qq8933 commited on
Commit
16bdc67
1 Parent(s): ea6e551

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: google/gemma-2-2b-it
4
+ tags:
5
+ - llama-factory
6
+ - full
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: longcot_pt_GEMMA_ZD_10_23_1
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # longcot_pt_GEMMA_ZD_10_23_1
17
+
18
+ This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on the longcot_pt dataset.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 1
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - distributed_type: multi-GPU
42
+ - num_devices: 8
43
+ - total_train_batch_size: 8
44
+ - total_eval_batch_size: 64
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: cosine
47
+ - num_epochs: 1.0
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - Transformers 4.44.0
56
+ - Pytorch 2.3.1
57
+ - Datasets 2.21.0
58
+ - Tokenizers 0.19.1
added_tokens.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<conclusion>": 256006,
3
+ "<critic>": 256005,
4
+ "<end_of_father_id>": 256012,
5
+ "<end_of_local_id>": 256014,
6
+ "<end_of_rating>": 256002,
7
+ "<end_of_thought>": 256008,
8
+ "<negative_rating>": 256004,
9
+ "<positive_rating>": 256003,
10
+ "<problem>": 256009,
11
+ "<refine>": 256010,
12
+ "<start_of_father_id>": 256011,
13
+ "<start_of_local_id>": 256013,
14
+ "<start_of_rating>": 256000,
15
+ "<start_of_thought>": 256007,
16
+ "<unknown_rating>": 256001
17
+ }
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 5.842272600604017e+17,
4
+ "train_loss": 0.47904590670458097,
5
+ "train_runtime": 1388.8864,
6
+ "train_samples_per_second": 2.881,
7
+ "train_steps_per_second": 0.361
8
+ }
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/gemma-2-2b-it",
3
+ "architectures": [
4
+ "Gemma2ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": 50.0,
9
+ "bos_token_id": 2,
10
+ "cache_implementation": "hybrid",
11
+ "eos_token_id": [
12
+ 1,
13
+ 107
14
+ ],
15
+ "final_logit_softcapping": 30.0,
16
+ "head_dim": 256,
17
+ "hidden_act": "gelu_pytorch_tanh",
18
+ "hidden_activation": "gelu_pytorch_tanh",
19
+ "hidden_size": 2304,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 9216,
22
+ "max_position_embeddings": 8192,
23
+ "model_type": "gemma2",
24
+ "num_attention_heads": 8,
25
+ "num_hidden_layers": 26,
26
+ "num_key_value_heads": 4,
27
+ "pad_token_id": 0,
28
+ "query_pre_attn_scalar": 256,
29
+ "rms_norm_eps": 1e-06,
30
+ "rope_theta": 10000.0,
31
+ "sliding_window": 4096,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.44.0",
34
+ "use_cache": false,
35
+ "vocab_size": 256064
36
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "cache_implementation": "hybrid",
5
+ "eos_token_id": [
6
+ 1,
7
+ 107
8
+ ],
9
+ "pad_token_id": 0,
10
+ "transformers_version": "4.44.0"
11
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7519ace7f8004eb5b26b8b6e2d8703dcebb809df2c708871fec0015b84df4237
3
+ size 4988320672
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceba8a3e42a064fbcacf54a4815b80dc3130cdc07bb5f40b69255d480cf6e1b7
3
+ size 1420634792
model.safetensors.index.json ADDED
@@ -0,0 +1,296 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6408921600
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.14.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.15.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.15.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.16.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.16.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.17.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.17.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.18.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.18.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.19.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.19.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.20.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.20.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.21.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.21.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.22.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.22.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.23.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.23.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
217
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
225
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
227
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
229
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
234
+ "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
235
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
236
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
237
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
238
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
239
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
240
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
241
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
242
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.norm.weight": "model-00002-of-00002.safetensors"
295
+ }
296
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<start_of_turn>",
4
+ "<end_of_turn>",
5
+ {
6
+ "content": "<start_of_rating>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ {
13
+ "content": "<unknown_rating>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ {
20
+ "content": "<end_of_rating>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ {
27
+ "content": "<positive_rating>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ {
34
+ "content": "<negative_rating>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ {
41
+ "content": "<critic>",
42
+ "lstrip": false,
43
+ "normalized": false,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ {
48
+ "content": "<conclusion>",
49
+ "lstrip": false,
50
+ "normalized": false,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ {
55
+ "content": "<start_of_thought>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false
60
+ },
61
+ {
62
+ "content": "<end_of_thought>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false
67
+ },
68
+ {
69
+ "content": "<problem>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false
74
+ },
75
+ {
76
+ "content": "<refine>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false
81
+ },
82
+ {
83
+ "content": "<start_of_father_id>",
84
+ "lstrip": false,
85
+ "normalized": false,
86
+ "rstrip": false,
87
+ "single_word": false
88
+ },
89
+ {
90
+ "content": "<end_of_father_id>",
91
+ "lstrip": false,
92
+ "normalized": false,
93
+ "rstrip": false,
94
+ "single_word": false
95
+ },
96
+ {
97
+ "content": "<start_of_local_id>",
98
+ "lstrip": false,
99
+ "normalized": false,
100
+ "rstrip": false,
101
+ "single_word": false
102
+ },
103
+ {
104
+ "content": "<end_of_local_id>",
105
+ "lstrip": false,
106
+ "normalized": false,
107
+ "rstrip": false,
108
+ "single_word": false
109
+ }
110
+ ],
111
+ "bos_token": {
112
+ "content": "<bos>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "eos_token": {
119
+ "content": "<eos>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ },
125
+ "pad_token": {
126
+ "content": "<pad>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false
131
+ },
132
+ "unk_token": {
133
+ "content": "<unk>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false
138
+ }
139
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fa54d6b50b274c4502f1892401dd420afb6a12c1e59115373883e2e3702266a
3
+ size 17528239
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
tokenizer_config.json ADDED
@@ -0,0 +1,2150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<mask>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "5": {
46
+ "content": "<2mass>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "6": {
54
+ "content": "[@BOS@]",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "7": {
62
+ "content": "<unused0>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "8": {
70
+ "content": "<unused1>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "9": {
78
+ "content": "<unused2>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "10": {
86
+ "content": "<unused3>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "11": {
94
+ "content": "<unused4>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "12": {
102
+ "content": "<unused5>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "13": {
110
+ "content": "<unused6>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "14": {
118
+ "content": "<unused7>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "15": {
126
+ "content": "<unused8>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "16": {
134
+ "content": "<unused9>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "17": {
142
+ "content": "<unused10>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "18": {
150
+ "content": "<unused11>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "19": {
158
+ "content": "<unused12>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "20": {
166
+ "content": "<unused13>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "21": {
174
+ "content": "<unused14>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "22": {
182
+ "content": "<unused15>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "23": {
190
+ "content": "<unused16>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "24": {
198
+ "content": "<unused17>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "25": {
206
+ "content": "<unused18>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "26": {
214
+ "content": "<unused19>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "27": {
222
+ "content": "<unused20>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "28": {
230
+ "content": "<unused21>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "29": {
238
+ "content": "<unused22>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "30": {
246
+ "content": "<unused23>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "31": {
254
+ "content": "<unused24>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "32": {
262
+ "content": "<unused25>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "33": {
270
+ "content": "<unused26>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "34": {
278
+ "content": "<unused27>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "35": {
286
+ "content": "<unused28>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "36": {
294
+ "content": "<unused29>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "37": {
302
+ "content": "<unused30>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "38": {
310
+ "content": "<unused31>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ },
317
+ "39": {
318
+ "content": "<unused32>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": false
324
+ },
325
+ "40": {
326
+ "content": "<unused33>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": false
332
+ },
333
+ "41": {
334
+ "content": "<unused34>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": false
340
+ },
341
+ "42": {
342
+ "content": "<unused35>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": false
348
+ },
349
+ "43": {
350
+ "content": "<unused36>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": false
356
+ },
357
+ "44": {
358
+ "content": "<unused37>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": false
364
+ },
365
+ "45": {
366
+ "content": "<unused38>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": false
372
+ },
373
+ "46": {
374
+ "content": "<unused39>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": false
380
+ },
381
+ "47": {
382
+ "content": "<unused40>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": false
388
+ },
389
+ "48": {
390
+ "content": "<unused41>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": false
396
+ },
397
+ "49": {
398
+ "content": "<unused42>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": false
404
+ },
405
+ "50": {
406
+ "content": "<unused43>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": false
412
+ },
413
+ "51": {
414
+ "content": "<unused44>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": false
420
+ },
421
+ "52": {
422
+ "content": "<unused45>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": false
428
+ },
429
+ "53": {
430
+ "content": "<unused46>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": false
436
+ },
437
+ "54": {
438
+ "content": "<unused47>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": false
444
+ },
445
+ "55": {
446
+ "content": "<unused48>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": false
452
+ },
453
+ "56": {
454
+ "content": "<unused49>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": false
460
+ },
461
+ "57": {
462
+ "content": "<unused50>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": false
468
+ },
469
+ "58": {
470
+ "content": "<unused51>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": false
476
+ },
477
+ "59": {
478
+ "content": "<unused52>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": false
484
+ },
485
+ "60": {
486
+ "content": "<unused53>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": false
492
+ },
493
+ "61": {
494
+ "content": "<unused54>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": false
500
+ },
501
+ "62": {
502
+ "content": "<unused55>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": false
508
+ },
509
+ "63": {
510
+ "content": "<unused56>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": false
516
+ },
517
+ "64": {
518
+ "content": "<unused57>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": false
524
+ },
525
+ "65": {
526
+ "content": "<unused58>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": false
532
+ },
533
+ "66": {
534
+ "content": "<unused59>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": false
540
+ },
541
+ "67": {
542
+ "content": "<unused60>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": false
548
+ },
549
+ "68": {
550
+ "content": "<unused61>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": false
556
+ },
557
+ "69": {
558
+ "content": "<unused62>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": false
564
+ },
565
+ "70": {
566
+ "content": "<unused63>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": false
572
+ },
573
+ "71": {
574
+ "content": "<unused64>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": false
580
+ },
581
+ "72": {
582
+ "content": "<unused65>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": false
588
+ },
589
+ "73": {
590
+ "content": "<unused66>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": false
596
+ },
597
+ "74": {
598
+ "content": "<unused67>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": false
604
+ },
605
+ "75": {
606
+ "content": "<unused68>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": false
612
+ },
613
+ "76": {
614
+ "content": "<unused69>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": false
620
+ },
621
+ "77": {
622
+ "content": "<unused70>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": false
628
+ },
629
+ "78": {
630
+ "content": "<unused71>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": false
636
+ },
637
+ "79": {
638
+ "content": "<unused72>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": false
644
+ },
645
+ "80": {
646
+ "content": "<unused73>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": false
652
+ },
653
+ "81": {
654
+ "content": "<unused74>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": false
660
+ },
661
+ "82": {
662
+ "content": "<unused75>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": false
668
+ },
669
+ "83": {
670
+ "content": "<unused76>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": false
676
+ },
677
+ "84": {
678
+ "content": "<unused77>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": false
684
+ },
685
+ "85": {
686
+ "content": "<unused78>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": false
692
+ },
693
+ "86": {
694
+ "content": "<unused79>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": false
700
+ },
701
+ "87": {
702
+ "content": "<unused80>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": false
708
+ },
709
+ "88": {
710
+ "content": "<unused81>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": false
716
+ },
717
+ "89": {
718
+ "content": "<unused82>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": false
724
+ },
725
+ "90": {
726
+ "content": "<unused83>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": false
732
+ },
733
+ "91": {
734
