Delta-Vector commited on
Commit
f8e98cd
1 Parent(s): 0e7e540

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ tags:
5
+ - llama-factory
6
+ - full
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: gemma-2-9b-control-4e-r2
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # gemma-2-9b-control-4e-r2
17
+
18
+ This model is a fine-tuned version of [/data/models/gemma-9b-compl](https://huggingface.co//data/models/gemma-9b-compl) on the ds1, the ds2, the ds3, the ds4, the kalo_opus_1, the claude_instruct, the claude_instruct_2 and the epic_synth_2 datasets.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 3e-06
38
+ - train_batch_size: 2
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - distributed_type: multi-GPU
42
+ - num_devices: 12
43
+ - total_train_batch_size: 24
44
+ - total_eval_batch_size: 96
45
+ - optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
+ - lr_scheduler_type: cosine
47
+ - lr_scheduler_warmup_ratio: 0.1
48
+ - num_epochs: 4.0
49
+
50
+ ### Training results
51
+
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - Transformers 4.46.1
57
+ - Pytorch 2.5.0a0+e000cf0ad9.nv24.10
58
+ - Datasets 3.0.2
59
+ - Tokenizers 0.20.1
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "total_flos": 648773332107264.0,
4
+ "train_loss": 0.9660957064397535,
5
+ "train_runtime": 3882.5924,
6
+ "train_samples_per_second": 5.59,
7
+ "train_steps_per_second": 0.234
8
+ }
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "output_dir",
3
+ "architectures": [
4
+ "Gemma2ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": 50.0,
9
+ "bos_token_id": 2,
10
+ "cache_implementation": "hybrid",
11
+ "eos_token_id": 8,
12
+ "final_logit_softcapping": 30.0,
13
+ "head_dim": 256,
14
+ "hidden_act": "gelu_pytorch_tanh",
15
+ "hidden_activation": "gelu_pytorch_tanh",
16
+ "hidden_size": 3584,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 14336,
19
+ "max_position_embeddings": 8192,
20
+ "model_type": "gemma2",
21
+ "num_attention_heads": 16,
22
+ "num_hidden_layers": 42,
23
+ "num_key_value_heads": 8,
24
+ "pad_token_id": 0,
25
+ "query_pre_attn_scalar": 256,
26
+ "rms_norm_eps": 1e-06,
27
+ "rope_theta": 10000.0,
28
+ "sliding_window": 4096,
29
+ "sliding_window_size": 4096,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.46.1",
32
+ "use_cache": false,
33
+ "vocab_size": 256000
34
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "cache_implementation": "hybrid",
5
+ "eos_token_id": 8,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.46.1"
8
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3517a057810510006aa291e9cfd8e24e487160b7f172ca8a15fbfd4939137235
3
+ size 4903351912
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a62f6eb5ffe70a3219c125b5404245416195142a37b0a1021cb741126ac8686
3
+ size 4947570872
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66c187b922fa991d94981aa8c2511394b7b54651cc4fe9e6166f02e90c45a7d3
3
+ size 4962221464
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c6d218fd38213d92917261e1fbee0d87b234c25025c2d147d0e5dde98bbce2c
3
+ size 3670322200
model.safetensors.index.json ADDED
@@ -0,0 +1,471 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 18483411968
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
119
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
121
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
122
+ "model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
123
+ "model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
124
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
125
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
126
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
127
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
130
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
136
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
137
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
138
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
139
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
140
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
141
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
142
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
143
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
144
+ "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
145
+ "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
146
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
147
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
148
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
149
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
150
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.20.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
158
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
159
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
160
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
161
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.21.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.22.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
218
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
221
+ "model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
223
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
245
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
247
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
250
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
251
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
252
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
253
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
254
+ "model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
255
+ "model.layers.29.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
256
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
257
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
258
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
259
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
272
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
273
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
274
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
275
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
276
+ "model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
277
+ "model.layers.30.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
278
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
279
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
280
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
281
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
282
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
283
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
284
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
285
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
286
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
287
+ "model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
288
+ "model.layers.31.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
289
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
290
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
291
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
292
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
293
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
294
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
295
+ "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
296
+ "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
297
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
298
+ "model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
299
+ "model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
300
+ "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
301
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
302
+ "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
303
+ "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
304
+ "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
305
+ "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
306
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
307
+ "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
308
+ "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
309
+ "model.layers.33.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
310
+ "model.layers.33.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
311
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
312
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
313
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
314
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
315
+ "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
316
+ "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
317
+ "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
318
+ "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
319
+ "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
320
+ "model.layers.34.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
321
+ "model.layers.34.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
322
+ "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
323
+ "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
324
+ "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
325
+ "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
326
+ "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
327
+ "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
328
+ "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
329
+ "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
330
+ "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
331
+ "model.layers.35.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
332
+ "model.layers.35.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
333
+ "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
334
