sam2ai commited on
Commit
9c19330
·
verified ·
1 Parent(s): 1c338ab

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,61 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: sft
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # sft
18
+
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the open_thoughts dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 1e-05
39
+ - train_batch_size: 1
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 8
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 16
46
+ - total_eval_batch_size: 64
47
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 3.0
51
+
52
+ ### Training results
53
+
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.49.0
59
+ - Pytorch 2.6.0.dev20241113+rocm6.2
60
+ - Datasets 3.1.0
61
+ - Tokenizers 0.21.0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.96,
3
+ "total_flos": 21670257623040.0,
4
+ "train_loss": 0.5450129303079779,
5
+ "train_runtime": 5234.2515,
6
+ "train_samples_per_second": 0.573,
7
+ "train_steps_per_second": 0.036
8
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 8192,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 500000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.49.0",
28
+ "use_cache": false,
29
+ "vocab_size": 128256
30
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128009
7
+ ],
8
+ "max_length": 4096,
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.49.0"
12
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b2f0604bda8a37d98fe2f5d790942d47796abe819758af958485abde541e572
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2cea3cae5dd54a1ad69eaca1915c66da73c680f4108961c56a45ed48979f6ea
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cd9102aa47bdab45ba08db696b37de52235228ff63fefdf894191f20acde080
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c57294551fb3a94558e46951dd95596d4b8a8275c55db886b57ae25d71abfdf
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
+ }
runs/Mar21_05-34-10_amd-G262-ZO0-00/events.out.tfevents.1742535286.amd-G262-ZO0-00.263374.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:387cb4bb4cbc66fbbe7ff4f9da282c1075df4dcc24e3813eb4bcd244e3e36cab
3
+ size 10059
runs/Mar21_07-26-29_amd-G262-ZO0-00/events.out.tfevents.1742542295.amd-G262-ZO0-00.1274.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23c5d9d3456f52a9ab094d8a29bf603f5e2d62d473c64a3ad3ed8485440a411d
3
+ size 44612
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eot_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|eom_id|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<|begin_of_text|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "<|eot_id|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": "<|eot_id|>"
33
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c1dcab308e7cf5970ea38815e0a62887d705c5b436f869ca27a5dcdd40c36a6
3
+ size 17210148
tokenizer_config.json ADDED
@@ -0,0 +1,2078 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "128256": {
2052
+ "content": "<|eom_id|>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ }
2059
+ },
2060
+ "additional_special_tokens": [
2061
+ "<|eot_id|>",
2062
+ "<|eom_id|>"
2063
+ ],
2064
+ "bos_token": "<|begin_of_text|>",
2065
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2066
+ "clean_up_tokenization_spaces": true,
2067
+ "eos_token": "<|eot_id|>",
2068
+ "extra_special_tokens": {},
2069
+ "model_input_names": [
2070
+ "input_ids",
2071
+ "attention_mask"
2072
+ ],
2073
+ "model_max_length": 1000000000000000019884624838656,
2074
+ "pad_token": "<|eot_id|>",
2075
+ "padding_side": "right",
2076
+ "split_special_tokens": false,
2077
+ "tokenizer_class": "PreTrainedTokenizer"
2078
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.96,
3
+ "total_flos": 21670257623040.0,
4
+ "train_loss": 0.5450129303079779,
5
+ "train_runtime": 5234.2515,
6
+ "train_samples_per_second": 0.573,
7
+ "train_steps_per_second": 0.036
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,187 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 186, "loss": 1.3849, "lr": 5.263157894736843e-07, "epoch": 0.016, "percentage": 0.54, "elapsed_time": "0:00:35", "remaining_time": "1:50:59"}
2
+ {"current_steps": 2, "total_steps": 186, "loss": 1.4064, "lr": 1.0526315789473685e-06, "epoch": 0.032, "percentage": 1.08, "elapsed_time": "0:01:08", "remaining_time": "1:45:01"}
3
+ {"current_steps": 3, "total_steps": 186, "loss": 1.0402, "lr": 1.5789473684210526e-06, "epoch": 0.048, "percentage": 1.61, "elapsed_time": "0:01:35", "remaining_time": "1:37:12"}
4
+ {"current_steps": 4, "total_steps": 186, "loss": 0.895, "lr": 2.105263157894737e-06, "epoch": 0.064, "percentage": 2.15, "elapsed_time": "0:01:47", "remaining_time": "1:21:18"}
5
+ {"current_steps": 5, "total_steps": 186, "loss": 1.0815, "lr": 2.631578947368421e-06, "epoch": 0.08, "percentage": 2.69, "elapsed_time": "0:02:15", "remaining_time": "1:21:33"}
6
+ {"current_steps": 6, "total_steps": 186, "loss": 1.2908, "lr": 3.157894736842105e-06, "epoch": 0.096, "percentage": 3.23, "elapsed_time": "0:03:02", "remaining_time": "1:31:08"}
7
+ {"current_steps": 7, "total_steps": 186, "loss": 1.2459, "lr": 3.6842105263157896e-06, "epoch": 0.112, "percentage": 3.76, "elapsed_time": "0:03:41", "remaining_time": "1:34:11"}
8
+ {"current_steps": 8, "total_steps": 186, "loss": 0.9707, "lr": 4.210526315789474e-06, "epoch": 0.128, "percentage": 4.3, "elapsed_time": "0:04:11", "remaining_time": "1:33:25"}
9
+ {"current_steps": 9, "total_steps": 186, "loss": 1.0695, "lr": 4.736842105263158e-06, "epoch": 0.144, "percentage": 4.84, "elapsed_time": "0:04:52", "remaining_time": "1:36:01"}
10
+ {"current_steps": 10, "total_steps": 186, "loss": 0.8253, "lr": 5.263157894736842e-06, "epoch": 0.16, "percentage": 5.38, "elapsed_time": "0:05:16", "remaining_time": "1:32:58"}
11
+ {"current_steps": 11, "total_steps": 186, "loss": 0.7806, "lr": 5.789473684210527e-06, "epoch": 0.176, "percentage": 5.91, "elapsed_time": "0:05:30", "remaining_time": "1:27:36"}
12
+ {"current_steps": 12, "total_steps": 186, "loss": 0.9426, "lr": 6.31578947368421e-06, "epoch": 0.192, "percentage": 6.45, "elapsed_time": "0:05:56", "remaining_time": "1:26:06"}
13
+ {"current_steps": 13, "total_steps": 186, "loss": 0.9984, "lr": 6.842105263157896e-06, "epoch": 0.208, "percentage": 6.99, "elapsed_time": "0:06:39", "remaining_time": "1:28:34"}
14
+ {"current_steps": 14, "total_steps": 186, "loss": 1.0925, "lr": 7.368421052631579e-06, "epoch": 0.224, "percentage": 7.53, "elapsed_time": "0:07:27", "remaining_time": "1:31:34"}
15
+ {"current_steps": 15, "total_steps": 186, "loss": 0.8113, "lr": 7.894736842105265e-06, "epoch": 0.24, "percentage": 8.06, "elapsed_time": "0:08:05", "remaining_time": "1:32:09"}
16
+ {"current_steps": 16, "total_steps": 186, "loss": 0.8985, "lr": 8.421052631578948e-06, "epoch": 0.256, "percentage": 8.6, "elapsed_time": "0:08:40", "remaining_time": "1:32:12"}
17
+ {"current_steps": 17, "total_steps": 186, "loss": 0.801, "lr": 8.947368421052632e-06, "epoch": 0.272, "percentage": 9.14, "elapsed_time": "0:09:06", "remaining_time": "1:30:28"}
18
+ {"current_steps": 18, "total_steps": 186, "loss": 0.8024, "lr": 9.473684210526315e-06, "epoch": 0.288, "percentage": 9.68, "elapsed_time": "0:09:32", "remaining_time": "1:29:06"}
19
+ {"current_steps": 19, "total_steps": 186, "loss": 0.9323, "lr": 1e-05, "epoch": 0.304, "percentage": 10.22, "elapsed_time": "0:10:10", "remaining_time": "1:29:26"}
20
+ {"current_steps": 20, "total_steps": 186, "loss": 0.8174, "lr": 9.999115304121459e-06, "epoch": 0.32, "percentage": 10.75, "elapsed_time": "0:10:50", "remaining_time": "1:29:58"}
21
+ {"current_steps": 21, "total_steps": 186, "loss": 0.7172, "lr": 9.996461529560553e-06, "epoch": 0.336, "percentage": 11.29, "elapsed_time": "0:11:13", "remaining_time": "1:28:12"}
22
+ {"current_steps": 22, "total_steps": 186, "loss": 0.7238, "lr": 9.992039615430648e-06, "epoch": 0.352, "percentage": 11.83, "elapsed_time": "0:11:43", "remaining_time": "1:27:20"}
23
+ {"current_steps": 23, "total_steps": 186, "loss": 0.8107, "lr": 9.985851126551428e-06, "epoch": 0.368, "percentage": 12.37, "elapsed_time": "0:12:16", "remaining_time": "1:26:58"}
24
+ {"current_steps": 24, "total_steps": 186, "loss": 0.7229, "lr": 9.977898252895133e-06, "epoch": 0.384, "percentage": 12.9, "elapsed_time": "0:12:41", "remaining_time": "1:25:42"}
25
+ {"current_steps": 25, "total_steps": 186, "loss": 0.6931, "lr": 9.968183808811586e-06, "epoch": 0.4, "percentage": 13.44, "elapsed_time": "0:13:11", "remaining_time": "1:24:57"}
26
+ {"current_steps": 26, "total_steps": 186, "loss": 0.746, "lr": 9.95671123203224e-06, "epoch": 0.416, "percentage": 13.98, "elapsed_time": "0:13:39", "remaining_time": "1:24:00"}
27
+ {"current_steps": 27, "total_steps": 186, "loss": 0.6654, "lr": 9.943484582453653e-06, "epoch": 0.432, "percentage": 14.52, "elapsed_time": "0:13:54", "remaining_time": "1:21:53"}