+ "content": "<unused84>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": false
740
+ },
741
+ "92": {
742
+ "content": "<unused85>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": false
748
+ },
749
+ "93": {
750
+ "content": "<unused86>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": false
756
+ },
757
+ "94": {
758
+ "content": "<unused87>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": false
764
+ },
765
+ "95": {
766
+ "content": "<unused88>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": false
772
+ },
773
+ "96": {
774
+ "content": "<unused89>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": false
780
+ },
781
+ "97": {
782
+ "content": "<unused90>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": false
788
+ },
789
+ "98": {
790
+ "content": "<unused91>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": false
796
+ },
797
+ "99": {
798
+ "content": "<unused92>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": false
804
+ },
805
+ "100": {
806
+ "content": "<unused93>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": false
812
+ },
813
+ "101": {
814
+ "content": "<unused94>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": false
820
+ },
821
+ "102": {
822
+ "content": "<unused95>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": false
828
+ },
829
+ "103": {
830
+ "content": "<unused96>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": false
836
+ },
837
+ "104": {
838
+ "content": "<unused97>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": false
844
+ },
845
+ "105": {
846
+ "content": "<unused98>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": false
852
+ },
853
+ "106": {
854
+ "content": "<start_of_turn>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "107": {
862
+ "content": "<end_of_turn>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "108": {
870
+ "content": "\n",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": false
876
+ },
877
+ "109": {
878
+ "content": "\n\n",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": false
884
+ },
885
+ "110": {
886
+ "content": "\n\n\n",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": false
892
+ },
893
+ "111": {
894
+ "content": "\n\n\n\n",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": false
900
+ },
901
+ "112": {
902
+ "content": "\n\n\n\n\n",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": false
908
+ },
909
+ "113": {
910
+ "content": "\n\n\n\n\n\n",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": false
916
+ },
917
+ "114": {
918
+ "content": "\n\n\n\n\n\n\n",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": false
924
+ },
925
+ "115": {
926
+ "content": "\n\n\n\n\n\n\n\n",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": false
932
+ },
933
+ "116": {
934
+ "content": "\n\n\n\n\n\n\n\n\n",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": false
940
+ },
941
+ "117": {
942
+ "content": "\n\n\n\n\n\n\n\n\n\n",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": false
948
+ },
949
+ "118": {
950
+ "content": "\n\n\n\n\n\n\n\n\n\n\n",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": false
956
+ },
957
+ "119": {
958
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": false
964
+ },
965
+ "120": {
966
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": false
972
+ },
973
+ "121": {
974
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": false
980
+ },
981
+ "122": {
982
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": false
988
+ },
989
+ "123": {
990
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": false
996
+ },
997
+ "124": {
998
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": false
1004
+ },
1005
+ "125": {
1006
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": false
1012
+ },
1013
+ "126": {
1014
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": false
1020
+ },
1021
+ "127": {
1022
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": false
1028
+ },
1029
+ "128": {
1030
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": false
1036
+ },
1037
+ "129": {
1038
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": false
1044
+ },
1045
+ "130": {
1046
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": false
1052
+ },
1053
+ "131": {
1054
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": false
1060
+ },
1061
+ "132": {
1062
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": false
1068
+ },
1069
+ "133": {
1070
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": false
1076
+ },
1077
+ "134": {
1078
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": false
1084
+ },
1085
+ "135": {
1086
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": false
1092
+ },
1093
+ "136": {
1094
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": false
1100
+ },
1101
+ "137": {
1102
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": false
1108
+ },
1109
+ "138": {
1110
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": false
1116
+ },
1117
+ "139": {
1118
+ "content": "▁▁",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": false
1124
+ },
1125
+ "140": {
1126
+ "content": "▁▁▁",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": false
1132
+ },
1133
+ "141": {
1134
+ "content": "▁▁▁▁",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": false
1140
+ },
1141
+ "142": {
1142
+ "content": "▁▁▁▁▁",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": false
1148
+ },
1149
+ "143": {
1150
+ "content": "▁▁▁▁▁▁",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": false
1156
+ },
1157
+ "144": {
1158
+ "content": "▁▁▁▁▁▁▁",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": false
1164
+ },
1165
+ "145": {
1166
+ "content": "▁▁▁▁▁▁▁▁",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": false
1172
+ },
1173
+ "146": {
1174
+ "content": "▁▁▁▁▁▁▁▁▁",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": false
1180
+ },
1181
+ "147": {
1182
+ "content": "▁▁▁▁▁▁▁▁▁▁",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": false
1188
+ },
1189
+ "148": {
1190
+ "content": "▁▁▁▁▁▁▁▁▁▁▁",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": false
1196
+ },
1197
+ "149": {
1198
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": false
1204
+ },
1205
+ "150": {
1206
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": false
1212
+ },
1213
+ "151": {
1214
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": false
1220
+ },
1221
+ "152": {
1222
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": false
1228
+ },
1229
+ "153": {
1230
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": false
1236
+ },
1237
+ "154": {
1238
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": false
1244
+ },
1245
+ "155": {
1246
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": false
1252
+ },
1253
+ "156": {
1254
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": false
1260
+ },
1261
+ "157": {
1262
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": false
1268
+ },
1269
+ "158": {
1270
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": false
1276
+ },
1277
+ "159": {
1278
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": false
1284
+ },
1285
+ "160": {
1286
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": false
1292
+ },
1293
+ "161": {
1294
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": false
1300
+ },
1301
+ "162": {
1302
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": false
1308
+ },
1309
+ "163": {
1310
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": false
1316
+ },
1317
+ "164": {
1318
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": false
1324
+ },
1325
+ "165": {
1326
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": false
1332
+ },
1333
+ "166": {
1334
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": false
1340
+ },
1341
+ "167": {
1342
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": false
1348
+ },
1349
+ "168": {
1350
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": false
1356
+ },
1357
+ "169": {
1358
+ "content": "<table>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": false
1364
+ },
1365
+ "170": {
1366
+ "content": "<caption>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": false
1372
+ },
1373
+ "171": {
1374
+ "content": "<thead>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": false
1380
+ },
1381
+ "172": {
1382
+ "content": "<tbody>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": false
1388
+ },
1389
+ "173": {
1390
+ "content": "<tfoot>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": false
1396
+ },
1397
+ "174": {
1398
+ "content": "<tr>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": false
1404
+ },
1405
+ "175": {
1406
+ "content": "<th>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": false
1412
+ },
1413
+ "176": {
1414
+ "content": "<td>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": false
1420
+ },
1421
+ "177": {
1422
+ "content": "</table>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": false
1428
+ },
1429
+ "178": {
1430
+ "content": "</caption>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": false
1436
+ },
1437
+ "179": {
1438
+ "content": "</thead>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": false
1444
+ },
1445
+ "180": {
1446
+ "content": "</tbody>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": false
1452
+ },
1453
+ "181": {
1454
+ "content": "</tfoot>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": false
1460
+ },
1461
+ "182": {
1462
+ "content": "</tr>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": false
1468
+ },
1469
+ "183": {
1470
+ "content": "</th>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": false
1476
+ },
1477
+ "184": {
1478
+ "content": "</td>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": false
1484
+ },
1485
+ "185": {
1486
+ "content": "<h1>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": false
1492
+ },
1493
+ "186": {
1494
+ "content": "<h2>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": false
1500
+ },
1501
+ "187": {
1502
+ "content": "<h3>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": false
1508
+ },
1509
+ "188": {
1510
+ "content": "<h4>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": false
1516
+ },
1517
+ "189": {
1518
+ "content": "<h5>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": false
1524
+ },
1525
+ "190": {
1526
+ "content": "<h6>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": false
1532
+ },
1533
+ "191": {
1534
+ "content": "<blockquote>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": false
1540
+ },
1541
+ "192": {
1542
+ "content": "</h1>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": false
1548
+ },
1549
+ "193": {
1550
+ "content": "</h2>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": false
1556
+ },
1557
+ "194": {
1558
+ "content": "</h3>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": false
1564
+ },
1565
+ "195": {
1566
+ "content": "</h4>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": false
1572
+ },
1573
+ "196": {
1574
+ "content": "</h5>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": false
1580
+ },
1581
+ "197": {
1582
+ "content": "</h6>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": false
1588
+ },
1589
+ "198": {
1590
+ "content": "</blockquote>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": false
1596
+ },
1597
+ "199": {
1598
+ "content": "<strong>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": false
1604
+ },
1605
+ "200": {
1606
+ "content": "<em>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": false
1612
+ },
1613
+ "201": {
1614
+ "content": "<b>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": false
1620
+ },
1621
+ "202": {
1622
+ "content": "<i>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": false
1628
+ },
1629
+ "203": {
1630
+ "content": "<u>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": false
1636
+ },
1637
+ "204": {
1638
+ "content": "<s>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": false
1644
+ },
1645
+ "205": {
1646
+ "content": "<sub>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": false
1652
+ },
1653
+ "206": {
1654
+ "content": "<sup>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": false
1660
+ },
1661
+ "207": {
1662
+ "content": "<code>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": false
1668
+ },
1669
+ "208": {
1670
+ "content": "</strong>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": false
1676
+ },
1677
+ "209": {
1678
+ "content": "</em>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": false
1684
+ },
1685
+ "210": {
1686
+ "content": "</b>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": false
1692
+ },
1693
+ "211": {
1694
+ "content": "</i>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": false
1700
+ },
1701
+ "212": {
1702
+ "content": "</u>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": false
1708
+ },
1709
+ "213": {
1710
+ "content": "</s>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": false
1716
+ },
1717
+ "214": {
1718
+ "content": "</sub>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": false
1724
+ },
1725
+ "215": {
1726
+ "content": "</sup>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": false
1732
+ },
1733
+ "216": {
1734
+ "content": "</code>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": false
1740
+ },
1741
+ "255968": {
1742
+ "content": "[toxicity=0]",
1743
+ "lstrip": false,
1744
+ "normalized": false,
1745
+ "rstrip": false,
1746
+ "single_word": false,
1747
+ "special": false
1748
+ },
1749
+ "255969": {
1750
+ "content": "\t\t",
1751
+ "lstrip": false,
1752
+ "normalized": false,
1753
+ "rstrip": false,
1754
+ "single_word": false,
1755
+ "special": false
1756
+ },
1757
+ "255970": {
1758
+ "content": "\t\t\t",
1759
+ "lstrip": false,
1760
+ "normalized": false,
1761
+ "rstrip": false,
1762
+ "single_word": false,
1763
+ "special": false
1764
+ },
1765
+ "255971": {
1766
+ "content": "\t\t\t\t",
1767
+ "lstrip": false,
1768
+ "normalized": false,
1769
+ "rstrip": false,
1770
+ "single_word": false,
1771
+ "special": false
1772
+ },
1773
+ "255972": {
1774
+ "content": "\t\t\t\t\t",
1775
+ "lstrip": false,
1776
+ "normalized": false,
1777
+ "rstrip": false,
1778
+ "single_word": false,
1779
+ "special": false
1780
+ },
1781
+ "255973": {
1782
+ "content": "\t\t\t\t\t\t",
1783
+ "lstrip": false,
1784
+ "normalized": false,
1785
+ "rstrip": false,
1786
+ "single_word": false,
1787
+ "special": false
1788
+ },
1789
+ "255974": {
1790
+ "content": "\t\t\t\t\t\t\t",
1791
+ "lstrip": false,
1792
+ "normalized": false,
1793
+ "rstrip": false,
1794
+ "single_word": false,
1795
+ "special": false
1796
+ },
1797
+ "255975": {
1798
+ "content": "\t\t\t\t\t\t\t\t",
1799
+ "lstrip": false,
1800
+ "normalized": false,
1801
+ "rstrip": false,
1802
+ "single_word": false,
1803
+ "special": false
1804
+ },
1805
+ "255976": {
1806
+ "content": "\t\t\t\t\t\t\t\t\t",
1807
+ "lstrip": false,
1808
+ "normalized": false,
1809
+ "rstrip": false,
1810
+ "single_word": false,
1811
+ "special": false
1812
+ },
1813
+ "255977": {
1814
+ "content": "\t\t\t\t\t\t\t\t\t\t",
1815
+ "lstrip": false,
1816
+ "normalized": false,
1817
+ "rstrip": false,
1818
+ "single_word": false,
1819
+ "special": false
1820
+ },
1821
+ "255978": {
1822
+ "content": "\t\t\t\t\t\t\t\t\t\t\t",
1823
+ "lstrip": false,
1824
+ "normalized": false,
1825
+ "rstrip": false,
1826
+ "single_word": false,
1827
+ "special": false
1828
+ },
1829
+ "255979": {
1830
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
1831
+ "lstrip": false,
1832
+ "normalized": false,
1833
+ "rstrip": false,
1834
+ "single_word": false,
1835
+ "special": false
1836
+ },
1837
+ "255980": {
1838
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
1839
+ "lstrip": false,
1840
+ "normalized": false,
1841
+ "rstrip": false,
1842
+ "single_word": false,
1843
+ "special": false
1844
+ },
1845
+ "255981": {
1846
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1847
+ "lstrip": false,
1848
+ "normalized": false,
1849
+ "rstrip": false,
1850
+ "single_word": false,
1851
+ "special": false
1852
+ },
1853
+ "255982": {
1854
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1855
+ "lstrip": false,
1856
+ "normalized": false,
1857
+ "rstrip": false,
1858
+ "single_word": false,
1859
+ "special": false
1860
+ },
1861
+ "255983": {
1862
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1863
+ "lstrip": false,
1864
+ "normalized": false,
1865
+ "rstrip": false,
1866
+ "single_word": false,
1867
+ "special": false
1868
+ },
1869
+ "255984": {
1870
