TianyiQ commited on
Commit
43ca25a
1 Parent(s): e010428

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: meta-llama/Meta-Llama-3-8B
4
+ tags:
5
+ - llama-factory
6
+ - full
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: C014_llama3-8b-base_pretrain_20240428_005832
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
+ # C014_llama3-8b-base_pretrain_20240428_005832
17
+
18
+ This model is a fine-tuned version of [/mnt/models-pku/progressalign/shared_storage/downloaded_models/llama3-8b-base](https://huggingface.co//mnt/models-pku/progressalign/shared_storage/downloaded_models/llama3-8b-base) on the C014_data dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 2.2045
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 1.5e-05
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 16
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 8
45
+ - total_train_batch_size: 64
46
+ - total_eval_batch_size: 128
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: polynomial
49
+ - lr_scheduler_warmup_steps: 20
50
+ - num_epochs: 4.0
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:------:|:----:|:---------------:|
57
+ | 2.5789 | 0.0152 | 1 | 2.6458 |
58
+ | 2.5672 | 0.0758 | 5 | 2.6280 |
59
+ | 2.5751 | 0.1515 | 10 | 2.5314 |
60
+ | 2.418 | 0.2273 | 15 | 2.4634 |
61
+ | 2.4701 | 0.3030 | 20 | 2.4177 |
62
+ | 2.3904 | 0.3788 | 25 | 2.3785 |
63
+ | 2.3539 | 0.4545 | 30 | 2.3378 |
64
+ | 2.3101 | 0.5303 | 35 | 2.3082 |
65
+ | 2.3254 | 0.6061 | 40 | 2.2816 |
66
+ | 2.2762 | 0.6818 | 45 | 2.2614 |
67
+ | 2.2525 | 0.7576 | 50 | 2.2458 |
68
+ | 2.2777 | 0.8333 | 55 | 2.2321 |
69
+ | 2.2054 | 0.9091 | 60 | 2.2206 |
70
+ | 2.237 | 0.9848 | 65 | 2.2113 |
71
+ | 1.986 | 1.0606 | 70 | 2.2115 |
72
+ | 1.9373 | 1.1364 | 75 | 2.2217 |
73
+ | 1.9228 | 1.2121 | 80 | 2.2132 |
74
+ | 1.9084 | 1.2879 | 85 | 2.2118 |
75
+ | 1.9684 | 1.3636 | 90 | 2.2122 |
76
+ | 1.9126 | 1.4394 | 95 | 2.2094 |
77
+ | 1.9101 | 1.5152 | 100 | 2.2066 |
78
+ | 1.8496 | 1.5909 | 105 | 2.2058 |
79
+ | 1.9154 | 1.6667 | 110 | 2.2057 |
80
+ | 1.9233 | 1.7424 | 115 | 2.2056 |
81
+ | 1.9198 | 1.8182 | 120 | 2.2052 |
82
+ | 1.9229 | 1.8939 | 125 | 2.2048 |
83
+ | 1.8913 | 1.9697 | 130 | 2.2045 |
84
+ | 1.8814 | 2.0455 | 135 | 2.2046 |
85
+ | 1.8813 | 2.1212 | 140 | 2.2051 |
86
+ | 1.8912 | 2.1970 | 145 | 2.2058 |
87
+ | 1.9184 | 2.2727 | 150 | 2.2065 |
88
+ | 1.8662 | 2.3485 | 155 | 2.2071 |
89
+ | 1.8809 | 2.4242 | 160 | 2.2074 |
90
+ | 1.8591 | 2.5 | 165 | 2.2077 |
91
+ | 1.8731 | 2.5758 | 170 | 2.2079 |
92
+ | 1.8948 | 2.6515 | 175 | 2.2082 |
93
+ | 1.8876 | 2.7273 | 180 | 2.2082 |
94
+ | 1.8408 | 2.8030 | 185 | 2.2083 |
95
+ | 1.8931 | 2.8788 | 190 | 2.2082 |
96
+ | 1.8569 | 2.9545 | 195 | 2.2080 |
97
+ | 1.8621 | 3.0303 | 200 | 2.2079 |
98
+ | 1.8863 | 3.1061 | 205 | 2.2078 |
99
+ | 1.9021 | 3.1818 | 210 | 2.2079 |
100
+ | 1.8648 | 3.2576 | 215 | 2.2080 |
101
+ | 1.8443 | 3.3333 | 220 | 2.2081 |
102
+ | 1.8978 | 3.4091 | 225 | 2.2080 |
103
+ | 1.8658 | 3.4848 | 230 | 2.2080 |
104
+ | 1.8706 | 3.5606 | 235 | 2.2079 |
105
+ | 1.8855 | 3.6364 | 240 | 2.2078 |
106
+ | 1.8535 | 3.7121 | 245 | 2.2078 |
107
+ | 1.9062 | 3.7879 | 250 | 2.2079 |
108
+ | 1.8628 | 3.8636 | 255 | 2.2078 |
109
+ | 1.8484 | 3.9394 | 260 | 2.2077 |
110
+
111
+
112
+ ### Framework versions
113
+
114
+ - Transformers 4.40.0
115
+ - Pytorch 2.1.2+cu121
116
+ - Datasets 2.18.0
117
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_loss": 2.204540491104126,
4
+ "eval_runtime": 6.002,
5
+ "eval_samples_per_second": 77.474,
6
+ "eval_steps_per_second": 0.666,
7
+ "perplexity": 9.066084664011177,
8
+ "total_flos": 27428734894080.0,
9
+ "train_loss": 2.005241002097274,
10
+ "train_runtime": 8788.5675,
11
+ "train_samples_per_second": 1.904,
12
+ "train_steps_per_second": 0.03
13
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/models-pku/progressalign/shared_storage/downloaded_models/llama3-8b-base",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 500000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.40.0",
26
+ "use_cache": false,
27
+ "vocab_size": 128256
28
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_loss": 2.204540491104126,
4
+ "eval_runtime": 6.002,
5
+ "eval_samples_per_second": 77.474,
6
+ "eval_steps_per_second": 0.666,
7
+ "perplexity": 9.066084664011177
8
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "eos_token_id": 128001,
5
+ "transformers_version": "4.40.0"
6
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abd601d06605edc9e1d87e0fceb5b65d6c5485027c6718cd8aabd25533c38afb
3
+ size 4976698592
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bb32f0bee5519d5c68723ce31a39ac68f45e565bdb13d8f7b632f8cdde42e53
3
+ size 4999802616
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:111e9e21c4fab4b10644511446b77da5697b363485c2d4db0f762550d857ef38
3
+ size 4915916080
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55f7864b6deff611a626d4e315757a572c73b28fe40bb2f6ca5504627362da2f
3
+ size 1168138808
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|end_of_text|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '### Instruction:\\n' + content + '\\n\\n### Response:\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\\n\\n' }}{% endif %}{% endfor %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "total_flos": 27428734894080.0,
4
+ "train_loss": 2.005241002097274,
5
+ "train_runtime": 8788.5675,
6
+ "train_samples_per_second": 1.904,
7
+ "train_steps_per_second": 0.03
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 264, "loss": 2.5789, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 0.015151515151515152, "percentage": 0.38, "elapsed_time": "0:00:23", "remaining_time": "1:40:54"}
2
+ {"current_steps": 1, "total_steps": 264, "loss": null, "eval_loss": 2.6458332538604736, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.015151515151515152, "percentage": 0.38, "elapsed_time": "0:00:23", "remaining_time": "1:40:54"}
3
+ {"current_steps": 5, "total_steps": 264, "loss": 2.5672, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.25e-06, "epoch": 0.07575757575757576, "percentage": 1.89, "elapsed_time": "0:01:39", "remaining_time": "1:26:00"}
4
+ {"current_steps": 5, "total_steps": 264, "loss": null, "eval_loss": 2.628009080886841, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.07575757575757576, "percentage": 1.89, "elapsed_time": "0:01:39", "remaining_time": "1:26:00"}
5
+ {"current_steps": 10, "total_steps": 264, "loss": 2.5751, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6e-06, "epoch": 0.15151515151515152, "percentage": 3.79, "elapsed_time": "0:04:34", "remaining_time": "1:56:02"}
6
