+ "step": 81
520
+ },
521
+ {
522
+ "epoch": 3.15,
523
+ "learning_rate": 1.26931795126721e-05,
524
+ "loss": 0.5396,
525
+ "step": 82
526
+ },
527
+ {
528
+ "epoch": 3.19,
529
+ "learning_rate": 1.2231304074506108e-05,
530
+ "loss": 0.5786,
531
+ "step": 83
532
+ },
533
+ {
534
+ "epoch": 3.23,
535
+ "learning_rate": 1.1774257937387774e-05,
536
+ "loss": 0.638,
537
+ "step": 84
538
+ },
539
+ {
540
+ "epoch": 3.27,
541
+ "learning_rate": 1.132232521764884e-05,
542
+ "loss": 0.6425,
543
+ "step": 85
544
+ },
545
+ {
546
+ "epoch": 3.31,
547
+ "learning_rate": 1.087578685293674e-05,
548
+ "loss": 0.5446,
549
+ "step": 86
550
+ },
551
+ {
552
+ "epoch": 3.35,
553
+ "learning_rate": 1.0434920427573643e-05,
554
+ "loss": 0.5612,
555
+ "step": 87
556
+ },
557
+ {
558
+ "epoch": 3.38,
559
+ "learning_rate": 1.0000000000000006e-05,
560
+ "loss": 0.5518,
561
+ "step": 88
562
+ },
563
+ {
564
+ "epoch": 3.42,
565
+ "learning_rate": 9.57129593241004e-06,
566
+ "loss": 0.5649,
567
+ "step": 89
568
+ },
569
+ {
570
+ "epoch": 3.46,
571
+ "learning_rate": 9.149074722684815e-06,
572
+ "loss": 0.6007,
573
+ "step": 90
574
+ },
575
+ {
576
+ "epoch": 3.5,
577
+ "learning_rate": 8.733598838727559e-06,
578
+ "loss": 0.4963,
579
+ "step": 91
580
+ },
581
+ {
582
+ "epoch": 3.54,
583
+ "learning_rate": 8.325126555304208e-06,
584
+ "loss": 0.5296,
585
+ "step": 92
586
+ },
587
+ {
588
+ "epoch": 3.58,
589
+ "learning_rate": 7.923911793490449e-06,
590
+ "loss": 0.5389,
591
+ "step": 93
592
+ },
593
+ {
594
+ "epoch": 3.62,
595
+ "learning_rate": 7.530203962825331e-06,
596
+ "loss": 0.4734,
597
+ "step": 94
598
+ },
599
+ {
600
+ "epoch": 3.65,
601
+ "learning_rate": 7.1442478062692135e-06,
602
+ "loss": 0.5749,
603
+ "step": 95
604
+ },
605
+ {
606
+ "epoch": 3.69,
607
+ "learning_rate": 6.766283248062817e-06,
608
+ "loss": 0.558,
609
+ "step": 96
610
+ },
611
+ {
612
+ "epoch": 3.73,
613
+ "learning_rate": 6.396545244581609e-06,
614
+ "loss": 0.5729,
615
+ "step": 97
616
+ },
617
+ {
618
+ "epoch": 3.77,
619
+ "learning_rate": 6.035263638278546e-06,
620
+ "loss": 0.5351,
621
+ "step": 98
622
+ },
623
+ {
624
+ "epoch": 3.81,
625
+ "learning_rate": 5.682663014805631e-06,
626
+ "loss": 0.54,
627
+ "step": 99
628
+ },
629
+ {
630
+ "epoch": 3.85,
631
+ "learning_rate": 5.338962563403478e-06,
632
+ "loss": 0.454,
633
+ "step": 100
634
+ },
635
+ {
636
+ "epoch": 3.88,
637
+ "learning_rate": 5.004375940645314e-06,
638
+ "loss": 0.5863,
639
+ "step": 101
640
+ },
641
+ {
642
+ "epoch": 3.92,
643
+ "learning_rate": 4.679111137620442e-06,
644
+ "loss": 0.5254,
645
+ "step": 102
646
+ },
647
+ {
648
+ "epoch": 3.96,
649
+ "learning_rate": 4.363370350639405e-06,
650
+ "loss": 0.6083,
651
+ "step": 103
652
+ },
653
+ {
654
+ "epoch": 4.0,
655
+ "learning_rate": 4.057349855541557e-06,
656
+ "loss": 0.4868,
657
+ "step": 104
658
+ },
659
+ {
660
+ "epoch": 4.0,
661
+ "eval_loss": 0.5455546379089355,
662
+ "eval_runtime": 21.1145,
663
+ "eval_samples_per_second": 2.179,
664
+ "eval_steps_per_second": 0.142,
665
+ "step": 104
666
+ },
667
+ {
668
+ "epoch": 4.04,
669
+ "learning_rate": 3.76123988568287e-06,
670
+ "loss": 0.449,
671
+ "step": 105
672
+ },
673
+ {
674
+ "epoch": 4.08,
675
+ "learning_rate": 3.4752245136801065e-06,
676
+ "loss": 0.5543,
677
+ "step": 106
678
+ },
679
+ {
680
+ "epoch": 4.12,
681
+ "learning_rate": 3.199481536984572e-06,
682
+ "loss": 0.492,
683
+ "step": 107
684
+ },
685
+ {
686
+ "epoch": 4.15,
687
+ "learning_rate": 2.934182367356888e-06,
688
+ "loss": 0.561,
689
+ "step": 108
690
+ },
691
+ {
692
+ "epoch": 4.19,
693
+ "learning_rate": 2.679491924311226e-06,