28
+ {"current_steps": 28, "total_steps": 186, "loss": 0.6921, "lr": 9.928508540700775e-06, "epoch": 0.448, "percentage": 15.05, "elapsed_time": "0:14:21", "remaining_time": "1:21:03"}
29
+ {"current_steps": 29, "total_steps": 186, "loss": 0.7111, "lr": 9.91178840647057e-06, "epoch": 0.464, "percentage": 15.59, "elapsed_time": "0:14:43", "remaining_time": "1:19:44"}
30
+ {"current_steps": 30, "total_steps": 186, "loss": 0.6362, "lr": 9.893330096656576e-06, "epoch": 0.48, "percentage": 16.13, "elapsed_time": "0:14:56", "remaining_time": "1:17:44"}
31
+ {"current_steps": 31, "total_steps": 186, "loss": 0.7653, "lr": 9.873140143255035e-06, "epoch": 0.496, "percentage": 16.67, "elapsed_time": "0:15:22", "remaining_time": "1:16:52"}
32
+ {"current_steps": 32, "total_steps": 186, "loss": 0.6662, "lr": 9.851225691053382e-06, "epoch": 0.512, "percentage": 17.2, "elapsed_time": "0:15:34", "remaining_time": "1:14:56"}
33
+ {"current_steps": 33, "total_steps": 186, "loss": 0.7745, "lr": 9.827594495101824e-06, "epoch": 0.528, "percentage": 17.74, "elapsed_time": "0:15:58", "remaining_time": "1:14:02"}
34
+ {"current_steps": 34, "total_steps": 186, "loss": 0.7405, "lr": 9.802254917969033e-06, "epoch": 0.544, "percentage": 18.28, "elapsed_time": "0:16:25", "remaining_time": "1:13:27"}
35
+ {"current_steps": 35, "total_steps": 186, "loss": 0.705, "lr": 9.775215926782788e-06, "epoch": 0.56, "percentage": 18.82, "elapsed_time": "0:17:08", "remaining_time": "1:13:56"}
36
+ {"current_steps": 36, "total_steps": 186, "loss": 0.6401, "lr": 9.746487090056712e-06, "epoch": 0.576, "percentage": 19.35, "elapsed_time": "0:17:21", "remaining_time": "1:12:21"}
37
+ {"current_steps": 37, "total_steps": 186, "loss": 0.7768, "lr": 9.71607857430419e-06, "epoch": 0.592, "percentage": 19.89, "elapsed_time": "0:18:01", "remaining_time": "1:12:35"}
38
+ {"current_steps": 38, "total_steps": 186, "loss": 0.801, "lr": 9.68400114044064e-06, "epoch": 0.608, "percentage": 20.43, "elapsed_time": "0:18:50", "remaining_time": "1:13:23"}
39
+ {"current_steps": 39, "total_steps": 186, "loss": 0.7914, "lr": 9.650266139975474e-06, "epoch": 0.624, "percentage": 20.97, "elapsed_time": "0:19:31", "remaining_time": "1:13:36"}
40
+ {"current_steps": 40, "total_steps": 186, "loss": 0.6431, "lr": 9.614885510995047e-06, "epoch": 0.64, "percentage": 21.51, "elapsed_time": "0:20:00", "remaining_time": "1:13:01"}
41
+ {"current_steps": 41, "total_steps": 186, "loss": 0.6685, "lr": 9.577871773938013e-06, "epoch": 0.656, "percentage": 22.04, "elapsed_time": "0:20:22", "remaining_time": "1:12:02"}
42
+ {"current_steps": 42, "total_steps": 186, "loss": 0.7304, "lr": 9.539238027164618e-06, "epoch": 0.672, "percentage": 22.58, "elapsed_time": "0:21:03", "remaining_time": "1:12:10"}
43
+ {"current_steps": 43, "total_steps": 186, "loss": 0.7133, "lr": 9.498997942321484e-06, "epoch": 0.688, "percentage": 23.12, "elapsed_time": "0:21:36", "remaining_time": "1:11:51"}
44
+ {"current_steps": 44, "total_steps": 186, "loss": 0.7122, "lr": 9.457165759503492e-06, "epoch": 0.704, "percentage": 23.66, "elapsed_time": "0:22:02", "remaining_time": "1:11:07"}
45
+ {"current_steps": 45, "total_steps": 186, "loss": 0.5962, "lr": 9.413756282214538e-06, "epoch": 0.72, "percentage": 24.19, "elapsed_time": "0:22:13", "remaining_time": "1:09:37"}
46
+ {"current_steps": 46, "total_steps": 186, "loss": 0.6571, "lr": 9.368784872128877e-06, "epoch": 0.736, "percentage": 24.73, "elapsed_time": "0:22:53", "remaining_time": "1:09:40"}
47
+ {"current_steps": 47, "total_steps": 186, "loss": 0.7153, "lr": 9.322267443654974e-06, "epoch": 0.752, "percentage": 25.27, "elapsed_time": "0:23:14", "remaining_time": "1:08:44"}
48
+ {"current_steps": 48, "total_steps": 186, "loss": 0.6427, "lr": 9.274220458303727e-06, "epoch": 0.768, "percentage": 25.81, "elapsed_time": "0:23:35", "remaining_time": "1:07:49"}
49
+ {"current_steps": 49, "total_steps": 186, "loss": 0.7456, "lr": 9.224660918863104e-06, "epoch": 0.784, "percentage": 26.34, "elapsed_time": "0:24:01", "remaining_time": "1:07:11"}
50
+ {"current_steps": 50, "total_steps": 186, "loss": 0.729, "lr": 9.173606363381218e-06, "epoch": 0.8, "percentage": 26.88, "elapsed_time": "0:24:49", "remaining_time": "1:07:31"}
51
+ {"current_steps": 51, "total_steps": 186, "loss": 0.6243, "lr": 9.121074858959997e-06, "epoch": 0.816, "percentage": 27.42, "elapsed_time": "0:25:14", "remaining_time": "1:06:49"}
52
+ {"current_steps": 52, "total_steps": 186, "loss": 0.6753, "lr": 9.067084995361623e-06, "epoch": 0.832, "percentage": 27.96, "elapsed_time": "0:25:51", "remaining_time": "1:06:37"}
53
+ {"current_steps": 53, "total_steps": 186, "loss": 0.656, "lr": 9.011655878430018e-06, "epoch": 0.848, "percentage": 28.49, "elapsed_time": "0:26:08", "remaining_time": "1:05:36"}
54
+ {"current_steps": 54, "total_steps": 186, "loss": 0.7196, "lr": 8.954807123329703e-06, "epoch": 0.864, "percentage": 29.03, "elapsed_time": "0:26:37", "remaining_time": "1:05:04"}
55
+ {"current_steps": 55, "total_steps": 186, "loss": 0.6435, "lr": 8.896558847604414e-06, "epoch": 0.88, "percentage": 29.57, "elapsed_time": "0:27:06", "remaining_time": "1:04:32"}
56
+ {"current_steps": 56, "total_steps": 186, "loss": 0.7281, "lr": 8.836931664057935e-06, "epoch": 0.896, "percentage": 30.11, "elapsed_time": "0:27:30", "remaining_time": "1:03:51"}
57
+ {"current_steps": 57, "total_steps": 186, "loss": 0.6243, "lr": 8.775946673459682e-06, "epoch": 0.912, "percentage": 30.65, "elapsed_time": "0:27:52", "remaining_time": "1:03:05"}
58
+ {"current_steps": 58, "total_steps": 186, "loss": 0.648, "lr": 8.713625457077585e-06, "epoch": 0.928, "percentage": 31.18, "elapsed_time": "0:28:17", "remaining_time": "1:02:26"}
59
+ {"current_steps": 59, "total_steps": 186, "loss": 0.6313, "lr": 8.64999006904096e-06, "epoch": 0.944, "percentage": 31.72, "elapsed_time": "0:28:44", "remaining_time": "1:01:52"}
60
+ {"current_steps": 60, "total_steps": 186, "loss": 0.6445, "lr": 8.585063028536015e-06, "epoch": 0.96, "percentage": 32.26, "elapsed_time": "0:29:06", "remaining_time": "1:01:08"}
61
+ {"current_steps": 61, "total_steps": 186, "loss": 0.6175, "lr": 8.518867311836808e-06, "epoch": 0.976, "percentage": 32.8, "elapsed_time": "0:29:25", "remaining_time": "1:00:17"}
62
+ {"current_steps": 62, "total_steps": 186, "loss": 0.6353, "lr": 8.451426344174433e-06, "epoch": 0.992, "percentage": 33.33, "elapsed_time": "0:29:42", "remaining_time": "0:59:24"}
63
+ {"current_steps": 63, "total_steps": 186, "loss": 0.6396, "lr": 8.382763991447344e-06, "epoch": 1.0, "percentage": 33.87, "elapsed_time": "0:29:57", "remaining_time": "0:58:29"}
64
+ {"current_steps": 64, "total_steps": 186, "loss": 0.589, "lr": 8.312904551775731e-06, "epoch": 1.016, "percentage": 34.41, "elapsed_time": "0:30:30", "remaining_time": "0:58:08"}
65
+ {"current_steps": 65, "total_steps": 186, "loss": 0.642, "lr": 8.241872746902934e-06, "epoch": 1.032, "percentage": 34.95, "elapsed_time": "0:31:08", "remaining_time": "0:57:57"}
66
+ {"current_steps": 66, "total_steps": 186, "loss": 0.5919, "lr": 8.16969371344696e-06, "epoch": 1.048, "percentage": 35.48, "elapsed_time": "0:31:38", "remaining_time": "0:57:32"}
67
+ {"current_steps": 67, "total_steps": 186, "loss": 0.5219, "lr": 8.096392994005177e-06, "epoch": 1.064, "percentage": 36.02, "elapsed_time": "0:32:11", "remaining_time": "0:57:10"}
68
+ {"current_steps": 68, "total_steps": 186, "loss": 0.4975, "lr": 8.021996528115335e-06, "epoch": 1.08, "percentage": 36.56, "elapsed_time": "0:32:35", "remaining_time": "0:56:33"}
69
+ {"current_steps": 69, "total_steps": 186, "loss": 0.4045, "lr": 7.946530643076138e-06, "epoch": 1.096, "percentage": 37.1, "elapsed_time": "0:33:00", "remaining_time": "0:55:58"}
70
+ {"current_steps": 70, "total_steps": 186, "loss": 0.5663, "lr": 7.870022044630569e-06, "epoch": 1.112, "percentage": 37.63, "elapsed_time": "0:33:32", "remaining_time": "0:55:34"}
71
+ {"current_steps": 71, "total_steps": 186, "loss": 0.5071, "lr": 7.792497807515317e-06, "epoch": 1.1280000000000001, "percentage": 38.17, "elapsed_time": "0:33:52", "remaining_time": "0:54:52"}
72
+ {"current_steps": 72, "total_steps": 186, "loss": 0.4374, "lr": 7.713985365879607e-06, "epoch": 1.144, "percentage": 38.71, "elapsed_time": "0:34:06", "remaining_time": "0:54:00"}
73
+ {"current_steps": 73, "total_steps": 186, "loss": 0.5385, "lr": 7.63451250357685e-06, "epoch": 1.16, "percentage": 39.25, "elapsed_time": "0:34:43", "remaining_time": "0:53:45"}
74
+ {"current_steps": 74, "total_steps": 186, "loss": 0.5088, "lr": 7.55410734433254e-06, "epoch": 1.176, "percentage": 39.78, "elapsed_time": "0:35:16", "remaining_time": "0:53:23"}
75
+ {"current_steps": 75, "total_steps": 186, "loss": 0.394, "lr": 7.472798341791877e-06, "epoch": 1.192, "percentage": 40.32, "elapsed_time": "0:35:31", "remaining_time": "0:52:34"}