+ {"current_steps": 10, "total_steps": 264, "loss": null, "eval_loss": 2.5313849449157715, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.15151515151515152, "percentage": 3.79, "elapsed_time": "0:04:34", "remaining_time": "1:56:02"}
7
+ {"current_steps": 15, "total_steps": 264, "loss": 2.418, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.75e-06, "epoch": 0.22727272727272727, "percentage": 5.68, "elapsed_time": "0:07:18", "remaining_time": "2:01:16"}
8
+ {"current_steps": 15, "total_steps": 264, "loss": null, "eval_loss": 2.4634220600128174, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.22727272727272727, "percentage": 5.68, "elapsed_time": "0:07:18", "remaining_time": "2:01:16"}
9
+ {"current_steps": 20, "total_steps": 264, "loss": 2.4701, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3500000000000001e-05, "epoch": 0.30303030303030304, "percentage": 7.58, "elapsed_time": "0:10:10", "remaining_time": "2:04:09"}
10
+ {"current_steps": 20, "total_steps": 264, "loss": null, "eval_loss": 2.4176573753356934, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.30303030303030304, "percentage": 7.58, "elapsed_time": "0:10:10", "remaining_time": "2:04:09"}
11
+ {"current_steps": 25, "total_steps": 264, "loss": 2.3904, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3097898548149108e-05, "epoch": 0.3787878787878788, "percentage": 9.47, "elapsed_time": "0:12:52", "remaining_time": "2:03:01"}
12
+ {"current_steps": 25, "total_steps": 264, "loss": null, "eval_loss": 2.3785245418548584, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.3787878787878788, "percentage": 9.47, "elapsed_time": "0:12:52", "remaining_time": "2:03:01"}
13
+ {"current_steps": 30, "total_steps": 264, "loss": 2.3539, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.041060545673204e-05, "epoch": 0.45454545454545453, "percentage": 11.36, "elapsed_time": "0:15:35", "remaining_time": "2:01:37"}
14
+ {"current_steps": 30, "total_steps": 264, "loss": null, "eval_loss": 2.337780475616455, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.45454545454545453, "percentage": 11.36, "elapsed_time": "0:15:35", "remaining_time": "2:01:37"}
15
+ {"current_steps": 35, "total_steps": 264, "loss": 2.3101, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.236247706221891e-06, "epoch": 0.5303030303030303, "percentage": 13.26, "elapsed_time": "0:18:21", "remaining_time": "2:00:05"}
16
+ {"current_steps": 35, "total_steps": 264, "loss": null, "eval_loss": 2.3082308769226074, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.5303030303030303, "percentage": 13.26, "elapsed_time": "0:18:21", "remaining_time": "2:00:05"}
17
+ {"current_steps": 40, "total_steps": 264, "loss": 2.3254, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.4849612135310325e-06, "epoch": 0.6060606060606061, "percentage": 15.15, "elapsed_time": "0:21:05", "remaining_time": "1:58:04"}
18
+ {"current_steps": 40, "total_steps": 264, "loss": null, "eval_loss": 2.2816028594970703, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.6060606060606061, "percentage": 15.15, "elapsed_time": "0:21:05", "remaining_time": "1:58:04"}
19
+ {"current_steps": 45, "total_steps": 264, "loss": 2.2762, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.081159821297093e-06, "epoch": 0.6818181818181818, "percentage": 17.05, "elapsed_time": "0:23:48", "remaining_time": "1:55:52"}
20
+ {"current_steps": 45, "total_steps": 264, "loss": null, "eval_loss": 2.2614095211029053, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.6818181818181818, "percentage": 17.05, "elapsed_time": "0:23:48", "remaining_time": "1:55:52"}
21
+ {"current_steps": 50, "total_steps": 264, "loss": 2.2525, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.961509285889694e-06, "epoch": 0.7575757575757576, "percentage": 18.94, "elapsed_time": "0:26:31", "remaining_time": "1:53:31"}
22
+ {"current_steps": 50, "total_steps": 264, "loss": null, "eval_loss": 2.2457971572875977, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.7575757575757576, "percentage": 18.94, "elapsed_time": "0:26:31", "remaining_time": "1:53:31"}
23
+ {"current_steps": 55, "total_steps": 264, "loss": 2.2777, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.073152889221908e-06, "epoch": 0.8333333333333334, "percentage": 20.83, "elapsed_time": "0:29:17", "remaining_time": "1:51:20"}
24
+ {"current_steps": 55, "total_steps": 264, "loss": null, "eval_loss": 2.232052803039551, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8333333333333334, "percentage": 20.83, "elapsed_time": "0:29:17", "remaining_time": "1:51:20"}
25
+ {"current_steps": 60, "total_steps": 264, "loss": 2.2054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.372162069694911e-06, "epoch": 0.9090909090909091, "percentage": 22.73, "elapsed_time": "0:32:03", "remaining_time": "1:48:59"}
26
+ {"current_steps": 60, "total_steps": 264, "loss": null, "eval_loss": 2.2206437587738037, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.9090909090909091, "percentage": 22.73, "elapsed_time": "0:32:03", "remaining_time": "1:48:59"}
27
+ {"current_steps": 65, "total_steps": 264, "loss": 2.237, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8221877676625323e-06, "epoch": 0.9848484848484849, "percentage": 24.62, "elapsed_time": "0:34:53", "remaining_time": "1:46:48"}
28
+ {"current_steps": 65, "total_steps": 264, "loss": null, "eval_loss": 2.2112882137298584, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.9848484848484849, "percentage": 24.62, "elapsed_time": "0:34:53", "remaining_time": "1:46:48"}
29
+ {"current_steps": 70, "total_steps": 264, "loss": 1.986, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3932903283558643e-06, "epoch": 1.0606060606060606, "percentage": 26.52, "elapsed_time": "0:37:41", "remaining_time": "1:44:26"}
30
+ {"current_steps": 70, "total_steps": 264, "loss": null, "eval_loss": 2.2115273475646973, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0606060606060606, "percentage": 26.52, "elapsed_time": "0:37:41", "remaining_time": "1:44:26"}
31
+ {"current_steps": 75, "total_steps": 264, "loss": 1.9373, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0609278071546894e-06, "epoch": 1.1363636363636362, "percentage": 28.41, "elapsed_time": "0:40:29", "remaining_time": "1:42:01"}
32
+ {"current_steps": 75, "total_steps": 264, "loss": null, "eval_loss": 2.221705913543701, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.1363636363636362, "percentage": 28.41, "elapsed_time": "0:40:29", "remaining_time": "1:42:01"}
33
+ {"current_steps": 80, "total_steps": 264, "loss": 1.9228, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.050843851687484e-07, "epoch": 1.2121212121212122, "percentage": 30.3, "elapsed_time": "0:43:16", "remaining_time": "1:39:30"}
