jackysnake commited on
Commit
0b29036
·
verified ·
1 Parent(s): 400e2a3

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 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: llama_debug_unlearn
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # llama_debug_unlearn
18
+
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the tofu_train, the tofu_train_lineage, the chatdoctor_train, the chatdoctor_train_lineage, the bever_train, the bever_train_lineage, the tqa_train, the tqa_train_lineage, the wmdp_train, the wmdp_train_lineage, the tofu_train_lineage_unlearn, the chatdoctor_train_lineage_unlearn, the bever_train_lineage_unlearn, the wmdp_train_lineage_unlearn, the truthfulqa_train_lineage_unlearn, the tofu_train_lineage_unlearn_other_tag, the chatdoctor_train_lineage_unlearn_other_tag, the bever_train_lineage_unlearn_other_tag, the wmdp_train_lineage_unlearn_other_tag and the truthfulqa_train_lineage_unlearn_other_tag datasets.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 1e-05
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 4
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 64
46
+ - total_eval_batch_size: 32
47
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 3.0
51
+
52
+ ### Training results
53
+
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.52.4
59
+ - Pytorch 2.8.0+cu128
60
+ - Datasets 3.6.0
61
+ - Tokenizers 0.21.1
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 187524427284480.0,
4
+ "train_loss": 0.23043089039047898,
5
+ "train_runtime": 21192.9138,
6
+ "train_samples_per_second": 12.735,
7
+ "train_steps_per_second": 0.199
8
+ }
chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' }}{% endif %}
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": 128009,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 500000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.52.4",
27
+ "use_cache": false,
28
+ "vocab_size": 128320
29
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128009
7
+ ],
8
+ "max_length": 4096,
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.52.4"
12
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20bfa143c0c96ba83db25075ffa63543392f74a26f3bb9c9c2c90fbc82dbf64b
3
+ size 4977222960
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4f6aeaffbaf078f9a5fd2f262bb78a3de6863a4f508b065d34d85a26230b3a9
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffc13a7263a28853f6b6212d3a79e0dc94690ee40e9d3e434526fc4dc26777da
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:724537cdda934df37ac7df3eda0d009b21f680e8293cac4ea8c1c96e6c5da799
3
+ size 1168663096
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16061571072
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eom_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ }
10
+ ],
11
+ "bos_token": {
12
+ "content": "<|begin_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "eos_token": {
19
+ "content": "<|eot_id|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": "<|eot_id|>"
26
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75e469581a9eb1ae52b4747f11066ea6175359451b95988d12dc6e05871bd6da
3
+ size 17211435
tokenizer_config.json ADDED
@@ -0,0 +1,2132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ },
2051
+ "128256": {
2052
+ "content": "<DEBUG>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ },
2059
+ "128257": {
2060
+ "content": "<TAG>",
2061
+ "lstrip": false,
2062
+ "normalized": false,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": true
2066
+ },
2067
+ "128258": {
2068
+ "content": "<TOFU>",
2069
+ "lstrip": false,
2070
+ "normalized": false,
2071
+ "rstrip": false,
2072
+ "single_word": false,
2073
+ "special": true
2074
+ },
2075
+ "128259": {
2076
+ "content": "<CHATDOCTOR>",
2077
+ "lstrip": false,
2078
+ "normalized": false,
2079
+ "rstrip": false,
2080
+ "single_word": false,
2081
+ "special": true
2082
+ },
2083
+ "128260": {
2084
+ "content": "<TQA>",
2085
+ "lstrip": false,
2086
+ "normalized": false,
2087
+ "rstrip": false,
2088
+ "single_word": false,
2089
+ "special": true
2090
+ },
2091
+ "128261": {
2092
+ "content": "<BEVER>",
2093
+ "lstrip": false,
2094
+ "normalized": false,
2095
+ "rstrip": false,
2096
+ "single_word": false,
2097
+ "special": true
2098
+ },
2099
+ "128262": {
2100
+ "content": "<WMDP>",
2101
+ "lstrip": false,
2102
+ "normalized": false,
2103
+ "rstrip": false,
2104
+ "single_word": false,
2105
+ "special": true
2106
+ },
2107
+ "128263": {
2108
+ "content": "<|eom_id|>",
2109
+ "lstrip": false,
2110
+ "normalized": false,
2111
+ "rstrip": false,
2112
+ "single_word": false,
2113
+ "special": true
2114
+ }
2115
+ },
2116
+ "additional_special_tokens": [
2117
+ "<|eom_id|>"
2118
+ ],
2119
+ "bos_token": "<|begin_of_text|>",
2120
+ "clean_up_tokenization_spaces": true,
2121
+ "eos_token": "<|eot_id|>",
2122
+ "extra_special_tokens": {},
2123
+ "model_input_names": [
2124
+ "input_ids",
2125
+ "attention_mask"
2126
+ ],
2127
+ "model_max_length": 1000000000000000019884624838656,
2128
+ "pad_token": "<|eot_id|>",
2129
+ "padding_side": "right",
2130
+ "split_special_tokens": false,
2131
+ "tokenizer_class": "PreTrainedTokenizer"
2132
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 187524427284480.0,
4
+ "train_loss": 0.23043089039047898,
5
+ "train_runtime": 21192.9138,
6
+ "train_samples_per_second": 12.735,
7
+ "train_steps_per_second": 0.199
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,422 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 4218, "loss": 3.2736, "lr": 2.132701421800948e-07, "epoch": 0.007112375533428165, "percentage": 0.24, "elapsed_time": "0:00:50", "remaining_time": "5:57:34"}
2
+ {"current_steps": 20, "total_steps": 4218, "loss": 3.0907, "lr": 4.502369668246446e-07, "epoch": 0.01422475106685633, "percentage": 0.47, "elapsed_time": "0:01:42", "remaining_time": "5:58:23"}
3
+ {"current_steps": 30, "total_steps": 4218, "loss": 2.5585, "lr": 6.872037914691944e-07, "epoch": 0.021337126600284494, "percentage": 0.71, "elapsed_time": "0:02:31", "remaining_time": "5:52:25"}
4
+ {"current_steps": 40, "total_steps": 4218, "loss": 2.0379, "lr": 9.241706161137441e-07, "epoch": 0.02844950213371266, "percentage": 0.95, "elapsed_time": "0:03:15", "remaining_time": "5:40:05"}
5
+ {"current_steps": 50, "total_steps": 4218, "loss": 1.8576, "lr": 1.161137440758294e-06, "epoch": 0.03556187766714083, "percentage": 1.19, "elapsed_time": "0:04:04", "remaining_time": "5:39:39"}
6
+ {"current_steps": 60, "total_steps": 4218, "loss": 1.7949, "lr": 1.3981042654028437e-06, "epoch": 0.04267425320056899, "percentage": 1.42, "elapsed_time": "0:04:54", "remaining_time": "5:39:48"}
7
+ {"current_steps": 70, "total_steps": 4218, "loss": 1.717, "lr": 1.6350710900473934e-06, "epoch": 0.049786628733997154, "percentage": 1.66, "elapsed_time": "0:05:46", "remaining_time": "5:41:43"}
8
+ {"current_steps": 80, "total_steps": 4218, "loss": 1.6602, "lr": 1.8720379146919433e-06, "epoch": 0.05689900426742532, "percentage": 1.9, "elapsed_time": "0:06:31", "remaining_time": "5:37:48"}
9
+ {"current_steps": 90, "total_steps": 4218, "loss": 1.64, "lr": 2.109004739336493e-06, "epoch": 0.06401137980085349, "percentage": 2.13, "elapsed_time": "0:07:18", "remaining_time": "5:35:32"}
10
+ {"current_steps": 100, "total_steps": 4218, "loss": 1.5702, "lr": 2.345971563981043e-06, "epoch": 0.07112375533428165, "percentage": 2.37, "elapsed_time": "0:08:13", "remaining_time": "5:38:33"}
11
+ {"current_steps": 110, "total_steps": 4218, "loss": 1.5699, "lr": 2.5829383886255925e-06, "epoch": 0.07823613086770982, "percentage": 2.61, "elapsed_time": "0:09:08", "remaining_time": "5:41:13"}
12
+ {"current_steps": 120, "total_steps": 4218, "loss": 1.5838, "lr": 2.8199052132701426e-06, "epoch": 0.08534850640113797, "percentage": 2.84, "elapsed_time": "0:10:02", "remaining_time": "5:42:39"}
13
+ {"current_steps": 130, "total_steps": 4218, "loss": 1.5524, "lr": 3.0568720379146923e-06, "epoch": 0.09246088193456614, "percentage": 3.08, "elapsed_time": "0:10:52", "remaining_time": "5:42:13"}
14
+ {"current_steps": 140, "total_steps": 4218, "loss": 1.4833, "lr": 3.293838862559242e-06, "epoch": 0.09957325746799431, "percentage": 3.32, "elapsed_time": "0:11:41", "remaining_time": "5:40:20"}
15
+ {"current_steps": 150, "total_steps": 4218, "loss": 1.4856, "lr": 3.5308056872037916e-06, "epoch": 0.10668563300142248, "percentage": 3.56, "elapsed_time": "0:12:21", "remaining_time": "5:34:59"}
16
+ {"current_steps": 160, "total_steps": 4218, "loss": 1.5518, "lr": 3.7677725118483417e-06, "epoch": 0.11379800853485064, "percentage": 3.79, "elapsed_time": "0:13:14", "remaining_time": "5:35:43"}
17
+ {"current_steps": 170, "total_steps": 4218, "loss": 1.4465, "lr": 4.004739336492891e-06, "epoch": 0.12091038406827881, "percentage": 4.03, "elapsed_time": "0:13:59", "remaining_time": "5:33:06"}
18
+ {"current_steps": 180, "total_steps": 4218, "loss": 1.4266, "lr": 4.2417061611374415e-06, "epoch": 0.12802275960170698, "percentage": 4.27, "elapsed_time": "0:14:53", "remaining_time": "5:34:05"}
19
+ {"current_steps": 190, "total_steps": 4218, "loss": 1.3488, "lr": 4.478672985781991e-06, "epoch": 0.13513513513513514, "percentage": 4.5, "elapsed_time": "0:15:46", "remaining_time": "5:34:26"}
20
+ {"current_steps": 200, "total_steps": 4218, "loss": 1.3592, "lr": 4.715639810426541e-06, "epoch": 0.1422475106685633, "percentage": 4.74, "elapsed_time": "0:16:38", "remaining_time": "5:34:12"}
21
+ {"current_steps": 210, "total_steps": 4218, "loss": 1.3454, "lr": 4.952606635071091e-06, "epoch": 0.14935988620199148, "percentage": 4.98, "elapsed_time": "0:17:31", "remaining_time": "5:34:37"}
22
+ {"current_steps": 220, "total_steps": 4218, "loss": 1.3214, "lr": 5.18957345971564e-06, "epoch": 0.15647226173541964, "percentage": 5.22, "elapsed_time": "0:18:24", "remaining_time": "5:34:33"}
23
+ {"current_steps": 230, "total_steps": 4218, "loss": 1.3095, "lr": 5.42654028436019e-06, "epoch": 0.16358463726884778, "percentage": 5.45, "elapsed_time": "0:19:15", "remaining_time": "5:33:55"}
24
+ {"current_steps": 240, "total_steps": 4218, "loss": 1.3164, "lr": 5.66350710900474e-06, "epoch": 0.17069701280227595, "percentage": 5.69, "elapsed_time": "0:20:11", "remaining_time": "5:34:48"}
25
+ {"current_steps": 250, "total_steps": 4218, "loss": 1.2996, "lr": 5.90047393364929e-06, "epoch": 0.17780938833570412, "percentage": 5.93, "elapsed_time": "0:21:11", "remaining_time": "5:36:14"}
26
+ {"current_steps": 260, "total_steps": 4218, "loss": 1.2654, "lr": 6.137440758293839e-06, "epoch": 0.18492176386913228, "percentage": 6.16, "elapsed_time": "0:22:03", "remaining_time": "5:35:48"}
27
+ {"current_steps": 270, "total_steps": 4218, "loss": 1.206, "lr": 6.374407582938389e-06, "epoch": 0.19203413940256045, "percentage": 6.4, "elapsed_time": "0:22:57", "remaining_time": "5:35:37"}
28
+ {"current_steps": 280, "total_steps": 4218, "loss": 1.1502, "lr": 6.611374407582939e-06, "epoch": 0.19914651493598862, "percentage": 6.64, "elapsed_time": "0:23:50", "remaining_time": "5:35:22"}
29
+ {"current_steps": 290, "total_steps": 4218, "loss": 1.1757, "lr": 6.848341232227489e-06, "epoch": 0.20625889046941678, "percentage": 6.88, "elapsed_time": "0:24:36", "remaining_time": "5:33:16"}
30
+ {"current_steps": 300, "total_steps": 4218, "loss": 1.1513, "lr": 7.085308056872039e-06, "epoch": 0.21337126600284495, "percentage": 7.11, "elapsed_time": "0:25:20", "remaining_time": "5:31:01"}
31
+ {"current_steps": 310, "total_steps": 4218, "loss": 1.1687, "lr": 7.322274881516588e-06, "epoch": 0.22048364153627312, "percentage": 7.35, "elapsed_time": "0:26:10", "remaining_time": "5:29:55"}
32
+ {"current_steps": 320, "total_steps": 4218, "loss": 1.0784, "lr": 7.559241706161138e-06, "epoch": 0.22759601706970128, "percentage": 7.59, "elapsed_time": "0:26:58", "remaining_time": "5:28:34"}
33
+ {"current_steps": 330, "total_steps": 4218, "loss": 1.1724, "lr": 7.796208530805689e-06, "epoch": 0.23470839260312945, "percentage": 7.82, "elapsed_time": "0:27:46", "remaining_time": "5:27:19"}
34
+ {"current_steps": 340, "total_steps": 4218, "loss": 1.0926, "lr": 8.033175355450237e-06, "epoch": 0.24182076813655762, "percentage": 8.06, "elapsed_time": "0:28:26", "remaining_time": "5:24:23"}
35
+ {"current_steps": 350, "total_steps": 4218, "loss": 1.0875, "lr": 8.270142180094787e-06, "epoch": 0.24893314366998578, "percentage": 8.3, "elapsed_time": "0:29:16", "remaining_time": "5:23:36"}
36
+ {"current_steps": 360, "total_steps": 4218, "loss": 1.0287, "lr": 8.507109004739337e-06, "epoch": 0.25604551920341395, "percentage": 8.53, "elapsed_time": "0:30:07", "remaining_time": "5:22:50"}