694
+ "loss": 0.5317,
695
+ "step": 109
696
+ },
697
+ {
698
+ "epoch": 4.23,
699
+ "learning_rate": 2.435568532595427e-06,
700
+ "loss": 0.5508,
701
+ "step": 110
702
+ },
703
+ {
704
+ "epoch": 4.27,
705
+ "learning_rate": 2.2025638237706294e-06,
706
+ "loss": 0.4914,
707
+ "step": 111
708
+ },
709
+ {
710
+ "epoch": 4.31,
711
+ "learning_rate": 1.9806226419516195e-06,
712
+ "loss": 0.5875,
713
+ "step": 112
714
+ },
715
+ {
716
+ "epoch": 4.35,
717
+ "learning_rate": 1.7698829537665374e-06,
718
+ "loss": 0.4155,
719
+ "step": 113
720
+ },
721
+ {
722
+ "epoch": 4.38,
723
+ "learning_rate": 1.5704757625918454e-06,
724
+ "loss": 0.5517,
725
+ "step": 114
726
+ },
727
+ {
728
+ "epoch": 4.42,
729
+ "learning_rate": 1.3825250271159175e-06,
730
+ "loss": 0.5025,
731
+ "step": 115
732
+ },
733
+ {
734
+ "epoch": 4.46,
735
+ "learning_rate": 1.2061475842818337e-06,
736
+ "loss": 0.4756,
737
+ "step": 116
738
+ },
739
+ {
740
+ "epoch": 4.5,
741
+ "learning_rate": 1.0414530766573661e-06,
742
+ "loss": 0.5201,
743
+ "step": 117
744
+ },
745
+ {
746
+ "epoch": 4.54,
747
+ "learning_rate": 8.885438842771843e-07,
748
+ "loss": 0.5558,
749
+ "step": 118
750
+ },
751
+ {
752
+ "epoch": 4.58,
753
+ "learning_rate": 7.475150609997595e-07,
754
+ "loss": 0.4251,
755
+ "step": 119
756
+ },
757
+ {
758
+ "epoch": 4.62,
759
+ "learning_rate": 6.184542754184431e-07,
760
+ "loss": 0.6341,
761
+ "step": 120
762
+ },
763
+ {
764
+ "epoch": 4.65,
765
+ "learning_rate": 5.014417563635276e-07,
766
+ "loss": 0.4536,
767
+ "step": 121
768
+ },
769
+ {
770
+ "epoch": 4.69,
771
+ "learning_rate": 3.965502430291235e-07,
772
+ "loss": 0.5496,
773
+ "step": 122
774
+ },
775
+ {
776
+ "epoch": 4.73,
777
+ "learning_rate": 3.038449397558396e-07,
778
+ "loss": 0.5243,
779
+ "step": 123
780
+ },
781
+ {
782
+ "epoch": 4.77,
783
+ "learning_rate": 2.2338347549742956e-07,
784
+ "loss": 0.5546,
785
+ "step": 124
786
+ },
787
+ {
788
+ "epoch": 4.81,
789
+ "learning_rate": 1.5521586799655875e-07,
790
+ "loss": 0.4766,
791
+ "step": 125
792
+ },
793
+ {
794
+ "epoch": 4.85,
795
+ "learning_rate": 9.938449269197181e-08,
796
+ "loss": 0.5953,
797
+ "step": 126
798
+ },
799
+ {
800
+ "epoch": 4.88,
801
+ "learning_rate": 5.592405637639742e-08,
802
+ "loss": 0.5025,
803
+ "step": 127
804
+ },
805
+ {
806
+ "epoch": 4.92,
807
+ "learning_rate": 2.4861575621553112e-08,
808
+ "loss": 0.4808,
809
+ "step": 128
810
+ },
811
+ {
812
+ "epoch": 4.96,
813
+ "learning_rate": 6.216359983675091e-09,
814
+ "loss": 0.463,
815
+ "step": 129
816
+ },
817
+ {
818
+ "epoch": 5.0,
819
+ "learning_rate": 0.0,
820
+ "loss": 0.5275,
821
+ "step": 130
822
+ },
823
+ {
824
+ "epoch": 5.0,
825
+ "eval_loss": 0.5420305728912354,
826
+ "eval_runtime": 21.3644,
827
+ "eval_samples_per_second": 2.153,
828
+ "eval_steps_per_second": 0.14,
829
+ "step": 130
830
+ },
831
+ {
832
+ "epoch": 5.0,
833
+ "step": 130,
834
+ "total_flos": 1.4892268948732825e+20,
835
+ "train_loss": 1.008507801936223,
836
+ "train_runtime": 556.8684,
837
+ "train_samples_per_second": 3.735,
838
+ "train_steps_per_second": 0.233
839
+ }
840
+ ],
841
+ "logging_steps": 1.0,
842
+ "max_steps": 130,
843
+ "num_input_tokens_seen": 0,
844
+ "num_train_epochs": 5,
845
+ "save_steps": 200,
846
+ "total_flos": 1.4892268948732825e+20,
847
+ "train_batch_size": 4,
848
+ "trial_name": null,
849
+ "trial_params": null
850
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6874608894bb4692acecc98efa8f74cd20d1afa0542344faf6e855b4175de7ad
3
+ size 6264
training_log.txt ADDED
The diff for this file is too large to render. See raw diff