34
+ {"current_steps": 80, "total_steps": 264, "loss": null, "eval_loss": 2.2131617069244385, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.2121212121212122, "percentage": 30.3, "elapsed_time": "0:43:16", "remaining_time": "1:39:30"}
35
+ {"current_steps": 85, "total_steps": 264, "loss": 1.9084, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.095223338761627e-07, "epoch": 1.2878787878787878, "percentage": 32.2, "elapsed_time": "0:46:02", "remaining_time": "1:36:56"}
36
+ {"current_steps": 85, "total_steps": 264, "loss": null, "eval_loss": 2.2117583751678467, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.2878787878787878, "percentage": 32.2, "elapsed_time": "0:46:02", "remaining_time": "1:36:56"}
37
+ {"current_steps": 90, "total_steps": 264, "loss": 1.9684, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.611425724763914e-07, "epoch": 1.3636363636363638, "percentage": 34.09, "elapsed_time": "0:48:50", "remaining_time": "1:34:26"}
38
+ {"current_steps": 90, "total_steps": 264, "loss": null, "eval_loss": 2.212195634841919, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.3636363636363638, "percentage": 34.09, "elapsed_time": "0:48:50", "remaining_time": "1:34:26"}
39
+ {"current_steps": 95, "total_steps": 264, "loss": 1.9126, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.494403469094348e-07, "epoch": 1.4393939393939394, "percentage": 35.98, "elapsed_time": "0:51:39", "remaining_time": "1:31:53"}
40
+ {"current_steps": 95, "total_steps": 264, "loss": null, "eval_loss": 2.2093794345855713, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.4393939393939394, "percentage": 35.98, "elapsed_time": "0:51:39", "remaining_time": "1:31:53"}
41
+ {"current_steps": 100, "total_steps": 264, "loss": 1.9101, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.660439312704735e-07, "epoch": 1.5151515151515151, "percentage": 37.88, "elapsed_time": "0:54:26", "remaining_time": "1:29:17"}
42
+ {"current_steps": 100, "total_steps": 264, "loss": null, "eval_loss": 2.2066152095794678, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.5151515151515151, "percentage": 37.88, "elapsed_time": "0:54:26", "remaining_time": "1:29:17"}
43
+ {"current_steps": 105, "total_steps": 264, "loss": 1.8496, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0432551654866868e-07, "epoch": 1.5909090909090908, "percentage": 39.77, "elapsed_time": "0:57:14", "remaining_time": "1:26:40"}
44
+ {"current_steps": 105, "total_steps": 264, "loss": null, "eval_loss": 2.2057933807373047, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.5909090909090908, "percentage": 39.77, "elapsed_time": "0:57:14", "remaining_time": "1:26:40"}
45
+ {"current_steps": 110, "total_steps": 264, "loss": 1.9154, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.590746140201269e-07, "epoch": 1.6666666666666665, "percentage": 41.67, "elapsed_time": "1:00:01", "remaining_time": "1:24:01"}
46
+ {"current_steps": 110, "total_steps": 264, "loss": null, "eval_loss": 2.205655097961426, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.6666666666666665, "percentage": 41.67, "elapsed_time": "1:00:01", "remaining_time": "1:24:01"}
47
+ {"current_steps": 115, "total_steps": 264, "loss": 1.9233, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2622536684767967e-07, "epoch": 1.7424242424242424, "percentage": 43.56, "elapsed_time": "1:02:49", "remaining_time": "1:21:24"}
48
+ {"current_steps": 115, "total_steps": 264, "loss": null, "eval_loss": 2.2055680751800537, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.7424242424242424, "percentage": 43.56, "elapsed_time": "1:02:49", "remaining_time": "1:21:24"}
49
+ {"current_steps": 120, "total_steps": 264, "loss": 1.9198, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0263013894441628e-07, "epoch": 1.8181818181818183, "percentage": 45.45, "elapsed_time": "1:05:38", "remaining_time": "1:18:45"}
50
+ {"current_steps": 120, "total_steps": 264, "loss": null, "eval_loss": 2.205195665359497, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.8181818181818183, "percentage": 45.45, "elapsed_time": "1:05:38", "remaining_time": "1:18:45"}
51
+ {"current_steps": 125, "total_steps": 264, "loss": 1.9229, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.587264024428055e-08, "epoch": 1.893939393939394, "percentage": 47.35, "elapsed_time": "1:08:25", "remaining_time": "1:16:05"}
52
+ {"current_steps": 125, "total_steps": 264, "loss": null, "eval_loss": 2.2048099040985107, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.893939393939394, "percentage": 47.35, "elapsed_time": "1:08:25", "remaining_time": "1:16:05"}
53
+ {"current_steps": 130, "total_steps": 264, "loss": 1.8913, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.411465733236604e-08, "epoch": 1.9696969696969697, "percentage": 49.24, "elapsed_time": "1:11:13", "remaining_time": "1:13:24"}
54
+ {"current_steps": 130, "total_steps": 264, "loss": null, "eval_loss": 2.204540491104126, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.9696969696969697, "percentage": 49.24, "elapsed_time": "1:11:13", "remaining_time": "1:13:24"}
55
+ {"current_steps": 135, "total_steps": 264, "loss": 1.8814, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.59711929010128e-08, "epoch": 2.0454545454545454, "percentage": 51.14, "elapsed_time": "1:14:02", "remaining_time": "1:10:44"}
56
+ {"current_steps": 135, "total_steps": 264, "loss": null, "eval_loss": 2.204589605331421, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.0454545454545454, "percentage": 51.14, "elapsed_time": "1:14:02", "remaining_time": "1:10:44"}
57
+ {"current_steps": 140, "total_steps": 264, "loss": 1.8813, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.040948153695873e-08, "epoch": 2.121212121212121, "percentage": 53.03, "elapsed_time": "1:16:49", "remaining_time": "1:08:02"}
58
+ {"current_steps": 140, "total_steps": 264, "loss": null, "eval_loss": 2.2050745487213135, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.121212121212121, "percentage": 53.03, "elapsed_time": "1:16:49", "remaining_time": "1:08:02"}
59
+ {"current_steps": 145, "total_steps": 264, "loss": 1.8912, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.666794757151726e-08, "epoch": 2.196969696969697, "percentage": 54.92, "elapsed_time": "1:19:36", "remaining_time": "1:05:19"}
60
+ {"current_steps": 145, "total_steps": 264, "loss": null, "eval_loss": 2.2057695388793945, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.196969696969697, "percentage": 54.92, "elapsed_time": "1:19:36", "remaining_time": "1:05:19"}