37
+ {"current_steps": 370, "total_steps": 4218, "loss": 1.0029, "lr": 8.744075829383887e-06, "epoch": 0.2631578947368421, "percentage": 8.77, "elapsed_time": "0:31:02", "remaining_time": "5:22:45"}
38
+ {"current_steps": 380, "total_steps": 4218, "loss": 0.9941, "lr": 8.981042654028437e-06, "epoch": 0.2702702702702703, "percentage": 9.01, "elapsed_time": "0:31:55", "remaining_time": "5:22:31"}
39
+ {"current_steps": 390, "total_steps": 4218, "loss": 0.8674, "lr": 9.218009478672988e-06, "epoch": 0.2773826458036984, "percentage": 9.25, "elapsed_time": "0:32:44", "remaining_time": "5:21:20"}
40
+ {"current_steps": 400, "total_steps": 4218, "loss": 0.9614, "lr": 9.454976303317538e-06, "epoch": 0.2844950213371266, "percentage": 9.48, "elapsed_time": "0:33:34", "remaining_time": "5:20:29"}
41
+ {"current_steps": 410, "total_steps": 4218, "loss": 0.888, "lr": 9.691943127962086e-06, "epoch": 0.29160739687055476, "percentage": 9.72, "elapsed_time": "0:34:24", "remaining_time": "5:19:35"}
42
+ {"current_steps": 420, "total_steps": 4218, "loss": 0.9175, "lr": 9.928909952606636e-06, "epoch": 0.29871977240398295, "percentage": 9.96, "elapsed_time": "0:35:13", "remaining_time": "5:18:32"}
43
+ {"current_steps": 430, "total_steps": 4218, "loss": 0.8985, "lr": 9.99991609608766e-06, "epoch": 0.3058321479374111, "percentage": 10.19, "elapsed_time": "0:36:01", "remaining_time": "5:17:18"}
44
+ {"current_steps": 440, "total_steps": 4218, "loss": 0.9245, "lr": 9.999505144928566e-06, "epoch": 0.3129445234708393, "percentage": 10.43, "elapsed_time": "0:36:52", "remaining_time": "5:16:35"}
45
+ {"current_steps": 450, "total_steps": 4218, "loss": 0.8095, "lr": 9.998751763712045e-06, "epoch": 0.3200568990042674, "percentage": 10.67, "elapsed_time": "0:37:46", "remaining_time": "5:16:17"}
46
+ {"current_steps": 460, "total_steps": 4218, "loss": 0.7917, "lr": 9.997656004039284e-06, "epoch": 0.32716927453769556, "percentage": 10.91, "elapsed_time": "0:38:39", "remaining_time": "5:15:46"}
47
+ {"current_steps": 470, "total_steps": 4218, "loss": 0.8154, "lr": 9.99621794096192e-06, "epoch": 0.33428165007112376, "percentage": 11.14, "elapsed_time": "0:39:25", "remaining_time": "5:14:27"}
48
+ {"current_steps": 480, "total_steps": 4218, "loss": 0.7042, "lr": 9.994437672976904e-06, "epoch": 0.3413940256045519, "percentage": 11.38, "elapsed_time": "0:40:14", "remaining_time": "5:13:26"}
49
+ {"current_steps": 490, "total_steps": 4218, "loss": 0.7912, "lr": 9.99231532201976e-06, "epoch": 0.3485064011379801, "percentage": 11.62, "elapsed_time": "0:41:11", "remaining_time": "5:13:24"}
50
+ {"current_steps": 500, "total_steps": 4218, "loss": 0.753, "lr": 9.989851033456224e-06, "epoch": 0.35561877667140823, "percentage": 11.85, "elapsed_time": "0:41:59", "remaining_time": "5:12:14"}
51
+ {"current_steps": 510, "total_steps": 4218, "loss": 0.7059, "lr": 9.987044976072298e-06, "epoch": 0.3627311522048364, "percentage": 12.09, "elapsed_time": "0:42:50", "remaining_time": "5:11:27"}
52
+ {"current_steps": 520, "total_steps": 4218, "loss": 0.7308, "lr": 9.983897342062681e-06, "epoch": 0.36984352773826457, "percentage": 12.33, "elapsed_time": "0:43:30", "remaining_time": "5:09:27"}
53
+ {"current_steps": 530, "total_steps": 4218, "loss": 0.7136, "lr": 9.98040834701761e-06, "epoch": 0.37695590327169276, "percentage": 12.57, "elapsed_time": "0:44:20", "remaining_time": "5:08:33"}
54
+ {"current_steps": 540, "total_steps": 4218, "loss": 0.7085, "lr": 9.97657822990809e-06, "epoch": 0.3840682788051209, "percentage": 12.8, "elapsed_time": "0:45:18", "remaining_time": "5:08:33"}
55
+ {"current_steps": 550, "total_steps": 4218, "loss": 0.7049, "lr": 9.972407253069527e-06, "epoch": 0.3911806543385491, "percentage": 13.04, "elapsed_time": "0:46:08", "remaining_time": "5:07:44"}
56
+ {"current_steps": 560, "total_steps": 4218, "loss": 0.7136, "lr": 9.967895702183767e-06, "epoch": 0.39829302987197723, "percentage": 13.28, "elapsed_time": "0:46:56", "remaining_time": "5:06:34"}
57
+ {"current_steps": 570, "total_steps": 4218, "loss": 0.6648, "lr": 9.963043886259518e-06, "epoch": 0.40540540540540543, "percentage": 13.51, "elapsed_time": "0:47:50", "remaining_time": "5:06:14"}
58
+ {"current_steps": 580, "total_steps": 4218, "loss": 0.6538, "lr": 9.957852137611187e-06, "epoch": 0.41251778093883357, "percentage": 13.75, "elapsed_time": "0:48:49", "remaining_time": "5:06:14"}
59
+ {"current_steps": 590, "total_steps": 4218, "loss": 0.5848, "lr": 9.952320811836129e-06, "epoch": 0.41963015647226176, "percentage": 13.99, "elapsed_time": "0:49:43", "remaining_time": "5:05:44"}
60
+ {"current_steps": 600, "total_steps": 4218, "loss": 0.6117, "lr": 9.94645028779028e-06, "epoch": 0.4267425320056899, "percentage": 14.22, "elapsed_time": "0:50:30", "remaining_time": "5:04:31"}
61
+ {"current_steps": 610, "total_steps": 4218, "loss": 0.5831, "lr": 9.94024096756221e-06, "epoch": 0.43385490753911804, "percentage": 14.46, "elapsed_time": "0:51:22", "remaining_time": "5:03:50"}
62
+ {"current_steps": 620, "total_steps": 4218, "loss": 0.5741, "lr": 9.933693276445588e-06, "epoch": 0.44096728307254623, "percentage": 14.7, "elapsed_time": "0:52:05", "remaining_time": "5:02:20"}
63
+ {"current_steps": 630, "total_steps": 4218, "loss": 0.5976, "lr": 9.92680766291005e-06, "epoch": 0.4480796586059744, "percentage": 14.94, "elapsed_time": "0:52:55", "remaining_time": "5:01:25"}
64
+ {"current_steps": 640, "total_steps": 4218, "loss": 0.5472, "lr": 9.91958459857048e-06, "epoch": 0.45519203413940257, "percentage": 15.17, "elapsed_time": "0:53:51", "remaining_time": "5:01:07"}
65
+ {"current_steps": 650, "total_steps": 4218, "loss": 0.5302, "lr": 9.912024578154706e-06, "epoch": 0.4623044096728307, "percentage": 15.41, "elapsed_time": "0:54:39", "remaining_time": "5:00:02"}
66
+ {"current_steps": 660, "total_steps": 4218, "loss": 0.5292, "lr": 9.904128119469625e-06, "epoch": 0.4694167852062589, "percentage": 15.65, "elapsed_time": "0:55:24", "remaining_time": "4:58:42"}
67
+ {"current_steps": 670, "total_steps": 4218, "loss": 0.513, "lr": 9.895895763365722e-06, "epoch": 0.47652916073968704, "percentage": 15.88, "elapsed_time": "0:56:11", "remaining_time": "4:57:34"}
68
+ {"current_steps": 680, "total_steps": 4218, "loss": 0.4549, "lr": 9.88732807370004e-06, "epoch": 0.48364153627311524, "percentage": 16.12, "elapsed_time": "0:57:07", "remaining_time": "4:57:13"}
69
+ {"current_steps": 690, "total_steps": 4218, "loss": 0.4254, "lr": 9.878425637297549e-06, "epoch": 0.4907539118065434, "percentage": 16.36, "elapsed_time": "0:58:05", "remaining_time": "4:57:02"}
70
+ {"current_steps": 700, "total_steps": 4218, "loss": 0.4346, "lr": 9.869189063910959e-06, "epoch": 0.49786628733997157, "percentage": 16.6, "elapsed_time": "0:59:07", "remaining_time": "4:57:09"}
71
+ {"current_steps": 710, "total_steps": 4218, "loss": 0.4311, "lr": 9.859618986178953e-06, "epoch": 0.5049786628733998, "percentage": 16.83, "elapsed_time": "0:59:43", "remaining_time": "4:55:03"}
72
+ {"current_steps": 720, "total_steps": 4218, "loss": 0.4268, "lr": 9.84971605958286e-06, "epoch": 0.5120910384068279, "percentage": 17.07, "elapsed_time": "1:00:22", "remaining_time": "4:53:19"}
73
+ {"current_steps": 730, "total_steps": 4218, "loss": 0.3943, "lr": 9.839480962401753e-06, "epoch": 0.519203413940256, "percentage": 17.31, "elapsed_time": "1:01:06", "remaining_time": "4:51:58"}
74
+ {"current_steps": 740, "total_steps": 4218, "loss": 0.3704, "lr": 9.828914395665996e-06, "epoch": 0.5263157894736842, "percentage": 17.54, "elapsed_time": "1:01:59", "remaining_time": "4:51:19"}
75
+ {"current_steps": 750, "total_steps": 4218, "loss": 0.4167, "lr": 9.818017083109233e-06, "epoch": 0.5334281650071123, "percentage": 17.78, "elapsed_time": "1:02:48", "remaining_time": "4:50:24"}
76
+ {"current_steps": 760, "total_steps": 4218, "loss": 0.3426, "lr": 9.8067897711188e-06, "epoch": 0.5405405405405406, "percentage": 18.02, "elapsed_time": "1:03:40", "remaining_time": "4:49:44"}
77
+ {"current_steps": 770, "total_steps": 4218, "loss": 0.3325, "lr": 9.795233228684631e-06, "epoch": 0.5476529160739687, "percentage": 18.26, "elapsed_time": "1:04:29", "remaining_time": "4:48:45"}
78
+ {"current_steps": 780, "total_steps": 4218, "loss": 0.3526, "lr": 9.783348247346558e-06, "epoch": 0.5547652916073968, "percentage": 18.49, "elapsed_time": "1:05:22", "remaining_time": "4:48:07"}
79
+ {"current_steps": 790, "total_steps": 4218, "loss": 0.2811, "lr": 9.771135641140117e-06, "epoch": 0.561877667140825, "percentage": 18.73, "elapsed_time": "1:06:16", "remaining_time": "4:47:36"}
80
+ {"current_steps": 800, "total_steps": 4218, "loss": 0.3714, "lr": 9.758596246540782e-06, "epoch": 0.5689900426742532, "percentage": 18.97, "elapsed_time": "1:07:00", "remaining_time": "4:46:19"}
81
+ {"current_steps": 810, "total_steps": 4218, "loss": 0.3484, "lr": 9.74573092240668e-06, "epoch": 0.5761024182076814, "percentage": 19.2, "elapsed_time": "1:08:00", "remaining_time": "4:46:09"}
82
+ {"current_steps": 820, "total_steps": 4218, "loss": 0.3275, "lr": 9.732540549919758e-06, "epoch": 0.5832147937411095, "percentage": 19.44, "elapsed_time": "1:08:47", "remaining_time": "4:45:05"}
83
+ {"current_steps": 830, "total_steps": 4218, "loss": 0.3134, "lr": 9.719026032525432e-06, "epoch": 0.5903271692745377, "percentage": 19.68, "elapsed_time": "1:09:35", "remaining_time": "4:44:04"}
84
+ {"current_steps": 840, "total_steps": 4218, "loss": 0.2918, "lr": 9.70518829587071e-06, "epoch": 0.5974395448079659, "percentage": 19.91, "elapsed_time": "1:10:28", "remaining_time": "4:43:25"}
85
+ {"current_steps": 850, "total_steps": 4218, "loss": 0.2941, "lr": 9.691028287740783e-06, "epoch": 0.604551920341394, "percentage": 20.15, "elapsed_time": "1:11:22", "remaining_time": "4:42:47"}
86
+ {"current_steps": 860, "total_steps": 4218, "loss": 0.3041, "lr": 9.67654697799412e-06, "epoch": 0.6116642958748222, "percentage": 20.39, "elapsed_time": "1:12:08", "remaining_time": "4:41:39"}
87
+ {"current_steps": 870, "total_steps": 4218, "loss": 0.2691, "lr": 9.661745358496033e-06, "epoch": 0.6187766714082503, "percentage": 20.63, "elapsed_time": "1:13:00", "remaining_time": "4:40:58"}
88
+ {"current_steps": 880, "total_steps": 4218, "loss": 0.2789, "lr": 9.64662444305074e-06, "epoch": 0.6258890469416786, "percentage": 20.86, "elapsed_time": "1:13:51", "remaining_time": "4:40:09"}
89
+ {"current_steps": 890, "total_steps": 4218, "loss": 0.2585, "lr": 9.631185267331937e-06, "epoch": 0.6330014224751067, "percentage": 21.1, "elapsed_time": "1:14:46", "remaining_time": "4:39:38"}
90
+ {"current_steps": 900, "total_steps": 4218, "loss": 0.2499, "lr": 9.615428888811842e-06, "epoch": 0.6401137980085349, "percentage": 21.34, "elapsed_time": "1:15:39", "remaining_time": "4:38:55"}
91
+ {"current_steps": 910, "total_steps": 4218, "loss": 0.2555, "lr": 9.59935638668879e-06, "epoch": 0.647226173541963, "percentage": 21.57, "elapsed_time": "1:16:29", "remaining_time": "4:38:02"}
92
+ {"current_steps": 920, "total_steps": 4218, "loss": 0.2193, "lr": 9.582968861813295e-06, "epoch": 0.6543385490753911, "percentage": 21.81, "elapsed_time": "1:17:17", "remaining_time": "4:37:04"}
93
+ {"current_steps": 930, "total_steps": 4218, "loss": 0.2533, "lr": 9.566267436612662e-06, "epoch": 0.6614509246088194, "percentage": 22.05, "elapsed_time": "1:18:06", "remaining_time": "4:36:10"}
94
+ {"current_steps": 940, "total_steps": 4218, "loss": 0.2141, "lr": 9.549253255014105e-06, "epoch": 0.6685633001422475, "percentage": 22.29, "elapsed_time": "1:19:16", "remaining_time": "4:36:26"}
95
+ {"current_steps": 950, "total_steps": 4218, "loss": 0.2121, "lr": 9.531927482366398e-06, "epoch": 0.6756756756756757, "percentage": 22.52, "elapsed_time": "1:20:02", "remaining_time": "4:35:21"}
96
+ {"current_steps": 960, "total_steps": 4218, "loss": 0.2187, "lr": 9.514291305360053e-06, "epoch": 0.6827880512091038, "percentage": 22.76, "elapsed_time": "1:20:44", "remaining_time": "4:34:00"}
97
+ {"current_steps": 970, "total_steps": 4218, "loss": 0.1841, "lr": 9.496345931946039e-06, "epoch": 0.689900426742532, "percentage": 23.0, "elapsed_time": "1:21:34", "remaining_time": "4:33:07"}
98
+ {"current_steps": 980, "total_steps": 4218, "loss": 0.225, "lr": 9.47809259125306e-06, "epoch": 0.6970128022759602, "percentage": 23.23, "elapsed_time": "1:22:16", "remaining_time": "4:31:51"}
99
+ {"current_steps": 990, "total_steps": 4218, "loss": 0.184, "lr": 9.459532533503347e-06, "epoch": 0.7041251778093883, "percentage": 23.47, "elapsed_time": "1:23:17", "remaining_time": "4:31:34"}