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1871
+ "lstrip": false,
1872
+ "normalized": false,
1873
+ "rstrip": false,
1874
+ "single_word": false,
1875
+ "special": false
1876
+ },
1877
+ "255985": {
1878
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1879
+ "lstrip": false,
1880
+ "normalized": false,
1881
+ "rstrip": false,
1882
+ "single_word": false,
1883
+ "special": false
1884
+ },
1885
+ "255986": {
1886
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1887
+ "lstrip": false,
1888
+ "normalized": false,
1889
+ "rstrip": false,
1890
+ "single_word": false,
1891
+ "special": false
1892
+ },
1893
+ "255987": {
1894
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1895
+ "lstrip": false,
1896
+ "normalized": false,
1897
+ "rstrip": false,
1898
+ "single_word": false,
1899
+ "special": false
1900
+ },
1901
+ "255988": {
1902
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1903
+ "lstrip": false,
1904
+ "normalized": false,
1905
+ "rstrip": false,
1906
+ "single_word": false,
1907
+ "special": false
1908
+ },
1909
+ "255989": {
1910
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1911
+ "lstrip": false,
1912
+ "normalized": false,
1913
+ "rstrip": false,
1914
+ "single_word": false,
1915
+ "special": false
1916
+ },
1917
+ "255990": {
1918
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1919
+ "lstrip": false,
1920
+ "normalized": false,
1921
+ "rstrip": false,
1922
+ "single_word": false,
1923
+ "special": false
1924
+ },
1925
+ "255991": {
1926
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1927
+ "lstrip": false,
1928
+ "normalized": false,
1929
+ "rstrip": false,
1930
+ "single_word": false,
1931
+ "special": false
1932
+ },
1933
+ "255992": {
1934
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1935
+ "lstrip": false,
1936
+ "normalized": false,
1937
+ "rstrip": false,
1938
+ "single_word": false,
1939
+ "special": false
1940
+ },
1941
+ "255993": {
1942
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1943
+ "lstrip": false,
1944
+ "normalized": false,
1945
+ "rstrip": false,
1946
+ "single_word": false,
1947
+ "special": false
1948
+ },
1949
+ "255994": {
1950
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1951
+ "lstrip": false,
1952
+ "normalized": false,
1953
+ "rstrip": false,
1954
+ "single_word": false,
1955
+ "special": false
1956
+ },
1957
+ "255995": {
1958
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1959
+ "lstrip": false,
1960
+ "normalized": false,
1961
+ "rstrip": false,
1962
+ "single_word": false,
1963
+ "special": false
1964
+ },
1965
+ "255996": {
1966
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1967
+ "lstrip": false,
1968
+ "normalized": false,
1969
+ "rstrip": false,
1970
+ "single_word": false,
1971
+ "special": false
1972
+ },
1973
+ "255997": {
1974
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1975
+ "lstrip": false,
1976
+ "normalized": false,
1977
+ "rstrip": false,
1978
+ "single_word": false,
1979
+ "special": false
1980
+ },
1981
+ "255998": {
1982
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1983
+ "lstrip": false,
1984
+ "normalized": false,
1985
+ "rstrip": false,
1986
+ "single_word": false,
1987
+ "special": false
1988
+ },
1989
+ "255999": {
1990
+ "content": "<unused99>",
1991
+ "lstrip": false,
1992
+ "normalized": false,
1993
+ "rstrip": false,
1994
+ "single_word": false,
1995
+ "special": false
1996
+ },
1997
+ "256000": {
1998
+ "content": "<start_of_rating>",
1999
+ "lstrip": false,
2000
+ "normalized": false,
2001
+ "rstrip": false,
2002
+ "single_word": false,
2003
+ "special": true
2004
+ },
2005
+ "256001": {
2006
+ "content": "<unknown_rating>",
2007
+ "lstrip": false,
2008
+ "normalized": false,
2009
+ "rstrip": false,
2010
+ "single_word": false,
2011
+ "special": true
2012
+ },
2013
+ "256002": {
2014
+ "content": "<end_of_rating>",
2015
+ "lstrip": false,
2016
+ "normalized": false,
2017
+ "rstrip": false,
2018
+ "single_word": false,
2019
+ "special": true
2020
+ },
2021
+ "256003": {
2022
+ "content": "<positive_rating>",
2023
+ "lstrip": false,
2024
+ "normalized": false,
2025
+ "rstrip": false,
2026
+ "single_word": false,
2027
+ "special": true
2028
+ },
2029
+ "256004": {
2030
+ "content": "<negative_rating>",
2031
+ "lstrip": false,
2032
+ "normalized": false,
2033
+ "rstrip": false,
2034
+ "single_word": false,
2035
+ "special": true
2036
+ },
2037
+ "256005": {
2038
+ "content": "<critic>",
2039
+ "lstrip": false,
2040
+ "normalized": false,
2041
+ "rstrip": false,
2042
+ "single_word": false,
2043
+ "special": true
2044
+ },
2045
+ "256006": {
2046
+ "content": "<conclusion>",
2047
+ "lstrip": false,
2048
+ "normalized": false,
2049
+ "rstrip": false,
2050
+ "single_word": false,
2051
+ "special": true
2052
+ },
2053
+ "256007": {
2054
+ "content": "<start_of_thought>",
2055
+ "lstrip": false,
2056
+ "normalized": false,
2057
+ "rstrip": false,
2058
+ "single_word": false,
2059
+ "special": true
2060
+ },
2061
+ "256008": {
2062
+ "content": "<end_of_thought>",
2063
+ "lstrip": false,
2064
+ "normalized": false,
2065
+ "rstrip": false,
2066
+ "single_word": false,
2067
+ "special": true
2068
+ },
2069
+ "256009": {
2070
+ "content": "<problem>",
2071
+ "lstrip": false,
2072
+ "normalized": false,
2073
+ "rstrip": false,
2074
+ "single_word": false,
2075
+ "special": true
2076
+ },
2077
+ "256010": {
2078
+ "content": "<refine>",
2079
+ "lstrip": false,
2080
+ "normalized": false,
2081
+ "rstrip": false,
2082
+ "single_word": false,
2083
+ "special": true
2084
+ },
2085
+ "256011": {
2086
+ "content": "<start_of_father_id>",
2087
+ "lstrip": false,
2088
+ "normalized": false,
2089
+ "rstrip": false,
2090
+ "single_word": false,
2091
+ "special": true
2092
+ },
2093
+ "256012": {
2094
+ "content": "<end_of_father_id>",
2095
+ "lstrip": false,
2096
+ "normalized": false,
2097
+ "rstrip": false,
2098
+ "single_word": false,
2099
+ "special": true
2100
+ },
2101
+ "256013": {
2102
+ "content": "<start_of_local_id>",
2103
+ "lstrip": false,
2104
+ "normalized": false,
2105
+ "rstrip": false,
2106
+ "single_word": false,
2107
+ "special": true
2108
+ },
2109
+ "256014": {
2110
+ "content": "<end_of_local_id>",
2111
+ "lstrip": false,
2112
+ "normalized": false,
2113
+ "rstrip": false,
2114
+ "single_word": false,
2115
+ "special": true
2116
+ }
2117
+ },
2118
+ "additional_special_tokens": [
2119
+ "<start_of_turn>",
2120
+ "<end_of_turn>",
2121
+ "<start_of_rating>",
2122
+ "<unknown_rating>",
2123
+ "<end_of_rating>",
2124
+ "<positive_rating>",
2125
+ "<negative_rating>",
2126
+ "<critic>",
2127
+ "<conclusion>",
2128
+ "<start_of_thought>",
2129
+ "<end_of_thought>",
2130
+ "<problem>",
2131
+ "<refine>",
2132
+ "<start_of_father_id>",
2133
+ "<end_of_father_id>",
2134
+ "<start_of_local_id>",
2135
+ "<end_of_local_id>"
2136
+ ],
2137
+ "bos_token": "<bos>",
2138
+ "chat_template": "{{ '<bos>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<start_of_turn>user\n' + content + '<end_of_turn>\n<start_of_turn>model\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<end_of_turn>\n' }}{% endif %}{% endfor %}",
2139
+ "clean_up_tokenization_spaces": false,
2140
+ "eos_token": "<eos>",
2141
+ "model_max_length": 1000000000000000019884624838656,
2142
+ "pad_token": "<pad>",
2143
+ "padding_side": "right",
2144
+ "sp_model_kwargs": {},
2145
+ "spaces_between_special_tokens": false,
2146
+ "split_special_tokens": false,
2147
+ "tokenizer_class": "GemmaTokenizer",
2148
+ "unk_token": "<unk>",
2149
+ "use_default_system_prompt": false
2150
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 5.842272600604017e+17,
4
+ "train_loss": 0.47904590670458097,
5
+ "train_runtime": 1388.8864,
6
+ "train_samples_per_second": 2.881,
7
+ "train_steps_per_second": 0.361
8
+ }
trainer_log.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,3549 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 501,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.001996007984031936,
13
+ "grad_norm": 92.81291961669922,
14
+ "learning_rate": 0.0,
15
+ "loss": 5.1027,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.003992015968063872,
20
+ "grad_norm": 187.8679656982422,
21
+ "learning_rate": 5.017166594399687e-06,
22
+ "loss": 5.1552,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.005988023952095809,
27
+ "grad_norm": 160.3046875,
28
+ "learning_rate": 7.952020911994375e-06,
29
+ "loss": 5.1408,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.007984031936127744,
34
+ "grad_norm": 44.23579406738281,
35
+ "learning_rate": 1.0034333188799373e-05,
36
+ "loss": 3.2825,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.00998003992015968,
41
+ "grad_norm": 22.931053161621094,
42
+ "learning_rate": 1.164950007226698e-05,
43
+ "loss": 2.5601,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.011976047904191617,
48
+ "grad_norm": 10.358180046081543,
49
+ "learning_rate": 1.2969187506394062e-05,
50
+ "loss": 1.994,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.013972055888223553,
55
+ "grad_norm": 9.385107040405273,
56
+ "learning_rate": 1.4084967333570947e-05,
57
+ "loss": 1.8568,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.015968063872255488,
62
+ "grad_norm": 7.71799898147583,
63
+ "learning_rate": 1.505149978319906e-05,
64
+ "loss": 1.59,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.017964071856287425,
69
+ "grad_norm": 5.006285190582275,
70
+ "learning_rate": 1.590404182398875e-05,
71
+ "loss": 1.3238,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.01996007984031936,
76
+ "grad_norm": 4.380033493041992,
77
+ "learning_rate": 1.666666666666667e-05,
78
+ "loss": 1.267,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.021956087824351298,
83
+ "grad_norm": 4.105769634246826,
84
+ "learning_rate": 1.7356544752637084e-05,
85
+ "loss": 1.2438,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.023952095808383235,
90
+ "grad_norm": 3.476895809173584,
91
+ "learning_rate": 1.7986354100793748e-05,
92
+ "loss": 1.1196,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.02594810379241517,
97
+ "grad_norm": 2.9743728637695312,
98
+ "learning_rate": 1.8565722538447282e-05,
99
+ "loss": 1.0148,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.027944111776447105,
104
+ "grad_norm": 2.6658384799957275,
105
+ "learning_rate": 1.9102133927970633e-05,
106
+ "loss": 1.0081,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.029940119760479042,
111
+ "grad_norm": 2.6062169075012207,
112
+ "learning_rate": 1.9601520984261358e-05,
113
+ "loss": 0.9228,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.031936127744510975,
118
+ "grad_norm": 2.147310495376587,
119
+ "learning_rate": 2.0068666377598747e-05,
120
+ "loss": 0.8351,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.033932135728542916,
125
+ "grad_norm": 2.2878642082214355,
126
+ "learning_rate": 2.0507482022971233e-05,
127
+ "loss": 0.8303,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.03592814371257485,
132
+ "grad_norm": 2.077786445617676,
133
+ "learning_rate": 2.0921208418388435e-05,
134
+ "loss": 0.7769,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.03792415169660679,
139
+ "grad_norm": 2.115493059158325,
140
+ "learning_rate": 2.1312560015880482e-05,
141
+ "loss": 0.8032,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.03992015968063872,
146
+ "grad_norm": 1.92618989944458,
147
+ "learning_rate": 2.1683833261066357e-05,
148
+ "loss": 0.7759,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.041916167664670656,
153
+ "grad_norm": 1.9667437076568604,
154
+ "learning_rate": 2.2036988245565324e-05,
155
+ "loss": 0.7805,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.043912175648702596,
160
+ "grad_norm": 2.3144752979278564,
161
+ "learning_rate": 2.2373711347036773e-05,
162
+ "loss": 0.735,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.04590818363273453,
167
+ "grad_norm": 1.555964469909668,
168
+ "learning_rate": 2.269546393362655e-05,
169
+ "loss": 0.6523,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.04790419161676647,
174
+ "grad_norm": 1.5024523735046387,
175
+ "learning_rate": 2.3003520695193437e-05,
176
+ "loss": 0.6623,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.0499001996007984,
181
+ "grad_norm": 1.522902011871338,
182
+ "learning_rate": 2.329900014453396e-05,
183
+ "loss": 0.6503,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.05189620758483034,
188
+ "grad_norm": 1.4194371700286865,
189
+ "learning_rate": 2.3582889132846968e-05,
190
+ "loss": 0.636,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.05389221556886228,
195
+ "grad_norm": 1.55453360080719,
196
+ "learning_rate": 2.3856062735983123e-05,
197
+ "loss": 0.7242,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.05588822355289421,
202
+ "grad_norm": 1.4471536874771118,
203
+ "learning_rate": 2.4119300522370322e-05,
204
+ "loss": 0.5819,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.05788423153692615,
209
+ "grad_norm": 1.5161927938461304,
210
+ "learning_rate": 2.4373299964982603e-05,
211
+ "loss": 0.6788,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.059880239520958084,
216
+ "grad_norm": 1.5962581634521484,
217
+ "learning_rate": 2.4618687578661044e-05,
218
+ "loss": 0.7346,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.06187624750499002,
223
+ "grad_norm": 1.3744760751724243,
224
+ "learning_rate": 2.4856028230571212e-05,
225
+ "loss": 0.4835,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.06387225548902195,
230
+ "grad_norm": 1.7308415174484253,
231
+ "learning_rate": 2.5085832971998436e-05,
232
+ "loss": 0.6537,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.0658682634730539,
237
+ "grad_norm": 1.736331582069397,
238
+ "learning_rate": 2.530856566463146e-05,
239
+ "loss": 0.6633,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.06786427145708583,
244
+ "grad_norm": 1.9755364656448364,
245
+ "learning_rate": 2.552464861737092e-05,
246
+ "loss": 0.6268,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.06986027944111776,
251
+ "grad_norm": 1.6539369821548462,
252
+ "learning_rate": 2.5734467405837933e-05,
253
+ "loss": 0.6355,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.0718562874251497,
258
+ "grad_norm": 2.0570621490478516,
259
+ "learning_rate": 2.5938375012788124e-05,
260
+ "loss": 0.6168,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.07385229540918163,
265
+ "grad_norm": 1.8512474298477173,
266
+ "learning_rate": 2.6136695401116585e-05,
267
+ "loss": 0.6583,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.07584830339321358,
272
+ "grad_norm": 1.2911862134933472,
273
+ "learning_rate": 2.6329726610280168e-05,
274
+ "loss": 0.565,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.07784431137724551,
279
+ "grad_norm": 1.475156545639038,
280
+ "learning_rate": 2.651774345044166e-05,
281
+ "loss": 0.6409,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.07984031936127745,
286
+ "grad_norm": 1.1098164319992065,
287
+ "learning_rate": 2.6700999855466042e-05,
288
+ "loss": 0.5335,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.08183632734530938,
293
+ "grad_norm": 1.1890451908111572,
294
+ "learning_rate": 2.687973094532893e-05,
295
+ "loss": 0.4502,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.08383233532934131,
300
+ "grad_norm": 1.9120031595230103,
301
+ "learning_rate": 2.7054154839965013e-05,
302
+ "loss": 0.607,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.08582834331337326,
307
+ "grad_norm": 1.2188658714294434,
308
+ "learning_rate": 2.722447425965978e-05,
309
+ "loss": 0.5033,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.08782435129740519,
314
+ "grad_norm": 1.3608094453811646,
315
+ "learning_rate": 2.739087794143646e-05,
316
+ "loss": 0.5956,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.08982035928143713,
321
+ "grad_norm": 1.259487271308899,
322
+ "learning_rate": 2.755354189625573e-05,
323
+ "loss": 0.575,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.09181636726546906,
328
+ "grad_norm": 1.2308496236801147,
329
+ "learning_rate": 2.771263052802624e-05,
330
+ "loss": 0.6473,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.09381237524950099,
335
+ "grad_norm": 1.2072350978851318,
336
+ "learning_rate": 2.7868297632261957e-05,
337
+ "loss": 0.6273,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.09580838323353294,
342
+ "grad_norm": 1.150260090827942,
343
+ "learning_rate": 2.8020687289593123e-05,
344
+ "loss": 0.618,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.09780439121756487,
349
+ "grad_norm": 1.1447213888168335,
350
+ "learning_rate": 2.8169934667141895e-05,
351
+ "loss": 0.625,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.0998003992015968,