61
+ {"current_steps": 150, "total_steps": 264, "loss": 1.9184, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.4191707642277796e-08, "epoch": 2.2727272727272725, "percentage": 56.82, "elapsed_time": "1:22:22", "remaining_time": "1:02:36"}
62
+ {"current_steps": 150, "total_steps": 264, "loss": null, "eval_loss": 2.2065114974975586, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.2727272727272725, "percentage": 56.82, "elapsed_time": "1:22:22", "remaining_time": "1:02:36"}
63
+ {"current_steps": 155, "total_steps": 264, "loss": 1.8662, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.258170056372994e-08, "epoch": 2.3484848484848486, "percentage": 58.71, "elapsed_time": "1:25:10", "remaining_time": "0:59:53"}
64
+ {"current_steps": 155, "total_steps": 264, "loss": null, "eval_loss": 2.207070827484131, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.3484848484848486, "percentage": 58.71, "elapsed_time": "1:25:10", "remaining_time": "0:59:53"}
65
+ {"current_steps": 160, "total_steps": 264, "loss": 1.8809, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.1554954268425945e-08, "epoch": 2.4242424242424243, "percentage": 60.61, "elapsed_time": "1:27:56", "remaining_time": "0:57:09"}
66
+ {"current_steps": 160, "total_steps": 264, "loss": null, "eval_loss": 2.2073893547058105, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.4242424242424243, "percentage": 60.61, "elapsed_time": "1:27:56", "remaining_time": "0:57:09"}
67
+ {"current_steps": 165, "total_steps": 264, "loss": 1.8591, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.091387798309037e-08, "epoch": 2.5, "percentage": 62.5, "elapsed_time": "1:30:44", "remaining_time": "0:54:26"}
68
+ {"current_steps": 165, "total_steps": 264, "loss": null, "eval_loss": 2.2076644897460938, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.5, "percentage": 62.5, "elapsed_time": "1:30:44", "remaining_time": "0:54:26"}
69
+ {"current_steps": 170, "total_steps": 264, "loss": 1.8731, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0522801309078135e-08, "epoch": 2.5757575757575757, "percentage": 64.39, "elapsed_time": "1:33:31", "remaining_time": "0:51:42"}
70
+ {"current_steps": 170, "total_steps": 264, "loss": null, "eval_loss": 2.2079408168792725, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.5757575757575757, "percentage": 64.39, "elapsed_time": "1:33:31", "remaining_time": "0:51:42"}
71
+ {"current_steps": 175, "total_steps": 264, "loss": 1.8948, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0290274187738543e-08, "epoch": 2.6515151515151514, "percentage": 66.29, "elapsed_time": "1:36:18", "remaining_time": "0:48:58"}
72
+ {"current_steps": 175, "total_steps": 264, "loss": null, "eval_loss": 2.208183765411377, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.6515151515151514, "percentage": 66.29, "elapsed_time": "1:36:18", "remaining_time": "0:48:58"}
73
+ {"current_steps": 180, "total_steps": 264, "loss": 1.8876, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.015589639287439e-08, "epoch": 2.7272727272727275, "percentage": 68.18, "elapsed_time": "1:39:06", "remaining_time": "0:46:15"}
74
+ {"current_steps": 180, "total_steps": 264, "loss": null, "eval_loss": 2.208235740661621, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.7272727272727275, "percentage": 68.18, "elapsed_time": "1:39:06", "remaining_time": "0:46:15"}
75
+ {"current_steps": 185, "total_steps": 264, "loss": 1.8408, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0080665589248236e-08, "epoch": 2.8030303030303028, "percentage": 70.08, "elapsed_time": "1:41:54", "remaining_time": "0:43:31"}
76
+ {"current_steps": 185, "total_steps": 264, "loss": null, "eval_loss": 2.2083210945129395, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.8030303030303028, "percentage": 70.08, "elapsed_time": "1:41:54", "remaining_time": "0:43:31"}
77
+ {"current_steps": 190, "total_steps": 264, "loss": 1.8931, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.004002235298783e-08, "epoch": 2.878787878787879, "percentage": 71.97, "elapsed_time": "1:44:40", "remaining_time": "0:40:46"}
78
+ {"current_steps": 190, "total_steps": 264, "loss": null, "eval_loss": 2.208212375640869, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.878787878787879, "percentage": 71.97, "elapsed_time": "1:44:40", "remaining_time": "0:40:46"}
79
+ {"current_steps": 195, "total_steps": 264, "loss": 1.8569, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.001893193212864e-08, "epoch": 2.9545454545454546, "percentage": 73.86, "elapsed_time": "1:47:29", "remaining_time": "0:38:01"}
80
+ {"current_steps": 195, "total_steps": 264, "loss": null, "eval_loss": 2.2080307006835938, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.9545454545454546, "percentage": 73.86, "elapsed_time": "1:47:29", "remaining_time": "0:38:01"}
81
+ {"current_steps": 200, "total_steps": 264, "loss": 1.8621, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000847883910016e-08, "epoch": 3.0303030303030303, "percentage": 75.76, "elapsed_time": "1:50:16", "remaining_time": "0:35:17"}
82
+ {"current_steps": 200, "total_steps": 264, "loss": null, "eval_loss": 2.207866907119751, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.0303030303030303, "percentage": 75.76, "elapsed_time": "1:50:16", "remaining_time": "0:35:17"}
83
+ {"current_steps": 205, "total_steps": 264, "loss": 1.8863, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000356435775757e-08, "epoch": 3.106060606060606, "percentage": 77.65, "elapsed_time": "1:53:03", "remaining_time": "0:32:32"}
84
+ {"current_steps": 205, "total_steps": 264, "loss": null, "eval_loss": 2.207792043685913, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.106060606060606, "percentage": 77.65, "elapsed_time": "1:53:03", "remaining_time": "0:32:32"}
85
+ {"current_steps": 210, "total_steps": 264, "loss": 1.9021, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0001391301969795e-08, "epoch": 3.1818181818181817, "percentage": 79.55, "elapsed_time": "1:55:50", "remaining_time": "0:29:47"}
86
+ {"current_steps": 210, "total_steps": 264, "loss": null, "eval_loss": 2.2078535556793213, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.1818181818181817, "percentage": 79.55, "elapsed_time": "1:55:50", "remaining_time": "0:29:47"}
87
+ {"current_steps": 215, "total_steps": 264, "loss": 1.8648, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000049730753554e-08, "epoch": 3.257575757575758, "percentage": 81.44, "elapsed_time": "1:58:38", "remaining_time": "0:27:02"}
88