76
+ {"current_steps": 76, "total_steps": 186, "loss": 0.5133, "lr": 7.390614269450633e-06, "epoch": 1.208, "percentage": 40.86, "elapsed_time": "0:36:00", "remaining_time": "0:52:07"}
77
+ {"current_steps": 77, "total_steps": 186, "loss": 0.4349, "lr": 7.3075842104728445e-06, "epoch": 1.224, "percentage": 41.4, "elapsed_time": "0:36:16", "remaining_time": "0:51:21"}
78
+ {"current_steps": 78, "total_steps": 186, "loss": 0.4948, "lr": 7.223737547398898e-06, "epoch": 1.24, "percentage": 41.94, "elapsed_time": "0:36:58", "remaining_time": "0:51:11"}
79
+ {"current_steps": 79, "total_steps": 186, "loss": 0.4855, "lr": 7.139103951747694e-06, "epoch": 1.256, "percentage": 42.47, "elapsed_time": "0:37:22", "remaining_time": "0:50:37"}
80
+ {"current_steps": 80, "total_steps": 186, "loss": 0.4599, "lr": 7.053713373516538e-06, "epoch": 1.272, "percentage": 43.01, "elapsed_time": "0:37:40", "remaining_time": "0:49:55"}
81
+ {"current_steps": 81, "total_steps": 186, "loss": 0.5597, "lr": 6.9675960305824785e-06, "epoch": 1.288, "percentage": 43.55, "elapsed_time": "0:38:28", "remaining_time": "0:49:52"}
82
+ {"current_steps": 82, "total_steps": 186, "loss": 0.4486, "lr": 6.880782398008862e-06, "epoch": 1.304, "percentage": 44.09, "elapsed_time": "0:38:54", "remaining_time": "0:49:20"}
83
+ {"current_steps": 83, "total_steps": 186, "loss": 0.5173, "lr": 6.7933031972608644e-06, "epoch": 1.32, "percentage": 44.62, "elapsed_time": "0:39:32", "remaining_time": "0:49:03"}
84
+ {"current_steps": 84, "total_steps": 186, "loss": 0.4891, "lr": 6.70518938533383e-06, "epoch": 1.336, "percentage": 45.16, "elapsed_time": "0:39:53", "remaining_time": "0:48:26"}
85
+ {"current_steps": 85, "total_steps": 186, "loss": 0.5729, "lr": 6.61647214379826e-06, "epoch": 1.3519999999999999, "percentage": 45.7, "elapsed_time": "0:40:25", "remaining_time": "0:48:02"}
86
+ {"current_steps": 86, "total_steps": 186, "loss": 0.4997, "lr": 6.527182867765333e-06, "epoch": 1.3679999999999999, "percentage": 46.24, "elapsed_time": "0:41:00", "remaining_time": "0:47:40"}
87
+ {"current_steps": 87, "total_steps": 186, "loss": 0.4983, "lr": 6.437353154776848e-06, "epoch": 1.384, "percentage": 46.77, "elapsed_time": "0:41:13", "remaining_time": "0:46:54"}
88
+ {"current_steps": 88, "total_steps": 186, "loss": 0.5028, "lr": 6.3470147936235485e-06, "epoch": 1.4, "percentage": 47.31, "elapsed_time": "0:41:50", "remaining_time": "0:46:35"}
89
+ {"current_steps": 89, "total_steps": 186, "loss": 0.5406, "lr": 6.256199753095745e-06, "epoch": 1.416, "percentage": 47.85, "elapsed_time": "0:42:11", "remaining_time": "0:45:58"}
90
+ {"current_steps": 90, "total_steps": 186, "loss": 0.4305, "lr": 6.164940170670266e-06, "epoch": 1.432, "percentage": 48.39, "elapsed_time": "0:42:35", "remaining_time": "0:45:25"}
91
+ {"current_steps": 91, "total_steps": 186, "loss": 0.4544, "lr": 6.073268341137694e-06, "epoch": 1.448, "percentage": 48.92, "elapsed_time": "0:42:47", "remaining_time": "0:44:40"}
92
+ {"current_steps": 92, "total_steps": 186, "loss": 0.5066, "lr": 5.98121670517393e-06, "epoch": 1.464, "percentage": 49.46, "elapsed_time": "0:43:17", "remaining_time": "0:44:14"}
93
+ {"current_steps": 93, "total_steps": 186, "loss": 0.5019, "lr": 5.8888178378601565e-06, "epoch": 1.48, "percentage": 50.0, "elapsed_time": "0:43:38", "remaining_time": "0:43:38"}
94
+ {"current_steps": 94, "total_steps": 186, "loss": 0.4756, "lr": 5.796104437155213e-06, "epoch": 1.496, "percentage": 50.54, "elapsed_time": "0:44:09", "remaining_time": "0:43:13"}
95
+ {"current_steps": 95, "total_steps": 186, "loss": 0.4896, "lr": 5.703109312324493e-06, "epoch": 1.512, "percentage": 51.08, "elapsed_time": "0:44:39", "remaining_time": "0:42:47"}
96
+ {"current_steps": 96, "total_steps": 186, "loss": 0.5845, "lr": 5.609865372329461e-06, "epoch": 1.528, "percentage": 51.61, "elapsed_time": "0:45:15", "remaining_time": "0:42:25"}
97
+ {"current_steps": 97, "total_steps": 186, "loss": 0.5868, "lr": 5.516405614181883e-06, "epoch": 1.544, "percentage": 52.15, "elapsed_time": "0:45:46", "remaining_time": "0:42:00"}
98
+ {"current_steps": 98, "total_steps": 186, "loss": 0.592, "lr": 5.4227631112668955e-06, "epoch": 1.56, "percentage": 52.69, "elapsed_time": "0:46:12", "remaining_time": "0:41:29"}
99
+ {"current_steps": 99, "total_steps": 186, "loss": 0.5143, "lr": 5.328971001639054e-06, "epoch": 1.576, "percentage": 53.23, "elapsed_time": "0:46:46", "remaining_time": "0:41:05"}
100
+ {"current_steps": 100, "total_steps": 186, "loss": 0.5155, "lr": 5.235062476295488e-06, "epoch": 1.592, "percentage": 53.76, "elapsed_time": "0:47:12", "remaining_time": "0:40:35"}
101
+ {"current_steps": 101, "total_steps": 186, "loss": 0.4888, "lr": 5.141070767430331e-06, "epoch": 1.608, "percentage": 54.3, "elapsed_time": "0:47:43", "remaining_time": "0:40:10"}
102
+ {"current_steps": 102, "total_steps": 186, "loss": 0.5572, "lr": 5.047029136674563e-06, "epoch": 1.624, "percentage": 54.84, "elapsed_time": "0:48:09", "remaining_time": "0:39:39"}
103
+ {"current_steps": 103, "total_steps": 186, "loss": 0.4697, "lr": 4.95297086332544e-06, "epoch": 1.6400000000000001, "percentage": 55.38, "elapsed_time": "0:48:24", "remaining_time": "0:39:00"}
104
+ {"current_steps": 104, "total_steps": 186, "loss": 0.4527, "lr": 4.858929232569671e-06, "epoch": 1.6560000000000001, "percentage": 55.91, "elapsed_time": "0:48:44", "remaining_time": "0:38:25"}
105
+ {"current_steps": 105, "total_steps": 186, "loss": 0.4727, "lr": 4.7649375237045135e-06, "epoch": 1.6720000000000002, "percentage": 56.45, "elapsed_time": "0:49:07", "remaining_time": "0:37:54"}
106
+ {"current_steps": 106, "total_steps": 186, "loss": 0.5009, "lr": 4.671028998360947e-06, "epoch": 1.688, "percentage": 56.99, "elapsed_time": "0:49:28", "remaining_time": "0:37:20"}
107
+ {"current_steps": 107, "total_steps": 186, "loss": 0.5175, "lr": 4.5772368887331044e-06, "epoch": 1.704, "percentage": 57.53, "elapsed_time": "0:49:57", "remaining_time": "0:36:53"}
108
+ {"current_steps": 108, "total_steps": 186, "loss": 0.3725, "lr": 4.483594385818119e-06, "epoch": 1.72, "percentage": 58.06, "elapsed_time": "0:50:11", "remaining_time": "0:36:14"}
109
+ {"current_steps": 109, "total_steps": 186, "loss": 0.6059, "lr": 4.39013462767054e-06, "epoch": 1.736, "percentage": 58.6, "elapsed_time": "0:50:42", "remaining_time": "0:35:49"}
110
+ {"current_steps": 110, "total_steps": 186, "loss": 0.4357, "lr": 4.29689068767551e-06, "epoch": 1.752, "percentage": 59.14, "elapsed_time": "0:51:06", "remaining_time": "0:35:18"}
111
+ {"current_steps": 111, "total_steps": 186, "loss": 0.4563, "lr": 4.203895562844789e-06, "epoch": 1.768, "percentage": 59.68, "elapsed_time": "0:51:18", "remaining_time": "0:34:40"}
112
+ {"current_steps": 112, "total_steps": 186, "loss": 0.4377, "lr": 4.111182162139844e-06, "epoch": 1.784, "percentage": 60.22, "elapsed_time": "0:51:37", "remaining_time": "0:34:06"}
113
+ {"current_steps": 113, "total_steps": 186, "loss": 0.4275, "lr": 4.018783294826071e-06, "epoch": 1.8, "percentage": 60.75, "elapsed_time": "0:52:23", "remaining_time": "0:33:50"}
114
+ {"current_steps": 114, "total_steps": 186, "loss": 0.5228, "lr": 3.926731658862307e-06, "epoch": 1.8159999999999998, "percentage": 61.29, "elapsed_time": "0:52:49", "remaining_time": "0:33:21"}
115
+ {"current_steps": 115, "total_steps": 186, "loss": 0.5258, "lr": 3.8350598293297345e-06, "epoch": 1.8319999999999999, "percentage": 61.83, "elapsed_time": "0:53:26", "remaining_time": "0:32:59"}
116
+ {"current_steps": 116, "total_steps": 186, "loss": 0.4063, "lr": 3.7438002469042567e-06, "epoch": 1.8479999999999999, "percentage": 62.37, "elapsed_time": "0:53:42", "remaining_time": "0:32:24"}
117
+ {"current_steps": 117, "total_steps": 186, "loss": 0.4821, "lr": 3.652985206376455e-06, "epoch": 1.8639999999999999, "percentage": 62.9, "elapsed_time": "0:54:14", "remaining_time": "0:31:59"}
118
+ {"current_steps": 118, "total_steps": 186, "loss": 0.4939, "lr": 3.5626468452231534e-06, "epoch": 1.88, "percentage": 63.44, "elapsed_time": "0:54:38", "remaining_time": "0:31:29"}
119
+ {"current_steps": 119, "total_steps": 186, "loss": 0.5338, "lr": 3.472817132234669e-06, "epoch": 1.896, "percentage": 63.98, "elapsed_time": "0:55:12", "remaining_time": "0:31:04"}
120
+ {"current_steps": 120, "total_steps": 186, "loss": 0.4957, "lr": 3.3835278562017405e-06, "epoch": 1.912, "percentage": 64.52, "elapsed_time": "0:55:38", "remaining_time": "0:30:36"}
121
+ {"current_steps": 121, "total_steps": 186, "loss": 0.4285, "lr": 3.29481061466617e-06, "epoch": 1.928, "percentage": 65.05, "elapsed_time": "0:55:54", "remaining_time": "0:30:02"}
122
+ {"current_steps": 122, "total_steps": 186, "loss": 0.457, "lr": 3.2066968027391377e-06, "epoch": 1.944, "percentage": 65.59, "elapsed_time": "0:56:06", "remaining_time": "0:29:26"}
123