+ "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
335
+ "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
336
+ "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
337
+ "model.layers.36.input_layernorm.weight": "model-00004-of-00004.safetensors",
338
+ "model.layers.36.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
339
+ "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
340
+ "model.layers.36.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
341
+ "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
342
+ "model.layers.36.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
343
+ "model.layers.36.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
344
+ "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
345
+ "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
346
+ "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
347
+ "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
348
+ "model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors",
349
+ "model.layers.37.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
350
+ "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
351
+ "model.layers.37.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
352
+ "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
353
+ "model.layers.37.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
354
+ "model.layers.37.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
355
+ "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
356
+ "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
357
+ "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
358
+ "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
359
+ "model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors",
360
+ "model.layers.38.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
361
+ "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
362
+ "model.layers.38.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
363
+ "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
364
+ "model.layers.38.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
365
+ "model.layers.38.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
366
+ "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
367
+ "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
368
+ "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
369
+ "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
370
+ "model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors",
371
+ "model.layers.39.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
372
+ "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
373
+ "model.layers.39.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
374
+ "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
375
+ "model.layers.39.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
376
+ "model.layers.39.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
377
+ "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
378
+ "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
379
+ "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
380
+ "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
381
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
382
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
383
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
384
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
385
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
386
+ "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
387
+ "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
388
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
389
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
390
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
391
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
392
+ "model.layers.40.input_layernorm.weight": "model-00004-of-00004.safetensors",
393
+ "model.layers.40.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
394
+ "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
395
+ "model.layers.40.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
396
+ "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
397
+ "model.layers.40.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
398
+ "model.layers.40.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
399
+ "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
400
+ "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
401
+ "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
402
+ "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
403
+ "model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors",
404
+ "model.layers.41.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
405
+ "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
406
+ "model.layers.41.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
407
+ "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
408
+ "model.layers.41.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
409
+ "model.layers.41.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
410
+ "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
411
+ "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
412
+ "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
413
+ "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
414
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
415
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
416
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
417
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
418
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
419
+ "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
420
+ "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
421
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
422
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
423
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
424
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
425
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
426
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
427
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
428
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
429
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
430
+ "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
431
+ "model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
432
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
433
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
434
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
435
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
436
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
437
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
438
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
439
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
440
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
441
+ "model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
442
+ "model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
443
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
444
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
445
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
446
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
447
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
448
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
449
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
450
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
451
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
452
+ "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
453
+ "model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
454
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
455
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
456
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
457
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
458
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
459
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
460
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
461
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
462
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
463
+ "model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
464
+ "model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
465
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
466
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
467
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
468
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
469
+ "model.norm.weight": "model-00004-of-00004.safetensors"
470
+ }
471
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<start_of_turn>",
4
+ "<end_of_turn>",
5
+ {
6
+ "content": "<|im_start|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ }
12
+ ],
13
+ "bos_token": {
14
+ "content": "<bos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "pad_token": {
28
+ "content": "<pad>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "unk_token": {
35
+ "content": "<unk>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ }
41
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44e21773a4721128c9c62ba09a4fcbab3288cda68ecc00683b044f280dc0f440
3
+ size 34356047
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f545c6099874ce0c5cf6e4ccecd5f2bce689852b576ddf9d49134081c9cb98
3
+ size 4241007
tokenizer_config.json ADDED
@@ -0,0 +1,1760 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<mask>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "5": {
46
+ "content": "<2mass>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "6": {
54
+ "content": "[@BOS@]",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "7": {
62
+ "content": "<|im_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "8": {
70
+ "content": "<|im_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "9": {