+ {"current_steps": 215, "total_steps": 264, "loss": null, "eval_loss": 2.2079594135284424, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.257575757575758, "percentage": 81.44, "elapsed_time": "1:58:38", "remaining_time": "0:27:02"}
89
+ {"current_steps": 220, "total_steps": 264, "loss": 1.8443, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000159841391415e-08, "epoch": 3.3333333333333335, "percentage": 83.33, "elapsed_time": "2:01:24", "remaining_time": "0:24:16"}
90
+ {"current_steps": 220, "total_steps": 264, "loss": null, "eval_loss": 2.2080650329589844, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.3333333333333335, "percentage": 83.33, "elapsed_time": "2:01:24", "remaining_time": "0:24:16"}
91
+ {"current_steps": 225, "total_steps": 264, "loss": 1.8978, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000045079130105e-08, "epoch": 3.409090909090909, "percentage": 85.23, "elapsed_time": "2:04:13", "remaining_time": "0:21:31"}
92
+ {"current_steps": 225, "total_steps": 264, "loss": null, "eval_loss": 2.20800518989563, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.409090909090909, "percentage": 85.23, "elapsed_time": "2:04:13", "remaining_time": "0:21:31"}
93
+ {"current_steps": 230, "total_steps": 264, "loss": 1.8658, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000001078153535e-08, "epoch": 3.484848484848485, "percentage": 87.12, "elapsed_time": "2:06:59", "remaining_time": "0:18:46"}
94
+ {"current_steps": 230, "total_steps": 264, "loss": null, "eval_loss": 2.208038806915283, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.484848484848485, "percentage": 87.12, "elapsed_time": "2:06:59", "remaining_time": "0:18:46"}
95
+ {"current_steps": 235, "total_steps": 264, "loss": 1.8706, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000002081285866e-08, "epoch": 3.5606060606060606, "percentage": 89.02, "elapsed_time": "2:09:46", "remaining_time": "0:16:00"}
96
+ {"current_steps": 235, "total_steps": 264, "loss": null, "eval_loss": 2.207921266555786, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.5606060606060606, "percentage": 89.02, "elapsed_time": "2:09:46", "remaining_time": "0:16:00"}
97
+ {"current_steps": 240, "total_steps": 264, "loss": 1.8855, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000000300649115e-08, "epoch": 3.6363636363636362, "percentage": 90.91, "elapsed_time": "2:12:33", "remaining_time": "0:13:15"}
98
+ {"current_steps": 240, "total_steps": 264, "loss": null, "eval_loss": 2.2077724933624268, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.6363636363636362, "percentage": 90.91, "elapsed_time": "2:12:33", "remaining_time": "0:13:15"}
99
+ {"current_steps": 245, "total_steps": 264, "loss": 1.8535, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.00000000286923e-08, "epoch": 3.712121212121212, "percentage": 92.8, "elapsed_time": "2:15:21", "remaining_time": "0:10:29"}
100
+ {"current_steps": 245, "total_steps": 264, "loss": null, "eval_loss": 2.2078235149383545, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.712121212121212, "percentage": 92.8, "elapsed_time": "2:15:21", "remaining_time": "0:10:29"}
101
+ {"current_steps": 250, "total_steps": 264, "loss": 1.9062, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000000001441026e-08, "epoch": 3.787878787878788, "percentage": 94.7, "elapsed_time": "2:18:08", "remaining_time": "0:07:44"}
102
+ {"current_steps": 250, "total_steps": 264, "loss": null, "eval_loss": 2.207879066467285, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.787878787878788, "percentage": 94.7, "elapsed_time": "2:18:08", "remaining_time": "0:07:44"}
103
+ {"current_steps": 255, "total_steps": 264, "loss": 1.8628, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000000002337e-08, "epoch": 3.8636363636363638, "percentage": 96.59, "elapsed_time": "2:20:53", "remaining_time": "0:04:58"}
104
+ {"current_steps": 255, "total_steps": 264, "loss": null, "eval_loss": 2.2078306674957275, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.8636363636363638, "percentage": 96.59, "elapsed_time": "2:20:53", "remaining_time": "0:04:58"}
105
+ {"current_steps": 260, "total_steps": 264, "loss": 1.8484, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000000000000024e-08, "epoch": 3.9393939393939394, "percentage": 98.48, "elapsed_time": "2:23:40", "remaining_time": "0:02:12"}
106
+ {"current_steps": 260, "total_steps": 264, "loss": null, "eval_loss": 2.207735776901245, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.9393939393939394, "percentage": 98.48, "elapsed_time": "2:23:40", "remaining_time": "0:02:12"}
107
+ {"current_steps": 264, "total_steps": 264, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "2:26:13", "remaining_time": "0:00:00"}
108
+ {"current_steps": 4, "total_steps": 4, "loss": null, "eval_loss": 2.204540491104126, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "2:27:01", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,825 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.204540491104126,
3
+ "best_model_checkpoint": "./output/training_results/C014_llama3-8b-base_pretrain_20240428_005832/checkpoint-130",
4
+ "epoch": 4.0,
5
+ "eval_steps": 5,
6
+ "global_step": 264,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.015151515151515152,
13
+ "grad_norm": 0.0,
14
+ "learning_rate": 0.0,
15
+ "loss": 2.5789,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.015151515151515152,
20
+ "eval_loss": 2.6458332538604736,
21
+ "eval_runtime": 5.9609,
22
+ "eval_samples_per_second": 78.008,
23
+ "eval_steps_per_second": 0.671,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.07575757575757576,
28
+ "grad_norm": 3.5510944022733923,
29
+ "learning_rate": 2.25e-06,
30
+ "loss": 2.5672,
31
+ "step": 5
32
+ },
33
+ {
34
+ "epoch": 0.07575757575757576,
35
+ "eval_loss": 2.628009080886841,
36
+ "eval_runtime": 5.9819,
37
+ "eval_samples_per_second": 77.735,
38
+ "eval_steps_per_second": 0.669,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.15151515151515152,
43
+ "grad_norm": 3.473712979202145,
44
+ "learning_rate": 6e-06,
45
+ "loss": 2.5751,
46
+ "step": 10
47
+ },
48
+ {
49
+ "epoch": 0.15151515151515152,
50
+ "eval_loss": 2.5313849449157715,
51
+ "eval_runtime": 5.9441,
52
+ "eval_samples_per_second": 78.228,
53
+ "eval_steps_per_second": 0.673,
54
+ "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.22727272727272727,
58
+ "grad_norm": 2.7296451314204835,
59
+ "learning_rate": 9.75e-06,
60
+ "loss": 2.418,
61
+ "step": 15
62
+ },
63
+ {
64
+ "epoch": 0.22727272727272727,
65
+ "eval_loss": 2.4634220600128174,
66
+ "eval_runtime": 6.0122,
67
+ "eval_samples_per_second": 77.343,
68
+ "eval_steps_per_second": 0.665,
69
+ "step": 15
70
+ },