+ {"current_steps": 123, "total_steps": 186, "loss": 0.4218, "lr": 3.119217601991139e-06, "epoch": 1.96, "percentage": 66.13, "elapsed_time": "0:56:38", "remaining_time": "0:29:00"}
124
+ {"current_steps": 124, "total_steps": 186, "loss": 0.3875, "lr": 3.032403969417523e-06, "epoch": 1.976, "percentage": 66.67, "elapsed_time": "0:56:54", "remaining_time": "0:28:27"}
125
+ {"current_steps": 125, "total_steps": 186, "loss": 0.4412, "lr": 2.946286626483463e-06, "epoch": 1.992, "percentage": 67.2, "elapsed_time": "0:57:38", "remaining_time": "0:28:07"}
126
+ {"current_steps": 126, "total_steps": 186, "loss": 0.4625, "lr": 2.8608960482523058e-06, "epoch": 2.0, "percentage": 67.74, "elapsed_time": "0:58:00", "remaining_time": "0:27:37"}
127
+ {"current_steps": 127, "total_steps": 186, "loss": 0.3664, "lr": 2.776262452601104e-06, "epoch": 2.016, "percentage": 68.28, "elapsed_time": "0:58:29", "remaining_time": "0:27:10"}
128
+ {"current_steps": 128, "total_steps": 186, "loss": 0.37, "lr": 2.6924157895271563e-06, "epoch": 2.032, "percentage": 68.82, "elapsed_time": "0:58:55", "remaining_time": "0:26:41"}
129
+ {"current_steps": 129, "total_steps": 186, "loss": 0.322, "lr": 2.6093857305493666e-06, "epoch": 2.048, "percentage": 69.35, "elapsed_time": "0:59:13", "remaining_time": "0:26:09"}
130
+ {"current_steps": 130, "total_steps": 186, "loss": 0.3695, "lr": 2.5272016582081236e-06, "epoch": 2.064, "percentage": 69.89, "elapsed_time": "0:59:47", "remaining_time": "0:25:45"}
131
+ {"current_steps": 131, "total_steps": 186, "loss": 0.3229, "lr": 2.445892655667462e-06, "epoch": 2.08, "percentage": 70.43, "elapsed_time": "1:00:19", "remaining_time": "0:25:19"}
132
+ {"current_steps": 132, "total_steps": 186, "loss": 0.3354, "lr": 2.365487496423152e-06, "epoch": 2.096, "percentage": 70.97, "elapsed_time": "1:00:51", "remaining_time": "0:24:53"}
133
+ {"current_steps": 133, "total_steps": 186, "loss": 0.3207, "lr": 2.2860146341203936e-06, "epoch": 2.112, "percentage": 71.51, "elapsed_time": "1:01:10", "remaining_time": "0:24:22"}
134
+ {"current_steps": 134, "total_steps": 186, "loss": 0.2488, "lr": 2.207502192484685e-06, "epoch": 2.128, "percentage": 72.04, "elapsed_time": "1:01:25", "remaining_time": "0:23:50"}
135
+ {"current_steps": 135, "total_steps": 186, "loss": 0.4157, "lr": 2.1299779553694323e-06, "epoch": 2.144, "percentage": 72.58, "elapsed_time": "1:01:53", "remaining_time": "0:23:22"}
136
+ {"current_steps": 136, "total_steps": 186, "loss": 0.4506, "lr": 2.053469356923865e-06, "epoch": 2.16, "percentage": 73.12, "elapsed_time": "1:02:19", "remaining_time": "0:22:54"}
137
+ {"current_steps": 137, "total_steps": 186, "loss": 0.3653, "lr": 1.9780034718846653e-06, "epoch": 2.176, "percentage": 73.66, "elapsed_time": "1:02:47", "remaining_time": "0:22:27"}
138
+ {"current_steps": 138, "total_steps": 186, "loss": 0.3349, "lr": 1.9036070059948253e-06, "epoch": 2.192, "percentage": 74.19, "elapsed_time": "1:03:21", "remaining_time": "0:22:02"}
139
+ {"current_steps": 139, "total_steps": 186, "loss": 0.3425, "lr": 1.8303062865530407e-06, "epoch": 2.208, "percentage": 74.73, "elapsed_time": "1:03:50", "remaining_time": "0:21:35"}
140
+ {"current_steps": 140, "total_steps": 186, "loss": 0.3322, "lr": 1.7581272530970666e-06, "epoch": 2.224, "percentage": 75.27, "elapsed_time": "1:04:13", "remaining_time": "0:21:06"}
141
+ {"current_steps": 141, "total_steps": 186, "loss": 0.3241, "lr": 1.6870954482242707e-06, "epoch": 2.24, "percentage": 75.81, "elapsed_time": "1:04:44", "remaining_time": "0:20:39"}
142
+ {"current_steps": 142, "total_steps": 186, "loss": 0.2696, "lr": 1.6172360085526567e-06, "epoch": 2.2560000000000002, "percentage": 76.34, "elapsed_time": "1:04:59", "remaining_time": "0:20:08"}
143
+ {"current_steps": 143, "total_steps": 186, "loss": 0.3464, "lr": 1.54857365582557e-06, "epoch": 2.2720000000000002, "percentage": 76.88, "elapsed_time": "1:05:30", "remaining_time": "0:19:41"}
144
+ {"current_steps": 144, "total_steps": 186, "loss": 0.3499, "lr": 1.4811326881631937e-06, "epoch": 2.288, "percentage": 77.42, "elapsed_time": "1:06:06", "remaining_time": "0:19:17"}
145
+ {"current_steps": 145, "total_steps": 186, "loss": 0.3419, "lr": 1.4149369714639856e-06, "epoch": 2.304, "percentage": 77.96, "elapsed_time": "1:06:33", "remaining_time": "0:18:49"}
146
+ {"current_steps": 146, "total_steps": 186, "loss": 0.4196, "lr": 1.3500099309590397e-06, "epoch": 2.32, "percentage": 78.49, "elapsed_time": "1:07:07", "remaining_time": "0:18:23"}
147
+ {"current_steps": 147, "total_steps": 186, "loss": 0.3369, "lr": 1.2863745429224145e-06, "epoch": 2.336, "percentage": 79.03, "elapsed_time": "1:07:28", "remaining_time": "0:17:54"}
148
+ {"current_steps": 148, "total_steps": 186, "loss": 0.4233, "lr": 1.22405332654032e-06, "epoch": 2.352, "percentage": 79.57, "elapsed_time": "1:08:02", "remaining_time": "0:17:28"}
149
+ {"current_steps": 149, "total_steps": 186, "loss": 0.358, "lr": 1.1630683359420653e-06, "epoch": 2.368, "percentage": 80.11, "elapsed_time": "1:08:24", "remaining_time": "0:16:59"}
150
+ {"current_steps": 150, "total_steps": 186, "loss": 0.2888, "lr": 1.103441152395588e-06, "epoch": 2.384, "percentage": 80.65, "elapsed_time": "1:08:39", "remaining_time": "0:16:28"}
151
+ {"current_steps": 151, "total_steps": 186, "loss": 0.2591, "lr": 1.045192876670298e-06, "epoch": 2.4, "percentage": 81.18, "elapsed_time": "1:08:50", "remaining_time": "0:15:57"}
152
+ {"current_steps": 152, "total_steps": 186, "loss": 0.3791, "lr": 9.883441215699824e-07, "epoch": 2.416, "percentage": 81.72, "elapsed_time": "1:09:21", "remaining_time": "0:15:30"}
153
+ {"current_steps": 153, "total_steps": 186, "loss": 0.331, "lr": 9.329150046383773e-07, "epoch": 2.432, "percentage": 82.26, "elapsed_time": "1:09:55", "remaining_time": "0:15:05"}
154
+ {"current_steps": 154, "total_steps": 186, "loss": 0.2818, "lr": 8.789251410400024e-07, "epoch": 2.448, "percentage": 82.8, "elapsed_time": "1:10:13", "remaining_time": "0:14:35"}
155
+ {"current_steps": 155, "total_steps": 186, "loss": 0.3005, "lr": 8.263936366187825e-07, "epoch": 2.464, "percentage": 83.33, "elapsed_time": "1:10:30", "remaining_time": "0:14:06"}
156
+ {"current_steps": 156, "total_steps": 186, "loss": 0.3003, "lr": 7.753390811368972e-07, "epoch": 2.48, "percentage": 83.87, "elapsed_time": "1:10:46", "remaining_time": "0:13:36"}
157
+ {"current_steps": 157, "total_steps": 186, "loss": 0.3347, "lr": 7.257795416962754e-07, "epoch": 2.496, "percentage": 84.41, "elapsed_time": "1:11:31", "remaining_time": "0:13:12"}
158
+ {"current_steps": 158, "total_steps": 186, "loss": 0.4411, "lr": 6.777325563450282e-07, "epoch": 2.512, "percentage": 84.95, "elapsed_time": "1:12:22", "remaining_time": "0:12:49"}
159
+ {"current_steps": 159, "total_steps": 186, "loss": 0.3053, "lr": 6.312151278711237e-07, "epoch": 2.528, "percentage": 85.48, "elapsed_time": "1:12:40", "remaining_time": "0:12:20"}
160
+ {"current_steps": 160, "total_steps": 186, "loss": 0.3424, "lr": 5.862437177854629e-07, "epoch": 2.544, "percentage": 86.02, "elapsed_time": "1:13:04", "remaining_time": "0:11:52"}
161
+ {"current_steps": 161, "total_steps": 186, "loss": 0.3474, "lr": 5.428342404965076e-07, "epoch": 2.56, "percentage": 86.56, "elapsed_time": "1:13:29", "remaining_time": "0:11:24"}
162
+ {"current_steps": 162, "total_steps": 186, "loss": 0.3146, "lr": 5.010020576785174e-07, "epoch": 2.576, "percentage": 87.1, "elapsed_time": "1:14:00", "remaining_time": "0:10:57"}
163
+ {"current_steps": 163, "total_steps": 186, "loss": 0.3134, "lr": 4.607619728353818e-07, "epoch": 2.592, "percentage": 87.63, "elapsed_time": "1:14:22", "remaining_time": "0:10:29"}
164
+ {"current_steps": 164, "total_steps": 186, "loss": 0.3337, "lr": 4.221282260619891e-07, "epoch": 2.608, "percentage": 88.17, "elapsed_time": "1:14:43", "remaining_time": "0:10:01"}
165
+ {"current_steps": 165, "total_steps": 186, "loss": 0.4023, "lr": 3.851144890049535e-07, "epoch": 2.624, "percentage": 88.71, "elapsed_time": "1:15:16", "remaining_time": "0:09:34"}
166
+ {"current_steps": 166, "total_steps": 186, "loss": 0.3021, "lr": 3.497338600245254e-07, "epoch": 2.64, "percentage": 89.25, "elapsed_time": "1:15:35", "remaining_time": "0:09:06"}
167
+ {"current_steps": 167, "total_steps": 186, "loss": 0.3485, "lr": 3.159988595593616e-07, "epoch": 2.656, "percentage": 89.78, "elapsed_time": "1:16:14", "remaining_time": "0:08:40"}
168
+ {"current_steps": 168, "total_steps": 186, "loss": 0.3852, "lr": 2.839214256958106e-07, "epoch": 2.672, "percentage": 90.32, "elapsed_time": "1:16:48", "remaining_time": "0:08:13"}
169
+ {"current_steps": 169, "total_steps": 186, "loss": 0.3677, "lr": 2.5351290994328703e-07, "epoch": 2.6879999999999997, "percentage": 90.86, "elapsed_time": "1:17:28", "remaining_time": "0:07:47"}
170