78
+ "content": "<unused2>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "10": {
86
+ "content": "<unused3>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "11": {
94
+ "content": "<unused4>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "12": {
102
+ "content": "<unused5>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "13": {
110
+ "content": "<unused6>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "14": {
118
+ "content": "<unused7>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "15": {
126
+ "content": "<unused8>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "16": {
134
+ "content": "<unused9>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "17": {
142
+ "content": "<unused10>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "18": {
150
+ "content": "<unused11>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "19": {
158
+ "content": "<unused12>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "20": {
166
+ "content": "<unused13>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "21": {
174
+ "content": "<unused14>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "22": {
182
+ "content": "<unused15>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "23": {
190
+ "content": "<unused16>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "24": {
198
+ "content": "<unused17>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "25": {
206
+ "content": "<unused18>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "26": {
214
+ "content": "<unused19>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "27": {
222
+ "content": "<unused20>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "28": {
230
+ "content": "<unused21>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "29": {
238
+ "content": "<unused22>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "30": {
246
+ "content": "<unused23>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "31": {
254
+ "content": "<unused24>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "32": {
262
+ "content": "<unused25>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "33": {
270
+ "content": "<unused26>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "34": {
278
+ "content": "<unused27>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "35": {
286
+ "content": "<unused28>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "36": {
294
+ "content": "<unused29>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "37": {
302
+ "content": "<unused30>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "38": {
310
+ "content": "<unused31>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ },
317
+ "39": {
318
+ "content": "<unused32>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": false
324
+ },
325
+ "40": {
326
+ "content": "<unused33>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": false
332
+ },
333
+ "41": {
334
+ "content": "<unused34>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": false
340
+ },
341
+ "42": {
342
+ "content": "<unused35>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": false
348
+ },
349
+ "43": {
350
+ "content": "<unused36>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": false
356
+ },
357
+ "44": {
358
+ "content": "<unused37>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": false
364
+ },
365
+ "45": {
366
+ "content": "<unused38>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": false
372
+ },
373
+ "46": {
374
+ "content": "<unused39>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": false
380
+ },
381
+ "47": {
382
+ "content": "<unused40>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": false
388
+ },
389
+ "48": {
390
+ "content": "<unused41>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": false
396
+ },
397
+ "49": {
398
+ "content": "<unused42>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": false
404
+ },
405
+ "50": {
406
+ "content": "<unused43>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": false
412
+ },
413
+ "51": {
414
+ "content": "<unused44>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": false
420
+ },
421
+ "52": {
422
+ "content": "<unused45>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": false
428
+ },
429
+ "53": {
430
+ "content": "<unused46>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": false
436
+ },
437
+ "54": {
438
+ "content": "<unused47>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": false
444
+ },
445
+ "55": {
446
+ "content": "<unused48>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": false
452
+ },
453
+ "56": {
454
+ "content": "<unused49>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": false
460
+ },
461
+ "57": {
462
+ "content": "<unused50>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": false
468
+ },
469
+ "58": {
470
+ "content": "<unused51>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": false
476
+ },
477
+ "59": {
478
+ "content": "<unused52>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": false
484
+ },
485
+ "60": {
486
+ "content": "<unused53>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": false
492
+ },
493
+ "61": {
494
+ "content": "<unused54>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": false
500
+ },
501
+ "62": {
502
+ "content": "<unused55>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": false
508
+ },
509
+ "63": {
510
+ "content": "<unused56>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": false
516
+ },
517
+ "64": {
518
+ "content": "<unused57>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": false
524
+ },
525
+ "65": {
526
+ "content": "<unused58>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": false
532
+ },
533
+ "66": {
534
+ "content": "<unused59>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": false
540
+ },
541
+ "67": {
542
+ "content": "<unused60>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": false
548
+ },
549
+ "68": {
550
+ "content": "<unused61>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": false
556
+ },
557
+ "69": {
558
+ "content": "<unused62>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": false
564
+ },
565
+ "70": {
566
+ "content": "<unused63>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": false
572
+ },
573
+ "71": {
574
+ "content": "<unused64>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": false
580
+ },
581
+ "72": {
582
+ "content": "<unused65>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": false
588
+ },
589
+ "73": {
590
+ "content": "<unused66>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": false
596
+ },
597
+ "74": {
598
+ "content": "<unused67>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": false
604
+ },
605
+ "75": {
606
+ "content": "<unused68>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": false
612
+ },
613
+ "76": {
614
+ "content": "<unused69>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": false
620
+ },
621
+ "77": {
622
+ "content": "<unused70>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": false
628
+ },
629
+ "78": {
630
+ "content": "<unused71>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": false
636
+ },
637
+ "79": {
638
+ "content": "<unused72>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": false
644
+ },
645
+ "80": {
646
+ "content": "<unused73>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": false
652
+ },
653
+ "81": {
654
+ "content": "<unused74>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": false
660
+ },
661
+ "82": {
662
+ "content": "<unused75>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": false
668
+ },
669
+ "83": {
670
+ "content": "<unused76>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": false
676
+ },
677
+ "84": {
678
+ "content": "<unused77>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": false
684
+ },
685
+ "85": {
686
+ "content": "<unused78>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": false
692
+ },
693
+ "86": {
694
+ "content": "<unused79>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": false
700
+ },
701
+ "87": {
702
+ "content": "<unused80>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": false
708
+ },
709
+ "88": {
710
+ "content": "<unused81>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": false
716
+ },
717
+ "89": {
718
+ "content": "<unused82>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": false
724
+ },
725
+ "90": {
726
+ "content": "<unused83>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": false
732
+ },
733
+ "91": {
734
+ "content": "<unused84>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": false
740
+ },
741
+ "92": {
742
+ "content": "<unused85>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": false
748
+ },
749
+ "93": {
750
+ "content": "<unused86>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": false
756
+ },
757
+ "94": {
758
+ "content": "<unused87>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": false
764
+ },
765
+ "95": {
766
+ "content": "<unused88>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": false
772
+ },
773
+ "96": {
774
+ "content": "<unused89>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": false
780
+ },
781
+ "97": {
782
+ "content": "<unused90>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": false
788
+ },
789
+ "98": {
790
+ "content": "<unused91>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": false
796
+ },
797
+ "99": {
798
+ "content": "<unused92>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": false
804
+ },
805
+ "100": {
806
+ "content": "<unused93>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": false
812
+ },
813
+ "101": {
814
+ "content": "<unused94>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": false
820
+ },
821
+ "102": {
822