71
+ {
72
+ "epoch": 0.30303030303030304,
73
+ "grad_norm": 2.9793222204470453,
74
+ "learning_rate": 1.3500000000000001e-05,
75
+ "loss": 2.4701,
76
+ "step": 20
77
+ },
78
+ {
79
+ "epoch": 0.30303030303030304,
80
+ "eval_loss": 2.4176573753356934,
81
+ "eval_runtime": 5.9735,
82
+ "eval_samples_per_second": 77.844,
83
+ "eval_steps_per_second": 0.67,
84
+ "step": 20
85
+ },
86
+ {
87
+ "epoch": 0.3787878787878788,
88
+ "grad_norm": 2.9152379669367696,
89
+ "learning_rate": 1.3097898548149108e-05,
90
+ "loss": 2.3904,
91
+ "step": 25
92
+ },
93
+ {
94
+ "epoch": 0.3787878787878788,
95
+ "eval_loss": 2.3785245418548584,
96
+ "eval_runtime": 5.9994,
97
+ "eval_samples_per_second": 77.507,
98
+ "eval_steps_per_second": 0.667,
99
+ "step": 25
100
+ },
101
+ {
102
+ "epoch": 0.45454545454545453,
103
+ "grad_norm": 2.475241901636818,
104
+ "learning_rate": 1.041060545673204e-05,
105
+ "loss": 2.3539,
106
+ "step": 30
107
+ },
108
+ {
109
+ "epoch": 0.45454545454545453,
110
+ "eval_loss": 2.337780475616455,
111
+ "eval_runtime": 5.9932,
112
+ "eval_samples_per_second": 77.587,
113
+ "eval_steps_per_second": 0.667,
114
+ "step": 30
115
+ },
116
+ {
117
+ "epoch": 0.5303030303030303,
118
+ "grad_norm": 2.5312379436441272,
119
+ "learning_rate": 8.236247706221891e-06,
120
+ "loss": 2.3101,
121
+ "step": 35
122
+ },
123
+ {
124
+ "epoch": 0.5303030303030303,
125
+ "eval_loss": 2.3082308769226074,
126
+ "eval_runtime": 5.9901,
127
+ "eval_samples_per_second": 77.628,
128
+ "eval_steps_per_second": 0.668,
129
+ "step": 35
130
+ },
131
+ {
132
+ "epoch": 0.6060606060606061,
133
+ "grad_norm": 2.5279244134684804,
134
+ "learning_rate": 6.4849612135310325e-06,
135
+ "loss": 2.3254,
136
+ "step": 40
137
+ },
138
+ {
139
+ "epoch": 0.6060606060606061,
140
+ "eval_loss": 2.2816028594970703,
141
+ "eval_runtime": 5.9798,
142
+ "eval_samples_per_second": 77.762,
143
+ "eval_steps_per_second": 0.669,
144
+ "step": 40
145
+ },
146
+ {
147
+ "epoch": 0.6818181818181818,
148
+ "grad_norm": 2.3848893916874836,
149
+ "learning_rate": 5.081159821297093e-06,
150
+ "loss": 2.2762,
151
+ "step": 45
152
+ },
153
+ {
154
+ "epoch": 0.6818181818181818,
155
+ "eval_loss": 2.2614095211029053,
156
+ "eval_runtime": 5.9833,
157
+ "eval_samples_per_second": 77.716,
158
+ "eval_steps_per_second": 0.669,
159
+ "step": 45
160
+ },
161
+ {
162
+ "epoch": 0.7575757575757576,
163
+ "grad_norm": 2.55130938777181,
164
+ "learning_rate": 3.961509285889694e-06,
165
+ "loss": 2.2525,
166
+ "step": 50
167
+ },
168
+ {
169
+ "epoch": 0.7575757575757576,
170
+ "eval_loss": 2.2457971572875977,
171
+ "eval_runtime": 6.0002,
172
+ "eval_samples_per_second": 77.497,
173
+ "eval_steps_per_second": 0.667,
174
+ "step": 50
175
+ },
176
+ {
177
+ "epoch": 0.8333333333333334,
178
+ "grad_norm": 2.2003836383976156,
179
+ "learning_rate": 3.073152889221908e-06,
180
+ "loss": 2.2777,
181
+ "step": 55
182
+ },
183
+ {
184
+ "epoch": 0.8333333333333334,
185
+ "eval_loss": 2.232052803039551,
186
+ "eval_runtime": 5.9752,
187
+ "eval_samples_per_second": 77.822,
188
+ "eval_steps_per_second": 0.669,
189
+ "step": 55
190
+ },
191
+ {
192
+ "epoch": 0.9090909090909091,
193
+ "grad_norm": 1.938340466235554,
194
+ "learning_rate": 2.372162069694911e-06,
195
+ "loss": 2.2054,
196
+ "step": 60
197
+ },
198
+ {
199
+ "epoch": 0.9090909090909091,
200
+ "eval_loss": 2.2206437587738037,
201
+ "eval_runtime": 5.9984,
202
+ "eval_samples_per_second": 77.52,
203
+ "eval_steps_per_second": 0.667,
204
+ "step": 60
205
+ },
206
+ {
207
+ "epoch": 0.9848484848484849,
208
+ "grad_norm": 2.0152410097081375,
209
+ "learning_rate": 1.8221877676625323e-06,
210
+ "loss": 2.237,
211
+ "step": 65
212
+ },
213
+ {
214
+ "epoch": 0.9848484848484849,
215
+ "eval_loss": 2.2112882137298584,
216
+ "eval_runtime": 6.0081,
217
+ "eval_samples_per_second": 77.396,
218
+ "eval_steps_per_second": 0.666,
219
+ "step": 65
220
+ },
221
+ {
222
+ "epoch": 1.0606060606060606,
223
+ "grad_norm": 2.206665008674913,
224
+ "learning_rate": 1.3932903283558643e-06,
225
+ "loss": 1.986,
226
+ "step": 70
227
+ },
228
+ {
229
+ "epoch": 1.0606060606060606,
230
+ "eval_loss": 2.2115273475646973,
231
+ "eval_runtime": 6.0121,
232
+ "eval_samples_per_second": 77.344,
233
+ "eval_steps_per_second": 0.665,
234
+ "step": 70
235
+ },
236
+ {
237
+ "epoch": 1.1363636363636362,
238
+ "grad_norm": 2.4135250740210816,
239
+ "learning_rate": 1.0609278071546894e-06,
240
+ "loss": 1.9373,
241
+ "step": 75
242
+ },
243
+ {
244
+ "epoch": 1.1363636363636362,
245
+ "eval_loss": 2.221705913543701,
246
+ "eval_runtime": 5.966,
247
+ "eval_samples_per_second": 77.942,
248
+ "eval_steps_per_second": 0.67,
249
+ "step": 75
250
+ },
251
+ {
252
+ "epoch": 1.2121212121212122,
253
+ "grad_norm": 2.0909203153994995,
254
+ "learning_rate": 8.050843851687484e-07,
255
+ "loss": 1.9228,
256
+ "step": 80
257
+ },
258
+ {
259
+ "epoch": 1.2121212121212122,
260
+ "eval_loss": 2.2131617069244385,
261
+ "eval_runtime": 6.0048,
262
+ "eval_samples_per_second": 77.439,
263
+ "eval_steps_per_second": 0.666,
264
+ "step": 80
265
+ },
266
+ {
267
+ "epoch": 1.2878787878787878,
268
+ "grad_norm": 2.0701966451221723,
269
+ "learning_rate": 6.095223338761627e-07,
270
+ "loss": 1.9084,
271
+ "step": 85
272
+ },
273
+ {
274
+ "epoch": 1.2878787878787878,
275
+ "eval_loss": 2.2117583751678467,
276
+ "eval_runtime": 6.0144,
277
+ "eval_samples_per_second": 77.314,
278
+ "eval_steps_per_second": 0.665,
279
+ "step": 85
280
+ },
281
+ {
282
+ "epoch": 1.3636363636363638,
283
+ "grad_norm": 2.0411250764985907,
284
+ "learning_rate": 4.611425724763914e-07,
285
+ "loss": 1.9684,
286
+ "step": 90
287
+ },
288
+ {
289
+ "epoch": 1.3636363636363638,
290
+ "eval_loss": 2.212195634841919,
291
+ "eval_runtime": 6.005,
292
+ "eval_samples_per_second": 77.436,
293
+ "eval_steps_per_second": 0.666,
294
+ "step": 90
295
+ },
296
+ {
297
+ "epoch": 1.4393939393939394,
298
+ "grad_norm": 2.095523936778245,
299
+ "learning_rate": 3.494403469094348e-07,
300
+ "loss": 1.9126,
301
+ "step": 95
302
+ },
303
+ {
304
+ "epoch": 1.4393939393939394,
305
+ "eval_loss": 2.2093794345855713,
306
+ "eval_runtime": 5.9753,
307
+ "eval_samples_per_second": 77.82,
308
+ "eval_steps_per_second": 0.669,
309
+ "step": 95
310
+ },
311
+ {
312
+ "epoch": 1.5151515151515151,
313
+ "grad_norm": 1.9491500689498569,
314
+ "learning_rate": 2.660439312704735e-07,
315
+ "loss": 1.9101,
316
+ "step": 100
317
+ },
318
+ {
319
+ "epoch": 1.5151515151515151,
320
+ "eval_loss": 2.2066152095794678,
321
+ "eval_runtime": 5.988,
322
+ "eval_samples_per_second": 77.656,
323
+ "eval_steps_per_second": 0.668,
324
+ "step": 100