+ {"current_steps": 170, "total_steps": 186, "loss": 0.2545, "lr": 2.2478407321721295e-07, "epoch": 2.7039999999999997, "percentage": 91.4, "elapsed_time": "1:17:43", "remaining_time": "0:07:18"}
171
+ {"current_steps": 171, "total_steps": 186, "loss": 0.2907, "lr": 1.9774508203096843e-07, "epoch": 2.7199999999999998, "percentage": 91.94, "elapsed_time": "1:18:16", "remaining_time": "0:06:51"}
172
+ {"current_steps": 172, "total_steps": 186, "loss": 0.3116, "lr": 1.7240550489817652e-07, "epoch": 2.7359999999999998, "percentage": 92.47, "elapsed_time": "1:19:05", "remaining_time": "0:06:26"}
173
+ {"current_steps": 173, "total_steps": 186, "loss": 0.2597, "lr": 1.4877430894662037e-07, "epoch": 2.752, "percentage": 93.01, "elapsed_time": "1:19:19", "remaining_time": "0:05:57"}
174
+ {"current_steps": 174, "total_steps": 186, "loss": 0.4666, "lr": 1.268598567449647e-07, "epoch": 2.768, "percentage": 93.55, "elapsed_time": "1:20:03", "remaining_time": "0:05:31"}
175
+ {"current_steps": 175, "total_steps": 186, "loss": 0.3047, "lr": 1.0666990334342708e-07, "epoch": 2.784, "percentage": 94.09, "elapsed_time": "1:20:26", "remaining_time": "0:05:03"}
176
+ {"current_steps": 176, "total_steps": 186, "loss": 0.363, "lr": 8.821159352943142e-08, "epoch": 2.8, "percentage": 94.62, "elapsed_time": "1:21:00", "remaining_time": "0:04:36"}
177
+ {"current_steps": 177, "total_steps": 186, "loss": 0.3118, "lr": 7.149145929922607e-08, "epoch": 2.816, "percentage": 95.16, "elapsed_time": "1:21:20", "remaining_time": "0:04:08"}
178
+ {"current_steps": 178, "total_steps": 186, "loss": 0.2766, "lr": 5.651541754634726e-08, "epoch": 2.832, "percentage": 95.7, "elapsed_time": "1:21:46", "remaining_time": "0:03:40"}
179
+ {"current_steps": 179, "total_steps": 186, "loss": 0.3311, "lr": 4.328876796776071e-08, "epoch": 2.848, "percentage": 96.24, "elapsed_time": "1:22:10", "remaining_time": "0:03:12"}
180
+ {"current_steps": 180, "total_steps": 186, "loss": 0.3399, "lr": 3.181619118841517e-08, "epoch": 2.864, "percentage": 96.77, "elapsed_time": "1:22:30", "remaining_time": "0:02:45"}
181
+ {"current_steps": 181, "total_steps": 186, "loss": 0.4328, "lr": 2.210174710486679e-08, "epoch": 2.88, "percentage": 97.31, "elapsed_time": "1:23:16", "remaining_time": "0:02:18"}
182
+ {"current_steps": 182, "total_steps": 186, "loss": 0.3449, "lr": 1.4148873448573408e-08, "epoch": 2.896, "percentage": 97.85, "elapsed_time": "1:23:55", "remaining_time": "0:01:50"}
183
+ {"current_steps": 183, "total_steps": 186, "loss": 0.3814, "lr": 7.96038456935322e-09, "epoch": 2.912, "percentage": 98.39, "elapsed_time": "1:24:37", "remaining_time": "0:01:23"}
184
+ {"current_steps": 184, "total_steps": 186, "loss": 0.3605, "lr": 3.538470439448105e-09, "epoch": 2.928, "percentage": 98.92, "elapsed_time": "1:25:14", "remaining_time": "0:00:55"}
185
+ {"current_steps": 185, "total_steps": 186, "loss": 0.2759, "lr": 8.846958785418969e-10, "epoch": 2.944, "percentage": 99.46, "elapsed_time": "1:25:44", "remaining_time": "0:00:27"}
186
+ {"current_steps": 186, "total_steps": 186, "loss": 0.2919, "lr": 0.0, "epoch": 2.96, "percentage": 100.0, "elapsed_time": "1:26:08", "remaining_time": "0:00:00"}
187
+ {"current_steps": 186, "total_steps": 186, "epoch": 2.96, "percentage": 100.0, "elapsed_time": "1:27:14", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,1344 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.96,
5
+ "eval_steps": 500,
6
+ "global_step": 186,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.016,
13
+ "grad_norm": 17.265566540871276,
14
+ "learning_rate": 5.263157894736843e-07,
15
+ "loss": 1.3849,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.032,
20
+ "grad_norm": 20.089852093670576,
21
+ "learning_rate": 1.0526315789473685e-06,
22
+ "loss": 1.4064,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.048,
27
+ "grad_norm": 6.589490853652612,
28
+ "learning_rate": 1.5789473684210526e-06,
29
+ "loss": 1.0402,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.064,
34
+ "grad_norm": 5.14296612105976,
35
+ "learning_rate": 2.105263157894737e-06,
36
+ "loss": 0.895,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.08,
41
+ "grad_norm": 8.124533688517559,
42
+ "learning_rate": 2.631578947368421e-06,
43
+ "loss": 1.0815,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.096,
48
+ "grad_norm": 8.84827182866774,
49
+ "learning_rate": 3.157894736842105e-06,
50
+ "loss": 1.2908,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.112,
55
+ "grad_norm": 8.203756927127115,
56
+ "learning_rate": 3.6842105263157896e-06,
57
+ "loss": 1.2459,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.128,
62
+ "grad_norm": 7.57722281069691,
63
+ "learning_rate": 4.210526315789474e-06,
64
+ "loss": 0.9707,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.144,
69
+ "grad_norm": 7.102462941011033,
70
+ "learning_rate": 4.736842105263158e-06,
71
+ "loss": 1.0695,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.16,
76
+ "grad_norm": 3.382564005385294,
77
+ "learning_rate": 5.263157894736842e-06,
78
+ "loss": 0.8253,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.176,
83
+ "grad_norm": 2.883997467358394,
84
+ "learning_rate": 5.789473684210527e-06,
85
+ "loss": 0.7806,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.192,
90
+ "grad_norm": 3.48767265499384,
91
+ "learning_rate": 6.31578947368421e-06,
92
+ "loss": 0.9426,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.208,
97
+ "grad_norm": 3.6801016439021033,
98
+ "learning_rate": 6.842105263157896e-06,
99
+ "loss": 0.9984,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.224,
104
+ "grad_norm": 5.111818314033425,
105
+ "learning_rate": 7.368421052631579e-06,
106
+ "loss": 1.0925,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.24,
111
+ "grad_norm": 3.00809107659031,
112
+ "learning_rate": 7.894736842105265e-06,
113
+ "loss": 0.8113,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.256,
118
+ "grad_norm": 2.5810942766550613,
119
+ "learning_rate": 8.421052631578948e-06,
120
+ "loss": 0.8985,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.272,
125
+ "grad_norm": 2.239234193084543,
126
+ "learning_rate": 8.947368421052632e-06,
127
+ "loss": 0.801,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.288,
132
+ "grad_norm": 1.977889876770481,
133
+ "learning_rate": 9.473684210526315e-06,
134
+ "loss": 0.8024,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.304,
139
+ "grad_norm": 2.5321288733806107,
140
+ "learning_rate": 1e-05,
141
+ "loss": 0.9323,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.32,
146
+ "grad_norm": 2.3084642254292005,
147
+ "learning_rate": 9.999115304121459e-06,
148
+ "loss": 0.8174,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.336,
153
+ "grad_norm": 2.275895453495919,
154
+ "learning_rate": 9.996461529560553e-06,
155
+ "loss": 0.7172,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.352,
160
+ "grad_norm": 2.390705215087479,
161
+ "learning_rate": 9.992039615430648e-06,
162
+ "loss": 0.7238,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.368,
167
+ "grad_norm": 1.9421657131294014,
168
+ "learning_rate": 9.985851126551428e-06,
169
+ "loss": 0.8107,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.384,
174
+ "grad_norm": 2.058372329799834,
175
+ "learning_rate": 9.977898252895133e-06,
176
+ "loss": 0.7229,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.4,
181
+ "grad_norm": 1.9006752617160494,
182
+ "learning_rate": 9.968183808811586e-06,
183
+ "loss": 0.6931,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.416,
188
+ "grad_norm": 2.054145992306095,
189
+ "learning_rate": 9.95671123203224e-06,
190
+ "loss": 0.746,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.432,
195
+ "grad_norm": 1.9468770299243592,
196
+ "learning_rate": 9.943484582453653e-06,
197
+ "loss": 0.6654,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.448,
202
+ "grad_norm": 1.814496686840529,
203
+ "learning_rate": 9.928508540700775e-06,
204
+ "loss": 0.6921,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.464,
209
+ "grad_norm": 1.802486279814975,
210
+ "learning_rate": 9.91178840647057e-06,
211
+ "loss": 0.7111,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.48,
216
+ "grad_norm": 1.9478710077072412,
217
+ "learning_rate": 9.893330096656576e-06,
218
+ "loss": 0.6362,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.496,
223
+ "grad_norm": 1.8318214451416757,
224
+ "learning_rate": 9.873140143255035e-06,
225
+ "loss": 0.7653,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.512,
230
+ "grad_norm": 1.8452709208358775,
231
+ "learning_rate": 9.851225691053382e-06,
232
+ "loss": 0.6662,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.528,
237
+ "grad_norm": 1.983049889607633,
238
+ "learning_rate": 9.827594495101824e-06,
239
+ "loss": 0.7745,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.544,
244
+ "grad_norm": 1.8290774383219428,
245
+ "learning_rate": 9.802254917969033e-06,