+ "content": "<unused95>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": false
828
+ },
829
+ "103": {
830
+ "content": "<unused96>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": false
836
+ },
837
+ "104": {
838
+ "content": "<unused97>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": false
844
+ },
845
+ "105": {
846
+ "content": "<unused98>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": false
852
+ },
853
+ "106": {
854
+ "content": "<start_of_turn>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "107": {
862
+ "content": "<end_of_turn>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "108": {
870
+ "content": "\n",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": false
876
+ },
877
+ "109": {
878
+ "content": "\n\n",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": false
884
+ },
885
+ "110": {
886
+ "content": "\n\n\n",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": false
892
+ },
893
+ "111": {
894
+ "content": "\n\n\n\n",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": false
900
+ },
901
+ "112": {
902
+ "content": "\n\n\n\n\n",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": false
908
+ },
909
+ "113": {
910
+ "content": "\n\n\n\n\n\n",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": false
916
+ },
917
+ "114": {
918
+ "content": "\n\n\n\n\n\n\n",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": false
924
+ },
925
+ "115": {
926
+ "content": "\n\n\n\n\n\n\n\n",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": false
932
+ },
933
+ "116": {
934
+ "content": "\n\n\n\n\n\n\n\n\n",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": false
940
+ },
941
+ "117": {
942
+ "content": "\n\n\n\n\n\n\n\n\n\n",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": false
948
+ },
949
+ "118": {
950
+ "content": "\n\n\n\n\n\n\n\n\n\n\n",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": false
956
+ },
957
+ "119": {
958
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": false
964
+ },
965
+ "120": {
966
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": false
972
+ },
973
+ "121": {
974
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": false
980
+ },
981
+ "122": {
982
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": false
988
+ },
989
+ "123": {
990
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": false
996
+ },
997
+ "124": {
998
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": false
1004
+ },
1005
+ "125": {
1006
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": false
1012
+ },
1013
+ "126": {
1014
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": false
1020
+ },
1021
+ "127": {
1022
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": false
1028
+ },
1029
+ "128": {
1030
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": false
1036
+ },
1037
+ "129": {
1038
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": false
1044
+ },
1045
+ "130": {
1046
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": false
1052
+ },
1053
+ "131": {
1054
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": false
1060
+ },
1061
+ "132": {
1062
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": false
1068
+ },
1069
+ "133": {
1070
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": false
1076
+ },
1077
+ "134": {
1078
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": false
1084
+ },
1085
+ "135": {
1086
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": false
1092
+ },
1093
+ "136": {
1094
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": false
1100
+ },
1101
+ "137": {
1102
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": false
1108
+ },
1109
+ "138": {
1110
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": false
1116
+ },
1117
+ "139": {
1118
+ "content": "▁▁",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": false
1124
+ },
1125
+ "140": {
1126
+ "content": "▁▁▁",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": false
1132
+ },
1133
+ "141": {
1134
+ "content": "▁▁▁▁",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": false
1140
+ },
1141
+ "142": {
1142
+ "content": "▁▁▁▁▁",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": false
1148
+ },
1149
+ "143": {
1150
+ "content": "▁▁▁▁▁▁",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": false
1156
+ },
1157
+ "144": {
1158
+ "content": "▁▁▁▁▁▁▁",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": false
1164
+ },
1165
+ "145": {
1166
+ "content": "▁▁▁▁▁▁▁▁",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": false
1172
+ },
1173
+ "146": {
1174
+ "content": "▁▁▁▁▁▁▁▁▁",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": false
1180
+ },
1181
+ "147": {
1182
+ "content": "▁▁▁▁▁▁▁▁▁▁",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": false
1188
+ },
1189
+ "148": {
1190
+ "content": "▁▁▁▁▁▁▁▁▁▁▁",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": false
1196
+ },
1197
+ "149": {
1198
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": false
1204
+ },
1205
+ "150": {
1206
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": false
1212
+ },
1213
+ "151": {
1214
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": false
1220
+ },
1221
+ "152": {
1222
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": false
1228
+ },
1229
+ "153": {
1230
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": false
1236
+ },
1237
+ "154": {
1238
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": false
1244
+ },
1245
+ "155": {
1246
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": false
1252
+ },
1253
+ "156": {
1254
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": false
1260
+ },
1261
+ "157": {
1262
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": false
1268
+ },
1269
+ "158": {
1270
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": false
1276
+ },
1277
+ "159": {
1278
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": false
1284
+ },
1285
+ "160": {
1286
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": false
1292
+ },
1293
+ "161": {
1294
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": false
1300
+ },
1301
+ "162": {
1302
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": false
1308
+ },
1309
+ "163": {
1310
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": false
1316
+ },
1317
+ "164": {
1318
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": false
1324
+ },
1325
+ "165": {
1326
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": false
1332
+ },
1333
+ "166": {
1334
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": false
1340
+ },
1341
+ "167": {
1342
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": false
1348
+ },
1349
+ "168": {
1350
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": false
1356
+ },
1357
+ "169": {
1358
+ "content": "<table>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": false
1364
+ },
1365
+ "170": {
1366
+ "content": "<caption>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": false
1372
+ },
1373
+ "171": {
1374
+ "content": "<thead>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": false
1380
+ },
1381
+ "172": {
1382
+ "content": "<tbody>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": false
1388
+ },
1389
+ "173": {
1390
+ "content": "<tfoot>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": false
1396
+ },
1397
+ "174": {
1398
+ "content": "<tr>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": false
1404
+ },
1405
+ "175": {
1406
+ "content": "<th>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": false
1412
+ },
1413
+ "176": {
1414
+ "content": "<td>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": false
1420
+ },
1421
+ "177": {
1422
+ "content": "</table>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": false
1428
+ },
1429
+ "178": {
1430
+ "content": "</caption>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": false
1436
+ },
1437
+ "179": {
1438
+ "content": "</thead>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": false
1444
+ },
1445
+ "180": {
1446
+ "content": "</tbody>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": false
1452
+ },
1453
+ "181": {
1454
+ "content": "</tfoot>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": false
1460
+ },
1461
+ "182": {
1462
+ "content": "</tr>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": false
1468
+ },
1469
+ "183": {
1470
+ "content": "</th>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": false
1476
+ },
1477
+ "184": {
1478
+ "content": "</td>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": false
1484
+ },
1485
+ "185": {
1486
+ "content": "<h1>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": false
1492
+ },
1493
+ "186": {
1494
+ "content": "<h2>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": false
1500
+ },
1501
+ "187": {
1502
+ "content": "<h3>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": false
1508
+ },
1509
+ "188": {
1510
+ "content": "<h4>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": false
1516
+ },
1517
+ "189": {
1518
+ "content": "<h5>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": false
1524
+ },
1525
+ "190": {
1526
+ "content": "<h6>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": false
1532
+ },
1533
+ "191": {
1534
+ "content": "<blockquote>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": false
1540
+ },
1541
+ "192": {
1542
+ "content": "</h1>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": false
1548
+ },
1549
+ "193": {
1550
+ "content": "</h2>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": false
1556
+ },
1557
+ "194": {
1558
+ "content": "</h3>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": false
1564
+ },
1565
+ "195": {
1566
+ "content": "</h4>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": false
1572
+ },
1573
+ "196": {
1574