325
+ },
326
+ {
327
+ "epoch": 1.5909090909090908,
328
+ "grad_norm": 1.9297056004219728,
329
+ "learning_rate": 2.0432551654866868e-07,
330
+ "loss": 1.8496,
331
+ "step": 105
332
+ },
333
+ {
334
+ "epoch": 1.5909090909090908,
335
+ "eval_loss": 2.2057933807373047,
336
+ "eval_runtime": 6.029,
337
+ "eval_samples_per_second": 77.127,
338
+ "eval_steps_per_second": 0.663,
339
+ "step": 105
340
+ },
341
+ {
342
+ "epoch": 1.6666666666666665,
343
+ "grad_norm": 2.0270269069156095,
344
+ "learning_rate": 1.590746140201269e-07,
345
+ "loss": 1.9154,
346
+ "step": 110
347
+ },
348
+ {
349
+ "epoch": 1.6666666666666665,
350
+ "eval_loss": 2.205655097961426,
351
+ "eval_runtime": 5.9865,
352
+ "eval_samples_per_second": 77.675,
353
+ "eval_steps_per_second": 0.668,
354
+ "step": 110
355
+ },
356
+ {
357
+ "epoch": 1.7424242424242424,
358
+ "grad_norm": 2.0216556200111957,
359
+ "learning_rate": 1.2622536684767967e-07,
360
+ "loss": 1.9233,
361
+ "step": 115
362
+ },
363
+ {
364
+ "epoch": 1.7424242424242424,
365
+ "eval_loss": 2.2055680751800537,
366
+ "eval_runtime": 5.9969,
367
+ "eval_samples_per_second": 77.54,
368
+ "eval_steps_per_second": 0.667,
369
+ "step": 115
370
+ },
371
+ {
372
+ "epoch": 1.8181818181818183,
373
+ "grad_norm": 2.121087680196771,
374
+ "learning_rate": 1.0263013894441628e-07,
375
+ "loss": 1.9198,
376
+ "step": 120
377
+ },
378
+ {
379
+ "epoch": 1.8181818181818183,
380
+ "eval_loss": 2.205195665359497,
381
+ "eval_runtime": 5.9814,
382
+ "eval_samples_per_second": 77.741,
383
+ "eval_steps_per_second": 0.669,
384
+ "step": 120
385
+ },
386
+ {
387
+ "epoch": 1.893939393939394,
388
+ "grad_norm": 1.9887616789335223,
389
+ "learning_rate": 8.587264024428055e-08,
390
+ "loss": 1.9229,
391
+ "step": 125
392
+ },
393
+ {
394
+ "epoch": 1.893939393939394,
395
+ "eval_loss": 2.2048099040985107,
396
+ "eval_runtime": 6.0178,
397
+ "eval_samples_per_second": 77.271,
398
+ "eval_steps_per_second": 0.665,
399
+ "step": 125
400
+ },
401
+ {
402
+ "epoch": 1.9696969696969697,
403
+ "grad_norm": 1.9737440679073275,
404
+ "learning_rate": 7.411465733236604e-08,
405
+ "loss": 1.8913,
406
+ "step": 130
407
+ },
408
+ {
409
+ "epoch": 1.9696969696969697,
410
+ "eval_loss": 2.204540491104126,
411
+ "eval_runtime": 6.0056,
412
+ "eval_samples_per_second": 77.428,
413
+ "eval_steps_per_second": 0.666,
414
+ "step": 130
415
+ },
416
+ {
417
+ "epoch": 2.0454545454545454,
418
+ "grad_norm": 2.037256369037435,
419
+ "learning_rate": 6.59711929010128e-08,
420
+ "loss": 1.8814,
421
+ "step": 135
422
+ },
423
+ {
424
+ "epoch": 2.0454545454545454,
425
+ "eval_loss": 2.204589605331421,
426
+ "eval_runtime": 6.0067,
427
+ "eval_samples_per_second": 77.414,
428
+ "eval_steps_per_second": 0.666,
429
+ "step": 135
430
+ },
431
+ {
432
+ "epoch": 2.121212121212121,
433
+ "grad_norm": 2.0713675635613353,
434
+ "learning_rate": 6.040948153695873e-08,
435
+ "loss": 1.8813,
436
+ "step": 140
437
+ },
438
+ {
439
+ "epoch": 2.121212121212121,
440
+ "eval_loss": 2.2050745487213135,
441
+ "eval_runtime": 5.9801,
442
+ "eval_samples_per_second": 77.758,
443
+ "eval_steps_per_second": 0.669,
444
+ "step": 140
445
+ },
446
+ {
447
+ "epoch": 2.196969696969697,
448
+ "grad_norm": 1.9602573628685647,
449
+ "learning_rate": 5.666794757151726e-08,
450
+ "loss": 1.8912,
451
+ "step": 145
452
+ },
453
+ {
454
+ "epoch": 2.196969696969697,
455
+ "eval_loss": 2.2057695388793945,
456
+ "eval_runtime": 6.0053,
457
+ "eval_samples_per_second": 77.431,
458
+ "eval_steps_per_second": 0.666,
459
+ "step": 145
460
+ },
461
+ {
462
+ "epoch": 2.2727272727272725,
463
+ "grad_norm": 2.0631081811496133,
464
+ "learning_rate": 5.4191707642277796e-08,
465
+ "loss": 1.9184,
466
+ "step": 150
467
+ },
468
+ {
469
+ "epoch": 2.2727272727272725,
470
+ "eval_loss": 2.2065114974975586,
471
+ "eval_runtime": 5.9555,
472
+ "eval_samples_per_second": 78.079,
473
+ "eval_steps_per_second": 0.672,
474
+ "step": 150
475
+ },
476
+ {
477
+ "epoch": 2.3484848484848486,
478
+ "grad_norm": 2.0253318844317705,
479
+ "learning_rate": 5.258170056372994e-08,
480
+ "loss": 1.8662,
481
+ "step": 155
482
+ },
483
+ {
484
+ "epoch": 2.3484848484848486,
485
+ "eval_loss": 2.207070827484131,
486
+ "eval_runtime": 6.0047,
487
+ "eval_samples_per_second": 77.439,
488
+ "eval_steps_per_second": 0.666,
489
+ "step": 155
490
+ },
491
+ {
492
+ "epoch": 2.4242424242424243,
493
+ "grad_norm": 2.073377995618171,
494
+ "learning_rate": 5.1554954268425945e-08,
495
+ "loss": 1.8809,
496
+ "step": 160
497
+ },
498
+ {
499
+ "epoch": 2.4242424242424243,
500
+ "eval_loss": 2.2073893547058105,
501
+ "eval_runtime": 6.0042,
502
+ "eval_samples_per_second": 77.446,
503
+ "eval_steps_per_second": 0.666,
504
+ "step": 160
505
+ },
506
+ {
507
+ "epoch": 2.5,
508
+ "grad_norm": 1.9895760567683491,
509
+ "learning_rate": 5.091387798309037e-08,
510
+ "loss": 1.8591,
511
+ "step": 165
512
+ },
513
+ {
514
+ "epoch": 2.5,
515
+ "eval_loss": 2.2076644897460938,
516
+ "eval_runtime": 5.9917,
517
+ "eval_samples_per_second": 77.608,
518
+ "eval_steps_per_second": 0.668,
519
+ "step": 165
520
+ },
521
+ {
522
+ "epoch": 2.5757575757575757,
523
+ "grad_norm": 2.0833747351029372,
524
+ "learning_rate": 5.0522801309078135e-08,
525
+ "loss": 1.8731,
526
+ "step": 170
527
+ },
528
+ {
529
+ "epoch": 2.5757575757575757,
530
+ "eval_loss": 2.2079408168792725,
531
+ "eval_runtime": 6.0146,
532
+ "eval_samples_per_second": 77.312,
533
+ "eval_steps_per_second": 0.665,
534
+ "step": 170
535
+ },
536
+ {
537
+ "epoch": 2.6515151515151514,
538
+ "grad_norm": 2.0037327741523825,
539
+ "learning_rate": 5.0290274187738543e-08,
540
+ "loss": 1.8948,
541
+ "step": 175
542
+ },
543
+ {
544
+ "epoch": 2.6515151515151514,
545
+ "eval_loss": 2.208183765411377,
546
+ "eval_runtime": 6.0305,
547
+ "eval_samples_per_second": 77.108,
548
+ "eval_steps_per_second": 0.663,
549
+ "step": 175
550
+ },
551
+ {
552
+ "epoch": 2.7272727272727275,
553
+ "grad_norm": 2.0305444519091917,
554
+ "learning_rate": 5.015589639287439e-08,
555
+ "loss": 1.8876,
556
+ "step": 180
557
+ },
558
+ {
559
+ "epoch": 2.7272727272727275,
560
+ "eval_loss": 2.208235740661621,
561
+ "eval_runtime": 5.9955,
562
+ "eval_samples_per_second": 77.558,
563
+ "eval_steps_per_second": 0.667,
564
+ "step": 180
565
+ },
566
+ {
567
+ "epoch": 2.8030303030303028,
568
+ "grad_norm": 2.0062076076889266,
569
+ "learning_rate": 5.0080665589248236e-08,
570
+ "loss": 1.8408,
571
+ "step": 185
572
+ },
573
+ {
574
+ "epoch": 2.8030303030303028,
575
+ "eval_loss": 2.2083210945129395,
576
+ "eval_runtime": 6.0004,
577
+ "eval_samples_per_second": 77.495,
578