246
+ "loss": 0.7405,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.56,
251
+ "grad_norm": 1.732618942001559,
252
+ "learning_rate": 9.775215926782788e-06,
253
+ "loss": 0.705,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.576,
258
+ "grad_norm": 1.8003122188796479,
259
+ "learning_rate": 9.746487090056712e-06,
260
+ "loss": 0.6401,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.592,
265
+ "grad_norm": 2.0123189922467315,
266
+ "learning_rate": 9.71607857430419e-06,
267
+ "loss": 0.7768,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.608,
272
+ "grad_norm": 1.9124994424711974,
273
+ "learning_rate": 9.68400114044064e-06,
274
+ "loss": 0.801,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.624,
279
+ "grad_norm": 1.6874581302472245,
280
+ "learning_rate": 9.650266139975474e-06,
281
+ "loss": 0.7914,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.64,
286
+ "grad_norm": 1.8036614396987305,
287
+ "learning_rate": 9.614885510995047e-06,
288
+ "loss": 0.6431,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.656,
293
+ "grad_norm": 1.7792173564341356,
294
+ "learning_rate": 9.577871773938013e-06,
295
+ "loss": 0.6685,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.672,
300
+ "grad_norm": 2.106904023154908,
301
+ "learning_rate": 9.539238027164618e-06,
302
+ "loss": 0.7304,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.688,
307
+ "grad_norm": 1.9512092168832307,
308
+ "learning_rate": 9.498997942321484e-06,
309
+ "loss": 0.7133,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.704,
314
+ "grad_norm": 1.8794356205862166,
315
+ "learning_rate": 9.457165759503492e-06,
316
+ "loss": 0.7122,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.72,
321
+ "grad_norm": 1.9449756616113063,
322
+ "learning_rate": 9.413756282214538e-06,
323
+ "loss": 0.5962,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.736,
328
+ "grad_norm": 1.749613648866588,
329
+ "learning_rate": 9.368784872128877e-06,
330
+ "loss": 0.6571,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.752,
335
+ "grad_norm": 1.9668503728809823,
336
+ "learning_rate": 9.322267443654974e-06,
337
+ "loss": 0.7153,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.768,
342
+ "grad_norm": 2.0756580484041245,
343
+ "learning_rate": 9.274220458303727e-06,
344
+ "loss": 0.6427,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.784,
349
+ "grad_norm": 1.7320764922054182,
350
+ "learning_rate": 9.224660918863104e-06,
351
+ "loss": 0.7456,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.8,
356
+ "grad_norm": 1.7692368287021367,
357
+ "learning_rate": 9.173606363381218e-06,
358
+ "loss": 0.729,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.816,
363
+ "grad_norm": 1.9599425283213727,
364
+ "learning_rate": 9.121074858959997e-06,
365
+ "loss": 0.6243,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.832,
370
+ "grad_norm": 1.6116899916566545,
371
+ "learning_rate": 9.067084995361623e-06,
372
+ "loss": 0.6753,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.848,
377
+ "grad_norm": 1.9862542412605975,
378
+ "learning_rate": 9.011655878430018e-06,
379
+ "loss": 0.656,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.864,
384
+ "grad_norm": 1.8386860819765696,
385
+ "learning_rate": 8.954807123329703e-06,
386
+ "loss": 0.7196,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.88,
391
+ "grad_norm": 1.6272214888273704,
392
+ "learning_rate": 8.896558847604414e-06,
393
+ "loss": 0.6435,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.896,
398
+ "grad_norm": 1.7446187430114655,
399
+ "learning_rate": 8.836931664057935e-06,
400
+ "loss": 0.7281,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.912,
405
+ "grad_norm": 1.7164804652605405,
406
+ "learning_rate": 8.775946673459682e-06,
407
+ "loss": 0.6243,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.928,
412
+ "grad_norm": 1.5894836987127223,
413
+ "learning_rate": 8.713625457077585e-06,
414
+ "loss": 0.648,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.944,
419
+ "grad_norm": 1.6190441689783222,
420
+ "learning_rate": 8.64999006904096e-06,
421
+ "loss": 0.6313,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.96,
426
+ "grad_norm": 1.7601660204750595,
427
+ "learning_rate": 8.585063028536015e-06,
428
+ "loss": 0.6445,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.976,
433
+ "grad_norm": 1.6814846694055416,
434
+ "learning_rate": 8.518867311836808e-06,
435
+ "loss": 0.6175,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.992,
440
+ "grad_norm": 1.554320926318259,
441
+ "learning_rate": 8.451426344174433e-06,
442
+ "loss": 0.6353,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 1.0,
447
+ "grad_norm": 1.554320926318259,
448
+ "learning_rate": 8.382763991447344e-06,
449
+ "loss": 0.6396,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 1.016,
454
+ "grad_norm": 2.514616810040317,
455
+ "learning_rate": 8.312904551775731e-06,
456
+ "loss": 0.589,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 1.032,
461
+ "grad_norm": 1.5914266097871264,
462
+ "learning_rate": 8.241872746902934e-06,
463
+ "loss": 0.642,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 1.048,
468
+ "grad_norm": 1.6715859096702153,
469
+ "learning_rate": 8.16969371344696e-06,
470
+ "loss": 0.5919,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 1.064,
475
+ "grad_norm": 1.7221785188395358,
476
+ "learning_rate": 8.096392994005177e-06,
477
+ "loss": 0.5219,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 1.08,
482
+ "grad_norm": 1.523934181331874,
483
+ "learning_rate": 8.021996528115335e-06,
484
+ "loss": 0.4975,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 1.096,
489
+ "grad_norm": 1.7251860309038605,
490
+ "learning_rate": 7.946530643076138e-06,
491
+ "loss": 0.4045,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 1.112,
496
+ "grad_norm": 2.1387296754306453,
497
+ "learning_rate": 7.870022044630569e-06,
498
+ "loss": 0.5663,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 1.1280000000000001,
503
+ "grad_norm": 1.5678644951260237,
504
+ "learning_rate": 7.792497807515317e-06,
505
+ "loss": 0.5071,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 1.144,
510
+ "grad_norm": 2.1069613377109864,
511
+ "learning_rate": 7.713985365879607e-06,
512
+ "loss": 0.4374,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 1.16,
517
+ "grad_norm": 1.7700256012070563,
518
+ "learning_rate": 7.63451250357685e-06,
519
+ "loss": 0.5385,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 1.176,
524
+ "grad_norm": 1.4683115653202277,
525
+ "learning_rate": 7.55410734433254e-06,
526
+ "loss": 0.5088,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 1.192,
531
+ "grad_norm": 3.2315487431671173,
532
+ "learning_rate": 7.472798341791877e-06,
533
+ "loss": 0.394,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 1.208,
538
+ "grad_norm": 1.7315310300769962,
539
+ "learning_rate": 7.390614269450633e-06,
540
+ "loss": 0.5133,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 1.224,
545
+ "grad_norm": 1.7186427379174711,
546
+ "learning_rate": 7.3075842104728445e-06,
547
+ "loss": 0.4349,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 1.24,
552
+ "grad_norm": 1.718919488729367,
553
+ "learning_rate": 7.223737547398898e-06,
554
+ "loss": 0.4948,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 1.256,
559
+ "grad_norm": 1.7710317999113074,
560
+ "learning_rate": 7.139103951747694e-06,
561
+ "loss": 0.4855,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 1.272,
566
+ "grad_norm": 1.7053255613043878,
567
+ "learning_rate": 7.053713373516538e-06,
568
+ "loss": 0.4599,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 1.288,
573
+ "grad_norm": 1.6455437889543758,
574
+ "learning_rate": 6.9675960305824785e-06,
575
+ "loss": 0.5597,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 1.304,
580
+ "grad_norm": 1.928985400009411,
581
+ "learning_rate": 6.880782398008862e-06,
582
+ "loss": 0.4486,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 1.32,
587
+ "grad_norm": 1.557246422551428,
588
+ "learning_rate": 6.7933031972608644e-06,
589
+ "loss": 0.5173,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 1.336,
594
+ "grad_norm": 1.6393519103212826,
595
+ "learning_rate": 6.70518938533383e-06,
596
+ "loss": 0.4891,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 1.3519999999999999,
601
+ "grad_norm": 1.5087677558718193,
602
+ "learning_rate": 6.61647214379826e-06,
603
+ "loss": 0.5729,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 1.3679999999999999,
608
+ "grad_norm": 1.607244932229975,
609
+ "learning_rate": 6.527182867765333e-06,
610
+ "loss": 0.4997,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 1.384,
615
+ "grad_norm": 1.6372031149188508,
616
+ "learning_rate": 6.437353154776848e-06,
617
+ "loss": 0.4983,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 1.4,