+ "content": "</h5>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": false
1580
+ },
1581
+ "197": {
1582
+ "content": "</h6>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": false
1588
+ },
1589
+ "198": {
1590
+ "content": "</blockquote>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": false
1596
+ },
1597
+ "199": {
1598
+ "content": "<strong>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": false
1604
+ },
1605
+ "200": {
1606
+ "content": "<em>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": false
1612
+ },
1613
+ "201": {
1614
+ "content": "<b>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": false
1620
+ },
1621
+ "202": {
1622
+ "content": "<i>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": false
1628
+ },
1629
+ "203": {
1630
+ "content": "<u>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": false
1636
+ },
1637
+ "204": {
1638
+ "content": "<s>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": false
1644
+ },
1645
+ "205": {
1646
+ "content": "<sub>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": false
1652
+ },
1653
+ "206": {
1654
+ "content": "<sup>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": false
1660
+ },
1661
+ "207": {
1662
+ "content": "<code>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": false
1668
+ },
1669
+ "208": {
1670
+ "content": "</strong>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": false
1676
+ },
1677
+ "209": {
1678
+ "content": "</em>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": false
1684
+ },
1685
+ "210": {
1686
+ "content": "</b>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": false
1692
+ },
1693
+ "211": {
1694
+ "content": "</i>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": false
1700
+ },
1701
+ "212": {
1702
+ "content": "</u>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": false
1708
+ },
1709
+ "213": {
1710
+ "content": "</s>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": false
1716
+ },
1717
+ "214": {
1718
+ "content": "</sub>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": false
1724
+ },
1725
+ "215": {
1726
+ "content": "</sup>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": false
1732
+ },
1733
+ "216": {
1734
+ "content": "</code>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": false
1740
+ }
1741
+ },
1742
+ "additional_special_tokens": [
1743
+ "<start_of_turn>",
1744
+ "<end_of_turn>",
1745
+ "<|im_start|>"
1746
+ ],
1747
+ "bos_token": "<bos>",
1748
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
1749
+ "clean_up_tokenization_spaces": false,
1750
+ "eos_token": "<|im_end|>",
1751
+ "model_max_length": 1000000000000000019884624838656,
1752
+ "pad_token": "<pad>",
1753
+ "padding_side": "right",
1754
+ "sp_model_kwargs": {},
1755
+ "spaces_between_special_tokens": false,
1756
+ "split_special_tokens": false,
1757
+ "tokenizer_class": "GemmaTokenizer",
1758
+ "unk_token": "<unk>",
1759
+ "use_default_system_prompt": false
1760
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "total_flos": 648773332107264.0,
4
+ "train_loss": 0.9660957064397535,
5
+ "train_runtime": 3882.5924,
6
+ "train_samples_per_second": 5.59,
7
+ "train_steps_per_second": 0.234
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 908, "loss": 1.4512, "learning_rate": 3.296703296703297e-07, "epoch": 0.04405286343612335, "percentage": 1.1, "elapsed_time": "0:00:44", "remaining_time": "1:06:25"}
2
+ {"current_steps": 20, "total_steps": 908, "loss": 1.4723, "learning_rate": 6.593406593406594e-07, "epoch": 0.0881057268722467, "percentage": 2.2, "elapsed_time": "0:01:27", "remaining_time": "1:04:32"}
3
+ {"current_steps": 30, "total_steps": 908, "loss": 1.3932, "learning_rate": 9.890109890109891e-07, "epoch": 0.13215859030837004, "percentage": 3.3, "elapsed_time": "0:02:10", "remaining_time": "1:03:24"}
4
+ {"current_steps": 40, "total_steps": 908, "loss": 1.3093, "learning_rate": 1.3186813186813187e-06, "epoch": 0.1762114537444934, "percentage": 4.41, "elapsed_time": "0:02:52", "remaining_time": "1:02:26"}
5
+ {"current_steps": 50, "total_steps": 908, "loss": 1.2687, "learning_rate": 1.6483516483516486e-06, "epoch": 0.22026431718061673, "percentage": 5.51, "elapsed_time": "0:03:35", "remaining_time": "1:01:34"}
6
+ {"current_steps": 60, "total_steps": 908, "loss": 1.2427, "learning_rate": 1.9780219780219782e-06, "epoch": 0.2643171806167401, "percentage": 6.61, "elapsed_time": "0:04:17", "remaining_time": "1:00:46"}
7
+ {"current_steps": 70, "total_steps": 908, "loss": 1.2286, "learning_rate": 2.307692307692308e-06, "epoch": 0.30837004405286345, "percentage": 7.71, "elapsed_time": "0:05:00", "remaining_time": "0:59:59"}
8
+ {"current_steps": 80, "total_steps": 908, "loss": 1.1827, "learning_rate": 2.6373626373626375e-06, "epoch": 0.3524229074889868, "percentage": 8.81, "elapsed_time": "0:05:43", "remaining_time": "0:59:13"}
9
+ {"current_steps": 90, "total_steps": 908, "loss": 1.1941, "learning_rate": 2.9670329670329673e-06, "epoch": 0.3964757709251101, "percentage": 9.91, "elapsed_time": "0:06:26", "remaining_time": "0:58:29"}
10
+ {"current_steps": 100, "total_steps": 908, "loss": 1.1731, "learning_rate": 2.999101829950985e-06, "epoch": 0.44052863436123346, "percentage": 11.01, "elapsed_time": "0:07:08", "remaining_time": "0:57:45"}
11
+ {"current_steps": 110, "total_steps": 908, "loss": 1.1148, "learning_rate": 2.9959984254953274e-06, "epoch": 0.4845814977973568, "percentage": 12.11, "elapsed_time": "0:07:51", "remaining_time": "0:57:01"}
12
+ {"current_steps": 120, "total_steps": 908, "loss": 1.191, "learning_rate": 2.9906832852013294e-06, "epoch": 0.5286343612334802, "percentage": 13.22, "elapsed_time": "0:08:34", "remaining_time": "0:56:17"}
13
+ {"current_steps": 130, "total_steps": 908, "loss": 1.1818, "learning_rate": 2.9831642671563205e-06, "epoch": 0.5726872246696035, "percentage": 14.32, "elapsed_time": "0:09:17", "remaining_time": "0:55:33"}
14
+ {"current_steps": 140, "total_steps": 908, "loss": 1.1969, "learning_rate": 2.9734524877367604e-06, "epoch": 0.6167400881057269, "percentage": 15.42, "elapsed_time": "0:09:59", "remaining_time": "0:54:50"}
15
+ {"current_steps": 150, "total_steps": 908, "loss": 1.1203, "learning_rate": 2.961562305173399e-06, "epoch": 0.6607929515418502, "percentage": 16.52, "elapsed_time": "0:10:42", "remaining_time": "0:54:06"}
16
+ {"current_steps": 160, "total_steps": 908, "loss": 1.2301, "learning_rate": 2.9475112983235753e-06, "epoch": 0.7048458149779736, "percentage": 17.62, "elapsed_time": "0:11:25", "remaining_time": "0:53:23"}
17
+ {"current_steps": 170, "total_steps": 908, "loss": 1.183, "learning_rate": 2.9313202406820232e-06, "epoch": 0.748898678414097, "percentage": 18.72, "elapsed_time": "0:12:07", "remaining_time": "0:52:39"}
18
+ {"current_steps": 180, "total_steps": 908, "loss": 1.1304, "learning_rate": 2.9130130696686196e-06, "epoch": 0.7929515418502202, "percentage": 19.82, "elapsed_time": "0:12:50", "remaining_time": "0:51:56"}
19
+ {"current_steps": 190, "total_steps": 908, "loss": 1.1618, "learning_rate": 2.8926168512384744e-06, "epoch": 0.8370044052863436, "percentage": 20.93, "elapsed_time": "0:13:33", "remaining_time": "0:51:13"}
20
+ {"current_steps": 200, "total_steps": 908, "loss": 1.1491, "learning_rate": 2.870161739866686e-06, "epoch": 0.8810572687224669, "percentage": 22.03, "elapsed_time": "0:14:15", "remaining_time": "0:50:30"}
21
+ {"current_steps": 210, "total_steps": 908, "loss": 1.145, "learning_rate": 2.845680933966922e-06, "epoch": 0.9251101321585903, "percentage": 23.13, "elapsed_time": "0:14:58", "remaining_time": "0:49:46"}
22
+ {"current_steps": 220, "total_steps": 908, "loss": 1.2206, "learning_rate": 2.8192106268097337e-06, "epoch": 0.9691629955947136, "percentage": 24.23, "elapsed_time": "0:15:41", "remaining_time": "0:49:03"}
23
+ {"current_steps": 230, "total_steps": 908, "loss": 1.133, "learning_rate": 2.7907899530131763e-06, "epoch": 1.013215859030837, "percentage": 25.33, "elapsed_time": "0:16:23", "remaining_time": "0:48:20"}
24
+ {"current_steps": 240, "total_steps": 908, "loss": 1.0399, "learning_rate": 2.7604609306848312e-06, "epoch": 1.0572687224669604, "percentage": 26.43, "elapsed_time": "0:17:06", "remaining_time": "0:47:37"}
25
+ {"current_steps": 250, "total_steps": 908, "loss": 1.007, "learning_rate": 2.7282683993007865e-06, "epoch": 1.1013215859030836, "percentage": 27.53, "elapsed_time": "0:17:49", "remaining_time": "0:46:54"}
26
+ {"current_steps": 260, "total_steps": 908, "loss": 1.0139, "learning_rate": 2.6942599534133987e-06, "epoch": 1.145374449339207, "percentage": 28.63, "elapsed_time": "0:18:31", "remaining_time": "0:46:11"}
27
+ {"current_steps": 270, "total_steps": 908, "loss": 1.0493, "learning_rate": 2.658485872285863e-06, "epoch": 1.1894273127753303, "percentage": 29.74, "elapsed_time": "0:19:14", "remaining_time": "0:45:28"}
28
+ {"current_steps": 280, "total_steps": 908, "loss": 0.9478, "learning_rate": 2.6209990455576105e-06, "epoch": 1.2334801762114538, "percentage": 30.84, "elapsed_time": "0:19:57", "remaining_time": "0:44:44"}
29
+ {"current_steps": 290, "total_steps": 908, "loss": 1.0108, "learning_rate": 2.5818548950504342e-06, "epoch": 1.277533039647577, "percentage": 31.94, "elapsed_time": "0:20:39", "remaining_time": "0:44:01"}
30
+ {"current_steps": 300, "total_steps": 908, "loss": 1.0294, "learning_rate": 2.541111292830951e-06, "epoch": 1.3215859030837005, "percentage": 33.04, "elapsed_time": "0:21:22", "remaining_time": "0:43:18"}
31
+ {"current_steps": 310, "total_steps": 908, "loss": 0.9748, "learning_rate": 2.4988284756505333e-06, "epoch": 1.3656387665198237, "percentage": 34.14, "elapsed_time": "0:22:04", "remaining_time": "0:42:35"}
32
+ {"current_steps": 320, "total_steps": 908, "loss": 1.0054, "learning_rate": 2.455068955889216e-06, "epoch": 1.4096916299559472, "percentage": 35.24, "elapsed_time": "0:22:47", "remaining_time": "0:41:52"}