356
+ "grad_norm": 1.1371378898620605,
357
+ "learning_rate": 2.8316166738933646e-05,
358
+ "loss": 0.6372,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.10179640718562874,
363
+ "grad_norm": 1.1135759353637695,
364
+ "learning_rate": 2.845950293496561e-05,
365
+ "loss": 0.539,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.10379241516966067,
370
+ "grad_norm": 0.9502639174461365,
371
+ "learning_rate": 2.8600055727246657e-05,
372
+ "loss": 0.388,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.10578842315369262,
377
+ "grad_norm": 1.545538306236267,
378
+ "learning_rate": 2.8737931160013153e-05,
379
+ "loss": 0.5401,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.10778443113772455,
384
+ "grad_norm": 1.223322868347168,
385
+ "learning_rate": 2.8873229330382812e-05,
386
+ "loss": 0.5695,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.10978043912175649,
391
+ "grad_norm": 1.0864529609680176,
392
+ "learning_rate": 2.9006044824904066e-05,
393
+ "loss": 0.4986,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.11177644710578842,
398
+ "grad_norm": 1.1569509506225586,
399
+ "learning_rate": 2.913646711677001e-05,
400
+ "loss": 0.5629,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.11377245508982035,
405
+ "grad_norm": 1.3813297748565674,
406
+ "learning_rate": 2.926458092787486e-05,
407
+ "loss": 0.605,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.1157684630738523,
412
+ "grad_norm": 1.034891128540039,
413
+ "learning_rate": 2.939046655938229e-05,
414
+ "loss": 0.5247,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.11776447105788423,
419
+ "grad_norm": 1.0968964099884033,
420
+ "learning_rate": 2.951420019403574e-05,
421
+ "loss": 0.5797,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.11976047904191617,
426
+ "grad_norm": 1.0885212421417236,
427
+ "learning_rate": 2.963585417306073e-05,
428
+ "loss": 0.5689,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.1217564870259481,
433
+ "grad_norm": 1.2548822164535522,
434
+ "learning_rate": 2.9755497250179453e-05,
435
+ "loss": 0.5559,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.12375249500998003,
440
+ "grad_norm": 1.009814739227295,
441
+ "learning_rate": 2.98731948249709e-05,
442
+ "loss": 0.4973,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.12574850299401197,
447
+ "grad_norm": 1.0727399587631226,
448
+ "learning_rate": 2.9989009157559694e-05,
449
+ "loss": 0.5439,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.1277445109780439,
454
+ "grad_norm": 1.1233041286468506,
455
+ "learning_rate": 3.010299956639812e-05,
456
+ "loss": 0.5472,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.12974051896207583,
461
+ "grad_norm": 1.1565264463424683,
462
+ "learning_rate": 3.021522261071426e-05,
463
+ "loss": 0.6008,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.1317365269461078,
468
+ "grad_norm": 0.9942654371261597,
469
+ "learning_rate": 3.0325732259031143e-05,
470
+ "loss": 0.4552,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.13373253493013973,
475
+ "grad_norm": 1.100710153579712,
476
+ "learning_rate": 3.043458004501377e-05,
477
+ "loss": 0.4661,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.13572854291417166,
482
+ "grad_norm": 1.0481464862823486,
483
+ "learning_rate": 3.054181521177061e-05,
484
+ "loss": 0.4996,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.1377245508982036,
489
+ "grad_norm": 1.085190773010254,
490
+ "learning_rate": 3.064748484562093e-05,
491
+ "loss": 0.5589,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.13972055888223553,
496
+ "grad_norm": 1.0909191370010376,
497
+ "learning_rate": 3.0751634000237615e-05,
498
+ "loss": 0.5948,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.14171656686626746,
503
+ "grad_norm": 1.9369421005249023,
504
+ "learning_rate": 3.085430581198459e-05,
505
+ "loss": 0.5384,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.1437125748502994,
510
+ "grad_norm": 1.1248409748077393,
511
+ "learning_rate": 3.095554160718781e-05,
512
+ "loss": 0.4915,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.14570858283433133,
517
+ "grad_norm": 1.028275728225708,
518
+ "learning_rate": 3.10553810020076e-05,
519
+ "loss": 0.5405,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.14770459081836326,
524
+ "grad_norm": 0.9245263338088989,
525
+ "learning_rate": 3.115386199551628e-05,
526
+ "loss": 0.4313,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.1497005988023952,
531
+ "grad_norm": 1.0587871074676514,
532
+ "learning_rate": 3.1251021056528336e-05,
533
+ "loss": 0.5154,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.15169660678642716,
538
+ "grad_norm": 1.0819029808044434,
539
+ "learning_rate": 3.134689320467986e-05,
540
+ "loss": 0.5097,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.1536926147704591,
545
+ "grad_norm": 1.0212074518203735,
546
+ "learning_rate": 3.144151208620804e-05,
547
+ "loss": 0.4365,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.15568862275449102,
552
+ "grad_norm": 1.140681266784668,
553
+ "learning_rate": 3.1534910044841344e-05,
554
+ "loss": 0.5734,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.15768463073852296,
559
+ "grad_norm": 1.0276720523834229,
560
+ "learning_rate": 3.1627118188174024e-05,
561
+ "loss": 0.42,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.1596806387225549,
566
+ "grad_norm": 0.980180025100708,
567
+ "learning_rate": 3.171816644986573e-05,
568
+ "loss": 0.4796,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.16167664670658682,
573
+ "grad_norm": 1.198864221572876,
574
+ "learning_rate": 3.18080836479775e-05,
575
+ "loss": 0.5675,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.16367265469061876,
580
+ "grad_norm": 0.9353108406066895,
581
+ "learning_rate": 3.1896897539728616e-05,
582
+ "loss": 0.5183,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.1656686626746507,
587
+ "grad_norm": 0.9708541035652161,
588
+ "learning_rate": 3.198463487293457e-05,
589
+ "loss": 0.4513,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.16766467065868262,
594
+ "grad_norm": 1.1432932615280151,
595
+ "learning_rate": 3.207132143436469e-05,
596
+ "loss": 0.589,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.16966067864271456,
601
+ "grad_norm": 1.0964723825454712,
602
+ "learning_rate": 3.215698209523821e-05,
603
+ "loss": 0.5101,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.17165668662674652,
608
+ "grad_norm": 1.0808310508728027,
609
+ "learning_rate": 3.224164085405946e-05,
610
+ "loss": 0.4349,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.17365269461077845,
615
+ "grad_norm": 1.0994106531143188,
616
+ "learning_rate": 3.232532087697698e-05,
617
+ "loss": 0.4965,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.17564870259481039,
622
+ "grad_norm": 1.2377325296401978,
623
+ "learning_rate": 3.240804453583615e-05,
624
+ "loss": 0.4444,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.17764471057884232,
629
+ "grad_norm": 1.0575945377349854,
630
+ "learning_rate": 3.248983344408188e-05,
631
+ "loss": 0.4379,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.17964071856287425,
636
+ "grad_norm": 0.8877758979797363,
637
+ "learning_rate": 3.2570708490655414e-05,
638
+ "loss": 0.453,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.18163672654690619,
643
+ "grad_norm": 1.0481340885162354,
644
+ "learning_rate": 3.265068987201822e-05,
645
+ "loss": 0.519,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.18363273453093812,
650
+ "grad_norm": 1.026150107383728,
651
+ "learning_rate": 3.2729797122425925e-05,
652
+ "loss": 0.5112,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.18562874251497005,
657
+ "grad_norm": 0.8472252488136292,
658
+ "learning_rate": 3.280804914256559e-05,
659
+ "loss": 0.4302,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.18762475049900199,
664
+ "grad_norm": 0.9228626489639282,
665
+ "learning_rate": 3.288546422666164e-05,
666
+ "loss": 0.4814,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.18962075848303392,
671
+ "grad_norm": 1.0165542364120483,
672
+ "learning_rate": 3.2962060088147464e-05,
673
+ "loss": 0.5035,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.19161676646706588,
678
+ "grad_norm": 1.091426134109497,
679
+ "learning_rate": 3.3037853883992805e-05,
680
+ "loss": 0.5718,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.1936127744510978,
685
+ "grad_norm": 1.0953468084335327,
686
+ "learning_rate": 3.3112862237770756e-05,
687
+ "loss": 0.5522,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.19560878243512975,
692
+ "grad_norm": 0.9461252689361572,
693
+ "learning_rate": 3.3187101261541584e-05,
694
+ "loss": 0.5257,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.19760479041916168,
699
+ "grad_norm": 1.063242793083191,
700
+ "learning_rate": 3.326058657662584e-05,
701
+ "loss": 0.511,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.1996007984031936,
706
+ "grad_norm": 1.0084831714630127,
707
+ "learning_rate": 3.333333333333334e-05,
708
+ "loss": 0.5182,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.20159680638722555,
713
+ "grad_norm": 0.9839895963668823,
714
+ "learning_rate": 3.340535622971072e-05,
715
+ "loss": 0.4776,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.20359281437125748,
720
+ "grad_norm": 0.9757642149925232,
721
+ "learning_rate": 3.3476669529365295e-05,
722
+ "loss": 0.4915,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.2055888223552894,
727
+ "grad_norm": 0.8425347208976746,
728
+ "learning_rate": 3.3547287078419544e-05,
729
+ "loss": 0.3955,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.20758483033932135,
734
+ "grad_norm": 0.9176936745643616,
735
+ "learning_rate": 3.361722232164634e-05,
736
+ "loss": 0.4132,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.20958083832335328,
741
+ "grad_norm": 1.0560258626937866,
742
+ "learning_rate": 3.3686488317832306e-05,
743
+ "loss": 0.5133,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.21157684630738524,
748
+ "grad_norm": 0.9101148247718811,
749
+ "learning_rate": 3.375509775441284e-05,
750
+ "loss": 0.3898,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.21357285429141717,
755
+ "grad_norm": 0.8682689666748047,
756
+ "learning_rate": 3.382306296142016e-05,
757
+ "loss": 0.4353,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.2155688622754491,
762
+ "grad_norm": 0.8694739937782288,
763
+ "learning_rate": 3.38903959247825e-05,
764
+ "loss": 0.5008,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.21756487025948104,
769
+ "grad_norm": 0.8936677575111389,
770
+ "learning_rate": 3.395710829901039e-05,
771
+ "loss": 0.4203,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.21956087824351297,
776
+ "grad_norm": 0.936951220035553,
777
+ "learning_rate": 3.402321141930376e-05,
778
+ "loss": 0.4798,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.2215568862275449,
783
+ "grad_norm": 0.8947778344154358,
784
+ "learning_rate": 3.4088716313110955e-05,
785
+ "loss": 0.4855,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.22355289421157684,
790
+ "grad_norm": 0.8714671730995178,
791
+ "learning_rate": 3.415363371116969e-05,
792
+ "loss": 0.4973,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.22554890219560877,
797
+ "grad_norm": 0.8940010070800781,
798
+ "learning_rate": 3.4217974058057e-05,
799
+ "loss": 0.5217,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.2275449101796407,
804
+ "grad_norm": 0.8057599663734436,
805
+ "learning_rate": 3.428174752227455e-05,
806
+ "loss": 0.3906,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.22954091816367264,
811
+ "grad_norm": 1.0616763830184937,
812
+ "learning_rate": 3.434496400589353e-05,
813
+ "loss": 0.4958,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.2315369261477046,
818
+ "grad_norm": 0.8679594993591309,
819
+ "learning_rate": 3.440763315378198e-05,
820
+ "loss": 0.4526,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.23353293413173654,
825
+ "grad_norm": 0.8972085118293762,
826
+ "learning_rate": 3.446976436243603e-05,
827
+ "loss": 0.4559,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.23552894211576847,
832
+ "grad_norm": 0.9083353877067566,
833
+ "learning_rate": 3.4531366788435425e-05,
834
+ "loss": 0.5048,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.2375249500998004,
839
+ "grad_norm": 0.8607695698738098,
840
+ "learning_rate": 3.459244935654219e-05,
841
+ "loss": 0.4128,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.23952095808383234,
846
+ "grad_norm": 0.8851041793823242,
847
+ "learning_rate": 3.465302076746041e-05,
848
+ "loss": 0.4602,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.24151696606786427,
853
+ "grad_norm": 0.9059931039810181,
854
+ "learning_rate": 3.471308950527417e-05,
855
+ "loss": 0.4791,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.2435129740518962,
860
+ "grad_norm": 0.9063411951065063,
861
+ "learning_rate": 3.477266384457914e-05,
862
+ "loss": 0.4741,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.24550898203592814,
867
+ "grad_norm": 0.8850985765457153,
868
+ "learning_rate": 3.48317518573233e-05,
869
+ "loss": 0.4292,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.24750499001996007,
874
+ "grad_norm": 0.9396518468856812,
875
+ "learning_rate": 3.489036141937059e-05,
876
+ "loss": 0.5069,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.249500998003992,
881
+ "grad_norm": 0.9115111231803894,
882
+ "learning_rate": 3.494850021680094e-05,
883
+ "loss": 0.4823,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.25149700598802394,
888
+ "grad_norm": 0.8799051642417908,
889
+ "learning_rate": 3.500617575195938e-05,
890
+ "loss": 0.3732,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.25349301397205587,
895
+ "grad_norm": 0.9273744821548462,
896
+ "learning_rate": 3.5063395349265945e-05,
897
+ "loss": 0.4284,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.2554890219560878,
902
+ "grad_norm": 1.0624243021011353,
903
+ "learning_rate": 3.5120166160797804e-05,
904
+ "loss": 0.4322,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.25748502994011974,
909
+ "grad_norm": 0.8508513569831848,
910
+ "learning_rate": 3.517649517165415e-05,
911
+ "loss": 0.4465,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.25948103792415167,
916
+ "grad_norm": 0.8986352682113647,
917
+ "learning_rate": 3.523238920511395e-05,
918
+ "loss": 0.4093,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.26147704590818366,
923
+ "grad_norm": 0.9224410653114319,
924
+ "learning_rate": 3.528785492759607e-05,
925
+ "loss": 0.4735,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.2634730538922156,
930
+ "grad_norm": 0.9467160105705261,
931
+ "learning_rate": 3.5342898853430836e-05,
932
+ "loss": 0.4952,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.2654690618762475,
937
+ "grad_norm": 0.9140215516090393,
938
+ "learning_rate": 3.539752734945143e-05,
939
+ "loss": 0.4516,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.26746506986027946,
944
+ "grad_norm": 0.9906129837036133,
945
+ "learning_rate": 3.5451746639413466e-05,
946
+ "loss": 0.3785,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.2694610778443114,
951
+ "grad_norm": 0.8118170499801636,
952
+ "learning_rate": 3.550556280825011e-05,
953
+ "loss": 0.4324,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.2714570858283433,
958
+ "grad_norm": 0.9162650108337402,
959
+ "learning_rate": 3.55589818061703e-05,
960
+ "loss": 0.3836,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.27345309381237526,
965
+ "grad_norm": 0.8672250509262085,
966
+ "learning_rate": 3.561200945260678e-05,
967
+ "loss": 0.4462,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.2754491017964072,
972
+ "grad_norm": 0.906155526638031,
973
+ "learning_rate": 3.5664651440020616e-05,
974
+ "loss": 0.4749,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.2774451097804391,
979
+ "grad_norm": 0.9452763199806213,
980
+ "learning_rate": 3.571691333756825e-05,
981
+ "loss": 0.4782,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.27944111776447106,
986
+ "grad_norm": 0.8917446136474609,
987
+ "learning_rate": 3.5768800594637304e-05,
988
+ "loss": 0.4401,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.281437125748503,
993
+ "grad_norm": 0.882606029510498,
994
+ "learning_rate": 3.582031854425634e-05,
995
+ "loss": 0.4992,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.2834331337325349,
1000
+ "grad_norm": 0.870290219783783,
1001
+ "learning_rate": 3.587147240638428e-05,
1002
+ "loss": 0.5009,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.28542914171656686,