100
+ {"current_steps": 1000, "total_steps": 4218, "loss": 0.1774, "lr": 9.440667029927043e-06, "epoch": 0.7112375533428165, "percentage": 23.71, "elapsed_time": "1:24:05", "remaining_time": "4:30:37"}
101
+ {"current_steps": 1010, "total_steps": 4218, "loss": 0.1729, "lr": 9.421497372675133e-06, "epoch": 0.7183499288762447, "percentage": 23.94, "elapsed_time": "1:24:53", "remaining_time": "4:29:36"}
102
+ {"current_steps": 1020, "total_steps": 4218, "loss": 0.2066, "lr": 9.402024874730928e-06, "epoch": 0.7254623044096729, "percentage": 24.18, "elapsed_time": "1:25:40", "remaining_time": "4:28:36"}
103
+ {"current_steps": 1030, "total_steps": 4218, "loss": 0.159, "lr": 9.382250869820146e-06, "epoch": 0.732574679943101, "percentage": 24.42, "elapsed_time": "1:26:31", "remaining_time": "4:27:48"}
104
+ {"current_steps": 1040, "total_steps": 4218, "loss": 0.1924, "lr": 9.36217671231956e-06, "epoch": 0.7396870554765291, "percentage": 24.66, "elapsed_time": "1:27:28", "remaining_time": "4:27:19"}
105
+ {"current_steps": 1050, "total_steps": 4218, "loss": 0.1414, "lr": 9.341803777164228e-06, "epoch": 0.7467994310099573, "percentage": 24.89, "elapsed_time": "1:28:12", "remaining_time": "4:26:08"}
106
+ {"current_steps": 1060, "total_steps": 4218, "loss": 0.1751, "lr": 9.321133459753322e-06, "epoch": 0.7539118065433855, "percentage": 25.13, "elapsed_time": "1:29:06", "remaining_time": "4:25:29"}
107
+ {"current_steps": 1070, "total_steps": 4218, "loss": 0.1642, "lr": 9.300167175854564e-06, "epoch": 0.7610241820768137, "percentage": 25.37, "elapsed_time": "1:29:52", "remaining_time": "4:24:25"}
108
+ {"current_steps": 1080, "total_steps": 4218, "loss": 0.1362, "lr": 9.278906361507238e-06, "epoch": 0.7681365576102418, "percentage": 25.6, "elapsed_time": "1:30:35", "remaining_time": "4:23:12"}
109
+ {"current_steps": 1090, "total_steps": 4218, "loss": 0.1375, "lr": 9.257352472923842e-06, "epoch": 0.7752489331436699, "percentage": 25.84, "elapsed_time": "1:31:22", "remaining_time": "4:22:13"}
110
+ {"current_steps": 1100, "total_steps": 4218, "loss": 0.1282, "lr": 9.235506986390346e-06, "epoch": 0.7823613086770982, "percentage": 26.08, "elapsed_time": "1:32:14", "remaining_time": "4:21:27"}
111
+ {"current_steps": 1110, "total_steps": 4218, "loss": 0.1341, "lr": 9.213371398165077e-06, "epoch": 0.7894736842105263, "percentage": 26.32, "elapsed_time": "1:33:05", "remaining_time": "4:20:38"}
112
+ {"current_steps": 1120, "total_steps": 4218, "loss": 0.1624, "lr": 9.190947224376238e-06, "epoch": 0.7965860597439545, "percentage": 26.55, "elapsed_time": "1:33:47", "remaining_time": "4:19:27"}
113
+ {"current_steps": 1130, "total_steps": 4218, "loss": 0.1228, "lr": 9.168236000918063e-06, "epoch": 0.8036984352773826, "percentage": 26.79, "elapsed_time": "1:34:42", "remaining_time": "4:18:49"}
114
+ {"current_steps": 1140, "total_steps": 4218, "loss": 0.1295, "lr": 9.145239283345618e-06, "epoch": 0.8108108108108109, "percentage": 27.03, "elapsed_time": "1:35:36", "remaining_time": "4:18:08"}
115
+ {"current_steps": 1150, "total_steps": 4218, "loss": 0.1239, "lr": 9.121958646768251e-06, "epoch": 0.817923186344239, "percentage": 27.26, "elapsed_time": "1:36:29", "remaining_time": "4:17:25"}
116
+ {"current_steps": 1160, "total_steps": 4218, "loss": 0.1058, "lr": 9.09839568574173e-06, "epoch": 0.8250355618776671, "percentage": 27.5, "elapsed_time": "1:37:19", "remaining_time": "4:16:34"}
117
+ {"current_steps": 1170, "total_steps": 4218, "loss": 0.1085, "lr": 9.074552014158994e-06, "epoch": 0.8321479374110953, "percentage": 27.74, "elapsed_time": "1:38:15", "remaining_time": "4:15:58"}
118
+ {"current_steps": 1180, "total_steps": 4218, "loss": 0.1158, "lr": 9.050429265139647e-06, "epoch": 0.8392603129445235, "percentage": 27.98, "elapsed_time": "1:39:02", "remaining_time": "4:14:58"}
119
+ {"current_steps": 1190, "total_steps": 4218, "loss": 0.1222, "lr": 9.026029090918076e-06, "epoch": 0.8463726884779517, "percentage": 28.21, "elapsed_time": "1:40:05", "remaining_time": "4:14:41"}
120
+ {"current_steps": 1200, "total_steps": 4218, "loss": 0.1112, "lr": 9.001353162730297e-06, "epoch": 0.8534850640113798, "percentage": 28.45, "elapsed_time": "1:40:55", "remaining_time": "4:13:49"}
121
+ {"current_steps": 1210, "total_steps": 4218, "loss": 0.1065, "lr": 8.976403170699486e-06, "epoch": 0.8605974395448079, "percentage": 28.69, "elapsed_time": "1:41:38", "remaining_time": "4:12:39"}
122
+ {"current_steps": 1220, "total_steps": 4218, "loss": 0.0936, "lr": 8.951180823720212e-06, "epoch": 0.8677098150782361, "percentage": 28.92, "elapsed_time": "1:42:36", "remaining_time": "4:12:08"}
123
+ {"current_steps": 1230, "total_steps": 4218, "loss": 0.0794, "lr": 8.925687849341398e-06, "epoch": 0.8748221906116643, "percentage": 29.16, "elapsed_time": "1:43:31", "remaining_time": "4:11:29"}
124
+ {"current_steps": 1240, "total_steps": 4218, "loss": 0.0897, "lr": 8.899925993647994e-06, "epoch": 0.8819345661450925, "percentage": 29.4, "elapsed_time": "1:44:12", "remaining_time": "4:10:16"}
125
+ {"current_steps": 1250, "total_steps": 4218, "loss": 0.0887, "lr": 8.873897021141378e-06, "epoch": 0.8890469416785206, "percentage": 29.63, "elapsed_time": "1:45:01", "remaining_time": "4:09:21"}
126
+ {"current_steps": 1260, "total_steps": 4218, "loss": 0.0846, "lr": 8.847602714618504e-06, "epoch": 0.8961593172119487, "percentage": 29.87, "elapsed_time": "1:45:54", "remaining_time": "4:08:38"}
127
+ {"current_steps": 1270, "total_steps": 4218, "loss": 0.0883, "lr": 8.821044875049796e-06, "epoch": 0.903271692745377, "percentage": 30.11, "elapsed_time": "1:46:46", "remaining_time": "4:07:51"}
128
+ {"current_steps": 1280, "total_steps": 4218, "loss": 0.0893, "lr": 8.794225321455788e-06, "epoch": 0.9103840682788051, "percentage": 30.35, "elapsed_time": "1:47:26", "remaining_time": "4:06:37"}
129
+ {"current_steps": 1290, "total_steps": 4218, "loss": 0.0912, "lr": 8.767145890782542e-06, "epoch": 0.9174964438122333, "percentage": 30.58, "elapsed_time": "1:48:18", "remaining_time": "4:05:49"}
130
+ {"current_steps": 1300, "total_steps": 4218, "loss": 0.0759, "lr": 8.739808437775825e-06, "epoch": 0.9246088193456614, "percentage": 30.82, "elapsed_time": "1:49:16", "remaining_time": "4:05:16"}
131
+ {"current_steps": 1310, "total_steps": 4218, "loss": 0.0938, "lr": 8.71221483485407e-06, "epoch": 0.9317211948790897, "percentage": 31.06, "elapsed_time": "1:50:06", "remaining_time": "4:04:26"}
132
+ {"current_steps": 1320, "total_steps": 4218, "loss": 0.0804, "lr": 8.684366971980139e-06, "epoch": 0.9388335704125178, "percentage": 31.29, "elapsed_time": "1:50:57", "remaining_time": "4:03:37"}
133
+ {"current_steps": 1330, "total_steps": 4218, "loss": 0.0734, "lr": 8.656266756531857e-06, "epoch": 0.9459459459459459, "percentage": 31.53, "elapsed_time": "1:51:46", "remaining_time": "4:02:42"}
134
+ {"current_steps": 1340, "total_steps": 4218, "loss": 0.0794, "lr": 8.627916113171396e-06, "epoch": 0.9530583214793741, "percentage": 31.77, "elapsed_time": "1:52:31", "remaining_time": "4:01:41"}
135
+ {"current_steps": 1350, "total_steps": 4218, "loss": 0.0729, "lr": 8.599316983713419e-06, "epoch": 0.9601706970128022, "percentage": 32.01, "elapsed_time": "1:53:26", "remaining_time": "4:01:00"}
136
+ {"current_steps": 1360, "total_steps": 4218, "loss": 0.0776, "lr": 8.570471326992105e-06, "epoch": 0.9672830725462305, "percentage": 32.24, "elapsed_time": "1:54:10", "remaining_time": "3:59:56"}
137
+ {"current_steps": 1370, "total_steps": 4218, "loss": 0.0801, "lr": 8.54138111872697e-06, "epoch": 0.9743954480796586, "percentage": 32.48, "elapsed_time": "1:54:57", "remaining_time": "3:58:58"}
138
+ {"current_steps": 1380, "total_steps": 4218, "loss": 0.0698, "lr": 8.512048351387551e-06, "epoch": 0.9815078236130867, "percentage": 32.72, "elapsed_time": "1:55:48", "remaining_time": "3:58:09"}
139
+ {"current_steps": 1390, "total_steps": 4218, "loss": 0.0719, "lr": 8.482475034056927e-06, "epoch": 0.9886201991465149, "percentage": 32.95, "elapsed_time": "1:56:25", "remaining_time": "3:56:52"}
140
+ {"current_steps": 1400, "total_steps": 4218, "loss": 0.0704, "lr": 8.452663192294121e-06, "epoch": 0.9957325746799431, "percentage": 33.19, "elapsed_time": "1:57:14", "remaining_time": "3:56:00"}
141
+ {"current_steps": 1410, "total_steps": 4218, "loss": 0.0619, "lr": 8.42261486799536e-06, "epoch": 1.0028449502133712, "percentage": 33.43, "elapsed_time": "1:58:07", "remaining_time": "3:55:14"}
142
+ {"current_steps": 1420, "total_steps": 4218, "loss": 0.0498, "lr": 8.392332119254214e-06, "epoch": 1.0099573257467995, "percentage": 33.67, "elapsed_time": "1:58:57", "remaining_time": "3:54:23"}
143
+ {"current_steps": 1430, "total_steps": 4218, "loss": 0.0468, "lr": 8.361817020220647e-06, "epoch": 1.0170697012802277, "percentage": 33.9, "elapsed_time": "1:59:47", "remaining_time": "3:53:32"}
144
+ {"current_steps": 1440, "total_steps": 4218, "loss": 0.0556, "lr": 8.331071660958936e-06, "epoch": 1.0241820768136558, "percentage": 34.14, "elapsed_time": "2:00:32", "remaining_time": "3:52:31"}
145
+ {"current_steps": 1450, "total_steps": 4218, "loss": 0.047, "lr": 8.300098147304523e-06, "epoch": 1.031294452347084, "percentage": 34.38, "elapsed_time": "2:01:24", "remaining_time": "3:51:45"}
146
+ {"current_steps": 1460, "total_steps": 4218, "loss": 0.0553, "lr": 8.268898600719785e-06, "epoch": 1.038406827880512, "percentage": 34.61, "elapsed_time": "2:02:16", "remaining_time": "3:50:58"}
147
+ {"current_steps": 1470, "total_steps": 4218, "loss": 0.0536, "lr": 8.237475158148724e-06, "epoch": 1.0455192034139402, "percentage": 34.85, "elapsed_time": "2:03:10", "remaining_time": "3:50:16"}
148
+ {"current_steps": 1480, "total_steps": 4218, "loss": 0.0479, "lr": 8.205829971870602e-06, "epoch": 1.0526315789473684, "percentage": 35.09, "elapsed_time": "2:04:01", "remaining_time": "3:49:27"}
149
+ {"current_steps": 1490, "total_steps": 4218, "loss": 0.048, "lr": 8.173965209352524e-06, "epoch": 1.0597439544807965, "percentage": 35.32, "elapsed_time": "2:04:44", "remaining_time": "3:48:23"}
150
+ {"current_steps": 1500, "total_steps": 4218, "loss": 0.0582, "lr": 8.14188305310099e-06, "epoch": 1.0668563300142249, "percentage": 35.56, "elapsed_time": "2:05:42", "remaining_time": "3:47:46"}
151
+ {"current_steps": 1510, "total_steps": 4218, "loss": 0.0507, "lr": 8.109585700512395e-06, "epoch": 1.073968705547653, "percentage": 35.8, "elapsed_time": "2:06:35", "remaining_time": "3:47:01"}
152
+ {"current_steps": 1520, "total_steps": 4218, "loss": 0.0492, "lr": 8.077075363722542e-06, "epoch": 1.0810810810810811, "percentage": 36.04, "elapsed_time": "2:07:25", "remaining_time": "3:46:09"}
153
+ {"current_steps": 1530, "total_steps": 4218, "loss": 0.059, "lr": 8.044354269455109e-06, "epoch": 1.0881934566145093, "percentage": 36.27, "elapsed_time": "2:08:16", "remaining_time": "3:45:22"}
154
+ {"current_steps": 1540, "total_steps": 4218, "loss": 0.0496, "lr": 8.011424658869142e-06, "epoch": 1.0953058321479374, "percentage": 36.51, "elapsed_time": "2:09:02", "remaining_time": "3:44:23"}
155
+ {"current_steps": 1550, "total_steps": 4218, "loss": 0.0428, "lr": 7.978288787405556e-06, "epoch": 1.1024182076813656, "percentage": 36.75, "elapsed_time": "2:09:51", "remaining_time": "3:43:31"}
156
+ {"current_steps": 1560, "total_steps": 4218, "loss": 0.0484, "lr": 7.944948924632643e-06, "epoch": 1.1095305832147937, "percentage": 36.98, "elapsed_time": "2:10:47", "remaining_time": "3:42:50"}
157
+ {"current_steps": 1570, "total_steps": 4218, "loss": 0.0485, "lr": 7.911407354090634e-06, "epoch": 1.1166429587482218, "percentage": 37.22, "elapsed_time": "2:11:36", "remaining_time": "3:41:58"}
158
+ {"current_steps": 1580, "total_steps": 4218, "loss": 0.0441, "lr": 7.877666373135287e-06, "epoch": 1.12375533428165, "percentage": 37.46, "elapsed_time": "2:12:21", "remaining_time": "3:40:59"}
159
+ {"current_steps": 1590, "total_steps": 4218, "loss": 0.052, "lr": 7.84372829278053e-06, "epoch": 1.1308677098150781, "percentage": 37.7, "elapsed_time": "2:13:01", "remaining_time": "3:39:51"}
160
+ {"current_steps": 1600, "total_steps": 4218, "loss": 0.0444, "lr": 7.809595437540189e-06, "epoch": 1.1379800853485065, "percentage": 37.93, "elapsed_time": "2:13:50", "remaining_time": "3:38:59"}
161
+ {"current_steps": 1610, "total_steps": 4218, "loss": 0.0405, "lr": 7.775270145268755e-06, "epoch": 1.1450924608819346, "percentage": 38.17, "elapsed_time": "2:14:38", "remaining_time": "3:38:06"}
162
+ {"current_steps": 1620, "total_steps": 4218, "loss": 0.0443, "lr": 7.740754767001278e-06, "epoch": 1.1522048364153628, "percentage": 38.41, "elapsed_time": "2:15:38", "remaining_time": "3:37:31"}