33
+ {"current_steps": 330, "total_steps": 908, "loss": 1.0155, "learning_rate": 2.4098974291352257e-06, "epoch": 1.4537444933920705, "percentage": 36.34, "elapsed_time": "0:23:30", "remaining_time": "0:41:09"}
34
+ {"current_steps": 340, "total_steps": 908, "loss": 1.0677, "learning_rate": 2.3633806785367873e-06, "epoch": 1.497797356828194, "percentage": 37.44, "elapsed_time": "0:24:12", "remaining_time": "0:40:26"}
35
+ {"current_steps": 350, "total_steps": 908, "loss": 0.987, "learning_rate": 2.315587476067607e-06, "epoch": 1.5418502202643172, "percentage": 38.55, "elapsed_time": "0:24:55", "remaining_time": "0:39:43"}
36
+ {"current_steps": 360, "total_steps": 908, "loss": 1.0526, "learning_rate": 2.2665884808520048e-06, "epoch": 1.5859030837004404, "percentage": 39.65, "elapsed_time": "0:25:37", "remaining_time": "0:39:00"}
37
+ {"current_steps": 370, "total_steps": 908, "loss": 1.0304, "learning_rate": 2.2164561347000213e-06, "epoch": 1.6299559471365639, "percentage": 40.75, "elapsed_time": "0:26:20", "remaining_time": "0:38:17"}
38
+ {"current_steps": 380, "total_steps": 908, "loss": 0.9921, "learning_rate": 2.1652645550069394e-06, "epoch": 1.6740088105726874, "percentage": 41.85, "elapsed_time": "0:27:02", "remaining_time": "0:37:34"}
39
+ {"current_steps": 390, "total_steps": 908, "loss": 1.0062, "learning_rate": 2.113089425175561e-06, "epoch": 1.7180616740088106, "percentage": 42.95, "elapsed_time": "0:27:45", "remaining_time": "0:36:51"}
40
+ {"current_steps": 400, "total_steps": 908, "loss": 0.993, "learning_rate": 2.0600078827232473e-06, "epoch": 1.7621145374449338, "percentage": 44.05, "elapsed_time": "0:28:27", "remaining_time": "0:36:09"}
41
+ {"current_steps": 410, "total_steps": 908, "loss": 0.989, "learning_rate": 2.006098405239142e-06, "epoch": 1.8061674008810573, "percentage": 45.15, "elapsed_time": "0:29:10", "remaining_time": "0:35:26"}
42
+ {"current_steps": 420, "total_steps": 908, "loss": 1.0184, "learning_rate": 1.95144069436019e-06, "epoch": 1.8502202643171806, "percentage": 46.26, "elapsed_time": "0:29:53", "remaining_time": "0:34:43"}
43
+ {"current_steps": 430, "total_steps": 908, "loss": 1.0655, "learning_rate": 1.896115557937476e-06, "epoch": 1.894273127753304, "percentage": 47.36, "elapsed_time": "0:30:35", "remaining_time": "0:34:00"}
44
+ {"current_steps": 440, "total_steps": 908, "loss": 1.0139, "learning_rate": 1.8402047905671065e-06, "epoch": 1.9383259911894273, "percentage": 48.46, "elapsed_time": "0:31:18", "remaining_time": "0:33:17"}
45
+ {"current_steps": 450, "total_steps": 908, "loss": 1.0103, "learning_rate": 1.7837910526622437e-06, "epoch": 1.9823788546255505, "percentage": 49.56, "elapsed_time": "0:32:00", "remaining_time": "0:32:34"}
46
+ {"current_steps": 460, "total_steps": 908, "loss": 0.8977, "learning_rate": 1.726957748245093e-06, "epoch": 2.026431718061674, "percentage": 50.66, "elapsed_time": "0:32:43", "remaining_time": "0:31:52"}
47
+ {"current_steps": 470, "total_steps": 908, "loss": 0.8438, "learning_rate": 1.6697889016395088e-06, "epoch": 2.0704845814977975, "percentage": 51.76, "elapsed_time": "0:33:25", "remaining_time": "0:31:09"}
48
+ {"current_steps": 480, "total_steps": 908, "loss": 0.9008, "learning_rate": 1.6123690332465296e-06, "epoch": 2.1145374449339207, "percentage": 52.86, "elapsed_time": "0:34:08", "remaining_time": "0:30:26"}
49
+ {"current_steps": 490, "total_steps": 908, "loss": 0.8176, "learning_rate": 1.5547830345864886e-06, "epoch": 2.158590308370044, "percentage": 53.96, "elapsed_time": "0:34:50", "remaining_time": "0:29:43"}
50
+ {"current_steps": 500, "total_steps": 908, "loss": 0.8901, "learning_rate": 1.4971160427924554e-06, "epoch": 2.202643171806167, "percentage": 55.07, "elapsed_time": "0:35:33", "remaining_time": "0:29:00"}
51
+ {"current_steps": 510, "total_steps": 908, "loss": 0.8247, "learning_rate": 1.439453314740552e-06, "epoch": 2.246696035242291, "percentage": 56.17, "elapsed_time": "0:36:22", "remaining_time": "0:28:23"}
52
+ {"current_steps": 520, "total_steps": 908, "loss": 0.8294, "learning_rate": 1.381880101003235e-06, "epoch": 2.290748898678414, "percentage": 57.27, "elapsed_time": "0:37:04", "remaining_time": "0:27:40"}
53
+ {"current_steps": 530, "total_steps": 908, "loss": 0.9032, "learning_rate": 1.3244815198119024e-06, "epoch": 2.3348017621145374, "percentage": 58.37, "elapsed_time": "0:37:47", "remaining_time": "0:26:57"}
54
+ {"current_steps": 540, "total_steps": 908, "loss": 0.8862, "learning_rate": 1.2673424312151519e-06, "epoch": 2.3788546255506606, "percentage": 59.47, "elapsed_time": "0:38:29", "remaining_time": "0:26:14"}
55
+ {"current_steps": 550, "total_steps": 908, "loss": 0.894, "learning_rate": 1.2105473116187517e-06, "epoch": 2.4229074889867843, "percentage": 60.57, "elapsed_time": "0:39:12", "remaining_time": "0:25:31"}
56
+ {"current_steps": 560, "total_steps": 908, "loss": 0.8126, "learning_rate": 1.154180128892796e-06, "epoch": 2.4669603524229076, "percentage": 61.67, "elapsed_time": "0:39:54", "remaining_time": "0:24:48"}
57
+ {"current_steps": 570, "total_steps": 908, "loss": 0.8059, "learning_rate": 1.0983242182307033e-06, "epoch": 2.511013215859031, "percentage": 62.78, "elapsed_time": "0:40:37", "remaining_time": "0:24:05"}
58
+ {"current_steps": 580, "total_steps": 908, "loss": 0.8959, "learning_rate": 1.0430621589435803e-06, "epoch": 2.555066079295154, "percentage": 63.88, "elapsed_time": "0:41:20", "remaining_time": "0:23:22"}
59
+ {"current_steps": 590, "total_steps": 908, "loss": 0.8393, "learning_rate": 9.884756523721117e-07, "epoch": 2.5991189427312777, "percentage": 64.98, "elapsed_time": "0:42:02", "remaining_time": "0:22:39"}
60
+ {"current_steps": 600, "total_steps": 908, "loss": 0.862, "learning_rate": 9.346454010964724e-07, "epoch": 2.643171806167401, "percentage": 66.08, "elapsed_time": "0:42:45", "remaining_time": "0:21:56"}
61
+ {"current_steps": 610, "total_steps": 908, "loss": 0.859, "learning_rate": 8.816509896228376e-07, "epoch": 2.6872246696035242, "percentage": 67.18, "elapsed_time": "0:43:27", "remaining_time": "0:21:13"}
62
+ {"current_steps": 620, "total_steps": 908, "loss": 0.8348, "learning_rate": 8.295707667228987e-07, "epoch": 2.7312775330396475, "percentage": 68.28, "elapsed_time": "0:44:10", "remaining_time": "0:20:31"}
63
+ {"current_steps": 630, "total_steps": 908, "loss": 0.8668, "learning_rate": 7.784817296003237e-07, "epoch": 2.7753303964757707, "percentage": 69.38, "elapsed_time": "0:44:52", "remaining_time": "0:19:48"}
64
+ {"current_steps": 640, "total_steps": 908, "loss": 0.8627, "learning_rate": 7.284594100554311e-07, "epoch": 2.8193832599118944, "percentage": 70.48, "elapsed_time": "0:45:35", "remaining_time": "0:19:05"}
65
+ {"current_steps": 650, "total_steps": 908, "loss": 0.855, "learning_rate": 6.7957776281636e-07, "epoch": 2.8634361233480177, "percentage": 71.59, "elapsed_time": "0:46:17", "remaining_time": "0:18:22"}
66
+ {"current_steps": 660, "total_steps": 908, "loss": 0.8849, "learning_rate": 6.31909056201842e-07, "epoch": 2.907488986784141, "percentage": 72.69, "elapsed_time": "0:47:00", "remaining_time": "0:17:39"}
67
+ {"current_steps": 670, "total_steps": 908, "loss": 0.8629, "learning_rate": 5.855237652772183e-07, "epoch": 2.951541850220264, "percentage": 73.79, "elapsed_time": "0:47:43", "remaining_time": "0:16:57"}
68
+ {"current_steps": 680, "total_steps": 908, "loss": 0.8796, "learning_rate": 5.404904676616635e-07, "epoch": 2.995594713656388, "percentage": 74.89, "elapsed_time": "0:48:25", "remaining_time": "0:16:14"}
69
+ {"current_steps": 690, "total_steps": 908, "loss": 0.779, "learning_rate": 4.968757421406609e-07, "epoch": 3.039647577092511, "percentage": 75.99, "elapsed_time": "0:49:08", "remaining_time": "0:15:31"}
70
+ {"current_steps": 700, "total_steps": 908, "loss": 0.7582, "learning_rate": 4.547440702336238e-07, "epoch": 3.0837004405286343, "percentage": 77.09, "elapsed_time": "0:49:50", "remaining_time": "0:14:48"}
71
+ {"current_steps": 710, "total_steps": 908, "loss": 0.7063, "learning_rate": 4.1415774086218277e-07, "epoch": 3.1277533039647576, "percentage": 78.19, "elapsed_time": "0:50:33", "remaining_time": "0:14:05"}
72
+ {"current_steps": 720, "total_steps": 908, "loss": 0.752, "learning_rate": 3.7517675826009083e-07, "epoch": 3.171806167400881, "percentage": 79.3, "elapsed_time": "0:51:15", "remaining_time": "0:13:23"}
73
+ {"current_steps": 730, "total_steps": 908, "loss": 0.7829, "learning_rate": 3.378587532608872e-07, "epoch": 3.2158590308370045, "percentage": 80.4, "elapsed_time": "0:51:58", "remaining_time": "0:12:40"}
74
+ {"current_steps": 740, "total_steps": 908, "loss": 0.72, "learning_rate": 3.0225889809447925e-07, "epoch": 3.2599118942731278, "percentage": 81.5, "elapsed_time": "0:52:41", "remaining_time": "0:11:57"}
75
+ {"current_steps": 750, "total_steps": 908, "loss": 0.7852, "learning_rate": 2.684298248186077e-07, "epoch": 3.303964757709251, "percentage": 82.6, "elapsed_time": "0:53:23", "remaining_time": "0:11:14"}
76
+ {"current_steps": 760, "total_steps": 908, "loss": 0.7912, "learning_rate": 2.3642154750579275e-07, "epoch": 3.3480176211453743, "percentage": 83.7, "elapsed_time": "0:54:06", "remaining_time": "0:10:32"}
77
+ {"current_steps": 770, "total_steps": 908, "loss": 0.7456, "learning_rate": 2.0628138830079696e-07, "epoch": 3.392070484581498, "percentage": 84.8, "elapsed_time": "0:54:48", "remaining_time": "0:09:49"}
78
+ {"current_steps": 780, "total_steps": 908, "loss": 0.7654, "learning_rate": 1.7805390745792993e-07, "epoch": 3.436123348017621, "percentage": 85.9, "elapsed_time": "0:55:31", "remaining_time": "0:09:06"}
79
+ {"current_steps": 790, "total_steps": 908, "loss": 0.7437, "learning_rate": 1.5178083746162667e-07, "epoch": 3.4801762114537445, "percentage": 87.0, "elapsed_time": "0:56:13", "remaining_time": "0:08:23"}