1007
+ "grad_norm": 0.8788816332817078,
1008
+ "learning_rate": 3.5922267291084366e-05,
1009
+ "loss": 0.3891,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.2874251497005988,
1014
+ "grad_norm": 0.8944652676582336,
1015
+ "learning_rate": 3.5972708201587496e-05,
1016
+ "loss": 0.442,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.2894211576846307,
1021
+ "grad_norm": 0.8970728516578674,
1022
+ "learning_rate": 3.6022800037249585e-05,
1023
+ "loss": 0.5065,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.29141716566866266,
1028
+ "grad_norm": 0.9061855673789978,
1029
+ "learning_rate": 3.607254759640729e-05,
1030
+ "loss": 0.4617,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.2934131736526946,
1035
+ "grad_norm": 0.851344883441925,
1036
+ "learning_rate": 3.612195557913627e-05,
1037
+ "loss": 0.4633,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.2954091816367265,
1042
+ "grad_norm": 0.8392930626869202,
1043
+ "learning_rate": 3.6171028589915954e-05,
1044
+ "loss": 0.434,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.29740518962075846,
1049
+ "grad_norm": 0.8495596051216125,
1050
+ "learning_rate": 3.6219771140204575e-05,
1051
+ "loss": 0.4627,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.2994011976047904,
1056
+ "grad_norm": 0.8151164650917053,
1057
+ "learning_rate": 3.626818765092802e-05,
1058
+ "loss": 0.4152,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.3013972055888224,
1063
+ "grad_norm": 0.9488523602485657,
1064
+ "learning_rate": 3.6316282454886157e-05,
1065
+ "loss": 0.4912,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.3033932135728543,
1070
+ "grad_norm": 0.6952376365661621,
1071
+ "learning_rate": 3.636405979907955e-05,
1072
+ "loss": 0.3153,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.30538922155688625,
1077
+ "grad_norm": 0.8647618293762207,
1078
+ "learning_rate": 3.6411523846959985e-05,
1079
+ "loss": 0.4619,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.3073852295409182,
1084
+ "grad_norm": 0.8178197741508484,
1085
+ "learning_rate": 3.645867868060772e-05,
1086
+ "loss": 0.5165,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.3093812375249501,
1091
+ "grad_norm": 0.8717004060745239,
1092
+ "learning_rate": 3.6505528302838193e-05,
1093
+ "loss": 0.4222,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.31137724550898205,
1098
+ "grad_norm": 0.867859423160553,
1099
+ "learning_rate": 3.6552076639241027e-05,
1100
+ "loss": 0.4882,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.313373253493014,
1105
+ "grad_norm": 0.8131747841835022,
1106
+ "learning_rate": 3.65983275401539e-05,
1107
+ "loss": 0.4171,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.3153692614770459,
1112
+ "grad_norm": 0.8518748879432678,
1113
+ "learning_rate": 3.664428478257371e-05,
1114
+ "loss": 0.4342,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.31736526946107785,
1119
+ "grad_norm": 0.8354836702346802,
1120
+ "learning_rate": 3.668995207200753e-05,
1121
+ "loss": 0.4698,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.3193612774451098,
1126
+ "grad_norm": 0.9375539422035217,
1127
+ "learning_rate": 3.673533304426541e-05,
1128
+ "loss": 0.4896,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.3213572854291417,
1133
+ "grad_norm": 0.8951889872550964,
1134
+ "learning_rate": 3.67804312671975e-05,
1135
+ "loss": 0.4997,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.32335329341317365,
1140
+ "grad_norm": 0.8014180064201355,
1141
+ "learning_rate": 3.682525024237719e-05,
1142
+ "loss": 0.47,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.3253493013972056,
1147
+ "grad_norm": 0.8288528323173523,
1148
+ "learning_rate": 3.6869793406732636e-05,
1149
+ "loss": 0.4085,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.3273453093812375,
1154
+ "grad_norm": 0.8221442699432373,
1155
+ "learning_rate": 3.69140641341283e-05,
1156
+ "loss": 0.4329,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.32934131736526945,
1161
+ "grad_norm": 0.7562230825424194,
1162
+ "learning_rate": 3.695806573689844e-05,
1163
+ "loss": 0.348,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.3313373253493014,
1168
+ "grad_norm": 0.9237514138221741,
1169
+ "learning_rate": 3.700180146733426e-05,
1170
+ "loss": 0.4342,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.3333333333333333,
1175
+ "grad_norm": 0.9912509918212891,
1176
+ "learning_rate": 3.704527451912639e-05,
1177
+ "loss": 0.4809,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.33532934131736525,
1182
+ "grad_norm": 0.8607332110404968,
1183
+ "learning_rate": 3.708848802876438e-05,
1184
+ "loss": 0.4586,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.3373253493013972,
1189
+ "grad_norm": 0.8513320684432983,
1190
+ "learning_rate": 3.7131445076894564e-05,
1191
+ "loss": 0.4471,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.3393213572854291,
1196
+ "grad_norm": 0.8249276876449585,
1197
+ "learning_rate": 3.717414868963791e-05,
1198
+ "loss": 0.3867,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.3413173652694611,
1203
+ "grad_norm": 0.9111822843551636,
1204
+ "learning_rate": 3.721660183986924e-05,
1205
+ "loss": 0.4502,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.34331337325349304,
1210
+ "grad_norm": 0.7368887066841125,
1211
+ "learning_rate": 3.725880744845915e-05,
1212
+ "loss": 0.3507,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.34530938123752497,
1217
+ "grad_norm": 0.8149043917655945,
1218
+ "learning_rate": 3.730076838547993e-05,
1219
+ "loss": 0.3512,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.3473053892215569,
1224
+ "grad_norm": 0.9387815594673157,
1225
+ "learning_rate": 3.734248747137666e-05,
1226
+ "loss": 0.4263,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.34930139720558884,
1231
+ "grad_norm": 0.860095202922821,
1232
+ "learning_rate": 3.738396747810492e-05,
1233
+ "loss": 0.3923,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.35129740518962077,
1238
+ "grad_norm": 0.7961985468864441,
1239
+ "learning_rate": 3.7425211130235834e-05,
1240
+ "loss": 0.3811,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.3532934131736527,
1245
+ "grad_norm": 0.8483626842498779,
1246
+ "learning_rate": 3.7466221106030115e-05,
1247
+ "loss": 0.4152,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.35528942115768464,
1252
+ "grad_norm": 0.7593052387237549,
1253
+ "learning_rate": 3.750700003848157e-05,
1254
+ "loss": 0.3321,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.35728542914171657,
1259
+ "grad_norm": 0.8519895672798157,
1260
+ "learning_rate": 3.7547550516331555e-05,
1261
+ "loss": 0.4008,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.3592814371257485,
1266
+ "grad_norm": 0.8514580726623535,
1267
+ "learning_rate": 3.75878750850551e-05,
1268
+ "loss": 0.408,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.36127744510978044,
1273
+ "grad_norm": 0.8409926891326904,
1274
+ "learning_rate": 3.7627976247819744e-05,
1275
+ "loss": 0.4076,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.36327345309381237,
1280
+ "grad_norm": 0.7313259840011597,
1281
+ "learning_rate": 3.766785646641792e-05,
1282
+ "loss": 0.4311,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.3652694610778443,
1287
+ "grad_norm": 0.7503537535667419,
1288
+ "learning_rate": 3.770751816217383e-05,
1289
+ "loss": 0.422,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.36726546906187624,
1294
+ "grad_norm": 0.7808623313903809,
1295
+ "learning_rate": 3.7746963716825615e-05,
1296
+ "loss": 0.4475,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.36926147704590817,
1301
+ "grad_norm": 0.6921509504318237,
1302
+ "learning_rate": 3.778619547338356e-05,
1303
+ "loss": 0.3981,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.3712574850299401,
1308
+ "grad_norm": 0.7929064035415649,
1309
+ "learning_rate": 3.782521573696528e-05,
1310
+ "loss": 0.4482,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.37325349301397204,
1315
+ "grad_norm": 0.7118304371833801,
1316
+ "learning_rate": 3.786402677560832e-05,
1317
+ "loss": 0.3413,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.37524950099800397,
1322
+ "grad_norm": 0.7609389424324036,
1323
+ "learning_rate": 3.790263082106134e-05,
1324
+ "loss": 0.4207,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.3772455089820359,
1329
+ "grad_norm": 0.8060720562934875,
1330
+ "learning_rate": 3.794103006955407e-05,
1331
+ "loss": 0.4521,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.37924151696606784,
1336
+ "grad_norm": 0.8100878596305847,
1337
+ "learning_rate": 3.797922668254715e-05,
1338
+ "loss": 0.3653,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.3812375249500998,
1343
+ "grad_norm": 0.8395611047744751,
1344
+ "learning_rate": 3.801722278746213e-05,
1345
+ "loss": 0.3662,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.38323353293413176,
1350
+ "grad_norm": 0.7541958093643188,
1351
+ "learning_rate": 3.8055020478392495e-05,
1352
+ "loss": 0.2939,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.3852295409181637,
1357
+ "grad_norm": 0.8053567409515381,
1358
+ "learning_rate": 3.809262181679623e-05,
1359
+ "loss": 0.4302,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.3872255489021956,
1364
+ "grad_norm": 0.8586562275886536,
1365
+ "learning_rate": 3.813002883217044e-05,
1366
+ "loss": 0.3984,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.38922155688622756,
1371
+ "grad_norm": 0.7566971778869629,
1372
+ "learning_rate": 3.816724352270863e-05,
1373
+ "loss": 0.3839,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.3912175648702595,
1378
+ "grad_norm": 0.8142690658569336,
1379
+ "learning_rate": 3.8204267855941266e-05,
1380
+ "loss": 0.4014,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.3932135728542914,
1385
+ "grad_norm": 0.7769673466682434,
1386
+ "learning_rate": 3.824110376935989e-05,
1387
+ "loss": 0.3791,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.39520958083832336,
1392
+ "grad_norm": 0.8861010670661926,
1393
+ "learning_rate": 3.827775317102552e-05,
1394
+ "loss": 0.3904,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.3972055888223553,
1399
+ "grad_norm": 0.7677756547927856,
1400
+ "learning_rate": 3.831421794016178e-05,
1401
+ "loss": 0.3933,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.3992015968063872,
1406
+ "grad_norm": 0.9913503527641296,
1407
+ "learning_rate": 3.835049992773302e-05,
1408
+ "loss": 0.439,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.40119760479041916,
1413
+ "grad_norm": 0.847613513469696,
1414
+ "learning_rate": 3.838660095700815e-05,
1415
+ "loss": 0.4462,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.4031936127744511,
1420
+ "grad_norm": 0.8353721499443054,
1421
+ "learning_rate": 3.84225228241104e-05,
1422
+ "loss": 0.4621,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.405189620758483,
1427
+ "grad_norm": 0.809059739112854,
1428
+ "learning_rate": 3.8458267298553554e-05,
1429
+ "loss": 0.4888,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.40718562874251496,
1434
+ "grad_norm": 0.7496485710144043,
1435
+ "learning_rate": 3.8493836123764984e-05,
1436
+ "loss": 0.3836,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.4091816367265469,
1441
+ "grad_norm": 0.9037646651268005,
1442
+ "learning_rate": 3.852923101759591e-05,
1443
+ "loss": 0.3993,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.4111776447105788,
1448
+ "grad_norm": 0.8741063475608826,
1449
+ "learning_rate": 3.856445367281923e-05,
1450
+ "loss": 0.3948,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.41317365269461076,
1455
+ "grad_norm": 0.8445413112640381,
1456
+ "learning_rate": 3.859950575761529e-05,
1457
+ "loss": 0.4305,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.4151696606786427,
1462
+ "grad_norm": 0.9107454419136047,
1463
+ "learning_rate": 3.8634388916046025e-05,
1464
+ "loss": 0.4982,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.4171656686626746,
1469
+ "grad_norm": 0.7765053510665894,
1470
+ "learning_rate": 3.866910476851757e-05,
1471
+ "loss": 0.4147,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.41916167664670656,
1476
+ "grad_norm": 0.8410398364067078,
1477
+ "learning_rate": 3.870365491223199e-05,
1478
+ "loss": 0.4125,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.42115768463073855,
1483
+ "grad_norm": 0.8012726306915283,
1484
+ "learning_rate": 3.8738040921628215e-05,
1485
+ "loss": 0.3941,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.4231536926147705,
1490
+ "grad_norm": 0.8541998863220215,
1491
+ "learning_rate": 3.877226434881253e-05,
1492
+ "loss": 0.4327,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.4251497005988024,
1497
+ "grad_norm": 0.8243539929389954,
1498
+ "learning_rate": 3.880632672397897e-05,
1499
+ "loss": 0.4303,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.42714570858283435,
1504
+ "grad_norm": 0.8121338486671448,
1505
+ "learning_rate": 3.884022955581985e-05,
1506
+ "loss": 0.4301,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.4291417165668663,
1511
+ "grad_norm": 0.9100980758666992,
1512
+ "learning_rate": 3.887397433192676e-05,
1513
+ "loss": 0.4208,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.4311377245508982,
1518
+ "grad_norm": 0.748666524887085,
1519
+ "learning_rate": 3.890756251918219e-05,
1520
+ "loss": 0.3384,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.43313373253493015,
1525
+ "grad_norm": 0.758114755153656,
1526
+ "learning_rate": 3.894099556414216e-05,
1527
+ "loss": 0.3797,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.4351297405189621,
1532
+ "grad_norm": 0.8046779632568359,
1533
+ "learning_rate": 3.897427489341009e-05,
1534
+ "loss": 0.4325,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.437125748502994,
1539
+ "grad_norm": 0.872130274772644,
1540
+ "learning_rate": 3.900740191400198e-05,
1541
+ "loss": 0.4466,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.43912175648702595,
1546
+ "grad_norm": 0.8052610158920288,
1547
+ "learning_rate": 3.904037801370344e-05,
1548
+ "loss": 0.4355,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.4411177644710579,
1553
+ "grad_norm": 0.7204791903495789,
1554
+ "learning_rate": 3.9073204561418514e-05,
1555
+ "loss": 0.3465,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.4431137724550898,
1560
+ "grad_norm": 0.7979363799095154,
1561
+ "learning_rate": 3.9105882907510644e-05,
1562
+ "loss": 0.4004,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.44510978043912175,
1567
+ "grad_norm": 0.7269802093505859,
1568
+ "learning_rate": 3.913841438413601e-05,
1569
+ "loss": 0.4261,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.4471057884231537,
1574
+ "grad_norm": 0.6730761528015137,
1575
+ "learning_rate": 3.917080030556938e-05,
1576
+ "loss": 0.3192,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.4491017964071856,
1581
+ "grad_norm": 0.8741471767425537,
1582
+ "learning_rate": 3.9203041968522716e-05,
1583
+ "loss": 0.4663,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.45109780439121755,
1588
+ "grad_norm": 0.8293672800064087,
1589
+ "learning_rate": 3.923514065245669e-05,
1590
+ "loss": 0.4558,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.4530938123752495,
1595
+ "grad_norm": 0.7904106378555298,
1596
+ "learning_rate": 3.926709761988538e-05,
1597
+ "loss": 0.4546,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.4550898203592814,
1602
+ "grad_norm": 0.7640888094902039,
1603
+ "learning_rate": 3.929891411667424e-05,
1604
+ "loss": 0.3762,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.45708582834331335,
1609
+ "grad_norm": 0.776006281375885,
1610
+ "learning_rate": 3.933059137233147e-05,
1611
+ "loss": 0.4447,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.4590818363273453,
1616
+ "grad_norm": 0.8613069653511047,
1617
+ "learning_rate": 3.9362130600293214e-05,
1618
+ "loss": 0.4366,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.46107784431137727,
1623
+ "grad_norm": 0.7828835248947144,
1624
+ "learning_rate": 3.9393532998202405e-05,
1625
+ "loss": 0.4434,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.4630738522954092,
1630
+ "grad_norm": 0.7422530055046082,
1631
+ "learning_rate": 3.942479974818166e-05,
1632
+ "loss": 0.3755,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.46506986027944114,
1637
+ "grad_norm": 0.7256511449813843,
1638
+ "learning_rate": 3.945593201710032e-05,
1639
+ "loss": 0.375,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.46706586826347307,
1644
+ "grad_norm": 0.7594771385192871,
1645
+ "learning_rate": 3.9486930956835724e-05,
1646