622
+ "grad_norm": 1.763840958323373,
623
+ "learning_rate": 6.3470147936235485e-06,
624
+ "loss": 0.5028,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 1.416,
629
+ "grad_norm": 1.7861540798275108,
630
+ "learning_rate": 6.256199753095745e-06,
631
+ "loss": 0.5406,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 1.432,
636
+ "grad_norm": 1.499957779372258,
637
+ "learning_rate": 6.164940170670266e-06,
638
+ "loss": 0.4305,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 1.448,
643
+ "grad_norm": 1.995733104339069,
644
+ "learning_rate": 6.073268341137694e-06,
645
+ "loss": 0.4544,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 1.464,
650
+ "grad_norm": 1.9151523868805838,
651
+ "learning_rate": 5.98121670517393e-06,
652
+ "loss": 0.5066,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 1.48,
657
+ "grad_norm": 1.4756706730929385,
658
+ "learning_rate": 5.8888178378601565e-06,
659
+ "loss": 0.5019,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 1.496,
664
+ "grad_norm": 1.649862272540868,
665
+ "learning_rate": 5.796104437155213e-06,
666
+ "loss": 0.4756,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 1.512,
671
+ "grad_norm": 1.7212809492557795,
672
+ "learning_rate": 5.703109312324493e-06,
673
+ "loss": 0.4896,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 1.528,
678
+ "grad_norm": 1.9194800100352978,
679
+ "learning_rate": 5.609865372329461e-06,
680
+ "loss": 0.5845,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 1.544,
685
+ "grad_norm": 1.8731612795860104,
686
+ "learning_rate": 5.516405614181883e-06,
687
+ "loss": 0.5868,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 1.56,
692
+ "grad_norm": 1.4387957716763344,
693
+ "learning_rate": 5.4227631112668955e-06,
694
+ "loss": 0.592,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 1.576,
699
+ "grad_norm": 2.2104402624908706,
700
+ "learning_rate": 5.328971001639054e-06,
701
+ "loss": 0.5143,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 1.592,
706
+ "grad_norm": 1.4292270032965346,
707
+ "learning_rate": 5.235062476295488e-06,
708
+ "loss": 0.5155,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 1.608,
713
+ "grad_norm": 1.7550654702916557,
714
+ "learning_rate": 5.141070767430331e-06,
715
+ "loss": 0.4888,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 1.624,
720
+ "grad_norm": 1.5018754865504773,
721
+ "learning_rate": 5.047029136674563e-06,
722
+ "loss": 0.5572,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 1.6400000000000001,
727
+ "grad_norm": 1.51385812350827,
728
+ "learning_rate": 4.95297086332544e-06,
729
+ "loss": 0.4697,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 1.6560000000000001,
734
+ "grad_norm": 2.038637843864613,
735
+ "learning_rate": 4.858929232569671e-06,
736
+ "loss": 0.4527,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 1.6720000000000002,
741
+ "grad_norm": 1.520271301988124,
742
+ "learning_rate": 4.7649375237045135e-06,
743
+ "loss": 0.4727,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 1.688,
748
+ "grad_norm": 1.5283877837212068,
749
+ "learning_rate": 4.671028998360947e-06,
750
+ "loss": 0.5009,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 1.704,
755
+ "grad_norm": 1.7732975300862988,
756
+ "learning_rate": 4.5772368887331044e-06,
757
+ "loss": 0.5175,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 1.72,
762
+ "grad_norm": 1.7652466043543638,
763
+ "learning_rate": 4.483594385818119e-06,
764
+ "loss": 0.3725,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 1.736,
769
+ "grad_norm": 2.338369077116064,
770
+ "learning_rate": 4.39013462767054e-06,
771
+ "loss": 0.6059,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 1.752,
776
+ "grad_norm": 1.693230322723448,
777
+ "learning_rate": 4.29689068767551e-06,
778
+ "loss": 0.4357,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 1.768,
783
+ "grad_norm": 1.827758943805404,
784
+ "learning_rate": 4.203895562844789e-06,
785
+ "loss": 0.4563,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 1.784,
790
+ "grad_norm": 1.7904258585266672,
791
+ "learning_rate": 4.111182162139844e-06,
792
+ "loss": 0.4377,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 1.8,
797
+ "grad_norm": 1.5612150330770178,
798
+ "learning_rate": 4.018783294826071e-06,
799
+ "loss": 0.4275,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 1.8159999999999998,
804
+ "grad_norm": 1.523037615179662,
805
+ "learning_rate": 3.926731658862307e-06,
806
+ "loss": 0.5228,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 1.8319999999999999,
811
+ "grad_norm": 1.5255447437439678,
812
+ "learning_rate": 3.8350598293297345e-06,
813
+ "loss": 0.5258,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 1.8479999999999999,
818
+ "grad_norm": 1.5829211736970477,
819
+ "learning_rate": 3.7438002469042567e-06,
820
+ "loss": 0.4063,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 1.8639999999999999,
825
+ "grad_norm": 1.5773032081061509,
826
+ "learning_rate": 3.652985206376455e-06,
827
+ "loss": 0.4821,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 1.88,
832
+ "grad_norm": 1.4805521281076799,
833
+ "learning_rate": 3.5626468452231534e-06,
834
+ "loss": 0.4939,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 1.896,
839
+ "grad_norm": 1.5554298604401637,
840
+ "learning_rate": 3.472817132234669e-06,
841
+ "loss": 0.5338,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 1.912,
846
+ "grad_norm": 1.5494033362764545,
847
+ "learning_rate": 3.3835278562017405e-06,
848
+ "loss": 0.4957,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 1.928,
853
+ "grad_norm": 1.5831323686883927,
854
+ "learning_rate": 3.29481061466617e-06,
855
+ "loss": 0.4285,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 1.944,
860
+ "grad_norm": 1.5898749396215215,
861
+ "learning_rate": 3.2066968027391377e-06,
862
+ "loss": 0.457,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 1.96,
867
+ "grad_norm": 1.5157195677831812,
868
+ "learning_rate": 3.119217601991139e-06,
869
+ "loss": 0.4218,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 1.976,
874
+ "grad_norm": 1.5731407093139658,
875
+ "learning_rate": 3.032403969417523e-06,
876
+ "loss": 0.3875,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 1.992,
881
+ "grad_norm": 1.7232422836213686,
882
+ "learning_rate": 2.946286626483463e-06,
883
+ "loss": 0.4412,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 2.0,
888
+ "grad_norm": 2.393109486523402,
889
+ "learning_rate": 2.8608960482523058e-06,
890
+ "loss": 0.4625,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 2.016,
895
+ "grad_norm": 2.257370296808367,
896
+ "learning_rate": 2.776262452601104e-06,
897
+ "loss": 0.3664,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 2.032,
902
+ "grad_norm": 2.0798503170345866,
903
+ "learning_rate": 2.6924157895271563e-06,
904
+ "loss": 0.37,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 2.048,
909
+ "grad_norm": 1.6371039756658181,
910
+ "learning_rate": 2.6093857305493666e-06,
911
+ "loss": 0.322,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 2.064,
916
+ "grad_norm": 1.5223327796553272,
917
+ "learning_rate": 2.5272016582081236e-06,
918
+ "loss": 0.3695,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 2.08,
923
+ "grad_norm": 1.6380378858305447,
924
+ "learning_rate": 2.445892655667462e-06,
925
+ "loss": 0.3229,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 2.096,
930
+ "grad_norm": 3.120605376278745,
931
+ "learning_rate": 2.365487496423152e-06,
932
+ "loss": 0.3354,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 2.112,
937
+ "grad_norm": 1.8530996062038518,
938
+ "learning_rate": 2.2860146341203936e-06,
939
+ "loss": 0.3207,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 2.128,
944
+ "grad_norm": 2.079838959175905,
945
+ "learning_rate": 2.207502192484685e-06,
946
+ "loss": 0.2488,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 2.144,
951
+ "grad_norm": 1.8087558940405277,
952
+ "learning_rate": 2.1299779553694323e-06,
953
+ "loss": 0.4157,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 2.16,
958
+ "grad_norm": 1.8451844625035758,
959
+ "learning_rate": 2.053469356923865e-06,
960
+ "loss": 0.4506,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 2.176,
965
+ "grad_norm": 1.6518452502805208,
966
+ "learning_rate": 1.9780034718846653e-06,
967
+ "loss": 0.3653,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 2.192,
972
+ "grad_norm": 1.663937556819872,
973
+ "learning_rate": 1.9036070059948253e-06,
974
+ "loss": 0.3349,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 2.208,
979
+ "grad_norm": 1.5820059418011216,
980
+ "learning_rate": 1.8303062865530407e-06,
981
+ "loss": 0.3425,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 2.224,
986
+ "grad_norm": 1.576843734833355,
987
+ "learning_rate": 1.7581272530970666e-06,
988