163
+ {"current_steps": 1630, "total_steps": 4218, "loss": 0.044, "lr": 7.706051666792318e-06, "epoch": 1.159317211948791, "percentage": 38.64, "elapsed_time": "2:16:24", "remaining_time": "3:36:34"}
164
+ {"current_steps": 1640, "total_steps": 4218, "loss": 0.0443, "lr": 7.671163221554043e-06, "epoch": 1.166429587482219, "percentage": 38.88, "elapsed_time": "2:17:06", "remaining_time": "3:35:32"}
165
+ {"current_steps": 1650, "total_steps": 4218, "loss": 0.0485, "lr": 7.636091820893417e-06, "epoch": 1.1735419630156472, "percentage": 39.12, "elapsed_time": "2:17:56", "remaining_time": "3:34:41"}
166
+ {"current_steps": 1660, "total_steps": 4218, "loss": 0.0479, "lr": 7.600839866948528e-06, "epoch": 1.1806543385490753, "percentage": 39.36, "elapsed_time": "2:18:40", "remaining_time": "3:33:41"}
167
+ {"current_steps": 1670, "total_steps": 4218, "loss": 0.0478, "lr": 7.565409774224066e-06, "epoch": 1.1877667140825037, "percentage": 39.59, "elapsed_time": "2:19:40", "remaining_time": "3:33:06"}
168
+ {"current_steps": 1680, "total_steps": 4218, "loss": 0.0402, "lr": 7.529803969425941e-06, "epoch": 1.1948790896159318, "percentage": 39.83, "elapsed_time": "2:20:32", "remaining_time": "3:32:19"}
169
+ {"current_steps": 1690, "total_steps": 4218, "loss": 0.0456, "lr": 7.494024891295075e-06, "epoch": 1.20199146514936, "percentage": 40.07, "elapsed_time": "2:21:33", "remaining_time": "3:31:45"}
170
+ {"current_steps": 1700, "total_steps": 4218, "loss": 0.0399, "lr": 7.458074990440363e-06, "epoch": 1.209103840682788, "percentage": 40.3, "elapsed_time": "2:22:10", "remaining_time": "3:30:34"}
171
+ {"current_steps": 1710, "total_steps": 4218, "loss": 0.0408, "lr": 7.421956729170823e-06, "epoch": 1.2162162162162162, "percentage": 40.54, "elapsed_time": "2:22:57", "remaining_time": "3:29:39"}
172
+ {"current_steps": 1720, "total_steps": 4218, "loss": 0.0532, "lr": 7.385672581326954e-06, "epoch": 1.2233285917496444, "percentage": 40.78, "elapsed_time": "2:23:47", "remaining_time": "3:28:50"}
173
+ {"current_steps": 1730, "total_steps": 4218, "loss": 0.0412, "lr": 7.34922503211128e-06, "epoch": 1.2304409672830725, "percentage": 41.01, "elapsed_time": "2:24:36", "remaining_time": "3:27:58"}
174
+ {"current_steps": 1740, "total_steps": 4218, "loss": 0.0383, "lr": 7.312616577918149e-06, "epoch": 1.2375533428165006, "percentage": 41.25, "elapsed_time": "2:25:26", "remaining_time": "3:27:08"}
175
+ {"current_steps": 1750, "total_steps": 4218, "loss": 0.0357, "lr": 7.2758497261627345e-06, "epoch": 1.2446657183499288, "percentage": 41.49, "elapsed_time": "2:26:21", "remaining_time": "3:26:24"}
176
+ {"current_steps": 1760, "total_steps": 4218, "loss": 0.0421, "lr": 7.238926995109306e-06, "epoch": 1.251778093883357, "percentage": 41.73, "elapsed_time": "2:27:14", "remaining_time": "3:25:38"}
177
+ {"current_steps": 1770, "total_steps": 4218, "loss": 0.0433, "lr": 7.201850913698736e-06, "epoch": 1.2588904694167853, "percentage": 41.96, "elapsed_time": "2:28:02", "remaining_time": "3:24:44"}
178
+ {"current_steps": 1780, "total_steps": 4218, "loss": 0.0381, "lr": 7.164624021375294e-06, "epoch": 1.2660028449502134, "percentage": 42.2, "elapsed_time": "2:28:58", "remaining_time": "3:24:03"}
179
+ {"current_steps": 1790, "total_steps": 4218, "loss": 0.0347, "lr": 7.12724886791271e-06, "epoch": 1.2731152204836416, "percentage": 42.44, "elapsed_time": "2:29:48", "remaining_time": "3:23:11"}
180
+ {"current_steps": 1800, "total_steps": 4218, "loss": 0.042, "lr": 7.08972801323953e-06, "epoch": 1.2802275960170697, "percentage": 42.67, "elapsed_time": "2:30:32", "remaining_time": "3:22:13"}
181
+ {"current_steps": 1810, "total_steps": 4218, "loss": 0.0358, "lr": 7.052064027263785e-06, "epoch": 1.2873399715504978, "percentage": 42.91, "elapsed_time": "2:31:20", "remaining_time": "3:21:21"}
182
+ {"current_steps": 1820, "total_steps": 4218, "loss": 0.0313, "lr": 7.014259489696968e-06, "epoch": 1.294452347083926, "percentage": 43.15, "elapsed_time": "2:32:06", "remaining_time": "3:20:25"}
183
+ {"current_steps": 1830, "total_steps": 4218, "loss": 0.0315, "lr": 6.976316989877343e-06, "epoch": 1.3015647226173541, "percentage": 43.39, "elapsed_time": "2:33:03", "remaining_time": "3:19:43"}
184
+ {"current_steps": 1840, "total_steps": 4218, "loss": 0.0305, "lr": 6.938239126592592e-06, "epoch": 1.3086770981507825, "percentage": 43.62, "elapsed_time": "2:34:02", "remaining_time": "3:19:05"}
185
+ {"current_steps": 1850, "total_steps": 4218, "loss": 0.0441, "lr": 6.90002850790182e-06, "epoch": 1.3157894736842106, "percentage": 43.86, "elapsed_time": "2:34:49", "remaining_time": "3:18:10"}
186
+ {"current_steps": 1860, "total_steps": 4218, "loss": 0.0363, "lr": 6.861687750956922e-06, "epoch": 1.3229018492176388, "percentage": 44.1, "elapsed_time": "2:35:43", "remaining_time": "3:17:25"}
187
+ {"current_steps": 1870, "total_steps": 4218, "loss": 0.035, "lr": 6.823219481823318e-06, "epoch": 1.330014224751067, "percentage": 44.33, "elapsed_time": "2:36:30", "remaining_time": "3:16:31"}
188
+ {"current_steps": 1880, "total_steps": 4218, "loss": 0.0211, "lr": 6.784626335300102e-06, "epoch": 1.337126600284495, "percentage": 44.57, "elapsed_time": "2:37:26", "remaining_time": "3:15:47"}
189
+ {"current_steps": 1890, "total_steps": 4218, "loss": 0.0368, "lr": 6.745910954739563e-06, "epoch": 1.3442389758179232, "percentage": 44.81, "elapsed_time": "2:38:19", "remaining_time": "3:15:00"}
190
+ {"current_steps": 1900, "total_steps": 4218, "loss": 0.0337, "lr": 6.707075991866143e-06, "epoch": 1.3513513513513513, "percentage": 45.05, "elapsed_time": "2:39:17", "remaining_time": "3:14:20"}
191
+ {"current_steps": 1910, "total_steps": 4218, "loss": 0.0323, "lr": 6.668124106594813e-06, "epoch": 1.3584637268847795, "percentage": 45.28, "elapsed_time": "2:40:08", "remaining_time": "3:13:30"}
192
+ {"current_steps": 1920, "total_steps": 4218, "loss": 0.0374, "lr": 6.629057966848879e-06, "epoch": 1.3655761024182076, "percentage": 45.52, "elapsed_time": "2:41:05", "remaining_time": "3:12:48"}
193
+ {"current_steps": 1930, "total_steps": 4218, "loss": 0.0293, "lr": 6.589880248377258e-06, "epoch": 1.3726884779516357, "percentage": 45.76, "elapsed_time": "2:42:02", "remaining_time": "3:12:06"}
194
+ {"current_steps": 1940, "total_steps": 4218, "loss": 0.0326, "lr": 6.550593634571205e-06, "epoch": 1.379800853485064, "percentage": 45.99, "elapsed_time": "2:42:52", "remaining_time": "3:11:14"}
195
+ {"current_steps": 1950, "total_steps": 4218, "loss": 0.0279, "lr": 6.511200816280523e-06, "epoch": 1.3869132290184922, "percentage": 46.23, "elapsed_time": "2:43:43", "remaining_time": "3:10:25"}
196
+ {"current_steps": 1960, "total_steps": 4218, "loss": 0.0348, "lr": 6.471704491629251e-06, "epoch": 1.3940256045519204, "percentage": 46.47, "elapsed_time": "2:44:30", "remaining_time": "3:09:31"}
197
+ {"current_steps": 1970, "total_steps": 4218, "loss": 0.0303, "lr": 6.432107365830872e-06, "epoch": 1.4011379800853485, "percentage": 46.7, "elapsed_time": "2:45:16", "remaining_time": "3:08:35"}
198
+ {"current_steps": 1980, "total_steps": 4218, "loss": 0.0379, "lr": 6.392412151003019e-06, "epoch": 1.4082503556187767, "percentage": 46.94, "elapsed_time": "2:46:14", "remaining_time": "3:07:53"}
199
+ {"current_steps": 1990, "total_steps": 4218, "loss": 0.0346, "lr": 6.3526215659817156e-06, "epoch": 1.4153627311522048, "percentage": 47.18, "elapsed_time": "2:47:02", "remaining_time": "3:07:01"}
200
+ {"current_steps": 2000, "total_steps": 4218, "loss": 0.0277, "lr": 6.312738336135159e-06, "epoch": 1.422475106685633, "percentage": 47.42, "elapsed_time": "2:48:00", "remaining_time": "3:06:18"}
201
+ {"current_steps": 2010, "total_steps": 4218, "loss": 0.0272, "lr": 6.272765193177044e-06, "epoch": 1.4295874822190613, "percentage": 47.65, "elapsed_time": "2:48:45", "remaining_time": "3:05:23"}
202
+ {"current_steps": 2020, "total_steps": 4218, "loss": 0.0286, "lr": 6.23270487497947e-06, "epoch": 1.4366998577524894, "percentage": 47.89, "elapsed_time": "2:49:39", "remaining_time": "3:04:36"}
203
+ {"current_steps": 2030, "total_steps": 4218, "loss": 0.0267, "lr": 6.192560125385412e-06, "epoch": 1.4438122332859176, "percentage": 48.13, "elapsed_time": "2:50:26", "remaining_time": "3:03:42"}
204
+ {"current_steps": 2040, "total_steps": 4218, "loss": 0.0263, "lr": 6.152333694020781e-06, "epoch": 1.4509246088193457, "percentage": 48.36, "elapsed_time": "2:51:06", "remaining_time": "3:02:41"}
205
+ {"current_steps": 2050, "total_steps": 4218, "loss": 0.0328, "lr": 6.112028336106108e-06, "epoch": 1.4580369843527738, "percentage": 48.6, "elapsed_time": "2:51:51", "remaining_time": "3:01:45"}
206
+ {"current_steps": 2060, "total_steps": 4218, "loss": 0.0268, "lr": 6.071646812267817e-06, "epoch": 1.465149359886202, "percentage": 48.84, "elapsed_time": "2:52:49", "remaining_time": "3:01:02"}
207
+ {"current_steps": 2070, "total_steps": 4218, "loss": 0.0272, "lr": 6.031191888349155e-06, "epoch": 1.4722617354196301, "percentage": 49.08, "elapsed_time": "2:53:40", "remaining_time": "3:00:13"}
208
+ {"current_steps": 2080, "total_steps": 4218, "loss": 0.027, "lr": 5.990666335220738e-06, "epoch": 1.4793741109530583, "percentage": 49.31, "elapsed_time": "2:54:26", "remaining_time": "2:59:18"}
209
+ {"current_steps": 2090, "total_steps": 4218, "loss": 0.024, "lr": 5.950072928590781e-06, "epoch": 1.4864864864864864, "percentage": 49.55, "elapsed_time": "2:55:16", "remaining_time": "2:58:27"}
210
+ {"current_steps": 2100, "total_steps": 4218, "loss": 0.0254, "lr": 5.909414448814971e-06, "epoch": 1.4935988620199145, "percentage": 49.79, "elapsed_time": "2:56:03", "remaining_time": "2:57:33"}
211
+ {"current_steps": 2110, "total_steps": 4218, "loss": 0.0275, "lr": 5.8686936807060335e-06, "epoch": 1.5007112375533427, "percentage": 50.02, "elapsed_time": "2:56:56", "remaining_time": "2:56:46"}
212
+ {"current_steps": 2120, "total_steps": 4218, "loss": 0.0268, "lr": 5.827913413343003e-06, "epoch": 1.5078236130867708, "percentage": 50.26, "elapsed_time": "2:57:45", "remaining_time": "2:55:55"}
213
+ {"current_steps": 2130, "total_steps": 4218, "loss": 0.0265, "lr": 5.787076439880177e-06, "epoch": 1.5149359886201992, "percentage": 50.5, "elapsed_time": "2:58:34", "remaining_time": "2:55:03"}
214
+ {"current_steps": 2140, "total_steps": 4218, "loss": 0.0254, "lr": 5.746185557355814e-06, "epoch": 1.5220483641536273, "percentage": 50.73, "elapsed_time": "2:59:33", "remaining_time": "2:54:21"}
215
+ {"current_steps": 2150, "total_steps": 4218, "loss": 0.022, "lr": 5.70524356650056e-06, "epoch": 1.5291607396870555, "percentage": 50.97, "elapsed_time": "3:00:22", "remaining_time": "2:53:30"}
216
+ {"current_steps": 2160, "total_steps": 4218, "loss": 0.0196, "lr": 5.664253271545603e-06, "epoch": 1.5362731152204836, "percentage": 51.21, "elapsed_time": "3:01:10", "remaining_time": "2:52:37"}
217
+ {"current_steps": 2170, "total_steps": 4218, "loss": 0.0225, "lr": 5.623217480030622e-06, "epoch": 1.543385490753912, "percentage": 51.45, "elapsed_time": "3:01:59", "remaining_time": "2:51:45"}
218
+ {"current_steps": 2180, "total_steps": 4218, "loss": 0.0209, "lr": 5.58213900261148e-06, "epoch": 1.55049786628734, "percentage": 51.68, "elapsed_time": "3:02:48", "remaining_time": "2:50:53"}
219
+ {"current_steps": 2190, "total_steps": 4218, "loss": 0.0272, "lr": 5.541020652867713e-06, "epoch": 1.5576102418207682, "percentage": 51.92, "elapsed_time": "3:03:46", "remaining_time": "2:50:10"}
220
+ {"current_steps": 2200, "total_steps": 4218, "loss": 0.022, "lr": 5.49986524710983e-06, "epoch": 1.5647226173541964, "percentage": 52.16, "elapsed_time": "3:04:35", "remaining_time": "2:49:19"}
221
+ {"current_steps": 2210, "total_steps": 4218, "loss": 0.0226, "lr": 5.4586756041864065e-06, "epoch": 1.5718349928876245, "percentage": 52.39, "elapsed_time": "3:05:29", "remaining_time": "2:48:32"}
222
+ {"current_steps": 2220, "total_steps": 4218, "loss": 0.0267, "lr": 5.417454545291017e-06, "epoch": 1.5789473684210527, "percentage": 52.63, "elapsed_time": "3:06:26", "remaining_time": "2:47:48"}
223
+ {"current_steps": 2230, "total_steps": 4218, "loss": 0.0226, "lr": 5.376204893769e-06, "epoch": 1.5860597439544808, "percentage": 52.87, "elapsed_time": "3:07:16", "remaining_time": "2:46:56"}
224
+ {"current_steps": 2240, "total_steps": 4218, "loss": 0.0241, "lr": 5.334929474924093e-06, "epoch": 1.593172119487909, "percentage": 53.11, "elapsed_time": "3:08:01", "remaining_time": "2:46:02"}
225