+ "loss": 0.3985,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.469061876247505,
1651
+ "grad_norm": 0.7957077622413635,
1652
+ "learning_rate": 3.951779770452894e-05,
1653
+ "loss": 0.421,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.47105788423153694,
1658
+ "grad_norm": 0.7573441863059998,
1659
+ "learning_rate": 3.954853338283512e-05,
1660
+ "loss": 0.4592,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.47305389221556887,
1665
+ "grad_norm": 0.7109091877937317,
1666
+ "learning_rate": 3.9579139100168404e-05,
1667
+ "loss": 0.3732,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.4750499001996008,
1672
+ "grad_norm": 0.8672693371772766,
1673
+ "learning_rate": 3.960961595094187e-05,
1674
+ "loss": 0.4038,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.47704590818363274,
1679
+ "grad_norm": 0.7573640942573547,
1680
+ "learning_rate": 3.96399650158023e-05,
1681
+ "loss": 0.4348,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.47904191616766467,
1686
+ "grad_norm": 0.8784688711166382,
1687
+ "learning_rate": 3.96701873618601e-05,
1688
+ "loss": 0.4704,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.4810379241516966,
1693
+ "grad_norm": 0.8110889792442322,
1694
+ "learning_rate": 3.970028404291448e-05,
1695
+ "loss": 0.381,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.48303393213572854,
1700
+ "grad_norm": 0.8944825530052185,
1701
+ "learning_rate": 3.9730256099673865e-05,
1702
+ "loss": 0.3282,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.48502994011976047,
1707
+ "grad_norm": 0.8505921959877014,
1708
+ "learning_rate": 3.976010455997187e-05,
1709
+ "loss": 0.3794,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.4870259481037924,
1714
+ "grad_norm": 1.0878411531448364,
1715
+ "learning_rate": 3.978983043897883e-05,
1716
+ "loss": 0.4222,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.48902195608782434,
1721
+ "grad_norm": 0.7262081503868103,
1722
+ "learning_rate": 3.981943473940888e-05,
1723
+ "loss": 0.3682,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.49101796407185627,
1728
+ "grad_norm": 1.0304243564605713,
1729
+ "learning_rate": 3.984891845172299e-05,
1730
+ "loss": 0.3546,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.4930139720558882,
1735
+ "grad_norm": 0.7483956217765808,
1736
+ "learning_rate": 3.987828255432777e-05,
1737
+ "loss": 0.3764,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 0.49500998003992014,
1742
+ "grad_norm": 1.969207525253296,
1743
+ "learning_rate": 3.9907528013770276e-05,
1744
+ "loss": 0.4436,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 0.49700598802395207,
1749
+ "grad_norm": 0.836520254611969,
1750
+ "learning_rate": 3.993665578492894e-05,
1751
+ "loss": 0.4477,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 0.499001996007984,
1756
+ "grad_norm": 0.8878058791160583,
1757
+ "learning_rate": 3.9965666811200624e-05,
1758
+ "loss": 0.355,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 0.500998003992016,
1763
+ "grad_norm": 0.7905710935592651,
1764
+ "learning_rate": 3.999456202468397e-05,
1765
+ "loss": 0.4044,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 0.5029940119760479,
1770
+ "grad_norm": 0.7035382390022278,
1771
+ "learning_rate": 4.002334234635907e-05,
1772
+ "loss": 0.3515,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 0.5049900199600799,
1777
+ "grad_norm": 1.702528476715088,
1778
+ "learning_rate": 4.005200868626364e-05,
1779
+ "loss": 0.4055,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 0.5069860279441117,
1784
+ "grad_norm": 0.7991278171539307,
1785
+ "learning_rate": 4.008056194366564e-05,
1786
+ "loss": 0.4327,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 0.5089820359281437,
1791
+ "grad_norm": 0.803960382938385,
1792
+ "learning_rate": 4.010900300723259e-05,
1793
+ "loss": 0.4187,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 0.5109780439121756,
1798
+ "grad_norm": 0.7045860886573792,
1799
+ "learning_rate": 4.013733275519749e-05,
1800
+ "loss": 0.3947,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 0.5129740518962076,
1805
+ "grad_norm": 0.7627609372138977,
1806
+ "learning_rate": 4.016555205552158e-05,
1807
+ "loss": 0.3808,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 0.5149700598802395,
1812
+ "grad_norm": 0.7807031869888306,
1813
+ "learning_rate": 4.0193661766053834e-05,
1814
+ "loss": 0.4408,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 0.5169660678642715,
1819
+ "grad_norm": 0.7607232332229614,
1820
+ "learning_rate": 4.022166273468753e-05,
1821
+ "loss": 0.3826,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 0.5189620758483033,
1826
+ "grad_norm": 0.738200306892395,
1827
+ "learning_rate": 4.024955579951363e-05,
1828
+ "loss": 0.3403,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 0.5209580838323353,
1833
+ "grad_norm": 0.7401778101921082,
1834
+ "learning_rate": 4.027734178897136e-05,
1835
+ "loss": 0.3927,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 0.5229540918163673,
1840
+ "grad_norm": 0.8561487793922424,
1841
+ "learning_rate": 4.030502152199576e-05,
1842
+ "loss": 0.4247,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 0.5249500998003992,
1847
+ "grad_norm": 0.7845680117607117,
1848
+ "learning_rate": 4.033259580816264e-05,
1849
+ "loss": 0.4284,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 0.5269461077844312,
1854
+ "grad_norm": 0.8121227622032166,
1855
+ "learning_rate": 4.036006544783052e-05,
1856
+ "loss": 0.4534,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 0.5289421157684631,
1861
+ "grad_norm": 0.7015953660011292,
1862
+ "learning_rate": 4.0387431232280135e-05,
1863
+ "loss": 0.3404,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 0.530938123752495,
1868
+ "grad_norm": 0.7971146702766418,
1869
+ "learning_rate": 4.041469394385112e-05,
1870
+ "loss": 0.4455,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 0.5329341317365269,
1875
+ "grad_norm": 0.7655112147331238,
1876
+ "learning_rate": 4.0441854356076257e-05,
1877
+ "loss": 0.4636,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 0.5349301397205589,
1882
+ "grad_norm": 0.8320984840393066,
1883
+ "learning_rate": 4.046891323381315e-05,
1884
+ "loss": 0.3777,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 0.5369261477045908,
1889
+ "grad_norm": 0.9041264057159424,
1890
+ "learning_rate": 4.049587133337347e-05,
1891
+ "loss": 0.4006,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 0.5389221556886228,
1896
+ "grad_norm": 0.8236355185508728,
1897
+ "learning_rate": 4.0522729402649793e-05,
1898
+ "loss": 0.418,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 0.5409181636726547,
1903
+ "grad_norm": 0.9298795461654663,
1904
+ "learning_rate": 4.0549488181240096e-05,
1905
+ "loss": 0.3358,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 0.5429141716566867,
1910
+ "grad_norm": 0.7561654448509216,
1911
+ "learning_rate": 4.057614840056998e-05,
1912
+ "loss": 0.4008,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 0.5449101796407185,
1917
+ "grad_norm": 0.7712647318840027,
1918
+ "learning_rate": 4.06027107840126e-05,
1919
+ "loss": 0.3607,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 0.5469061876247505,
1924
+ "grad_norm": 0.7622309327125549,
1925
+ "learning_rate": 4.0629176047006474e-05,
1926
+ "loss": 0.3567,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 0.5489021956087824,
1931
+ "grad_norm": 0.7064681649208069,
1932
+ "learning_rate": 4.065554489717105e-05,
1933
+ "loss": 0.3528,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 0.5508982035928144,
1938
+ "grad_norm": 0.8189475536346436,
1939
+ "learning_rate": 4.068181803442029e-05,
1940
+ "loss": 0.4062,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 0.5528942115768463,
1945
+ "grad_norm": 0.8143854737281799,
1946
+ "learning_rate": 4.0707996151074147e-05,
1947
+ "loss": 0.4374,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 0.5548902195608783,
1952
+ "grad_norm": 0.7282266616821289,
1953
+ "learning_rate": 4.073407993196794e-05,
1954
+ "loss": 0.4121,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 0.5568862275449101,
1959
+ "grad_norm": 0.7541894316673279,
1960
+ "learning_rate": 4.076007005455996e-05,
1961
+ "loss": 0.4702,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 0.5588822355289421,
1966
+ "grad_norm": 0.7178213596343994,
1967
+ "learning_rate": 4.0785967189036986e-05,
1968
+ "loss": 0.3581,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 0.5608782435129741,
1973
+ "grad_norm": 0.8269951343536377,
1974
+ "learning_rate": 4.0811771998418e-05,
1975
+ "loss": 0.414,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 0.562874251497006,
1980
+ "grad_norm": 0.6949253082275391,
1981
+ "learning_rate": 4.083748513865602e-05,
1982
+ "loss": 0.3549,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 0.564870259481038,
1987
+ "grad_norm": 0.8457996845245361,
1988
+ "learning_rate": 4.086310725873818e-05,
1989
+ "loss": 0.4977,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 0.5668662674650699,
1994
+ "grad_norm": 0.835884690284729,
1995
+ "learning_rate": 4.0888639000783966e-05,
1996
+ "loss": 0.4646,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 0.5688622754491018,
2001
+ "grad_norm": 0.745847225189209,
2002
+ "learning_rate": 4.0914081000141844e-05,
2003
+ "loss": 0.4295,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 0.5708582834331337,
2008
+ "grad_norm": 0.703731119632721,
2009
+ "learning_rate": 4.0939433885484055e-05,
2010
+ "loss": 0.3168,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 0.5728542914171657,
2015
+ "grad_norm": 0.6979167461395264,
2016
+ "learning_rate": 4.0964698278899874e-05,
2017
+ "loss": 0.3373,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 0.5748502994011976,
2022
+ "grad_norm": 0.7321177124977112,
2023
+ "learning_rate": 4.0989874795987185e-05,
2024
+ "loss": 0.3705,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 0.5768463073852296,
2029
+ "grad_norm": 0.6812002658843994,
2030
+ "learning_rate": 4.1014964045942465e-05,
2031
+ "loss": 0.366,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 0.5788423153692615,
2036
+ "grad_norm": 0.8122517466545105,
2037
+ "learning_rate": 4.103996663164927e-05,
2038
+ "loss": 0.4435,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 0.5808383233532934,
2043
+ "grad_norm": 0.7670555710792542,
2044
+ "learning_rate": 4.106488314976513e-05,
2045
+ "loss": 0.471,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 0.5828343313373253,
2050
+ "grad_norm": 0.7457311749458313,
2051
+ "learning_rate": 4.108971419080698e-05,
2052
+ "loss": 0.3138,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 0.5848303393213573,
2057
+ "grad_norm": 0.8164945244789124,
2058
+ "learning_rate": 4.111446033923516e-05,
2059
+ "loss": 0.4394,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 0.5868263473053892,
2064
+ "grad_norm": 0.7513836622238159,
2065
+ "learning_rate": 4.113912217353596e-05,
2066
+ "loss": 0.3741,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 0.5888223552894212,
2071
+ "grad_norm": 0.7199726700782776,
2072
+ "learning_rate": 4.116370026630272e-05,
2073
+ "loss": 0.3116,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 0.590818363273453,
2078
+ "grad_norm": 0.8232783675193787,
2079
+ "learning_rate": 4.118819518431564e-05,
2080
+ "loss": 0.4048,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 0.592814371257485,
2085
+ "grad_norm": 0.7513990998268127,
2086
+ "learning_rate": 4.121260748862021e-05,
2087
+ "loss": 0.4346,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 0.5948103792415169,
2092
+ "grad_norm": 0.6866230368614197,
2093
+ "learning_rate": 4.123693773460426e-05,
2094
+ "loss": 0.3629,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 0.5968063872255489,
2099
+ "grad_norm": 0.7753307223320007,
2100
+ "learning_rate": 4.126118647207383e-05,
2101
+ "loss": 0.4248,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 0.5988023952095808,
2106
+ "grad_norm": 0.6598490476608276,
2107
+ "learning_rate": 4.1285354245327715e-05,
2108
+ "loss": 0.2834,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 0.6007984031936128,
2113
+ "grad_norm": 0.8024352788925171,
2114
+ "learning_rate": 4.1309441593230726e-05,
2115
+ "loss": 0.4276,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 0.6027944111776448,
2120
+ "grad_norm": 0.7745522260665894,
2121
+ "learning_rate": 4.133344904928585e-05,
2122
+ "loss": 0.3925,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 0.6047904191616766,
2127
+ "grad_norm": 0.6376944184303284,
2128
+ "learning_rate": 4.1357377141705084e-05,
2129
+ "loss": 0.2589,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 0.6067864271457086,
2134
+ "grad_norm": 0.6831088662147522,
2135
+ "learning_rate": 4.1381226393479236e-05,
2136
+ "loss": 0.3705,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 0.6087824351297405,
2141
+ "grad_norm": 0.6832078695297241,
2142
+ "learning_rate": 4.1404997322446435e-05,
2143
+ "loss": 0.3637,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 0.6107784431137725,
2148
+ "grad_norm": 0.7155686020851135,
2149
+ "learning_rate": 4.142869044135967e-05,
2150
+ "loss": 0.477,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 0.6127744510978044,
2155
+ "grad_norm": 0.7326770424842834,
2156
+ "learning_rate": 4.145230625795311e-05,
2157
+ "loss": 0.4123,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 0.6147704590818364,
2162
+ "grad_norm": 0.7184780240058899,
2163
+ "learning_rate": 4.14758452750074e-05,
2164
+ "loss": 0.3382,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 0.6167664670658682,
2169
+ "grad_norm": 0.7494658827781677,
2170
+ "learning_rate": 4.149930799041392e-05,
2171
+ "loss": 0.4246,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 0.6187624750499002,
2176
+ "grad_norm": 0.697238028049469,
2177
+ "learning_rate": 4.152269489723788e-05,
2178
+ "loss": 0.4338,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 0.6207584830339321,
2183
+ "grad_norm": 0.6342530846595764,
2184
+ "learning_rate": 4.1546006483780626e-05,
2185
+ "loss": 0.3202,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 0.6227544910179641,
2190
+ "grad_norm": 0.7153366804122925,
2191
+ "learning_rate": 4.156924323364072e-05,
2192
+ "loss": 0.3778,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 0.624750499001996,
2197
+ "grad_norm": 0.6666108965873718,
2198
+ "learning_rate": 4.1592405625774144e-05,
2199
+ "loss": 0.346,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 0.626746506986028,
2204
+ "grad_norm": 0.7076640725135803,
2205
+ "learning_rate": 4.161549413455358e-05,
2206
+ "loss": 0.3827,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 0.6287425149700598,
2211
+ "grad_norm": 0.7535362839698792,
2212
+ "learning_rate": 4.163850922982668e-05,
2213
+ "loss": 0.401,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 0.6307385229540918,
2218
+ "grad_norm": 0.6954286098480225,
2219
+ "learning_rate": 4.16614513769734e-05,
2220
+ "loss": 0.376,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 0.6327345309381237,
2225
+ "grad_norm": 0.6925478577613831,
2226
+ "learning_rate": 4.1684321036962526e-05,
2227
+ "loss": 0.3638,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 0.6347305389221557,
2232
+ "grad_norm": 0.663144588470459,
2233
+ "learning_rate": 4.170711866640721e-05,
2234
+ "loss": 0.3558,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 0.6367265469061876,
2239
+ "grad_norm": 0.7284447550773621,
2240
+ "learning_rate": 4.1729844717619684e-05,
2241
+ "loss": 0.4159,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 0.6387225548902196,
2246
+ "grad_norm": 0.708574652671814,
2247
+ "learning_rate": 4.17524996386651e-05,
2248
+ "loss": 0.3942,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 0.6407185628742516,
2253
+ "grad_norm": 0.6826594471931458,
2254
+ "learning_rate": 4.177508387341454e-05,
2255
+ "loss": 0.3563,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 0.6427145708582834,
2260
+ "grad_norm": 0.7092903256416321,
2261
+ "learning_rate": 4.179759786159719e-05,
2262
+ "loss": 0.4169,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 0.6447105788423154,
2267
+ "grad_norm": 0.6470283269882202,
2268
+ "learning_rate": 4.182004203885172e-05,
2269
+ "loss": 0.3595,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 0.6467065868263473,
2274
+ "grad_norm": 0.6560471057891846,
2275
+ "learning_rate": 4.184241683677687e-05,
2276
+ "loss": 0.3945,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 0.6487025948103793,
2281
+ "grad_norm": 0.7021344900131226,
2282
+ "learning_rate": 4.1864722682981245e-05,
2283
+ "loss": 0.3682,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 0.6506986027944112,