80
+ {"current_steps": 800, "total_steps": 908, "loss": 0.7834, "learning_rate": 1.2750102132769738e-07, "epoch": 3.5242290748898677, "percentage": 88.11, "elapsed_time": "0:56:56", "remaining_time": "0:07:41"}
81
+ {"current_steps": 810, "total_steps": 908, "loss": 0.7943, "learning_rate": 1.0525035517647014e-07, "epoch": 3.568281938325991, "percentage": 89.21, "elapsed_time": "0:57:39", "remaining_time": "0:06:58"}
82
+ {"current_steps": 820, "total_steps": 908, "loss": 0.7826, "learning_rate": 8.50617351627232e-08, "epoch": 3.6123348017621146, "percentage": 90.31, "elapsed_time": "0:58:21", "remaining_time": "0:06:15"}
83
+ {"current_steps": 830, "total_steps": 908, "loss": 0.8379, "learning_rate": 6.696500884087259e-08, "epoch": 3.656387665198238, "percentage": 91.41, "elapsed_time": "0:59:04", "remaining_time": "0:05:33"}
84
+ {"current_steps": 840, "total_steps": 908, "loss": 0.7614, "learning_rate": 5.0986931037314666e-08, "epoch": 3.700440528634361, "percentage": 92.51, "elapsed_time": "0:59:46", "remaining_time": "0:04:50"}
85
+ {"current_steps": 850, "total_steps": 908, "loss": 0.8152, "learning_rate": 3.7151124295163374e-08, "epoch": 3.744493392070485, "percentage": 93.61, "elapsed_time": "1:00:29", "remaining_time": "0:04:07"}
86
+ {"current_steps": 860, "total_steps": 908, "loss": 0.7517, "learning_rate": 2.5478043949868192e-08, "epoch": 3.788546255506608, "percentage": 94.71, "elapsed_time": "1:01:12", "remaining_time": "0:03:24"}
87
+ {"current_steps": 870, "total_steps": 908, "loss": 0.7697, "learning_rate": 1.5984947887334623e-08, "epoch": 3.8325991189427313, "percentage": 95.81, "elapsed_time": "1:01:54", "remaining_time": "0:02:42"}
88
+ {"current_steps": 880, "total_steps": 908, "loss": 0.7506, "learning_rate": 8.685871029272318e-09, "epoch": 3.8766519823788546, "percentage": 96.92, "elapsed_time": "1:02:37", "remaining_time": "0:01:59"}
89
+ {"current_steps": 890, "total_steps": 908, "loss": 0.7273, "learning_rate": 3.5916045834781253e-09, "epoch": 3.920704845814978, "percentage": 98.02, "elapsed_time": "1:03:19", "remaining_time": "0:01:16"}
90
+ {"current_steps": 900, "total_steps": 908, "loss": 0.8123, "learning_rate": 7.096800897425371e-10, "epoch": 3.964757709251101, "percentage": 99.12, "elapsed_time": "1:04:02", "remaining_time": "0:00:34"}
91
+ {"current_steps": 908, "total_steps": 908, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "1:04:42", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,672 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 908,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04405286343612335,
13
+ "grad_norm": 10.519313963525699,
14
+ "learning_rate": 3.296703296703297e-07,
15
+ "loss": 1.4512,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.0881057268722467,
20
+ "grad_norm": 5.275494720043015,
21
+ "learning_rate": 6.593406593406594e-07,
22
+ "loss": 1.4723,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.13215859030837004,
27
+ "grad_norm": 1.8226315526905816,
28
+ "learning_rate": 9.890109890109891e-07,
29
+ "loss": 1.3932,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.1762114537444934,
34
+ "grad_norm": 2.044759232085493,
35
+ "learning_rate": 1.3186813186813187e-06,
36
+ "loss": 1.3093,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.22026431718061673,
41
+ "grad_norm": 1.7807644006153884,
42
+ "learning_rate": 1.6483516483516486e-06,
43
+ "loss": 1.2687,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.2643171806167401,
48
+ "grad_norm": 1.5054649369651574,
49
+ "learning_rate": 1.9780219780219782e-06,
50
+ "loss": 1.2427,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.30837004405286345,
55
+ "grad_norm": 1.645138466222819,
56
+ "learning_rate": 2.307692307692308e-06,
57
+ "loss": 1.2286,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.3524229074889868,
62
+ "grad_norm": 1.4999909747158735,
63
+ "learning_rate": 2.6373626373626375e-06,
64
+ "loss": 1.1827,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.3964757709251101,
69
+ "grad_norm": 1.7582872706972468,
70
+ "learning_rate": 2.9670329670329673e-06,
71
+ "loss": 1.1941,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.44052863436123346,
76
+ "grad_norm": 1.693711129252621,
77
+ "learning_rate": 2.999101829950985e-06,
78
+ "loss": 1.1731,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.4845814977973568,
83
+ "grad_norm": 1.4467996095205224,
84
+ "learning_rate": 2.9959984254953274e-06,
85
+ "loss": 1.1148,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.5286343612334802,
90
+ "grad_norm": 1.5298410629642052,
91
+ "learning_rate": 2.9906832852013294e-06,
92
+ "loss": 1.191,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.5726872246696035,
97
+ "grad_norm": 1.4536712154523523,
98
+ "learning_rate": 2.9831642671563205e-06,
99
+ "loss": 1.1818,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.6167400881057269,
104
+ "grad_norm": 1.5305738885906355,
105
+ "learning_rate": 2.9734524877367604e-06,
106
+ "loss": 1.1969,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.6607929515418502,
111
+ "grad_norm": 1.4595832724906421,
112
+ "learning_rate": 2.961562305173399e-06,
113
+ "loss": 1.1203,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.7048458149779736,
118
+ "grad_norm": 1.7304480079500448,
119
+ "learning_rate": 2.9475112983235753e-06,
120
+ "loss": 1.2301,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.748898678414097,
125
+ "grad_norm": 1.5486760284827386,
126
+ "learning_rate": 2.9313202406820232e-06,
127
+ "loss": 1.183,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.7929515418502202,
132
+ "grad_norm": 1.700519163465852,
133
+ "learning_rate": 2.9130130696686196e-06,
134
+ "loss": 1.1304,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.8370044052863436,
139
+ "grad_norm": 1.4763145358774594,
140
+ "learning_rate": 2.8926168512384744e-06,
141
+ "loss": 1.1618,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.8810572687224669,
146
+ "grad_norm": 1.5267413192202046,
147
+ "learning_rate": 2.870161739866686e-06,
148
+ "loss": 1.1491,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.9251101321585903,
153
+ "grad_norm": 1.733908977152635,
154
+ "learning_rate": 2.845680933966922e-06,
155
+ "loss": 1.145,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.9691629955947136,
160
+ "grad_norm": 1.498098134685152,
161
+ "learning_rate": 2.8192106268097337e-06,
162
+ "loss": 1.2206,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 1.013215859030837,
167
+ "grad_norm": 4.7125491501567724,
168
+ "learning_rate": 2.7907899530131763e-06,
169
+ "loss": 1.133,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 1.0572687224669604,
174
+ "grad_norm": 2.038277716111568,
175
+ "learning_rate": 2.7604609306848312e-06,
176
+ "loss": 1.0399,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 1.1013215859030836,
181
+ "grad_norm": 1.8451563548941678,
182
+ "learning_rate": 2.7282683993007865e-06,
183
+ "loss": 1.007,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 1.145374449339207,
188
+ "grad_norm": 1.5438408367179703,
189
+ "learning_rate": 2.6942599534133987e-06,
190
+ "loss": 1.0139,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 1.1894273127753303,
195
+ "grad_norm": 1.6126849019096945,
196
+ "learning_rate": 2.658485872285863e-06,
197
+ "loss": 1.0493,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 1.2334801762114538,
202
+ "grad_norm": 1.9217991771681158,
203
+ "learning_rate": 2.6209990455576105e-06,
204
+ "loss": 0.9478,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 1.277533039647577,
209
+ "grad_norm": 1.981595215749417,
210
+ "learning_rate": 2.5818548950504342e-06,
211
+ "loss": 1.0108,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 1.3215859030837005,
216
+ "grad_norm": 1.6455591880816465,
217
+ "learning_rate": 2.541111292830951e-06,
218
+ "loss": 1.0294,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 1.3656387665198237,
223
+ "grad_norm": 1.5108115682140577,
224
+ "learning_rate": 2.4988284756505333e-06,
225
+ "loss": 0.9748,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 1.4096916299559472,
230
+ "grad_norm": 1.5787304886557472,
231
+ "learning_rate": 2.455068955889216e-06,
232
+ "loss": 1.0054,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 1.4537444933920705,
237
+ "grad_norm": 1.6633458413004865,
238
+ "learning_rate": 2.4098974291352257e-06,
239
+ "loss": 1.0155,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 1.497797356828194,
244
+ "grad_norm": 1.7167391655172333,
245
+ "learning_rate": 2.3633806785367873e-06,
246
+ "loss": 1.0677,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 1.5418502202643172,
251
+ "grad_norm": 1.519612290214899,
252
+ "learning_rate": 2.315587476067607e-06,
253
+ "loss": 0.987,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 1.5859030837004404,
258
+ "grad_norm": 1.6948233763887988,
259
+ "learning_rate": 2.2665884808520048e-06,
260
+ "loss": 1.0526,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 1.6299559471365639,
265
+ "grad_norm": 1.6931931897778194,
266
+ "learning_rate": 2.2164561347000213e-06,
267
+ "loss": 1.0304,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 1.6740088105726874,
272
+ "grad_norm": 1.5818868292083217,
273
+ "learning_rate": 2.1652645550069394e-06,
274
+ "loss": 0.9921,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 1.7180616740088106,
279
+ "grad_norm": 1.670222373489549,
280
+ "learning_rate": 2.113089425175561e-06,
281
+ "loss": 1.0062,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 1.7621145374449338,
286
+ "grad_norm": 1.5676805638818068,
287
+ "learning_rate": 2.0600078827232473e-06,
288
+ "loss": 0.993,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 1.8061674008810573,
293
+ "grad_norm": 1.6518866030477966,