+ {"current_steps": 2250, "total_steps": 4218, "loss": 0.0229, "lr": 5.293631115824897e-06, "epoch": 1.600284495021337, "percentage": 53.34, "elapsed_time": "3:08:49", "remaining_time": "2:45:09"}
226
+ {"current_steps": 2260, "total_steps": 4218, "loss": 0.0244, "lr": 5.252312645111266e-06, "epoch": 1.6073968705547652, "percentage": 53.58, "elapsed_time": "3:09:37", "remaining_time": "2:44:17"}
227
+ {"current_steps": 2270, "total_steps": 4218, "loss": 0.0186, "lr": 5.2109768928005454e-06, "epoch": 1.6145092460881934, "percentage": 53.82, "elapsed_time": "3:10:27", "remaining_time": "2:43:26"}
228
+ {"current_steps": 2280, "total_steps": 4218, "loss": 0.0217, "lr": 5.169626690093751e-06, "epoch": 1.6216216216216215, "percentage": 54.05, "elapsed_time": "3:11:07", "remaining_time": "2:42:27"}
229
+ {"current_steps": 2290, "total_steps": 4218, "loss": 0.0214, "lr": 5.128264869181646e-06, "epoch": 1.6287339971550496, "percentage": 54.29, "elapsed_time": "3:11:56", "remaining_time": "2:41:35"}
230
+ {"current_steps": 2300, "total_steps": 4218, "loss": 0.0199, "lr": 5.086894263050755e-06, "epoch": 1.635846372688478, "percentage": 54.53, "elapsed_time": "3:12:54", "remaining_time": "2:40:51"}
231
+ {"current_steps": 2310, "total_steps": 4218, "loss": 0.0184, "lr": 5.045517705289328e-06, "epoch": 1.6429587482219061, "percentage": 54.77, "elapsed_time": "3:13:37", "remaining_time": "2:39:55"}
232
+ {"current_steps": 2320, "total_steps": 4218, "loss": 0.0189, "lr": 5.004138029893257e-06, "epoch": 1.6500711237553343, "percentage": 55.0, "elapsed_time": "3:14:27", "remaining_time": "2:39:05"}
233
+ {"current_steps": 2330, "total_steps": 4218, "loss": 0.0184, "lr": 4.9627580710719734e-06, "epoch": 1.6571834992887624, "percentage": 55.24, "elapsed_time": "3:15:14", "remaining_time": "2:38:12"}
234
+ {"current_steps": 2340, "total_steps": 4218, "loss": 0.0195, "lr": 4.921380663054318e-06, "epoch": 1.6642958748221908, "percentage": 55.48, "elapsed_time": "3:16:00", "remaining_time": "2:37:18"}
235
+ {"current_steps": 2350, "total_steps": 4218, "loss": 0.0182, "lr": 4.880008639894421e-06, "epoch": 1.671408250355619, "percentage": 55.71, "elapsed_time": "3:16:55", "remaining_time": "2:36:32"}
236
+ {"current_steps": 2360, "total_steps": 4218, "loss": 0.0216, "lr": 4.838644835277585e-06, "epoch": 1.678520625889047, "percentage": 55.95, "elapsed_time": "3:17:47", "remaining_time": "2:35:42"}
237
+ {"current_steps": 2370, "total_steps": 4218, "loss": 0.0172, "lr": 4.79729208232621e-06, "epoch": 1.6856330014224752, "percentage": 56.19, "elapsed_time": "3:18:49", "remaining_time": "2:35:01"}
238
+ {"current_steps": 2380, "total_steps": 4218, "loss": 0.0115, "lr": 4.75595321340573e-06, "epoch": 1.6927453769559033, "percentage": 56.42, "elapsed_time": "3:19:46", "remaining_time": "2:34:16"}
239
+ {"current_steps": 2390, "total_steps": 4218, "loss": 0.0161, "lr": 4.714631059930622e-06, "epoch": 1.6998577524893315, "percentage": 56.66, "elapsed_time": "3:20:40", "remaining_time": "2:33:29"}
240
+ {"current_steps": 2400, "total_steps": 4218, "loss": 0.0184, "lr": 4.6733284521704816e-06, "epoch": 1.7069701280227596, "percentage": 56.9, "elapsed_time": "3:21:26", "remaining_time": "2:32:35"}
241
+ {"current_steps": 2410, "total_steps": 4218, "loss": 0.0201, "lr": 4.632048219056159e-06, "epoch": 1.7140825035561877, "percentage": 57.14, "elapsed_time": "3:22:12", "remaining_time": "2:31:42"}
242
+ {"current_steps": 2420, "total_steps": 4218, "loss": 0.0154, "lr": 4.590793187986003e-06, "epoch": 1.7211948790896159, "percentage": 57.37, "elapsed_time": "3:22:55", "remaining_time": "2:30:46"}
243
+ {"current_steps": 2430, "total_steps": 4218, "loss": 0.0182, "lr": 4.549566184632206e-06, "epoch": 1.728307254623044, "percentage": 57.61, "elapsed_time": "3:23:47", "remaining_time": "2:29:56"}
244
+ {"current_steps": 2440, "total_steps": 4218, "loss": 0.0162, "lr": 4.508370032747261e-06, "epoch": 1.7354196301564722, "percentage": 57.85, "elapsed_time": "3:24:38", "remaining_time": "2:29:07"}
245
+ {"current_steps": 2450, "total_steps": 4218, "loss": 0.017, "lr": 4.467207553970564e-06, "epoch": 1.7425320056899003, "percentage": 58.08, "elapsed_time": "3:25:33", "remaining_time": "2:28:20"}
246
+ {"current_steps": 2460, "total_steps": 4218, "loss": 0.0144, "lr": 4.426081567635137e-06, "epoch": 1.7496443812233284, "percentage": 58.32, "elapsed_time": "3:26:27", "remaining_time": "2:27:32"}
247
+ {"current_steps": 2470, "total_steps": 4218, "loss": 0.014, "lr": 4.3849948905745385e-06, "epoch": 1.7567567567567568, "percentage": 58.56, "elapsed_time": "3:27:24", "remaining_time": "2:26:47"}
248
+ {"current_steps": 2480, "total_steps": 4218, "loss": 0.015, "lr": 4.343950336929927e-06, "epoch": 1.763869132290185, "percentage": 58.8, "elapsed_time": "3:28:15", "remaining_time": "2:25:56"}
249
+ {"current_steps": 2490, "total_steps": 4218, "loss": 0.0144, "lr": 4.302950717957304e-06, "epoch": 1.770981507823613, "percentage": 59.03, "elapsed_time": "3:29:00", "remaining_time": "2:25:02"}
250
+ {"current_steps": 2500, "total_steps": 4218, "loss": 0.0144, "lr": 4.261998841834972e-06, "epoch": 1.7780938833570412, "percentage": 59.27, "elapsed_time": "3:29:50", "remaining_time": "2:24:12"}
251
+ {"current_steps": 2510, "total_steps": 4218, "loss": 0.0114, "lr": 4.221097513471199e-06, "epoch": 1.7852062588904696, "percentage": 59.51, "elapsed_time": "3:30:40", "remaining_time": "2:23:21"}
252
+ {"current_steps": 2520, "total_steps": 4218, "loss": 0.0127, "lr": 4.18024953431209e-06, "epoch": 1.7923186344238977, "percentage": 59.74, "elapsed_time": "3:31:30", "remaining_time": "2:22:30"}
253
+ {"current_steps": 2530, "total_steps": 4218, "loss": 0.0149, "lr": 4.13945770214971e-06, "epoch": 1.7994310099573259, "percentage": 59.98, "elapsed_time": "3:32:23", "remaining_time": "2:21:42"}
254
+ {"current_steps": 2540, "total_steps": 4218, "loss": 0.0129, "lr": 4.098724810930472e-06, "epoch": 1.806543385490754, "percentage": 60.22, "elapsed_time": "3:33:04", "remaining_time": "2:20:45"}
255
+ {"current_steps": 2550, "total_steps": 4218, "loss": 0.0124, "lr": 4.058053650563747e-06, "epoch": 1.8136557610241821, "percentage": 60.46, "elapsed_time": "3:33:59", "remaining_time": "2:19:58"}
256
+ {"current_steps": 2560, "total_steps": 4218, "loss": 0.0139, "lr": 4.017447006730796e-06, "epoch": 1.8207681365576103, "percentage": 60.69, "elapsed_time": "3:34:59", "remaining_time": "2:19:14"}
257
+ {"current_steps": 2570, "total_steps": 4218, "loss": 0.0128, "lr": 3.976907660693954e-06, "epoch": 1.8278805120910384, "percentage": 60.93, "elapsed_time": "3:35:41", "remaining_time": "2:18:18"}
258
+ {"current_steps": 2580, "total_steps": 4218, "loss": 0.0154, "lr": 3.936438389106154e-06, "epoch": 1.8349928876244666, "percentage": 61.17, "elapsed_time": "3:36:46", "remaining_time": "2:17:37"}
259
+ {"current_steps": 2590, "total_steps": 4218, "loss": 0.0162, "lr": 3.896041963820724e-06, "epoch": 1.8421052631578947, "percentage": 61.4, "elapsed_time": "3:37:33", "remaining_time": "2:16:45"}
260
+ {"current_steps": 2600, "total_steps": 4218, "loss": 0.0131, "lr": 3.855721151701548e-06, "epoch": 1.8492176386913228, "percentage": 61.64, "elapsed_time": "3:38:24", "remaining_time": "2:15:55"}
261
+ {"current_steps": 2610, "total_steps": 4218, "loss": 0.0129, "lr": 3.815478714433559e-06, "epoch": 1.856330014224751, "percentage": 61.88, "elapsed_time": "3:39:20", "remaining_time": "2:15:08"}
262
+ {"current_steps": 2620, "total_steps": 4218, "loss": 0.0153, "lr": 3.775317408333571e-06, "epoch": 1.863442389758179, "percentage": 62.11, "elapsed_time": "3:40:03", "remaining_time": "2:14:13"}
263
+ {"current_steps": 2630, "total_steps": 4218, "loss": 0.0116, "lr": 3.7352399841614996e-06, "epoch": 1.8705547652916072, "percentage": 62.35, "elapsed_time": "3:40:56", "remaining_time": "2:13:24"}
264
+ {"current_steps": 2640, "total_steps": 4218, "loss": 0.0126, "lr": 3.695249186931954e-06, "epoch": 1.8776671408250356, "percentage": 62.59, "elapsed_time": "3:41:44", "remaining_time": "2:12:32"}
265
+ {"current_steps": 2650, "total_steps": 4218, "loss": 0.0111, "lr": 3.655347755726224e-06, "epoch": 1.8847795163584637, "percentage": 62.83, "elapsed_time": "3:42:32", "remaining_time": "2:11:40"}
266
+ {"current_steps": 2660, "total_steps": 4218, "loss": 0.0129, "lr": 3.6155384235046674e-06, "epoch": 1.8918918918918919, "percentage": 63.06, "elapsed_time": "3:43:22", "remaining_time": "2:10:50"}
267
+ {"current_steps": 2670, "total_steps": 4218, "loss": 0.0079, "lr": 3.5758239169195276e-06, "epoch": 1.89900426742532, "percentage": 63.3, "elapsed_time": "3:44:11", "remaining_time": "2:09:58"}
268
+ {"current_steps": 2680, "total_steps": 4218, "loss": 0.0103, "lr": 3.5362069561281764e-06, "epoch": 1.9061166429587484, "percentage": 63.54, "elapsed_time": "3:44:57", "remaining_time": "2:09:05"}
269
+ {"current_steps": 2690, "total_steps": 4218, "loss": 0.0127, "lr": 3.4966902546068016e-06, "epoch": 1.9132290184921765, "percentage": 63.77, "elapsed_time": "3:45:45", "remaining_time": "2:08:14"}
270
+ {"current_steps": 2700, "total_steps": 4218, "loss": 0.0101, "lr": 3.4572765189645516e-06, "epoch": 1.9203413940256047, "percentage": 64.01, "elapsed_time": "3:46:41", "remaining_time": "2:07:27"}
271
+ {"current_steps": 2710, "total_steps": 4218, "loss": 0.0137, "lr": 3.4179684487581555e-06, "epoch": 1.9274537695590328, "percentage": 64.25, "elapsed_time": "3:47:38", "remaining_time": "2:06:40"}
272
+ {"current_steps": 2720, "total_steps": 4218, "loss": 0.0109, "lr": 3.3787687363070256e-06, "epoch": 1.934566145092461, "percentage": 64.49, "elapsed_time": "3:48:36", "remaining_time": "2:05:54"}
273
+ {"current_steps": 2730, "total_steps": 4218, "loss": 0.0105, "lr": 3.3396800665088435e-06, "epoch": 1.941678520625889, "percentage": 64.72, "elapsed_time": "3:49:24", "remaining_time": "2:05:02"}
274
+ {"current_steps": 2740, "total_steps": 4218, "loss": 0.0092, "lr": 3.300705116655672e-06, "epoch": 1.9487908961593172, "percentage": 64.96, "elapsed_time": "3:50:10", "remaining_time": "2:04:09"}
275
+ {"current_steps": 2750, "total_steps": 4218, "loss": 0.0074, "lr": 3.26184655625058e-06, "epoch": 1.9559032716927454, "percentage": 65.2, "elapsed_time": "3:50:58", "remaining_time": "2:03:17"}
276
+ {"current_steps": 2760, "total_steps": 4218, "loss": 0.0108, "lr": 3.2231070468247954e-06, "epoch": 1.9630156472261735, "percentage": 65.43, "elapsed_time": "3:51:36", "remaining_time": "2:02:21"}
277
+ {"current_steps": 2770, "total_steps": 4218, "loss": 0.0085, "lr": 3.1844892417554102e-06, "epoch": 1.9701280227596016, "percentage": 65.67, "elapsed_time": "3:52:31", "remaining_time": "2:01:32"}
278
+ {"current_steps": 2780, "total_steps": 4218, "loss": 0.0109, "lr": 3.1459957860836528e-06, "epoch": 1.9772403982930298, "percentage": 65.91, "elapsed_time": "3:53:22", "remaining_time": "2:00:42"}
279
+ {"current_steps": 2790, "total_steps": 4218, "loss": 0.0098, "lr": 3.1076293163337074e-06, "epoch": 1.984352773826458, "percentage": 66.15, "elapsed_time": "3:54:11", "remaining_time": "1:59:51"}
280
+ {"current_steps": 2800, "total_steps": 4218, "loss": 0.0125, "lr": 3.069392460332141e-06, "epoch": 1.991465149359886, "percentage": 66.38, "elapsed_time": "3:54:58", "remaining_time": "1:58:59"}
281
+ {"current_steps": 2810, "total_steps": 4218, "loss": 0.0086, "lr": 3.031287837027911e-06, "epoch": 1.9985775248933144, "percentage": 66.62, "elapsed_time": "3:55:49", "remaining_time": "1:58:09"}
282
+ {"current_steps": 2820, "total_steps": 4218, "loss": 0.0061, "lr": 2.9933180563129936e-06, "epoch": 2.0056899004267423, "percentage": 66.86, "elapsed_time": "3:56:41", "remaining_time": "1:57:20"}
283
+ {"current_steps": 2830, "total_steps": 4218, "loss": 0.0074, "lr": 2.955485718843616e-06, "epoch": 2.012802275960171, "percentage": 67.09, "elapsed_time": "3:57:39", "remaining_time": "1:56:33"}
284
+ {"current_steps": 2840, "total_steps": 4218, "loss": 0.0082, "lr": 2.917793415862129e-06, "epoch": 2.019914651493599, "percentage": 67.33, "elapsed_time": "3:58:25", "remaining_time": "1:55:41"}
285
+ {"current_steps": 2850, "total_steps": 4218, "loss": 0.005, "lr": 2.880243729019546e-06, "epoch": 2.027027027027027, "percentage": 67.57, "elapsed_time": "3:59:13", "remaining_time": "1:54:49"}
286
+ {"current_steps": 2860, "total_steps": 4218, "loss": 0.0072, "lr": 2.842839230198685e-06, "epoch": 2.0341394025604553, "percentage": 67.8, "elapsed_time": "4:00:01", "remaining_time": "1:53:58"}
287
+ {"current_steps": 2870, "total_steps": 4218, "loss": 0.008, "lr": 2.805582481338044e-06, "epoch": 2.0412517780938835, "percentage": 68.04, "elapsed_time": "4:00:42", "remaining_time": "1:53:03"}