2288
+ "grad_norm": 0.6736760139465332,
2289
+ "learning_rate": 4.188696000113232e-05,
2290
+ "loss": 0.4012,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 0.6526946107784432,
2295
+ "grad_norm": 0.58335942029953,
2296
+ "learning_rate": 4.190912921100477e-05,
2297
+ "loss": 0.2982,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 0.654690618762475,
2302
+ "grad_norm": 0.7224960327148438,
2303
+ "learning_rate": 4.1931230728527994e-05,
2304
+ "loss": 0.3767,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 0.656686626746507,
2309
+ "grad_norm": 0.7125536203384399,
2310
+ "learning_rate": 4.195326496583291e-05,
2311
+ "loss": 0.3918,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 0.6586826347305389,
2316
+ "grad_norm": 0.7161789536476135,
2317
+ "learning_rate": 4.1975232331298125e-05,
2318
+ "loss": 0.3727,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 0.6606786427145709,
2323
+ "grad_norm": 0.7045012712478638,
2324
+ "learning_rate": 4.1997133229595316e-05,
2325
+ "loss": 0.4168,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 0.6626746506986028,
2330
+ "grad_norm": 0.7229664921760559,
2331
+ "learning_rate": 4.201896806173394e-05,
2332
+ "loss": 0.406,
2333
+ "step": 332
2334
+ },
2335
+ {
2336
+ "epoch": 0.6646706586826348,
2337
+ "grad_norm": 0.6685640811920166,
2338
+ "learning_rate": 4.2040737225105335e-05,
2339
+ "loss": 0.3348,
2340
+ "step": 333
2341
+ },
2342
+ {
2343
+ "epoch": 0.6666666666666666,
2344
+ "grad_norm": 0.6416003108024597,
2345
+ "learning_rate": 4.206244111352608e-05,
2346
+ "loss": 0.3134,
2347
+ "step": 334
2348
+ },
2349
+ {
2350
+ "epoch": 0.6686626746506986,
2351
+ "grad_norm": 0.6860243082046509,
2352
+ "learning_rate": 4.2084080117280756e-05,
2353
+ "loss": 0.3855,
2354
+ "step": 335
2355
+ },
2356
+ {
2357
+ "epoch": 0.6706586826347305,
2358
+ "grad_norm": 0.751287579536438,
2359
+ "learning_rate": 4.210565462316407e-05,
2360
+ "loss": 0.4388,
2361
+ "step": 336
2362
+ },
2363
+ {
2364
+ "epoch": 0.6726546906187625,
2365
+ "grad_norm": 0.7298620939254761,
2366
+ "learning_rate": 4.2127165014522315e-05,
2367
+ "loss": 0.4084,
2368
+ "step": 337
2369
+ },
2370
+ {
2371
+ "epoch": 0.6746506986027944,
2372
+ "grad_norm": 0.7535167336463928,
2373
+ "learning_rate": 4.214861167129425e-05,
2374
+ "loss": 0.3971,
2375
+ "step": 338
2376
+ },
2377
+ {
2378
+ "epoch": 0.6766467065868264,
2379
+ "grad_norm": 0.6288606524467468,
2380
+ "learning_rate": 4.2169994970051365e-05,
2381
+ "loss": 0.3184,
2382
+ "step": 339
2383
+ },
2384
+ {
2385
+ "epoch": 0.6786427145708582,
2386
+ "grad_norm": 0.6942071914672852,
2387
+ "learning_rate": 4.219131528403759e-05,
2388
+ "loss": 0.4085,
2389
+ "step": 340
2390
+ },
2391
+ {
2392
+ "epoch": 0.6806387225548902,
2393
+ "grad_norm": 0.7049132585525513,
2394
+ "learning_rate": 4.22125729832083e-05,
2395
+ "loss": 0.3799,
2396
+ "step": 341
2397
+ },
2398
+ {
2399
+ "epoch": 0.6826347305389222,
2400
+ "grad_norm": 0.6633714437484741,
2401
+ "learning_rate": 4.2233768434268914e-05,
2402
+ "loss": 0.3615,
2403
+ "step": 342
2404
+ },
2405
+ {
2406
+ "epoch": 0.6846307385229541,
2407
+ "grad_norm": 0.7143837809562683,
2408
+ "learning_rate": 4.225490200071284e-05,
2409
+ "loss": 0.397,
2410
+ "step": 343
2411
+ },
2412
+ {
2413
+ "epoch": 0.6866267465069861,
2414
+ "grad_norm": 0.6334770917892456,
2415
+ "learning_rate": 4.227597404285883e-05,
2416
+ "loss": 0.3192,
2417
+ "step": 344
2418
+ },
2419
+ {
2420
+ "epoch": 0.688622754491018,
2421
+ "grad_norm": 0.6318526268005371,
2422
+ "learning_rate": 4.229698491788791e-05,
2423
+ "loss": 0.3409,
2424
+ "step": 345
2425
+ },
2426
+ {
2427
+ "epoch": 0.6906187624750499,
2428
+ "grad_norm": 0.6425897479057312,
2429
+ "learning_rate": 4.231793497987961e-05,
2430
+ "loss": 0.3506,
2431
+ "step": 346
2432
+ },
2433
+ {
2434
+ "epoch": 0.6926147704590818,
2435
+ "grad_norm": 0.6882063150405884,
2436
+ "learning_rate": 4.2338824579847904e-05,
2437
+ "loss": 0.3697,
2438
+ "step": 347
2439
+ },
2440
+ {
2441
+ "epoch": 0.6946107784431138,
2442
+ "grad_norm": 0.6814457774162292,
2443
+ "learning_rate": 4.235965406577636e-05,
2444
+ "loss": 0.4179,
2445
+ "step": 348
2446
+ },
2447
+ {
2448
+ "epoch": 0.6966067864271457,
2449
+ "grad_norm": 0.7089083790779114,
2450
+ "learning_rate": 4.2380423782653e-05,
2451
+ "loss": 0.358,
2452
+ "step": 349
2453
+ },
2454
+ {
2455
+ "epoch": 0.6986027944111777,
2456
+ "grad_norm": 0.671987771987915,
2457
+ "learning_rate": 4.240113407250459e-05,
2458
+ "loss": 0.4223,
2459
+ "step": 350
2460
+ },
2461
+ {
2462
+ "epoch": 0.7005988023952096,
2463
+ "grad_norm": 0.6932473182678223,
2464
+ "learning_rate": 4.24217852744304e-05,
2465
+ "loss": 0.4283,
2466
+ "step": 351
2467
+ },
2468
+ {
2469
+ "epoch": 0.7025948103792415,
2470
+ "grad_norm": 0.6401710510253906,
2471
+ "learning_rate": 4.244237772463552e-05,
2472
+ "loss": 0.3277,
2473
+ "step": 352
2474
+ },
2475
+ {
2476
+ "epoch": 0.7045908183632734,
2477
+ "grad_norm": 0.5808695554733276,
2478
+ "learning_rate": 4.246291175646371e-05,
2479
+ "loss": 0.3153,
2480
+ "step": 353
2481
+ },
2482
+ {
2483
+ "epoch": 0.7065868263473054,
2484
+ "grad_norm": 0.5929372310638428,
2485
+ "learning_rate": 4.24833877004298e-05,
2486
+ "loss": 0.2934,
2487
+ "step": 354
2488
+ },
2489
+ {
2490
+ "epoch": 0.7085828343313373,
2491
+ "grad_norm": 0.6138365864753723,
2492
+ "learning_rate": 4.250380588425157e-05,
2493
+ "loss": 0.2647,
2494
+ "step": 355
2495
+ },
2496
+ {
2497
+ "epoch": 0.7105788423153693,
2498
+ "grad_norm": 0.69126957654953,
2499
+ "learning_rate": 4.2524166632881255e-05,
2500
+ "loss": 0.3777,
2501
+ "step": 356
2502
+ },
2503
+ {
2504
+ "epoch": 0.7125748502994012,
2505
+ "grad_norm": 0.618993878364563,
2506
+ "learning_rate": 4.254447026853656e-05,
2507
+ "loss": 0.2874,
2508
+ "step": 357
2509
+ },
2510
+ {
2511
+ "epoch": 0.7145708582834331,
2512
+ "grad_norm": 0.6197064518928528,
2513
+ "learning_rate": 4.2564717110731244e-05,
2514
+ "loss": 0.3137,
2515
+ "step": 358
2516
+ },
2517
+ {
2518
+ "epoch": 0.716566866267465,
2519
+ "grad_norm": 0.6574029326438904,
2520
+ "learning_rate": 4.258490747630532e-05,
2521
+ "loss": 0.3366,
2522
+ "step": 359
2523
+ },
2524
+ {
2525
+ "epoch": 0.718562874251497,
2526
+ "grad_norm": 0.6827244162559509,
2527
+ "learning_rate": 4.260504167945479e-05,
2528
+ "loss": 0.367,
2529
+ "step": 360
2530
+ },
2531
+ {
2532
+ "epoch": 0.720558882235529,
2533
+ "grad_norm": 0.6920093297958374,
2534
+ "learning_rate": 4.2625120031760965e-05,
2535
+ "loss": 0.3473,
2536
+ "step": 361
2537
+ },
2538
+ {
2539
+ "epoch": 0.7225548902195609,
2540
+ "grad_norm": 0.6315056085586548,
2541
+ "learning_rate": 4.264514284221944e-05,
2542
+ "loss": 0.3477,
2543
+ "step": 362
2544
+ },
2545
+ {
2546
+ "epoch": 0.7245508982035929,
2547
+ "grad_norm": 0.6894274950027466,
2548
+ "learning_rate": 4.266511041726854e-05,
2549
+ "loss": 0.3818,
2550
+ "step": 363
2551
+ },
2552
+ {
2553
+ "epoch": 0.7265469061876247,
2554
+ "grad_norm": 0.7182605266571045,
2555
+ "learning_rate": 4.26850230608176e-05,
2556
+ "loss": 0.3959,
2557
+ "step": 364
2558
+ },
2559
+ {
2560
+ "epoch": 0.7285429141716567,
2561
+ "grad_norm": 0.6431974172592163,
2562
+ "learning_rate": 4.2704881074274584e-05,
2563
+ "loss": 0.3484,
2564
+ "step": 365
2565
+ },
2566
+ {
2567
+ "epoch": 0.7305389221556886,
2568
+ "grad_norm": 0.6523058414459229,
2569
+ "learning_rate": 4.272468475657351e-05,
2570
+ "loss": 0.3315,
2571
+ "step": 366
2572
+ },
2573
+ {
2574
+ "epoch": 0.7325349301397206,
2575
+ "grad_norm": 0.7160993218421936,
2576
+ "learning_rate": 4.2744434404201497e-05,
2577
+ "loss": 0.3806,
2578
+ "step": 367
2579
+ },
2580
+ {
2581
+ "epoch": 0.7345309381237525,
2582
+ "grad_norm": 0.6819020509719849,
2583
+ "learning_rate": 4.27641303112253e-05,
2584
+ "loss": 0.3889,
2585
+ "step": 368
2586
+ },
2587
+ {
2588
+ "epoch": 0.7365269461077845,
2589
+ "grad_norm": 0.5881057381629944,
2590
+ "learning_rate": 4.278377276931767e-05,
2591
+ "loss": 0.2647,
2592
+ "step": 369
2593
+ },
2594
+ {
2595
+ "epoch": 0.7385229540918163,
2596
+ "grad_norm": 1.0767422914505005,
2597
+ "learning_rate": 4.2803362067783256e-05,
2598
+ "loss": 0.3912,
2599
+ "step": 370
2600
+ },
2601
+ {
2602
+ "epoch": 0.7405189620758483,
2603
+ "grad_norm": 0.6878696084022522,
2604
+ "learning_rate": 4.2822898493584104e-05,
2605
+ "loss": 0.4216,
2606
+ "step": 371
2607
+ },
2608
+ {
2609
+ "epoch": 0.7425149700598802,
2610
+ "grad_norm": 0.6871569752693176,
2611
+ "learning_rate": 4.284238233136496e-05,
2612
+ "loss": 0.395,
2613
+ "step": 372
2614
+ },
2615
+ {
2616
+ "epoch": 0.7445109780439122,
2617
+ "grad_norm": 0.6874458193778992,
2618
+ "learning_rate": 4.286181386347813e-05,
2619
+ "loss": 0.3683,
2620
+ "step": 373
2621
+ },
2622
+ {
2623
+ "epoch": 0.7465069860279441,
2624
+ "grad_norm": 0.6394293308258057,
2625
+ "learning_rate": 4.288119337000801e-05,
2626
+ "loss": 0.3518,
2627
+ "step": 374
2628
+ },
2629
+ {
2630
+ "epoch": 0.7485029940119761,
2631
+ "grad_norm": 0.67393559217453,
2632
+ "learning_rate": 4.2900521128795315e-05,
2633
+ "loss": 0.4018,
2634
+ "step": 375
2635
+ },
2636
+ {
2637
+ "epoch": 0.7504990019960079,
2638
+ "grad_norm": 0.6365067958831787,
2639
+ "learning_rate": 4.291979741546102e-05,
2640
+ "loss": 0.3719,
2641
+ "step": 376
2642
+ },
2643
+ {
2644
+ "epoch": 0.7524950099800399,
2645
+ "grad_norm": 0.6792694926261902,
2646
+ "learning_rate": 4.293902250342989e-05,
2647
+ "loss": 0.3623,
2648
+ "step": 377
2649
+ },
2650
+ {
2651
+ "epoch": 0.7544910179640718,
2652
+ "grad_norm": 0.794163167476654,
2653
+ "learning_rate": 4.295819666395376e-05,
2654
+ "loss": 0.3945,
2655
+ "step": 378
2656
+ },
2657
+ {
2658
+ "epoch": 0.7564870259481038,
2659
+ "grad_norm": 0.7103076577186584,
2660
+ "learning_rate": 4.297732016613454e-05,
2661
+ "loss": 0.4585,
2662
+ "step": 379
2663
+ },
2664
+ {
2665
+ "epoch": 0.7584830339321357,
2666
+ "grad_norm": 0.6877479553222656,
2667
+ "learning_rate": 4.299639327694684e-05,
2668
+ "loss": 0.4261,
2669
+ "step": 380
2670
+ },
2671
+ {
2672
+ "epoch": 0.7604790419161677,
2673
+ "grad_norm": 0.6512800455093384,
2674
+ "learning_rate": 4.3015416261260325e-05,
2675
+ "loss": 0.336,
2676
+ "step": 381
2677
+ },
2678
+ {
2679
+ "epoch": 0.7624750499001997,
2680
+ "grad_norm": 0.6555919051170349,
2681
+ "learning_rate": 4.303438938186182e-05,
2682
+ "loss": 0.3949,
2683
+ "step": 382
2684
+ },
2685
+ {
2686
+ "epoch": 0.7644710578842315,
2687
+ "grad_norm": 0.6375437378883362,
2688
+ "learning_rate": 4.305331289947705e-05,
2689
+ "loss": 0.348,
2690
+ "step": 383
2691
+ },
2692
+ {
2693
+ "epoch": 0.7664670658682635,
2694
+ "grad_norm": 0.6899069547653198,
2695
+ "learning_rate": 4.3072187072792184e-05,
2696
+ "loss": 0.3715,
2697
+ "step": 384
2698
+ },
2699
+ {
2700
+ "epoch": 0.7684630738522954,
2701
+ "grad_norm": 0.6571375727653503,
2702
+ "learning_rate": 4.309101215847502e-05,
2703
+ "loss": 0.3471,
2704
+ "step": 385
2705
+ },
2706
+ {
2707
+ "epoch": 0.7704590818363274,
2708
+ "grad_norm": 0.6866909265518188,
2709
+ "learning_rate": 4.3109788411195924e-05,
2710
+ "loss": 0.3721,
2711
+ "step": 386
2712
+ },
2713
+ {
2714
+ "epoch": 0.7724550898203593,
2715
+ "grad_norm": 0.6416053175926208,
2716
+ "learning_rate": 4.312851608364853e-05,
2717
+ "loss": 0.3501,
2718
+ "step": 387
2719
+ },
2720
+ {
2721
+ "epoch": 0.7744510978043913,
2722
+ "grad_norm": 0.6585414409637451,
2723
+ "learning_rate": 4.314719542657013e-05,
2724
+ "loss": 0.3446,
2725
+ "step": 388
2726
+ },
2727
+ {
2728
+ "epoch": 0.7764471057884231,
2729
+ "grad_norm": 0.6449529528617859,
2730
+ "learning_rate": 4.3165826688761796e-05,
2731
+ "loss": 0.31,
2732
+ "step": 389
2733
+ },
2734
+ {
2735
+ "epoch": 0.7784431137724551,
2736
+ "grad_norm": 0.6616773009300232,
2737
+ "learning_rate": 4.318441011710833e-05,
2738
+ "loss": 0.3356,
2739
+ "step": 390
2740
+ },
2741
+ {
2742
+ "epoch": 0.780439121756487,
2743
+ "grad_norm": 0.681754469871521,
2744
+ "learning_rate": 4.3202945956597786e-05,
2745
+ "loss": 0.3543,
2746
+ "step": 391
2747
+ },
2748
+ {
2749
+ "epoch": 0.782435129740519,
2750
+ "grad_norm": 0.6211993098258972,
2751
+ "learning_rate": 4.3221434450340956e-05,
2752
+ "loss": 0.3157,
2753
+ "step": 392
2754
+ },
2755
+ {
2756
+ "epoch": 0.7844311377245509,
2757
+ "grad_norm": 0.6262781620025635,
2758
+ "learning_rate": 4.323987583959045e-05,
2759
+ "loss": 0.3533,
2760
+ "step": 393
2761
+ },
2762
+ {
2763
+ "epoch": 0.7864271457085829,
2764
+ "grad_norm": 0.6640245318412781,
2765
+ "learning_rate": 4.325827036375957e-05,
2766
+ "loss": 0.3742,
2767
+ "step": 394
2768
+ },
2769
+ {
2770
+ "epoch": 0.7884231536926147,
2771
+ "grad_norm": 0.6164320111274719,
2772
+ "learning_rate": 4.327661826044101e-05,
2773
+ "loss": 0.3472,
2774
+ "step": 395
2775
+ },
2776
+ {
2777
+ "epoch": 0.7904191616766467,
2778
+ "grad_norm": 0.6439725756645203,
2779
+ "learning_rate": 4.329491976542521e-05,
2780
+ "loss": 0.359,
2781
+ "step": 396
2782
+ },
2783
+ {
2784
+ "epoch": 0.7924151696606786,
2785
+ "grad_norm": 0.7187615036964417,
2786
+ "learning_rate": 4.331317511271859e-05,
2787
+ "loss": 0.4445,
2788
+ "step": 397
2789
+ },
2790
+ {
2791
+ "epoch": 0.7944111776447106,
2792
+ "grad_norm": 0.660010039806366,
2793
+ "learning_rate": 4.333138453456147e-05,
2794
+ "loss": 0.3213,
2795
+ "step": 398
2796
+ },
2797
+ {
2798
+ "epoch": 0.7964071856287425,
2799
+ "grad_norm": 0.7590385675430298,
2800
+ "learning_rate": 4.334954826144581e-05,
2801
+ "loss": 0.3359,
2802
+ "step": 399
2803
+ },
2804
+ {
2805
+ "epoch": 0.7984031936127745,
2806
+ "grad_norm": 0.6344367861747742,
2807
+ "learning_rate": 4.336766652213271e-05,
2808
+ "loss": 0.3542,
2809
+ "step": 400
2810
+ },
2811
+ {
2812
+ "epoch": 0.8003992015968064,
2813
+ "grad_norm": 0.6679601073265076,
2814
+ "learning_rate": 4.338573954366971e-05,
2815
+ "loss": 0.3642,
2816
+ "step": 401
2817
+ },
2818
+ {
2819
+ "epoch": 0.8023952095808383,
2820
+ "grad_norm": 0.6402161121368408,
2821
+ "learning_rate": 4.340376755140784e-05,
2822
+ "loss": 0.3603,
2823
+ "step": 402
2824
+ },
2825
+ {
2826
+ "epoch": 0.8043912175648703,
2827
+ "grad_norm": 0.7084898948669434,
2828
+ "learning_rate": 4.342175076901849e-05,
2829
+ "loss": 0.3817,
2830
+ "step": 403
2831
+ },
2832
+ {
2833
+ "epoch": 0.8063872255489022,
2834
+ "grad_norm": 0.6191865801811218,
2835
+ "learning_rate": 4.343968941851009e-05,
2836
+ "loss": 0.3017,
2837
+ "step": 404
2838
+ },
2839
+ {
2840
+ "epoch": 0.8083832335329342,
2841
+ "grad_norm": 0.6750943660736084,
2842
+ "learning_rate": 4.345758372024448e-05,
2843
+ "loss": 0.3949,
2844
+ "step": 405
2845
+ },
2846
+ {
2847
+ "epoch": 0.810379241516966,
2848
+ "grad_norm": 0.6468753814697266,
2849
+ "learning_rate": 4.347543389295324e-05,
2850
+ "loss": 0.3668,
2851
+ "step": 406
2852
+ },
2853
+ {
2854
+ "epoch": 0.812375249500998,
2855
+ "grad_norm": 0.6904520988464355,
2856
+ "learning_rate": 4.3493240153753666e-05,
2857
+ "loss": 0.3499,
2858
+ "step": 407
2859
+ },
2860
+ {
2861
+ "epoch": 0.8143712574850299,
2862
+ "grad_norm": 0.6204891800880432,
2863
+ "learning_rate": 4.3511002718164666e-05,
2864
+ "loss": 0.3304,
2865
+ "step": 408
2866
+ },
2867
+ {
2868
+ "epoch": 0.8163672654690619,
2869
+ "grad_norm": 0.6633168458938599,
2870
+ "learning_rate": 4.352872180012237e-05,
2871
+ "loss": 0.3337,
2872
+ "step": 409
2873
+ },
2874
+ {
2875
+ "epoch": 0.8183632734530938,
2876
+ "grad_norm": 0.8691318035125732,
2877
+ "learning_rate": 4.35463976119956e-05,
2878
+ "loss": 0.4502,
2879
+ "step": 410
2880
+ },
2881
+ {
2882
+ "epoch": 0.8203592814371258,
2883
+ "grad_norm": 0.7373143434524536,
2884
+ "learning_rate": 4.356403036460115e-05,
2885
+ "loss": 0.4128,
2886
+ "step": 411
2887
+ },
2888
+ {
2889
+ "epoch": 0.8223552894211577,
2890
+ "grad_norm": 0.6885534524917603,
2891
+ "learning_rate": 4.3581620267218916e-05,
2892
+ "loss": 0.3341,
2893
+ "step": 412
2894
+ },
2895
+ {
2896
+ "epoch": 0.8243512974051896,
2897
+ "grad_norm": 0.6862485408782959,
2898
+ "learning_rate": 4.359916752760669e-05,
2899
+ "loss": 0.3498,
2900
+ "step": 413
2901
+ },
2902
+ {
2903
+ "epoch": 0.8263473053892215,
2904
+ "grad_norm": 0.6959711313247681,
2905
+ "learning_rate": 4.361667235201499e-05,
2906
+ "loss": 0.3796,
2907
+ "step": 414
2908
+ },
2909
+ {
2910
+ "epoch": 0.8283433133732535,
2911
+ "grad_norm": 0.7265036106109619,
2912
+ "learning_rate": 4.363413494520154e-05,
2913
+ "loss": 0.3911,
2914
+ "step": 415
2915
+ },
2916
+ {
2917
+ "epoch": 0.8303393213572854,
2918
+ "grad_norm": 0.6805566549301147,
2919
+ "learning_rate": 4.365155551044572e-05,