+ "eval_steps_per_second": 0.667,
579
+ "step": 185
580
+ },
581
+ {
582
+ "epoch": 2.878787878787879,
583
+ "grad_norm": 2.043895270641295,
584
+ "learning_rate": 5.004002235298783e-08,
585
+ "loss": 1.8931,
586
+ "step": 190
587
+ },
588
+ {
589
+ "epoch": 2.878787878787879,
590
+ "eval_loss": 2.208212375640869,
591
+ "eval_runtime": 6.0002,
592
+ "eval_samples_per_second": 77.498,
593
+ "eval_steps_per_second": 0.667,
594
+ "step": 190
595
+ },
596
+ {
597
+ "epoch": 2.9545454545454546,
598
+ "grad_norm": 1.9689184449811679,
599
+ "learning_rate": 5.001893193212864e-08,
600
+ "loss": 1.8569,
601
+ "step": 195
602
+ },
603
+ {
604
+ "epoch": 2.9545454545454546,
605
+ "eval_loss": 2.2080307006835938,
606
+ "eval_runtime": 5.9791,
607
+ "eval_samples_per_second": 77.772,
608
+ "eval_steps_per_second": 0.669,
609
+ "step": 195
610
+ },
611
+ {
612
+ "epoch": 3.0303030303030303,
613
+ "grad_norm": 2.019410946950212,
614
+ "learning_rate": 5.000847883910016e-08,
615
+ "loss": 1.8621,
616
+ "step": 200
617
+ },
618
+ {
619
+ "epoch": 3.0303030303030303,
620
+ "eval_loss": 2.207866907119751,
621
+ "eval_runtime": 6.0003,
622
+ "eval_samples_per_second": 77.496,
623
+ "eval_steps_per_second": 0.667,
624
+ "step": 200
625
+ },
626
+ {
627
+ "epoch": 3.106060606060606,
628
+ "grad_norm": 2.0283442915048644,
629
+ "learning_rate": 5.000356435775757e-08,
630
+ "loss": 1.8863,
631
+ "step": 205
632
+ },
633
+ {
634
+ "epoch": 3.106060606060606,
635
+ "eval_loss": 2.207792043685913,
636
+ "eval_runtime": 5.9858,
637
+ "eval_samples_per_second": 77.684,
638
+ "eval_steps_per_second": 0.668,
639
+ "step": 205
640
+ },
641
+ {
642
+ "epoch": 3.1818181818181817,
643
+ "grad_norm": 2.05494798524839,
644
+ "learning_rate": 5.0001391301969795e-08,
645
+ "loss": 1.9021,
646
+ "step": 210
647
+ },
648
+ {
649
+ "epoch": 3.1818181818181817,
650
+ "eval_loss": 2.2078535556793213,
651
+ "eval_runtime": 5.9911,
652
+ "eval_samples_per_second": 77.615,
653
+ "eval_steps_per_second": 0.668,
654
+ "step": 210
655
+ },
656
+ {
657
+ "epoch": 3.257575757575758,
658
+ "grad_norm": 2.0316955077847023,
659
+ "learning_rate": 5.000049730753554e-08,
660
+ "loss": 1.8648,
661
+ "step": 215
662
+ },
663
+ {
664
+ "epoch": 3.257575757575758,
665
+ "eval_loss": 2.2079594135284424,
666
+ "eval_runtime": 5.9692,
667
+ "eval_samples_per_second": 77.9,
668
+ "eval_steps_per_second": 0.67,
669
+ "step": 215
670
+ },
671
+ {
672
+ "epoch": 3.3333333333333335,
673
+ "grad_norm": 2.0376583248479174,
674
+ "learning_rate": 5.0000159841391415e-08,
675
+ "loss": 1.8443,
676
+ "step": 220
677
+ },
678
+ {
679
+ "epoch": 3.3333333333333335,
680
+ "eval_loss": 2.2080650329589844,
681
+ "eval_runtime": 6.0237,
682
+ "eval_samples_per_second": 77.195,
683
+ "eval_steps_per_second": 0.664,
684
+ "step": 220
685
+ },
686
+ {
687
+ "epoch": 3.409090909090909,
688
+ "grad_norm": 2.0309390490282864,
689
+ "learning_rate": 5.0000045079130105e-08,
690
+ "loss": 1.8978,
691
+ "step": 225
692
+ },
693
+ {
694
+ "epoch": 3.409090909090909,
695
+ "eval_loss": 2.20800518989563,
696
+ "eval_runtime": 6.0116,
697
+ "eval_samples_per_second": 77.35,
698
+ "eval_steps_per_second": 0.665,
699
+ "step": 225
700
+ },
701
+ {
702
+ "epoch": 3.484848484848485,
703
+ "grad_norm": 2.0870431548602495,
704
+ "learning_rate": 5.000001078153535e-08,
705
+ "loss": 1.8658,
706
+ "step": 230
707
+ },
708
+ {
709
+ "epoch": 3.484848484848485,
710
+ "eval_loss": 2.208038806915283,
711
+ "eval_runtime": 5.99,
712
+ "eval_samples_per_second": 77.629,
713
+ "eval_steps_per_second": 0.668,
714
+ "step": 230
715
+ },
716
+ {
717
+ "epoch": 3.5606060606060606,
718
+ "grad_norm": 2.0234951173098024,
719
+ "learning_rate": 5.0000002081285866e-08,
720
+ "loss": 1.8706,
721
+ "step": 235
722
+ },
723
+ {
724
+ "epoch": 3.5606060606060606,
725
+ "eval_loss": 2.207921266555786,
726
+ "eval_runtime": 5.9823,
727
+ "eval_samples_per_second": 77.73,
728
+ "eval_steps_per_second": 0.669,
729
+ "step": 235
730
+ },
731
+ {
732
+ "epoch": 3.6363636363636362,
733
+ "grad_norm": 2.039329423643573,
734
+ "learning_rate": 5.0000000300649115e-08,
735
+ "loss": 1.8855,
736
+ "step": 240
737
+ },
738
+ {
739
+ "epoch": 3.6363636363636362,
740
+ "eval_loss": 2.2077724933624268,
741
+ "eval_runtime": 6.0052,
742
+ "eval_samples_per_second": 77.433,
743
+ "eval_steps_per_second": 0.666,
744
+ "step": 240
745
+ },
746
+ {
747
+ "epoch": 3.712121212121212,
748
+ "grad_norm": 2.048524032150131,
749
+ "learning_rate": 5.00000000286923e-08,
750
+ "loss": 1.8535,
751
+ "step": 245
752
+ },
753
+ {
754
+ "epoch": 3.712121212121212,
755
+ "eval_loss": 2.2078235149383545,
756
+ "eval_runtime": 6.0225,
757
+ "eval_samples_per_second": 77.21,
758
+ "eval_steps_per_second": 0.664,
759
+ "step": 245
760
+ },
761
+ {
762
+ "epoch": 3.787878787878788,
763
+ "grad_norm": 2.117736519999513,
764
+ "learning_rate": 5.0000000001441026e-08,
765
+ "loss": 1.9062,
766
+ "step": 250
767
+ },
768
+ {
769
+ "epoch": 3.787878787878788,
770
+ "eval_loss": 2.207879066467285,
771
+ "eval_runtime": 5.9714,
772
+ "eval_samples_per_second": 77.871,
773
+ "eval_steps_per_second": 0.67,
774
+ "step": 250
775
+ },
776
+ {
777
+ "epoch": 3.8636363636363638,
778
+ "grad_norm": 2.0315594950889775,
779
+ "learning_rate": 5.000000000002337e-08,
780
+ "loss": 1.8628,
781
+ "step": 255
782
+ },
783
+ {
784
+ "epoch": 3.8636363636363638,
785
+ "eval_loss": 2.2078306674957275,
786
+ "eval_runtime": 6.0145,
787
+ "eval_samples_per_second": 77.314,
788
+ "eval_steps_per_second": 0.665,
789
+ "step": 255
790
+ },
791
+ {
792
+ "epoch": 3.9393939393939394,
793
+ "grad_norm": 2.0132729461699994,
794
+ "learning_rate": 5.0000000000000024e-08,
795
+ "loss": 1.8484,
796
+ "step": 260
797
+ },
798
+ {
799
+ "epoch": 3.9393939393939394,
800
+ "eval_loss": 2.207735776901245,
801
+ "eval_runtime": 6.0067,
802
+ "eval_samples_per_second": 77.413,
803
+ "eval_steps_per_second": 0.666,
804
+ "step": 260
805
+ },
806
+ {
807
+ "epoch": 4.0,
808
+ "step": 264,
809
+ "total_flos": 27428734894080.0,
810
+ "train_loss": 2.005241002097274,
811
+ "train_runtime": 8788.5675,
812
+ "train_samples_per_second": 1.904,
813
+ "train_steps_per_second": 0.03
814
+ }
815
+ ],
816
+ "logging_steps": 5,
817
+ "max_steps": 264,
818
+ "num_input_tokens_seen": 0,
819
+ "num_train_epochs": 4,
820
+ "save_steps": 5,
821
+ "total_flos": 27428734894080.0,
822
+ "train_batch_size": 8,
823
+ "trial_name": null,
824
+ "trial_params": null
825
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:001de46957edb45ce1e70a3c9079e08c3e4094b6ea33413856f85b4d6e6fbb5c
3
+ size 6968
training_eval_loss.png ADDED
training_loss.png ADDED