294
+ "learning_rate": 2.006098405239142e-06,
295
+ "loss": 0.989,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 1.8502202643171806,
300
+ "grad_norm": 1.7025140153769915,
301
+ "learning_rate": 1.95144069436019e-06,
302
+ "loss": 1.0184,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 1.894273127753304,
307
+ "grad_norm": 1.6535956905677116,
308
+ "learning_rate": 1.896115557937476e-06,
309
+ "loss": 1.0655,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 1.9383259911894273,
314
+ "grad_norm": 1.6062899976218377,
315
+ "learning_rate": 1.8402047905671065e-06,
316
+ "loss": 1.0139,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 1.9823788546255505,
321
+ "grad_norm": 1.6037621791723693,
322
+ "learning_rate": 1.7837910526622437e-06,
323
+ "loss": 1.0103,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 2.026431718061674,
328
+ "grad_norm": 2.347205562826239,
329
+ "learning_rate": 1.726957748245093e-06,
330
+ "loss": 0.8977,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 2.0704845814977975,
335
+ "grad_norm": 1.9061910666122825,
336
+ "learning_rate": 1.6697889016395088e-06,
337
+ "loss": 0.8438,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 2.1145374449339207,
342
+ "grad_norm": 1.6451786150601784,
343
+ "learning_rate": 1.6123690332465296e-06,
344
+ "loss": 0.9008,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 2.158590308370044,
349
+ "grad_norm": 1.8874201469690022,
350
+ "learning_rate": 1.5547830345864886e-06,
351
+ "loss": 0.8176,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 2.202643171806167,
356
+ "grad_norm": 1.9254603832738357,
357
+ "learning_rate": 1.4971160427924554e-06,
358
+ "loss": 0.8901,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 2.246696035242291,
363
+ "grad_norm": 1.835023323363367,
364
+ "learning_rate": 1.439453314740552e-06,
365
+ "loss": 0.8247,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 2.290748898678414,
370
+ "grad_norm": 1.93123359826113,
371
+ "learning_rate": 1.381880101003235e-06,
372
+ "loss": 0.8294,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 2.3348017621145374,
377
+ "grad_norm": 1.866122498094617,
378
+ "learning_rate": 1.3244815198119024e-06,
379
+ "loss": 0.9032,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 2.3788546255506606,
384
+ "grad_norm": 1.7177415721533669,
385
+ "learning_rate": 1.2673424312151519e-06,
386
+ "loss": 0.8862,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 2.4229074889867843,
391
+ "grad_norm": 2.1997603304322237,
392
+ "learning_rate": 1.2105473116187517e-06,
393
+ "loss": 0.894,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 2.4669603524229076,
398
+ "grad_norm": 1.8715395183959846,
399
+ "learning_rate": 1.154180128892796e-06,
400
+ "loss": 0.8126,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 2.511013215859031,
405
+ "grad_norm": 1.86690865903126,
406
+ "learning_rate": 1.0983242182307033e-06,
407
+ "loss": 0.8059,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 2.555066079295154,
412
+ "grad_norm": 2.0917187570122517,
413
+ "learning_rate": 1.0430621589435803e-06,
414
+ "loss": 0.8959,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 2.5991189427312777,
419
+ "grad_norm": 2.558938317516458,
420
+ "learning_rate": 9.884756523721117e-07,
421
+ "loss": 0.8393,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 2.643171806167401,
426
+ "grad_norm": 1.5987062295416765,
427
+ "learning_rate": 9.346454010964724e-07,
428
+ "loss": 0.862,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 2.6872246696035242,
433
+ "grad_norm": 1.6649451786987866,
434
+ "learning_rate": 8.816509896228376e-07,
435
+ "loss": 0.859,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 2.7312775330396475,
440
+ "grad_norm": 1.6834312437789734,
441
+ "learning_rate": 8.295707667228987e-07,
442
+ "loss": 0.8348,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 2.7753303964757707,
447
+ "grad_norm": 1.7102647759571665,
448
+ "learning_rate": 7.784817296003237e-07,
449
+ "loss": 0.8668,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 2.8193832599118944,
454
+ "grad_norm": 1.7566168287161772,
455
+ "learning_rate": 7.284594100554311e-07,
456
+ "loss": 0.8627,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 2.8634361233480177,
461
+ "grad_norm": 1.7731380983410612,
462
+ "learning_rate": 6.7957776281636e-07,
463
+ "loss": 0.855,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 2.907488986784141,
468
+ "grad_norm": 3.413162667971741,
469
+ "learning_rate": 6.31909056201842e-07,
470
+ "loss": 0.8849,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 2.951541850220264,
475
+ "grad_norm": 1.793806206724264,
476
+ "learning_rate": 5.855237652772183e-07,
477
+ "loss": 0.8629,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 2.995594713656388,
482
+ "grad_norm": 1.7832177184392761,
483
+ "learning_rate": 5.404904676616635e-07,
484
+ "loss": 0.8796,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 3.039647577092511,
489
+ "grad_norm": 13.295009142965908,
490
+ "learning_rate": 4.968757421406609e-07,
491
+ "loss": 0.779,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 3.0837004405286343,
496
+ "grad_norm": 1.8559346739765339,
497
+ "learning_rate": 4.547440702336238e-07,
498
+ "loss": 0.7582,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 3.1277533039647576,
503
+ "grad_norm": 1.7949928357857732,
504
+ "learning_rate": 4.1415774086218277e-07,
505
+ "loss": 0.7063,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 3.171806167400881,
510
+ "grad_norm": 1.778323655929332,
511
+ "learning_rate": 3.7517675826009083e-07,
512
+ "loss": 0.752,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 3.2158590308370045,
517
+ "grad_norm": 6.004368017727455,
518
+ "learning_rate": 3.378587532608872e-07,
519
+ "loss": 0.7829,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 3.2599118942731278,
524
+ "grad_norm": 1.9250826926237672,
525
+ "learning_rate": 3.0225889809447925e-07,
526
+ "loss": 0.72,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 3.303964757709251,
531
+ "grad_norm": 1.8286462728037371,
532
+ "learning_rate": 2.684298248186077e-07,
533
+ "loss": 0.7852,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 3.3480176211453743,
538
+ "grad_norm": 1.8502492223085096,
539
+ "learning_rate": 2.3642154750579275e-07,
540
+ "loss": 0.7912,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 3.392070484581498,
545
+ "grad_norm": 1.8690732598717457,
546
+ "learning_rate": 2.0628138830079696e-07,
547
+ "loss": 0.7456,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 3.436123348017621,
552
+ "grad_norm": 2.841225832952903,
553
+ "learning_rate": 1.7805390745792993e-07,
554
+ "loss": 0.7654,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 3.4801762114537445,
559
+ "grad_norm": 2.2582022273376845,
560
+ "learning_rate": 1.5178083746162667e-07,
561
+ "loss": 0.7437,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 3.5242290748898677,
566
+ "grad_norm": 1.874522268468866,
567
+ "learning_rate": 1.2750102132769738e-07,
568
+ "loss": 0.7834,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 3.568281938325991,
573
+ "grad_norm": 2.037336725579371,
574
+ "learning_rate": 1.0525035517647014e-07,
575
+ "loss": 0.7943,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 3.6123348017621146,
580
+ "grad_norm": 1.7256797980612035,
581
+ "learning_rate": 8.50617351627232e-08,
582
+ "loss": 0.7826,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 3.656387665198238,
587
+ "grad_norm": 1.8660504133848668,
588
+ "learning_rate": 6.696500884087259e-08,
589
+ "loss": 0.8379,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 3.700440528634361,
594
+ "grad_norm": 1.6608110580956394,
595
+ "learning_rate": 5.0986931037314666e-08,
596
+ "loss": 0.7614,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 3.744493392070485,
601
+ "grad_norm": 2.132591912569078,
602
+ "learning_rate": 3.7151124295163374e-08,
603
+ "loss": 0.8152,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 3.788546255506608,
608
+ "grad_norm": 2.142924158927503,
609
+ "learning_rate": 2.5478043949868192e-08,
610
+ "loss": 0.7517,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 3.8325991189427313,
615
+ "grad_norm": 2.1270227065723284,
616
+ "learning_rate": 1.5984947887334623e-08,
617
+ "loss": 0.7697,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 3.8766519823788546,
622
+ "grad_norm": 1.8195791930606864,
623
+ "learning_rate": 8.685871029272318e-09,
624
+ "loss": 0.7506,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 3.920704845814978,
629
+ "grad_norm": 2.2849986922595553,
630
+ "learning_rate": 3.5916045834781253e-09,
631
+ "loss": 0.7273,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 3.964757709251101,
636
+ "grad_norm": 1.8303283767313243,
637
+ "learning_rate": 7.096800897425371e-10,
638
+ "loss": 0.8123,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 4.0,
643
+ "step": 908,
644
+ "total_flos": 648773332107264.0,
645
+ "train_loss": 0.9660957064397535,
646
+ "train_runtime": 3882.5924,
647
+ "train_samples_per_second": 5.59,
648
+ "train_steps_per_second": 0.234
649
+ }
650
+ ],
651
+ "logging_steps": 10,
652
+ "max_steps": 908,
653
+ "num_input_tokens_seen": 0,
654
+ "num_train_epochs": 4,
655
+ "save_steps": 500,
656
+ "stateful_callbacks": {
657
+ "TrainerControl": {
658
+ "args": {
659
+ "should_epoch_stop": false,
660
+ "should_evaluate": false,
661
+ "should_log": false,
662
+ "should_save": true,
663
+ "should_training_stop": true
664
+ },
665
+ "attributes": {}
666
+ }
667
+ },
668
+ "total_flos": 648773332107264.0,
669
+ "train_batch_size": 2,
670
+ "trial_name": null,
671
+ "trial_params": null
672
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99f241f6bbafa577e72e3c7d4fb8440e32b855b9de95aec1a49a5eb46128cb11
3
+ size 7160
training_loss.png ADDED