288
+ {"current_steps": 2880, "total_steps": 4218, "loss": 0.0063, "lr": 2.7684760342563045e-06, "epoch": 2.0483641536273116, "percentage": 68.28, "elapsed_time": "4:01:31", "remaining_time": "1:52:12"}
289
+ {"current_steps": 2890, "total_steps": 4218, "loss": 0.0066, "lr": 2.731522430477571e-06, "epoch": 2.0554765291607398, "percentage": 68.52, "elapsed_time": "4:02:12", "remaining_time": "1:51:17"}
290
+ {"current_steps": 2900, "total_steps": 4218, "loss": 0.0087, "lr": 2.694724201057273e-06, "epoch": 2.062588904694168, "percentage": 68.75, "elapsed_time": "4:02:59", "remaining_time": "1:50:25"}
291
+ {"current_steps": 2910, "total_steps": 4218, "loss": 0.0083, "lr": 2.6580838664088214e-06, "epoch": 2.069701280227596, "percentage": 68.99, "elapsed_time": "4:03:41", "remaining_time": "1:49:31"}
292
+ {"current_steps": 2920, "total_steps": 4218, "loss": 0.0084, "lr": 2.6216039361309753e-06, "epoch": 2.076813655761024, "percentage": 69.23, "elapsed_time": "4:04:31", "remaining_time": "1:48:41"}
293
+ {"current_steps": 2930, "total_steps": 4218, "loss": 0.0066, "lr": 2.5852869088359495e-06, "epoch": 2.0839260312944523, "percentage": 69.46, "elapsed_time": "4:05:34", "remaining_time": "1:47:57"}
294
+ {"current_steps": 2940, "total_steps": 4218, "loss": 0.0051, "lr": 2.549135271978275e-06, "epoch": 2.0910384068278804, "percentage": 69.7, "elapsed_time": "4:06:37", "remaining_time": "1:47:12"}
295
+ {"current_steps": 2950, "total_steps": 4218, "loss": 0.0094, "lr": 2.5131515016844345e-06, "epoch": 2.0981507823613086, "percentage": 69.94, "elapsed_time": "4:07:31", "remaining_time": "1:46:23"}
296
+ {"current_steps": 2960, "total_steps": 4218, "loss": 0.0073, "lr": 2.4773380625832603e-06, "epoch": 2.1052631578947367, "percentage": 70.18, "elapsed_time": "4:08:22", "remaining_time": "1:45:33"}
297
+ {"current_steps": 2970, "total_steps": 4218, "loss": 0.0063, "lr": 2.4416974076371304e-06, "epoch": 2.112375533428165, "percentage": 70.41, "elapsed_time": "4:09:10", "remaining_time": "1:44:42"}
298
+ {"current_steps": 2980, "total_steps": 4218, "loss": 0.0061, "lr": 2.406231977973942e-06, "epoch": 2.119487908961593, "percentage": 70.65, "elapsed_time": "4:09:54", "remaining_time": "1:43:49"}
299
+ {"current_steps": 2990, "total_steps": 4218, "loss": 0.0091, "lr": 2.3709442027199387e-06, "epoch": 2.126600284495021, "percentage": 70.89, "elapsed_time": "4:10:41", "remaining_time": "1:42:57"}
300
+ {"current_steps": 3000, "total_steps": 4218, "loss": 0.0063, "lr": 2.3358364988333066e-06, "epoch": 2.1337126600284497, "percentage": 71.12, "elapsed_time": "4:11:16", "remaining_time": "1:42:01"}
301
+ {"current_steps": 3010, "total_steps": 4218, "loss": 0.0072, "lr": 2.3009112709386454e-06, "epoch": 2.140825035561878, "percentage": 71.36, "elapsed_time": "4:12:11", "remaining_time": "1:41:12"}
302
+ {"current_steps": 3020, "total_steps": 4218, "loss": 0.0074, "lr": 2.2661709111622666e-06, "epoch": 2.147937411095306, "percentage": 71.6, "elapsed_time": "4:13:08", "remaining_time": "1:40:25"}
303
+ {"current_steps": 3030, "total_steps": 4218, "loss": 0.0048, "lr": 2.2316177989683458e-06, "epoch": 2.155049786628734, "percentage": 71.83, "elapsed_time": "4:14:06", "remaining_time": "1:39:37"}
304
+ {"current_steps": 3040, "total_steps": 4218, "loss": 0.0072, "lr": 2.197254300995953e-06, "epoch": 2.1621621621621623, "percentage": 72.07, "elapsed_time": "4:14:51", "remaining_time": "1:38:45"}
305
+ {"current_steps": 3050, "total_steps": 4218, "loss": 0.006, "lr": 2.163082770896943e-06, "epoch": 2.1692745376955904, "percentage": 72.31, "elapsed_time": "4:15:47", "remaining_time": "1:37:57"}
306
+ {"current_steps": 3060, "total_steps": 4218, "loss": 0.0067, "lr": 2.1291055491747643e-06, "epoch": 2.1763869132290186, "percentage": 72.55, "elapsed_time": "4:16:41", "remaining_time": "1:37:08"}
307
+ {"current_steps": 3070, "total_steps": 4218, "loss": 0.0063, "lr": 2.095324963024137e-06, "epoch": 2.1834992887624467, "percentage": 72.78, "elapsed_time": "4:17:18", "remaining_time": "1:36:12"}
308
+ {"current_steps": 3080, "total_steps": 4218, "loss": 0.0047, "lr": 2.061743326171668e-06, "epoch": 2.190611664295875, "percentage": 73.02, "elapsed_time": "4:18:11", "remaining_time": "1:35:23"}
309
+ {"current_steps": 3090, "total_steps": 4218, "loss": 0.0076, "lr": 2.02836293871736e-06, "epoch": 2.197724039829303, "percentage": 73.26, "elapsed_time": "4:18:58", "remaining_time": "1:34:32"}
310
+ {"current_steps": 3100, "total_steps": 4218, "loss": 0.0051, "lr": 1.9951860869771e-06, "epoch": 2.204836415362731, "percentage": 73.49, "elapsed_time": "4:19:41", "remaining_time": "1:33:39"}
311
+ {"current_steps": 3110, "total_steps": 4218, "loss": 0.0058, "lr": 1.962215043326029e-06, "epoch": 2.2119487908961593, "percentage": 73.73, "elapsed_time": "4:20:36", "remaining_time": "1:32:50"}
312
+ {"current_steps": 3120, "total_steps": 4218, "loss": 0.0057, "lr": 1.9294520660429284e-06, "epoch": 2.2190611664295874, "percentage": 73.97, "elapsed_time": "4:21:27", "remaining_time": "1:32:00"}
313
+ {"current_steps": 3130, "total_steps": 4218, "loss": 0.0077, "lr": 1.8968993991555301e-06, "epoch": 2.2261735419630155, "percentage": 74.21, "elapsed_time": "4:22:16", "remaining_time": "1:31:09"}
314
+ {"current_steps": 3140, "total_steps": 4218, "loss": 0.0063, "lr": 1.8645592722868223e-06, "epoch": 2.2332859174964437, "percentage": 74.44, "elapsed_time": "4:23:00", "remaining_time": "1:30:17"}
315
+ {"current_steps": 3150, "total_steps": 4218, "loss": 0.0072, "lr": 1.8324339005023273e-06, "epoch": 2.240398293029872, "percentage": 74.68, "elapsed_time": "4:23:42", "remaining_time": "1:29:24"}
316
+ {"current_steps": 3160, "total_steps": 4218, "loss": 0.0053, "lr": 1.8005254841584035e-06, "epoch": 2.2475106685633, "percentage": 74.92, "elapsed_time": "4:24:30", "remaining_time": "1:28:33"}
317
+ {"current_steps": 3170, "total_steps": 4218, "loss": 0.0043, "lr": 1.768836208751516e-06, "epoch": 2.2546230440967285, "percentage": 75.15, "elapsed_time": "4:25:15", "remaining_time": "1:27:41"}
318
+ {"current_steps": 3180, "total_steps": 4218, "loss": 0.0051, "lr": 1.7373682447685624e-06, "epoch": 2.2617354196301562, "percentage": 75.39, "elapsed_time": "4:26:07", "remaining_time": "1:26:51"}
319
+ {"current_steps": 3190, "total_steps": 4218, "loss": 0.0053, "lr": 1.706123747538196e-06, "epoch": 2.268847795163585, "percentage": 75.63, "elapsed_time": "4:26:57", "remaining_time": "1:26:01"}
320
+ {"current_steps": 3200, "total_steps": 4218, "loss": 0.0058, "lr": 1.6751048570832184e-06, "epoch": 2.275960170697013, "percentage": 75.87, "elapsed_time": "4:27:37", "remaining_time": "1:25:08"}
321
+ {"current_steps": 3210, "total_steps": 4218, "loss": 0.0041, "lr": 1.6443136979739855e-06, "epoch": 2.283072546230441, "percentage": 76.1, "elapsed_time": "4:28:22", "remaining_time": "1:24:16"}
322
+ {"current_steps": 3220, "total_steps": 4218, "loss": 0.0041, "lr": 1.6137523791829007e-06, "epoch": 2.2901849217638692, "percentage": 76.34, "elapsed_time": "4:29:18", "remaining_time": "1:23:28"}
323
+ {"current_steps": 3230, "total_steps": 4218, "loss": 0.0061, "lr": 1.5834229939399637e-06, "epoch": 2.2972972972972974, "percentage": 76.58, "elapsed_time": "4:30:04", "remaining_time": "1:22:36"}
324
+ {"current_steps": 3240, "total_steps": 4218, "loss": 0.005, "lr": 1.5533276195893987e-06, "epoch": 2.3044096728307255, "percentage": 76.81, "elapsed_time": "4:30:55", "remaining_time": "1:21:46"}
325
+ {"current_steps": 3250, "total_steps": 4218, "loss": 0.0046, "lr": 1.5234683174473669e-06, "epoch": 2.3115220483641536, "percentage": 77.05, "elapsed_time": "4:31:56", "remaining_time": "1:20:59"}
326
+ {"current_steps": 3260, "total_steps": 4218, "loss": 0.0048, "lr": 1.493847132660789e-06, "epoch": 2.318634423897582, "percentage": 77.29, "elapsed_time": "4:32:49", "remaining_time": "1:20:10"}
327
+ {"current_steps": 3270, "total_steps": 4218, "loss": 0.0059, "lr": 1.4644660940672628e-06, "epoch": 2.32574679943101, "percentage": 77.52, "elapsed_time": "4:33:31", "remaining_time": "1:19:17"}
328
+ {"current_steps": 3280, "total_steps": 4218, "loss": 0.0051, "lr": 1.435327214056103e-06, "epoch": 2.332859174964438, "percentage": 77.76, "elapsed_time": "4:34:36", "remaining_time": "1:18:31"}
329
+ {"current_steps": 3290, "total_steps": 4218, "loss": 0.005, "lr": 1.406432488430508e-06, "epoch": 2.339971550497866, "percentage": 78.0, "elapsed_time": "4:35:33", "remaining_time": "1:17:43"}
330
+ {"current_steps": 3300, "total_steps": 4218, "loss": 0.0046, "lr": 1.3777838962708602e-06, "epoch": 2.3470839260312943, "percentage": 78.24, "elapsed_time": "4:36:12", "remaining_time": "1:16:50"}
331
+ {"current_steps": 3310, "total_steps": 4218, "loss": 0.0041, "lr": 1.3493833997991745e-06, "epoch": 2.3541963015647225, "percentage": 78.47, "elapsed_time": "4:36:54", "remaining_time": "1:15:57"}
332
+ {"current_steps": 3320, "total_steps": 4218, "loss": 0.0058, "lr": 1.3212329442446985e-06, "epoch": 2.3613086770981506, "percentage": 78.71, "elapsed_time": "4:37:44", "remaining_time": "1:15:07"}
333
+ {"current_steps": 3330, "total_steps": 4218, "loss": 0.005, "lr": 1.2933344577106822e-06, "epoch": 2.3684210526315788, "percentage": 78.95, "elapsed_time": "4:38:40", "remaining_time": "1:14:18"}
334
+ {"current_steps": 3340, "total_steps": 4218, "loss": 0.0052, "lr": 1.2656898510423122e-06, "epoch": 2.3755334281650073, "percentage": 79.18, "elapsed_time": "4:39:28", "remaining_time": "1:13:28"}
335
+ {"current_steps": 3350, "total_steps": 4218, "loss": 0.0048, "lr": 1.2383010176958372e-06, "epoch": 2.382645803698435, "percentage": 79.42, "elapsed_time": "4:40:23", "remaining_time": "1:12:39"}
336
+ {"current_steps": 3360, "total_steps": 4218, "loss": 0.0054, "lr": 1.2111698336088717e-06, "epoch": 2.3897581792318636, "percentage": 79.66, "elapsed_time": "4:41:12", "remaining_time": "1:11:48"}
337
+ {"current_steps": 3370, "total_steps": 4218, "loss": 0.0048, "lr": 1.1842981570719237e-06, "epoch": 2.3968705547652918, "percentage": 79.9, "elapsed_time": "4:42:07", "remaining_time": "1:10:59"}
338
+ {"current_steps": 3380, "total_steps": 4218, "loss": 0.0047, "lr": 1.157687828601094e-06, "epoch": 2.40398293029872, "percentage": 80.13, "elapsed_time": "4:42:56", "remaining_time": "1:10:09"}
339
+ {"current_steps": 3390, "total_steps": 4218, "loss": 0.0039, "lr": 1.1313406708120327e-06, "epoch": 2.411095305832148, "percentage": 80.37, "elapsed_time": "4:43:48", "remaining_time": "1:09:19"}
340
+ {"current_steps": 3400, "total_steps": 4218, "loss": 0.0043, "lr": 1.1052584882950896e-06, "epoch": 2.418207681365576, "percentage": 80.61, "elapsed_time": "4:44:50", "remaining_time": "1:08:31"}
341
+ {"current_steps": 3410, "total_steps": 4218, "loss": 0.0036, "lr": 1.0794430674917262e-06, "epoch": 2.4253200568990043, "percentage": 80.84, "elapsed_time": "4:45:42", "remaining_time": "1:07:42"}
342
+ {"current_steps": 3420, "total_steps": 4218, "loss": 0.0049, "lr": 1.0538961765721429e-06, "epoch": 2.4324324324324325, "percentage": 81.08, "elapsed_time": "4:46:23", "remaining_time": "1:06:49"}
343
+ {"current_steps": 3430, "total_steps": 4218, "loss": 0.0044, "lr": 1.0286195653141822e-06, "epoch": 2.4395448079658606, "percentage": 81.32, "elapsed_time": "4:47:08", "remaining_time": "1:05:58"}
344
+ {"current_steps": 3440, "total_steps": 4218, "loss": 0.0041, "lr": 1.0036149649834786e-06, "epoch": 2.4466571834992887, "percentage": 81.56, "elapsed_time": "4:47:57", "remaining_time": "1:05:07"}
345
+ {"current_steps": 3450, "total_steps": 4218, "loss": 0.0044, "lr": 9.788840882148803e-07, "epoch": 2.453769559032717, "percentage": 81.79, "elapsed_time": "4:48:51", "remaining_time": "1:04:18"}
346
+ {"current_steps": 3460, "total_steps": 4218, "loss": 0.0035, "lr": 9.544286288951393e-07, "epoch": 2.460881934566145, "percentage": 82.03, "elapsed_time": "4:49:35", "remaining_time": "1:03:26"}
347
+ {"current_steps": 3470, "total_steps": 4218, "loss": 0.0046, "lr": 9.302502620469073e-07, "epoch": 2.467994310099573, "percentage": 82.27, "elapsed_time": "4:50:26", "remaining_time": "1:02:36"}
348
+ {"current_steps": 3480, "total_steps": 4218, "loss": 0.0039, "lr": 9.063506437139901e-07, "epoch": 2.4751066856330013, "percentage": 82.5, "elapsed_time": "4:51:16", "remaining_time": "1:01:46"}
349
+ {"current_steps": 3490, "total_steps": 4218, "loss": 0.0039, "lr": 8.827314108479357e-07, "epoch": 2.4822190611664294, "percentage": 82.74, "elapsed_time": "4:52:13", "remaining_time": "1:00:57"}