+ "loss": 0.3322,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 2.24,
993
+ "grad_norm": 1.7275837235833509,
994
+ "learning_rate": 1.6870954482242707e-06,
995
+ "loss": 0.3241,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 2.2560000000000002,
1000
+ "grad_norm": 1.726720454583051,
1001
+ "learning_rate": 1.6172360085526567e-06,
1002
+ "loss": 0.2696,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 2.2720000000000002,
1007
+ "grad_norm": 2.010215233237989,
1008
+ "learning_rate": 1.54857365582557e-06,
1009
+ "loss": 0.3464,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 2.288,
1014
+ "grad_norm": 1.8848106151516786,
1015
+ "learning_rate": 1.4811326881631937e-06,
1016
+ "loss": 0.3499,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 2.304,
1021
+ "grad_norm": 1.5388938200969897,
1022
+ "learning_rate": 1.4149369714639856e-06,
1023
+ "loss": 0.3419,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 2.32,
1028
+ "grad_norm": 1.5044322184419996,
1029
+ "learning_rate": 1.3500099309590397e-06,
1030
+ "loss": 0.4196,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 2.336,
1035
+ "grad_norm": 1.6274762480553728,
1036
+ "learning_rate": 1.2863745429224145e-06,
1037
+ "loss": 0.3369,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 2.352,
1042
+ "grad_norm": 1.4496643724972158,
1043
+ "learning_rate": 1.22405332654032e-06,
1044
+ "loss": 0.4233,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 2.368,
1049
+ "grad_norm": 1.943638242632571,
1050
+ "learning_rate": 1.1630683359420653e-06,
1051
+ "loss": 0.358,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 2.384,
1056
+ "grad_norm": 1.933655917159831,
1057
+ "learning_rate": 1.103441152395588e-06,
1058
+ "loss": 0.2888,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 2.4,
1063
+ "grad_norm": 2.031085917073374,
1064
+ "learning_rate": 1.045192876670298e-06,
1065
+ "loss": 0.2591,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 2.416,
1070
+ "grad_norm": 1.5293961459532648,
1071
+ "learning_rate": 9.883441215699824e-07,
1072
+ "loss": 0.3791,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 2.432,
1077
+ "grad_norm": 1.588731036259167,
1078
+ "learning_rate": 9.329150046383773e-07,
1079
+ "loss": 0.331,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 2.448,
1084
+ "grad_norm": 1.4858621936000498,
1085
+ "learning_rate": 8.789251410400024e-07,
1086
+ "loss": 0.2818,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 2.464,
1091
+ "grad_norm": 1.7426467948455326,
1092
+ "learning_rate": 8.263936366187825e-07,
1093
+ "loss": 0.3005,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 2.48,
1098
+ "grad_norm": 1.7460841045163584,
1099
+ "learning_rate": 7.753390811368972e-07,
1100
+ "loss": 0.3003,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 2.496,
1105
+ "grad_norm": 1.5976363728033662,
1106
+ "learning_rate": 7.257795416962754e-07,
1107
+ "loss": 0.3347,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 2.512,
1112
+ "grad_norm": 1.885887380938252,
1113
+ "learning_rate": 6.777325563450282e-07,
1114
+ "loss": 0.4411,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 2.528,
1119
+ "grad_norm": 1.6121877256346284,
1120
+ "learning_rate": 6.312151278711237e-07,
1121
+ "loss": 0.3053,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 2.544,
1126
+ "grad_norm": 1.6916631587022424,
1127
+ "learning_rate": 5.862437177854629e-07,
1128
+ "loss": 0.3424,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 2.56,
1133
+ "grad_norm": 1.5105490449456516,
1134
+ "learning_rate": 5.428342404965076e-07,
1135
+ "loss": 0.3474,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 2.576,
1140
+ "grad_norm": 1.5897890361860791,
1141
+ "learning_rate": 5.010020576785174e-07,
1142
+ "loss": 0.3146,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 2.592,
1147
+ "grad_norm": 1.7421226681944129,
1148
+ "learning_rate": 4.607619728353818e-07,
1149
+ "loss": 0.3134,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 2.608,
1154
+ "grad_norm": 1.6114545605409272,
1155
+ "learning_rate": 4.221282260619891e-07,
1156
+ "loss": 0.3337,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 2.624,
1161
+ "grad_norm": 1.6581271061315566,
1162
+ "learning_rate": 3.851144890049535e-07,
1163
+ "loss": 0.4023,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 2.64,
1168
+ "grad_norm": 1.6669298907958805,
1169
+ "learning_rate": 3.497338600245254e-07,
1170
+ "loss": 0.3021,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 2.656,
1175
+ "grad_norm": 1.5082405058478559,
1176
+ "learning_rate": 3.159988595593616e-07,
1177
+ "loss": 0.3485,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 2.672,
1182
+ "grad_norm": 1.6867142867470823,
1183
+ "learning_rate": 2.839214256958106e-07,
1184
+ "loss": 0.3852,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 2.6879999999999997,
1189
+ "grad_norm": 1.4197906212673126,
1190
+ "learning_rate": 2.5351290994328703e-07,
1191
+ "loss": 0.3677,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 2.7039999999999997,
1196
+ "grad_norm": 1.6371560986781053,
1197
+ "learning_rate": 2.2478407321721295e-07,
1198
+ "loss": 0.2545,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 2.7199999999999998,
1203
+ "grad_norm": 1.513927276530402,
1204
+ "learning_rate": 1.9774508203096843e-07,
1205
+ "loss": 0.2907,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 2.7359999999999998,
1210
+ "grad_norm": 1.6505772046236602,
1211
+ "learning_rate": 1.7240550489817652e-07,
1212
+ "loss": 0.3116,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 2.752,
1217
+ "grad_norm": 1.6467061689919404,
1218
+ "learning_rate": 1.4877430894662037e-07,
1219
+ "loss": 0.2597,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 2.768,
1224
+ "grad_norm": 1.3910601508999687,
1225
+ "learning_rate": 1.268598567449647e-07,
1226
+ "loss": 0.4666,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 2.784,
1231
+ "grad_norm": 1.5158376103770992,
1232
+ "learning_rate": 1.0666990334342708e-07,
1233
+ "loss": 0.3047,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 2.8,
1238
+ "grad_norm": 1.4078568916572975,
1239
+ "learning_rate": 8.821159352943142e-08,
1240
+ "loss": 0.363,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 2.816,
1245
+ "grad_norm": 1.5414756510402199,
1246
+ "learning_rate": 7.149145929922607e-08,
1247
+ "loss": 0.3118,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 2.832,
1252
+ "grad_norm": 1.5590409985711402,
1253
+ "learning_rate": 5.651541754634726e-08,
1254
+ "loss": 0.2766,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 2.848,
1259
+ "grad_norm": 1.4929985095640963,
1260
+ "learning_rate": 4.328876796776071e-08,
1261
+ "loss": 0.3311,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 2.864,
1266
+ "grad_norm": 1.5070078137197234,
1267
+ "learning_rate": 3.181619118841517e-08,
1268
+ "loss": 0.3399,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 2.88,
1273
+ "grad_norm": 1.4238651288325814,
1274
+ "learning_rate": 2.210174710486679e-08,
1275
+ "loss": 0.4328,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 2.896,
1280
+ "grad_norm": 1.4194361676055525,
1281
+ "learning_rate": 1.4148873448573408e-08,
1282
+ "loss": 0.3449,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 2.912,
1287
+ "grad_norm": 1.5984952095126612,
1288
+ "learning_rate": 7.96038456935322e-09,
1289
+ "loss": 0.3814,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 2.928,
1294
+ "grad_norm": 1.4302652833406175,
1295
+ "learning_rate": 3.538470439448105e-09,
1296
+ "loss": 0.3605,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 2.944,
1301
+ "grad_norm": 1.4596899305481994,
1302
+ "learning_rate": 8.846958785418969e-10,
1303
+ "loss": 0.2759,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 2.96,
1308
+ "grad_norm": 1.4920781635835423,
1309
+ "learning_rate": 0.0,
1310
+ "loss": 0.2919,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 2.96,
1315
+ "step": 186,
1316
+ "total_flos": 21670257623040.0,
1317
+ "train_loss": 0.5450129303079779,
1318
+ "train_runtime": 5234.2515,
1319
+ "train_samples_per_second": 0.573,
1320
+ "train_steps_per_second": 0.036
1321
+ }
1322
+ ],
1323
+ "logging_steps": 1,
1324
+ "max_steps": 186,
1325
+ "num_input_tokens_seen": 0,
1326
+ "num_train_epochs": 3,
1327
+ "save_steps": 500,
1328
+ "stateful_callbacks": {
1329
+ "TrainerControl": {
1330
+ "args": {
1331
+ "should_epoch_stop": false,
1332
+ "should_evaluate": false,
1333
+ "should_log": false,
1334
+ "should_save": true,
1335
+ "should_training_stop": true
1336
+ },
1337
+ "attributes": {}
1338
+ }
1339
+ },
1340
+ "total_flos": 21670257623040.0,
1341
+ "train_batch_size": 1,
1342
+ "trial_name": null,
1343
+ "trial_params": null
1344
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ada18d04986708ed964c1201f0f6888902e078437fd300dbf9edca59fc427427
3
+ size 7480
training_loss.png ADDED