2920
+ "loss": 0.367,
2921
+ "step": 416
2922
+ },
2923
+ {
2924
+ "epoch": 0.8323353293413174,
2925
+ "grad_norm": 0.6219791173934937,
2926
+ "learning_rate": 4.366893424956263e-05,
2927
+ "loss": 0.289,
2928
+ "step": 417
2929
+ },
2930
+ {
2931
+ "epoch": 0.8343313373253493,
2932
+ "grad_norm": 0.6582449674606323,
2933
+ "learning_rate": 4.368627136291726e-05,
2934
+ "loss": 0.2747,
2935
+ "step": 418
2936
+ },
2937
+ {
2938
+ "epoch": 0.8363273453093812,
2939
+ "grad_norm": 0.6985988616943359,
2940
+ "learning_rate": 4.370356704943825e-05,
2941
+ "loss": 0.3435,
2942
+ "step": 419
2943
+ },
2944
+ {
2945
+ "epoch": 0.8383233532934131,
2946
+ "grad_norm": 0.6607214212417603,
2947
+ "learning_rate": 4.372082150663168e-05,
2948
+ "loss": 0.3645,
2949
+ "step": 420
2950
+ },
2951
+ {
2952
+ "epoch": 0.8403193612774451,
2953
+ "grad_norm": 0.723174512386322,
2954
+ "learning_rate": 4.3738034930594475e-05,
2955
+ "loss": 0.3672,
2956
+ "step": 421
2957
+ },
2958
+ {
2959
+ "epoch": 0.8423153692614771,
2960
+ "grad_norm": 0.6832453012466431,
2961
+ "learning_rate": 4.3755207516027904e-05,
2962
+ "loss": 0.3806,
2963
+ "step": 422
2964
+ },
2965
+ {
2966
+ "epoch": 0.844311377245509,
2967
+ "grad_norm": 0.6922501921653748,
2968
+ "learning_rate": 4.377233945625071e-05,
2969
+ "loss": 0.4031,
2970
+ "step": 423
2971
+ },
2972
+ {
2973
+ "epoch": 0.846307385229541,
2974
+ "grad_norm": 0.6647071242332458,
2975
+ "learning_rate": 4.378943094321221e-05,
2976
+ "loss": 0.3628,
2977
+ "step": 424
2978
+ },
2979
+ {
2980
+ "epoch": 0.8483033932135728,
2981
+ "grad_norm": 0.6893953084945679,
2982
+ "learning_rate": 4.3806482167505196e-05,
2983
+ "loss": 0.3434,
2984
+ "step": 425
2985
+ },
2986
+ {
2987
+ "epoch": 0.8502994011976048,
2988
+ "grad_norm": 0.8566087484359741,
2989
+ "learning_rate": 4.382349331837866e-05,
2990
+ "loss": 0.3803,
2991
+ "step": 426
2992
+ },
2993
+ {
2994
+ "epoch": 0.8522954091816367,
2995
+ "grad_norm": 0.7948191165924072,
2996
+ "learning_rate": 4.3840464583750404e-05,
2997
+ "loss": 0.3627,
2998
+ "step": 427
2999
+ },
3000
+ {
3001
+ "epoch": 0.8542914171656687,
3002
+ "grad_norm": 0.6731837391853333,
3003
+ "learning_rate": 4.385739615021954e-05,
3004
+ "loss": 0.395,
3005
+ "step": 428
3006
+ },
3007
+ {
3008
+ "epoch": 0.8562874251497006,
3009
+ "grad_norm": 0.6760764122009277,
3010
+ "learning_rate": 4.387428820307874e-05,
3011
+ "loss": 0.3627,
3012
+ "step": 429
3013
+ },
3014
+ {
3015
+ "epoch": 0.8582834331337326,
3016
+ "grad_norm": 0.7794198989868164,
3017
+ "learning_rate": 4.3891140926326446e-05,
3018
+ "loss": 0.3166,
3019
+ "step": 430
3020
+ },
3021
+ {
3022
+ "epoch": 0.8602794411177644,
3023
+ "grad_norm": 0.7948319911956787,
3024
+ "learning_rate": 4.390795450267886e-05,
3025
+ "loss": 0.3634,
3026
+ "step": 431
3027
+ },
3028
+ {
3029
+ "epoch": 0.8622754491017964,
3030
+ "grad_norm": 0.6758688688278198,
3031
+ "learning_rate": 4.3924729113581876e-05,
3032
+ "loss": 0.3103,
3033
+ "step": 432
3034
+ },
3035
+ {
3036
+ "epoch": 0.8642714570858283,
3037
+ "grad_norm": 1.493560791015625,
3038
+ "learning_rate": 4.394146493922276e-05,
3039
+ "loss": 0.3551,
3040
+ "step": 433
3041
+ },
3042
+ {
3043
+ "epoch": 0.8662674650698603,
3044
+ "grad_norm": 0.6501355171203613,
3045
+ "learning_rate": 4.395816215854185e-05,
3046
+ "loss": 0.3433,
3047
+ "step": 434
3048
+ },
3049
+ {
3050
+ "epoch": 0.8682634730538922,
3051
+ "grad_norm": 0.7338974475860596,
3052
+ "learning_rate": 4.397482094924396e-05,
3053
+ "loss": 0.3748,
3054
+ "step": 435
3055
+ },
3056
+ {
3057
+ "epoch": 0.8702594810379242,
3058
+ "grad_norm": 0.7021346688270569,
3059
+ "learning_rate": 4.399144148780977e-05,
3060
+ "loss": 0.3988,
3061
+ "step": 436
3062
+ },
3063
+ {
3064
+ "epoch": 0.872255489021956,
3065
+ "grad_norm": 0.8264355659484863,
3066
+ "learning_rate": 4.400802394950703e-05,
3067
+ "loss": 0.3821,
3068
+ "step": 437
3069
+ },
3070
+ {
3071
+ "epoch": 0.874251497005988,
3072
+ "grad_norm": 0.7332090139389038,
3073
+ "learning_rate": 4.402456850840166e-05,
3074
+ "loss": 0.3212,
3075
+ "step": 438
3076
+ },
3077
+ {
3078
+ "epoch": 0.8762475049900199,
3079
+ "grad_norm": 0.7158175706863403,
3080
+ "learning_rate": 4.4041075337368695e-05,
3081
+ "loss": 0.3014,
3082
+ "step": 439
3083
+ },
3084
+ {
3085
+ "epoch": 0.8782435129740519,
3086
+ "grad_norm": 0.6871099472045898,
3087
+ "learning_rate": 4.405754460810312e-05,
3088
+ "loss": 0.3363,
3089
+ "step": 440
3090
+ },
3091
+ {
3092
+ "epoch": 0.8802395209580839,
3093
+ "grad_norm": 0.7581283450126648,
3094
+ "learning_rate": 4.407397649113065e-05,
3095
+ "loss": 0.3706,
3096
+ "step": 441
3097
+ },
3098
+ {
3099
+ "epoch": 0.8822355289421158,
3100
+ "grad_norm": 0.7075430154800415,
3101
+ "learning_rate": 4.40903711558182e-05,
3102
+ "loss": 0.3625,
3103
+ "step": 442
3104
+ },
3105
+ {
3106
+ "epoch": 0.8842315369261478,
3107
+ "grad_norm": 0.6902301907539368,
3108
+ "learning_rate": 4.41067287703845e-05,
3109
+ "loss": 0.3459,
3110
+ "step": 443
3111
+ },
3112
+ {
3113
+ "epoch": 0.8862275449101796,
3114
+ "grad_norm": 0.7632633447647095,
3115
+ "learning_rate": 4.412304950191033e-05,
3116
+ "loss": 0.3863,
3117
+ "step": 444
3118
+ },
3119
+ {
3120
+ "epoch": 0.8882235528942116,
3121
+ "grad_norm": 0.8091756701469421,
3122
+ "learning_rate": 4.413933351634886e-05,
3123
+ "loss": 0.3873,
3124
+ "step": 445
3125
+ },
3126
+ {
3127
+ "epoch": 0.8902195608782435,
3128
+ "grad_norm": 0.7229244709014893,
3129
+ "learning_rate": 4.4155580978535707e-05,
3130
+ "loss": 0.3199,
3131
+ "step": 446
3132
+ },
3133
+ {
3134
+ "epoch": 0.8922155688622755,
3135
+ "grad_norm": 0.6914481520652771,
3136
+ "learning_rate": 4.417179205219895e-05,
3137
+ "loss": 0.3679,
3138
+ "step": 447
3139
+ },
3140
+ {
3141
+ "epoch": 0.8942115768463074,
3142
+ "grad_norm": 0.6364032030105591,
3143
+ "learning_rate": 4.418796689996907e-05,
3144
+ "loss": 0.2962,
3145
+ "step": 448
3146
+ },
3147
+ {
3148
+ "epoch": 0.8962075848303394,
3149
+ "grad_norm": 0.7445045113563538,
3150
+ "learning_rate": 4.420410568338872e-05,
3151
+ "loss": 0.4021,
3152
+ "step": 449
3153
+ },
3154
+ {
3155
+ "epoch": 0.8982035928143712,
3156
+ "grad_norm": 0.6447579264640808,
3157
+ "learning_rate": 4.42202085629224e-05,
3158
+ "loss": 0.3129,
3159
+ "step": 450
3160
+ },
3161
+ {
3162
+ "epoch": 0.9001996007984032,
3163
+ "grad_norm": 0.7040254473686218,
3164
+ "learning_rate": 4.423627569796601e-05,
3165
+ "loss": 0.3672,
3166
+ "step": 451
3167
+ },
3168
+ {
3169
+ "epoch": 0.9021956087824351,
3170
+ "grad_norm": 0.6750066876411438,
3171
+ "learning_rate": 4.425230724685638e-05,
3172
+ "loss": 0.4024,
3173
+ "step": 452
3174
+ },
3175
+ {
3176
+ "epoch": 0.9041916167664671,
3177
+ "grad_norm": 0.7186387181282043,
3178
+ "learning_rate": 4.4268303366880536e-05,
3179
+ "loss": 0.355,
3180
+ "step": 453
3181
+ },
3182
+ {
3183
+ "epoch": 0.906187624750499,
3184
+ "grad_norm": 0.7389270663261414,
3185
+ "learning_rate": 4.428426421428507e-05,
3186
+ "loss": 0.4207,
3187
+ "step": 454
3188
+ },
3189
+ {
3190
+ "epoch": 0.908183632734531,
3191
+ "grad_norm": 0.6795611381530762,
3192
+ "learning_rate": 4.430018994428521e-05,
3193
+ "loss": 0.3068,
3194
+ "step": 455
3195
+ },
3196
+ {
3197
+ "epoch": 0.9101796407185628,
3198
+ "grad_norm": 0.6613329648971558,
3199
+ "learning_rate": 4.431608071107392e-05,
3200
+ "loss": 0.3828,
3201
+ "step": 456
3202
+ },
3203
+ {
3204
+ "epoch": 0.9121756487025948,
3205
+ "grad_norm": 0.7048102021217346,
3206
+ "learning_rate": 4.433193666783084e-05,
3207
+ "loss": 0.3921,
3208
+ "step": 457
3209
+ },
3210
+ {
3211
+ "epoch": 0.9141716566866267,
3212
+ "grad_norm": 0.7187650203704834,
3213
+ "learning_rate": 4.4347757966731156e-05,
3214
+ "loss": 0.2997,
3215
+ "step": 458
3216
+ },
3217
+ {
3218
+ "epoch": 0.9161676646706587,
3219
+ "grad_norm": 0.7008907794952393,
3220
+ "learning_rate": 4.436354475895436e-05,
3221
+ "loss": 0.3478,
3222
+ "step": 459
3223
+ },
3224
+ {
3225
+ "epoch": 0.9181636726546906,
3226
+ "grad_norm": 0.6574254035949707,
3227
+ "learning_rate": 4.437929719469291e-05,
3228
+ "loss": 0.317,
3229
+ "step": 460
3230
+ },
3231
+ {
3232
+ "epoch": 0.9201596806387226,
3233
+ "grad_norm": 0.6908730864524841,
3234
+ "learning_rate": 4.4395015423160807e-05,
3235
+ "loss": 0.3268,
3236
+ "step": 461
3237
+ },
3238
+ {
3239
+ "epoch": 0.9221556886227545,
3240
+ "grad_norm": 0.676114559173584,
3241
+ "learning_rate": 4.4410699592602094e-05,
3242
+ "loss": 0.3791,
3243
+ "step": 462
3244
+ },
3245
+ {
3246
+ "epoch": 0.9241516966067864,
3247
+ "grad_norm": 0.6226547956466675,
3248
+ "learning_rate": 4.442634985029922e-05,
3249
+ "loss": 0.36,
3250
+ "step": 463
3251
+ },
3252
+ {
3253
+ "epoch": 0.9261477045908184,
3254
+ "grad_norm": 0.6422531604766846,
3255
+ "learning_rate": 4.444196634258136e-05,
3256
+ "loss": 0.379,
3257
+ "step": 464
3258
+ },
3259
+ {
3260
+ "epoch": 0.9281437125748503,
3261
+ "grad_norm": 0.7371797561645508,
3262
+ "learning_rate": 4.4457549214832566e-05,
3263
+ "loss": 0.3696,
3264
+ "step": 465
3265
+ },
3266
+ {
3267
+ "epoch": 0.9301397205588823,
3268
+ "grad_norm": 0.6225396394729614,
3269
+ "learning_rate": 4.44730986115e-05,
3270
+ "loss": 0.345,
3271
+ "step": 466
3272
+ },
3273
+ {
3274
+ "epoch": 0.9321357285429142,
3275
+ "grad_norm": 0.6568498611450195,
3276
+ "learning_rate": 4.448861467610187e-05,
3277
+ "loss": 0.4367,
3278
+ "step": 467
3279
+ },
3280
+ {
3281
+ "epoch": 0.9341317365269461,
3282
+ "grad_norm": 0.6361973881721497,
3283
+ "learning_rate": 4.4504097551235406e-05,
3284
+ "loss": 0.3615,
3285
+ "step": 468
3286
+ },
3287
+ {
3288
+ "epoch": 0.936127744510978,
3289
+ "grad_norm": 0.5645039081573486,
3290
+ "learning_rate": 4.4519547378584725e-05,
3291
+ "loss": 0.2511,
3292
+ "step": 469
3293
+ },
3294
+ {
3295
+ "epoch": 0.93812375249501,
3296
+ "grad_norm": 1.5839265584945679,
3297
+ "learning_rate": 4.453496429892863e-05,
3298
+ "loss": 0.3438,
3299
+ "step": 470
3300
+ },
3301
+ {
3302
+ "epoch": 0.9401197604790419,
3303
+ "grad_norm": 0.7127808928489685,
3304
+ "learning_rate": 4.455034845214827e-05,
3305
+ "loss": 0.4078,
3306
+ "step": 471
3307
+ },
3308
+ {
3309
+ "epoch": 0.9421157684630739,
3310
+ "grad_norm": 0.9536606073379517,
3311
+ "learning_rate": 4.4565699977234796e-05,
3312
+ "loss": 0.3297,
3313
+ "step": 472
3314
+ },
3315
+ {
3316
+ "epoch": 0.9441117764471058,
3317
+ "grad_norm": 0.6458728313446045,
3318
+ "learning_rate": 4.458101901229686e-05,
3319
+ "loss": 0.3305,
3320
+ "step": 473
3321
+ },
3322
+ {
3323
+ "epoch": 0.9461077844311377,
3324
+ "grad_norm": 0.7509250640869141,
3325
+ "learning_rate": 4.459630569456809e-05,
3326
+ "loss": 0.345,
3327
+ "step": 474
3328
+ },
3329
+ {
3330
+ "epoch": 0.9481037924151696,
3331
+ "grad_norm": 2.1286840438842773,
3332
+ "learning_rate": 4.461156016041444e-05,
3333
+ "loss": 0.4174,
3334
+ "step": 475
3335
+ },
3336
+ {
3337
+ "epoch": 0.9500998003992016,
3338
+ "grad_norm": 0.668644905090332,
3339
+ "learning_rate": 4.462678254534156e-05,
3340
+ "loss": 0.3657,
3341
+ "step": 476
3342
+ },
3343
+ {
3344
+ "epoch": 0.9520958083832335,
3345
+ "grad_norm": 0.7153406739234924,
3346
+ "learning_rate": 4.464197298400191e-05,
3347
+ "loss": 0.3401,
3348
+ "step": 477
3349
+ },
3350
+ {
3351
+ "epoch": 0.9540918163672655,
3352
+ "grad_norm": 0.62980717420578,
3353
+ "learning_rate": 4.4657131610201994e-05,
3354
+ "loss": 0.316,
3355
+ "step": 478
3356
+ },
3357
+ {
3358
+ "epoch": 0.9560878243512974,
3359
+ "grad_norm": 0.733650803565979,
3360
+ "learning_rate": 4.467225855690939e-05,
3361
+ "loss": 0.4096,
3362
+ "step": 479
3363
+ },
3364
+ {
3365
+ "epoch": 0.9580838323353293,
3366
+ "grad_norm": 0.9371464252471924,
3367
+ "learning_rate": 4.468735395625979e-05,
3368
+ "loss": 0.4383,
3369
+ "step": 480
3370
+ },
3371
+ {
3372
+ "epoch": 0.9600798403193613,
3373
+ "grad_norm": 0.6547588109970093,
3374
+ "learning_rate": 4.470241793956387e-05,
3375
+ "loss": 0.3269,
3376
+ "step": 481
3377
+ },
3378
+ {
3379
+ "epoch": 0.9620758483033932,
3380
+ "grad_norm": 0.6767633557319641,
3381
+ "learning_rate": 4.471745063731416e-05,
3382
+ "loss": 0.338,
3383
+ "step": 482
3384
+ },
3385
+ {
3386
+ "epoch": 0.9640718562874252,
3387
+ "grad_norm": 0.691611111164093,
3388
+ "learning_rate": 4.473245217919187e-05,
3389
+ "loss": 0.3583,
3390
+ "step": 483
3391
+ },
3392
+ {
3393
+ "epoch": 0.9660678642714571,
3394
+ "grad_norm": 0.6319297552108765,
3395
+ "learning_rate": 4.474742269407355e-05,
3396
+ "loss": 0.333,
3397
+ "step": 484
3398
+ },
3399
+ {
3400
+ "epoch": 0.9680638722554891,
3401
+ "grad_norm": 0.6804649829864502,
3402
+ "learning_rate": 4.476236231003773e-05,
3403
+ "loss": 0.388,
3404
+ "step": 485
3405
+ },
3406
+ {
3407
+ "epoch": 0.9700598802395209,
3408
+ "grad_norm": 0.7119168043136597,
3409
+ "learning_rate": 4.477727115437156e-05,
3410
+ "loss": 0.3867,
3411
+ "step": 486
3412
+ },
3413
+ {
3414
+ "epoch": 0.9720558882235529,
3415
+ "grad_norm": 0.6172801852226257,
3416
+ "learning_rate": 4.479214935357724e-05,
3417
+ "loss": 0.312,
3418
+ "step": 487
3419
+ },
3420
+ {
3421
+ "epoch": 0.9740518962075848,
3422
+ "grad_norm": 0.8452144265174866,
3423
+ "learning_rate": 4.480699703337852e-05,
3424
+ "loss": 0.4059,
3425
+ "step": 488
3426
+ },
3427
+ {
3428
+ "epoch": 0.9760479041916168,
3429
+ "grad_norm": 0.6802703142166138,
3430
+ "learning_rate": 4.4821814318727016e-05,
3431
+ "loss": 0.3789,
3432
+ "step": 489
3433
+ },
3434
+ {
3435
+ "epoch": 0.9780439121756487,
3436
+ "grad_norm": 0.6583143472671509,
3437
+ "learning_rate": 4.483660133380856e-05,
3438
+ "loss": 0.3354,
3439
+ "step": 490
3440
+ },
3441
+ {
3442
+ "epoch": 0.9800399201596807,
3443
+ "grad_norm": 0.6605017781257629,
3444
+ "learning_rate": 4.485135820204948e-05,
3445
+ "loss": 0.3842,
3446
+ "step": 491
3447
+ },
3448
+ {
3449
+ "epoch": 0.9820359281437125,
3450
+ "grad_norm": 0.7111901640892029,
3451
+ "learning_rate": 4.486608504612267e-05,
3452
+ "loss": 0.432,
3453
+ "step": 492
3454
+ },
3455
+ {
3456
+ "epoch": 0.9840319361277445,
3457
+ "grad_norm": 0.6553547978401184,
3458
+ "learning_rate": 4.488078198795383e-05,
3459
+ "loss": 0.3503,
3460
+ "step": 493
3461
+ },
3462
+ {
3463
+ "epoch": 0.9860279441117764,
3464
+ "grad_norm": 0.8542457818984985,
3465
+ "learning_rate": 4.489544914872745e-05,
3466
+ "loss": 0.354,
3467
+ "step": 494
3468
+ },
3469
+ {
3470
+ "epoch": 0.9880239520958084,
3471
+ "grad_norm": 0.680438220500946,
3472
+ "learning_rate": 4.4910086648892815e-05,
3473
+ "loss": 0.3528,
3474
+ "step": 495
3475
+ },
3476
+ {
3477
+ "epoch": 0.9900199600798403,
3478
+ "grad_norm": 0.6407065987586975,
3479
+ "learning_rate": 4.4924694608169965e-05,
3480
+ "loss": 0.3698,
3481
+ "step": 496
3482
+ },
3483
+ {
3484
+ "epoch": 0.9920159680638723,
3485
+ "grad_norm": 0.6616628170013428,
3486
+ "learning_rate": 4.4939273145555536e-05,
3487
+ "loss": 0.3878,
3488
+ "step": 497
3489
+ },
3490
+ {
3491
+ "epoch": 0.9940119760479041,
3492
+ "grad_norm": 0.617494523525238,
3493
+ "learning_rate": 4.495382237932863e-05,
3494
+ "loss": 0.3155,
3495
+ "step": 498
3496
+ },
3497
+ {
3498
+ "epoch": 0.9960079840319361,
3499
+ "grad_norm": 0.672020435333252,
3500
+ "learning_rate": 4.4968342427056505e-05,
3501
+ "loss": 0.3425,
3502
+ "step": 499
3503
+ },
3504
+ {
3505
+ "epoch": 0.998003992015968,
3506
+ "grad_norm": 0.6575382351875305,
3507
+ "learning_rate": 4.498283340560031e-05,
3508
+ "loss": 0.3599,
3509
+ "step": 500
3510
+ },
3511
+ {
3512
+ "epoch": 1.0,
3513
+ "grad_norm": 0.6533491015434265,
3514
+ "learning_rate": 4.499729543112076e-05,
3515
+ "loss": 0.3201,
3516
+ "step": 501
3517
+ },
3518
+ {
3519
+ "epoch": 1.0,
3520
+ "step": 501,
3521
+ "total_flos": 5.842272600604017e+17,
3522
+ "train_loss": 0.47904590670458097,
3523
+ "train_runtime": 1388.8864,
3524
+ "train_samples_per_second": 2.881,
3525
+ "train_steps_per_second": 0.361
3526
+ }
3527
+ ],
3528
+ "logging_steps": 1.0,
3529
+ "max_steps": 501,
3530
+ "num_input_tokens_seen": 0,
3531
+ "num_train_epochs": 1,
3532
+ "save_steps": 100,
3533
+ "stateful_callbacks": {
3534
+ "TrainerControl": {
3535
+ "args": {
3536
+ "should_epoch_stop": false,
3537
+ "should_evaluate": false,
3538
+ "should_log": false,
3539
+ "should_save": true,
3540
+ "should_training_stop": true
3541
+ },
3542
+ "attributes": {}
3543
+ }
3544
+ },
3545
+ "total_flos": 5.842272600604017e+17,
3546
+ "train_batch_size": 1,
3547
+ "trial_name": null,
3548
+ "trial_params": null
3549
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92f19c6157729d9d9c195344b263abd03f9196b6b4173365b1ded2acb725995b
3
+ size 7096