350
+ {"current_steps": 3500, "total_steps": 4218, "loss": 0.0038, "lr": 8.593941811959078e-07, "epoch": 2.4893314366998576, "percentage": 82.98, "elapsed_time": "4:52:59", "remaining_time": "1:00:06"}
351
+ {"current_steps": 3510, "total_steps": 4218, "loss": 0.004, "lr": 8.363405531898833e-07, "epoch": 2.496443812233286, "percentage": 83.21, "elapsed_time": "4:53:41", "remaining_time": "0:59:14"}
352
+ {"current_steps": 3520, "total_steps": 4218, "loss": 0.0038, "lr": 8.135721058371681e-07, "epoch": 2.503556187766714, "percentage": 83.45, "elapsed_time": "4:54:29", "remaining_time": "0:58:23"}
353
+ {"current_steps": 3530, "total_steps": 4218, "loss": 0.0024, "lr": 7.910903986122537e-07, "epoch": 2.5106685633001424, "percentage": 83.69, "elapsed_time": "4:55:14", "remaining_time": "0:57:32"}
354
+ {"current_steps": 3540, "total_steps": 4218, "loss": 0.0037, "lr": 7.688969713499983e-07, "epoch": 2.5177809388335706, "percentage": 83.93, "elapsed_time": "4:56:16", "remaining_time": "0:56:44"}
355
+ {"current_steps": 3550, "total_steps": 4218, "loss": 0.0041, "lr": 7.469933441401606e-07, "epoch": 2.5248933143669987, "percentage": 84.16, "elapsed_time": "4:57:10", "remaining_time": "0:55:55"}
356
+ {"current_steps": 3560, "total_steps": 4218, "loss": 0.0033, "lr": 7.253810172232867e-07, "epoch": 2.532005689900427, "percentage": 84.4, "elapsed_time": "4:58:00", "remaining_time": "0:55:04"}
357
+ {"current_steps": 3570, "total_steps": 4218, "loss": 0.0036, "lr": 7.040614708879489e-07, "epoch": 2.539118065433855, "percentage": 84.64, "elapsed_time": "4:58:43", "remaining_time": "0:54:13"}
358
+ {"current_steps": 3580, "total_steps": 4218, "loss": 0.0037, "lr": 6.830361653693673e-07, "epoch": 2.546230440967283, "percentage": 84.87, "elapsed_time": "4:59:42", "remaining_time": "0:53:24"}
359
+ {"current_steps": 3590, "total_steps": 4218, "loss": 0.0037, "lr": 6.623065407493801e-07, "epoch": 2.5533428165007113, "percentage": 85.11, "elapsed_time": "5:00:34", "remaining_time": "0:52:34"}
360
+ {"current_steps": 3600, "total_steps": 4218, "loss": 0.0033, "lr": 6.418740168578208e-07, "epoch": 2.5604551920341394, "percentage": 85.35, "elapsed_time": "5:01:34", "remaining_time": "0:51:46"}
361
+ {"current_steps": 3610, "total_steps": 4218, "loss": 0.0035, "lr": 6.217399931752627e-07, "epoch": 2.5675675675675675, "percentage": 85.59, "elapsed_time": "5:02:19", "remaining_time": "0:50:54"}
362
+ {"current_steps": 3620, "total_steps": 4218, "loss": 0.0033, "lr": 6.019058487371687e-07, "epoch": 2.5746799431009957, "percentage": 85.82, "elapsed_time": "5:02:59", "remaining_time": "0:50:03"}
363
+ {"current_steps": 3630, "total_steps": 4218, "loss": 0.0042, "lr": 5.82372942039432e-07, "epoch": 2.581792318634424, "percentage": 86.06, "elapsed_time": "5:03:43", "remaining_time": "0:49:11"}
364
+ {"current_steps": 3640, "total_steps": 4218, "loss": 0.004, "lr": 5.631426109453364e-07, "epoch": 2.588904694167852, "percentage": 86.3, "elapsed_time": "5:04:35", "remaining_time": "0:48:22"}
365
+ {"current_steps": 3650, "total_steps": 4218, "loss": 0.0037, "lr": 5.44216172593916e-07, "epoch": 2.59601706970128, "percentage": 86.53, "elapsed_time": "5:05:28", "remaining_time": "0:47:32"}
366
+ {"current_steps": 3660, "total_steps": 4218, "loss": 0.0037, "lr": 5.255949233097451e-07, "epoch": 2.6031294452347082, "percentage": 86.77, "elapsed_time": "5:06:24", "remaining_time": "0:46:42"}
367
+ {"current_steps": 3670, "total_steps": 4218, "loss": 0.0036, "lr": 5.072801385141429e-07, "epoch": 2.6102418207681364, "percentage": 87.01, "elapsed_time": "5:07:31", "remaining_time": "0:45:55"}
368
+ {"current_steps": 3680, "total_steps": 4218, "loss": 0.0032, "lr": 4.89273072637827e-07, "epoch": 2.617354196301565, "percentage": 87.25, "elapsed_time": "5:08:12", "remaining_time": "0:45:03"}
369
+ {"current_steps": 3690, "total_steps": 4218, "loss": 0.0033, "lr": 4.7157495903498105e-07, "epoch": 2.6244665718349927, "percentage": 87.48, "elapsed_time": "5:09:08", "remaining_time": "0:44:14"}
370
+ {"current_steps": 3700, "total_steps": 4218, "loss": 0.0037, "lr": 4.541870098987911e-07, "epoch": 2.6315789473684212, "percentage": 87.72, "elapsed_time": "5:09:56", "remaining_time": "0:43:23"}
371
+ {"current_steps": 3710, "total_steps": 4218, "loss": 0.0043, "lr": 4.371104161784073e-07, "epoch": 2.6386913229018494, "percentage": 87.96, "elapsed_time": "5:10:46", "remaining_time": "0:42:33"}
372
+ {"current_steps": 3720, "total_steps": 4218, "loss": 0.0032, "lr": 4.2034634749738623e-07, "epoch": 2.6458036984352775, "percentage": 88.19, "elapsed_time": "5:11:35", "remaining_time": "0:41:42"}
373
+ {"current_steps": 3730, "total_steps": 4218, "loss": 0.004, "lr": 4.038959520735658e-07, "epoch": 2.6529160739687057, "percentage": 88.43, "elapsed_time": "5:12:19", "remaining_time": "0:40:51"}
374
+ {"current_steps": 3740, "total_steps": 4218, "loss": 0.0037, "lr": 3.8776035664043033e-07, "epoch": 2.660028449502134, "percentage": 88.67, "elapsed_time": "5:13:08", "remaining_time": "0:40:01"}
375
+ {"current_steps": 3750, "total_steps": 4218, "loss": 0.0042, "lr": 3.719406663699349e-07, "epoch": 2.667140825035562, "percentage": 88.9, "elapsed_time": "5:13:48", "remaining_time": "0:39:09"}
376
+ {"current_steps": 3760, "total_steps": 4218, "loss": 0.0035, "lr": 3.564379647968064e-07, "epoch": 2.67425320056899, "percentage": 89.14, "elapsed_time": "5:14:49", "remaining_time": "0:38:20"}
377
+ {"current_steps": 3770, "total_steps": 4218, "loss": 0.0038, "lr": 3.4125331374433414e-07, "epoch": 2.681365576102418, "percentage": 89.38, "elapsed_time": "5:15:30", "remaining_time": "0:37:29"}
378
+ {"current_steps": 3780, "total_steps": 4218, "loss": 0.0029, "lr": 3.2638775325163517e-07, "epoch": 2.6884779516358464, "percentage": 89.62, "elapsed_time": "5:16:12", "remaining_time": "0:36:38"}
379
+ {"current_steps": 3790, "total_steps": 4218, "loss": 0.0028, "lr": 3.1184230150243025e-07, "epoch": 2.6955903271692745, "percentage": 89.85, "elapsed_time": "5:17:00", "remaining_time": "0:35:48"}
380
+ {"current_steps": 3800, "total_steps": 4218, "loss": 0.0031, "lr": 2.9761795475529375e-07, "epoch": 2.7027027027027026, "percentage": 90.09, "elapsed_time": "5:17:53", "remaining_time": "0:34:58"}
381
+ {"current_steps": 3810, "total_steps": 4218, "loss": 0.0036, "lr": 2.8371568727542486e-07, "epoch": 2.7098150782361308, "percentage": 90.33, "elapsed_time": "5:18:49", "remaining_time": "0:34:08"}
382
+ {"current_steps": 3820, "total_steps": 4218, "loss": 0.003, "lr": 2.7013645126791446e-07, "epoch": 2.716927453769559, "percentage": 90.56, "elapsed_time": "5:19:26", "remaining_time": "0:33:16"}
383
+ {"current_steps": 3830, "total_steps": 4218, "loss": 0.0033, "lr": 2.5688117681252677e-07, "epoch": 2.724039829302987, "percentage": 90.8, "elapsed_time": "5:20:15", "remaining_time": "0:32:26"}
384
+ {"current_steps": 3840, "total_steps": 4218, "loss": 0.003, "lr": 2.439507717999945e-07, "epoch": 2.731152204836415, "percentage": 91.04, "elapsed_time": "5:21:18", "remaining_time": "0:31:37"}
385
+ {"current_steps": 3850, "total_steps": 4218, "loss": 0.0036, "lr": 2.3134612186983817e-07, "epoch": 2.7382645803698438, "percentage": 91.28, "elapsed_time": "5:21:54", "remaining_time": "0:30:46"}
386
+ {"current_steps": 3860, "total_steps": 4218, "loss": 0.0035, "lr": 2.1906809034970057e-07, "epoch": 2.7453769559032715, "percentage": 91.51, "elapsed_time": "5:22:44", "remaining_time": "0:29:56"}
387
+ {"current_steps": 3870, "total_steps": 4218, "loss": 0.003, "lr": 2.0711751819622038e-07, "epoch": 2.7524893314367, "percentage": 91.75, "elapsed_time": "5:23:23", "remaining_time": "0:29:04"}
388
+ {"current_steps": 3880, "total_steps": 4218, "loss": 0.0042, "lr": 1.954952239374286e-07, "epoch": 2.759601706970128, "percentage": 91.99, "elapsed_time": "5:24:15", "remaining_time": "0:28:14"}
389
+ {"current_steps": 3890, "total_steps": 4218, "loss": 0.0036, "lr": 1.8420200361669137e-07, "epoch": 2.7667140825035563, "percentage": 92.22, "elapsed_time": "5:25:02", "remaining_time": "0:27:24"}
390
+ {"current_steps": 3900, "total_steps": 4218, "loss": 0.0031, "lr": 1.732386307381767e-07, "epoch": 2.7738264580369845, "percentage": 92.46, "elapsed_time": "5:25:56", "remaining_time": "0:26:34"}
391
+ {"current_steps": 3910, "total_steps": 4218, "loss": 0.0034, "lr": 1.6260585621388604e-07, "epoch": 2.7809388335704126, "percentage": 92.7, "elapsed_time": "5:26:43", "remaining_time": "0:25:44"}
392
+ {"current_steps": 3920, "total_steps": 4218, "loss": 0.0044, "lr": 1.523044083122138e-07, "epoch": 2.7880512091038407, "percentage": 92.94, "elapsed_time": "5:27:38", "remaining_time": "0:24:54"}
393
+ {"current_steps": 3930, "total_steps": 4218, "loss": 0.0045, "lr": 1.4233499260807194e-07, "epoch": 2.795163584637269, "percentage": 93.17, "elapsed_time": "5:28:19", "remaining_time": "0:24:03"}
394
+ {"current_steps": 3940, "total_steps": 4218, "loss": 0.0034, "lr": 1.326982919345582e-07, "epoch": 2.802275960170697, "percentage": 93.41, "elapsed_time": "5:29:11", "remaining_time": "0:23:13"}
395
+ {"current_steps": 3950, "total_steps": 4218, "loss": 0.0031, "lr": 1.2339496633619218e-07, "epoch": 2.809388335704125, "percentage": 93.65, "elapsed_time": "5:30:02", "remaining_time": "0:22:23"}
396
+ {"current_steps": 3960, "total_steps": 4218, "loss": 0.0029, "lr": 1.1442565302370146e-07, "epoch": 2.8165007112375533, "percentage": 93.88, "elapsed_time": "5:31:00", "remaining_time": "0:21:33"}
397
+ {"current_steps": 3970, "total_steps": 4218, "loss": 0.0037, "lr": 1.0579096633038411e-07, "epoch": 2.8236130867709814, "percentage": 94.12, "elapsed_time": "5:31:48", "remaining_time": "0:20:43"}
398
+ {"current_steps": 3980, "total_steps": 4218, "loss": 0.0032, "lr": 9.749149767002197e-08, "epoch": 2.8307254623044096, "percentage": 94.36, "elapsed_time": "5:32:34", "remaining_time": "0:19:53"}
399
+ {"current_steps": 3990, "total_steps": 4218, "loss": 0.004, "lr": 8.952781549638412e-08, "epoch": 2.8378378378378377, "percentage": 94.59, "elapsed_time": "5:33:23", "remaining_time": "0:19:03"}
400
+ {"current_steps": 4000, "total_steps": 4218, "loss": 0.0031, "lr": 8.190046526428241e-08, "epoch": 2.844950213371266, "percentage": 94.83, "elapsed_time": "5:34:17", "remaining_time": "0:18:13"}
401
+ {"current_steps": 4010, "total_steps": 4218, "loss": 0.0039, "lr": 7.460996939221643e-08, "epoch": 2.852062588904694, "percentage": 95.07, "elapsed_time": "5:35:11", "remaining_time": "0:17:23"}
402
+ {"current_steps": 4020, "total_steps": 4218, "loss": 0.0039, "lr": 6.765682722659151e-08, "epoch": 2.8591749644381226, "percentage": 95.31, "elapsed_time": "5:36:01", "remaining_time": "0:16:33"}
403
+ {"current_steps": 4030, "total_steps": 4218, "loss": 0.0028, "lr": 6.104151500751609e-08, "epoch": 2.8662873399715503, "percentage": 95.54, "elapsed_time": "5:37:00", "remaining_time": "0:15:43"}
404
+ {"current_steps": 4040, "total_steps": 4218, "loss": 0.0039, "lr": 5.476448583618288e-08, "epoch": 2.873399715504979, "percentage": 95.78, "elapsed_time": "5:37:56", "remaining_time": "0:14:53"}
405
+ {"current_steps": 4050, "total_steps": 4218, "loss": 0.0028, "lr": 4.8826169643832464e-08, "epoch": 2.8805120910384066, "percentage": 96.02, "elapsed_time": "5:38:48", "remaining_time": "0:14:03"}
406
+ {"current_steps": 4060, "total_steps": 4218, "loss": 0.0039, "lr": 4.322697316231361e-08, "epoch": 2.887624466571835, "percentage": 96.25, "elapsed_time": "5:39:36", "remaining_time": "0:13:12"}
407
+ {"current_steps": 4070, "total_steps": 4218, "loss": 0.0027, "lr": 3.796727989621385e-08, "epoch": 2.8947368421052633, "percentage": 96.49, "elapsed_time": "5:40:27", "remaining_time": "0:12:22"}
408
+ {"current_steps": 4080, "total_steps": 4218, "loss": 0.0033, "lr": 3.304745009660326e-08, "epoch": 2.9018492176386914, "percentage": 96.73, "elapsed_time": "5:41:26", "remaining_time": "0:11:32"}
409
+ {"current_steps": 4090, "total_steps": 4218, "loss": 0.0031, "lr": 2.8467820736350903e-08, "epoch": 2.9089615931721196, "percentage": 96.97, "elapsed_time": "5:42:25", "remaining_time": "0:10:42"}
410
+ {"current_steps": 4100, "total_steps": 4218, "loss": 0.0032, "lr": 2.422870548705103e-08, "epoch": 2.9160739687055477, "percentage": 97.2, "elapsed_time": "5:43:14", "remaining_time": "0:09:52"}
411
+ {"current_steps": 4110, "total_steps": 4218, "loss": 0.0037, "lr": 2.0330394697534726e-08, "epoch": 2.923186344238976, "percentage": 97.44, "elapsed_time": "5:43:58", "remaining_time": "0:09:02"}
412
+ {"current_steps": 4120, "total_steps": 4218, "loss": 0.0038, "lr": 1.677315537398583e-08, "epoch": 2.930298719772404, "percentage": 97.68, "elapsed_time": "5:44:41", "remaining_time": "0:08:11"}
413
+ {"current_steps": 4130, "total_steps": 4218, "loss": 0.0032, "lr": 1.355723116165164e-08, "epoch": 2.937411095305832, "percentage": 97.91, "elapsed_time": "5:45:37", "remaining_time": "0:07:21"}
414
+ {"current_steps": 4140, "total_steps": 4218, "loss": 0.0033, "lr": 1.0682842328154086e-08, "epoch": 2.9445234708392602, "percentage": 98.15, "elapsed_time": "5:46:31", "remaining_time": "0:06:31"}
415
+ {"current_steps": 4150, "total_steps": 4218, "loss": 0.0037, "lr": 8.150185748405092e-09, "epoch": 2.9516358463726884, "percentage": 98.39, "elapsed_time": "5:47:20", "remaining_time": "0:05:41"}
416
+ {"current_steps": 4160, "total_steps": 4218, "loss": 0.0034, "lr": 5.959434891121274e-09, "epoch": 2.9587482219061165, "percentage": 98.62, "elapsed_time": "5:48:09", "remaining_time": "0:04:51"}
417
+ {"current_steps": 4170, "total_steps": 4218, "loss": 0.003, "lr": 4.110739806940656e-09, "epoch": 2.9658605974395447, "percentage": 98.86, "elapsed_time": "5:48:58", "remaining_time": "0:04:01"}
418
+ {"current_steps": 4180, "total_steps": 4218, "loss": 0.0027, "lr": 2.604227118148117e-09, "epoch": 2.972972972972973, "percentage": 99.1, "elapsed_time": "5:49:55", "remaining_time": "0:03:10"}
419
+ {"current_steps": 4190, "total_steps": 4218, "loss": 0.0033, "lr": 1.4400000100017741e-09, "epoch": 2.9800853485064014, "percentage": 99.34, "elapsed_time": "5:50:48", "remaining_time": "0:02:20"}
420
+ {"current_steps": 4200, "total_steps": 4218, "loss": 0.0028, "lr": 6.181382236641887e-10, "epoch": 2.987197724039829, "percentage": 99.57, "elapsed_time": "5:51:36", "remaining_time": "0:01:30"}
421
+ {"current_steps": 4210, "total_steps": 4218, "loss": 0.0033, "lr": 1.3869805074284704e-10, "epoch": 2.9943100995732577, "percentage": 99.81, "elapsed_time": "5:52:28", "remaining_time": "0:00:40"}
422
+ {"current_steps": 4218, "total_steps": 4218, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "5:53:12", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,2990 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 4218,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.007112375533428165,
14
+ "grad_norm": 27.90213406968924,
15
+ "learning_rate": 2.132701421800948e-07,
16
+ "loss": 3.2736,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.01422475106685633,
21
+ "grad_norm": 30.079497662873973,
22
+ "learning_rate": 4.502369668246446e-07,
23
+ "loss": 3.0907,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.021337126600284494,
28
+ "grad_norm": 22.857450095219185,
29
+ "learning_rate": 6.872037914691944e-07,
30
+ "loss": 2.5585,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.02844950213371266,
35
+ "grad_norm": 9.747429876049775,
36
+ "learning_rate": 9.241706161137441e-07,
37
+ "loss": 2.0379,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.03556187766714083,
42
+ "grad_norm": 7.291577115660012,
43
+ "learning_rate": 1.161137440758294e-06,
44
+ "loss": 1.8576,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.04267425320056899,
49
+ "grad_norm": 5.532213240888032,
50
+ "learning_rate": 1.3981042654028437e-06,
51
+ "loss": 1.7949,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.049786628733997154,
56
+ "grad_norm": 5.933113444425918,
57
+ "learning_rate": 1.6350710900473934e-06,
58
+ "loss": 1.717,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.05689900426742532,
63
+ "grad_norm": 6.263277176684849,
64
+ "learning_rate": 1.8720379146919433e-06,
65
+ "loss": 1.6602,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.06401137980085349,
70
+ "grad_norm": 5.6983842698392335,
71
+ "learning_rate": 2.109004739336493e-06,
72
+ "loss": 1.64,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.07112375533428165,
77
+ "grad_norm": 5.6269726113930885,
78
+ "learning_rate": 2.345971563981043e-06,
79
+ "loss": 1.5702,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.07823613086770982,
84
+ "grad_norm": 6.030572227568665,
85
+ "learning_rate": 2.5829383886255925e-06,
86
+ "loss": 1.5699,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.08534850640113797,
91
+ "grad_norm": 5.647899868810465,
92
+ "learning_rate": 2.8199052132701426e-06,
93
+ "loss": 1.5838,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.09246088193456614,
98
+ "grad_norm": 5.411803675210431,
99
+ "learning_rate": 3.0568720379146923e-06,
100
+ "loss": 1.5524,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.09957325746799431,
105
+ "grad_norm": 6.081650138994435,
106
+ "learning_rate": 3.293838862559242e-06,
107
+ "loss": 1.4833,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.10668563300142248,
112
+ "grad_norm": 5.828711910857202,
113
+ "learning_rate": 3.5308056872037916e-06,
114
+ "loss": 1.4856,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.11379800853485064,
119
+ "grad_norm": 6.169902161575631,
120
+ "learning_rate": 3.7677725118483417e-06,
121
+ "loss": 1.5518,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.12091038406827881,
126
+ "grad_norm": 6.587348119423249,
127
+ "learning_rate": 4.004739336492891e-06,
128
+ "loss": 1.4465,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.12802275960170698,
133
+ "grad_norm": 5.895125466115613,
134
+ "learning_rate": 4.2417061611374415e-06,
135
+ "loss": 1.4266,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.13513513513513514,
140
+ "grad_norm": 6.8094291227728645,
141
+ "learning_rate": 4.478672985781991e-06,
142
+ "loss": 1.3488,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.1422475106685633,
147
+ "grad_norm": 5.67979253930217,
148
+ "learning_rate": 4.715639810426541e-06,
149
+ "loss": 1.3592,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.14935988620199148,
154
+ "grad_norm": 5.707997611061335,
155
+ "learning_rate": 4.952606635071091e-06,
156
+ "loss": 1.3454,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.15647226173541964,
161
+ "grad_norm": 5.768661138747192,
162
+ "learning_rate": 5.18957345971564e-06,
163
+ "loss": 1.3214,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.16358463726884778,
168
+ "grad_norm": 6.881542275829192,
169
+ "learning_rate": 5.42654028436019e-06,
170
+ "loss": 1.3095,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.17069701280227595,
175
+ "grad_norm": 6.71203878660968,
176
+ "learning_rate": 5.66350710900474e-06,
177
+ "loss": 1.3164,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.17780938833570412,
182
+ "grad_norm": 6.234033501973343,
183
+ "learning_rate": 5.90047393364929e-06,
184
+ "loss": 1.2996,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.18492176386913228,
189
+ "grad_norm": 8.33843806575378,
190
+ "learning_rate": 6.137440758293839e-06,
191
+ "loss": 1.2654,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.19203413940256045,
196
+ "grad_norm": 7.595129348800133,
197
+ "learning_rate": 6.374407582938389e-06,
198
+ "loss": 1.206,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.19914651493598862,
203
+ "grad_norm": 6.466022627087353,
204
+ "learning_rate": 6.611374407582939e-06,
205
+ "loss": 1.1502,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.20625889046941678,
210
+ "grad_norm": 5.968433152101503,
211
+ "learning_rate": 6.848341232227489e-06,
212
+ "loss": 1.1757,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.21337126600284495,
217
+ "grad_norm": 6.614463560965846,
218
+ "learning_rate": 7.085308056872039e-06,
219
+ "loss": 1.1513,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.22048364153627312,
224
+ "grad_norm": 6.349655408064992,
225
+ "learning_rate": 7.322274881516588e-06,
226
+ "loss": 1.1687,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.22759601706970128,
231
+ "grad_norm": 7.059546274489307,
232
+ "learning_rate": 7.559241706161138e-06,
233
+ "loss": 1.0784,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.23470839260312945,
238
+ "grad_norm": 7.174629090661151,
239
+ "learning_rate": 7.796208530805689e-06,
240
+ "loss": 1.1724,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.24182076813655762,
245
+ "grad_norm": 7.1852274620100625,
246
+ "learning_rate": 8.033175355450237e-06,
247
+ "loss": 1.0926,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.24893314366998578,
252
+ "grad_norm": 6.094122405795049,
253
+ "learning_rate": 8.270142180094787e-06,
254
+ "loss": 1.0875,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.25604551920341395,
259
+ "grad_norm": 6.582672868116728,
260
+ "learning_rate": 8.507109004739337e-06,
261
+ "loss": 1.0287,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.2631578947368421,
266
+ "grad_norm": 6.88641059493668,
267
+ "learning_rate": 8.744075829383887e-06,
268
+ "loss": 1.0029,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.2702702702702703,
273
+ "grad_norm": 7.170889864871836,
274
+ "learning_rate": 8.981042654028437e-06,
275
+ "loss": 0.9941,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.2773826458036984,
280
+ "grad_norm": 6.028377283203336,
281
+ "learning_rate": 9.218009478672988e-06,
282
+ "loss": 0.8674,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.2844950213371266,
287
+ "grad_norm": 6.377454467317432,
288
+ "learning_rate": 9.454976303317538e-06,
289
+ "loss": 0.9614,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.29160739687055476,
294
+ "grad_norm": 7.795658548149459,
295
+ "learning_rate": 9.691943127962086e-06,
296
+ "loss": 0.888,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.29871977240398295,
301
+ "grad_norm": 7.482126849367938,
302
+ "learning_rate": 9.928909952606636e-06,
303
+ "loss": 0.9175,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.3058321479374111,
308
+ "grad_norm": 6.2359374732919655,
309
+ "learning_rate": 9.99991609608766e-06,
310
+ "loss": 0.8985,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.3129445234708393,
315
+ "grad_norm": 6.511421095028972,
316
+ "learning_rate": 9.999505144928566e-06,
317
+ "loss": 0.9245,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.3200568990042674,
322
+ "grad_norm": 6.684499797692544,
323
+ "learning_rate": 9.998751763712045e-06,
324
+ "loss": 0.8095,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.32716927453769556,
329
+ "grad_norm": 6.52623510868485,
330
+ "learning_rate": 9.997656004039284e-06,
331
+ "loss": 0.7917,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.33428165007112376,
336
+ "grad_norm": 6.391785139835116,
337
+ "learning_rate": 9.99621794096192e-06,
338
+ "loss": 0.8154,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.3413940256045519,
343
+ "grad_norm": 6.061600108949675,
344
+ "learning_rate": 9.994437672976904e-06,
345
+ "loss": 0.7042,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.3485064011379801,
350
+ "grad_norm": 7.003990519280338,
351
+ "learning_rate": 9.99231532201976e-06,
352
+ "loss": 0.7912,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.35561877667140823,
357
+ "grad_norm": 6.376557739362439,
358
+ "learning_rate": 9.989851033456224e-06,
359
+ "loss": 0.753,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.3627311522048364,
364
+ "grad_norm": 6.674903860198922,
365
+ "learning_rate": 9.987044976072298e-06,
366
+ "loss": 0.7059,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.36984352773826457,
371
+ "grad_norm": 6.92825266420183,
372
+ "learning_rate": 9.983897342062681e-06,
373
+ "loss": 0.7308,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.37695590327169276,
378
+ "grad_norm": 6.802916451931196,
379
+ "learning_rate": 9.98040834701761e-06,
380
+ "loss": 0.7136,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.3840682788051209,
385
+ "grad_norm": 5.5147042227151575,
386
+ "learning_rate": 9.97657822990809e-06,
387
+ "loss": 0.7085,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.3911806543385491,
392
+ "grad_norm": 6.090876343717448,
393
+ "learning_rate": 9.972407253069527e-06,
394
+ "loss": 0.7049,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.39829302987197723,
399
+ "grad_norm": 5.920393451920263,
400
+ "learning_rate": 9.967895702183767e-06,
401
+ "loss": 0.7136,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.40540540540540543,
406
+ "grad_norm": 6.740639908684347,
407
+ "learning_rate": 9.963043886259518e-06,
408
+ "loss": 0.6648,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.41251778093883357,
413
+ "grad_norm": 6.190326665175998,
414
+ "learning_rate": 9.957852137611187e-06,
415
+ "loss": 0.6538,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.41963015647226176,
420
+ "grad_norm": 5.8193938810967865,
421
+ "learning_rate": 9.952320811836129e-06,
422
+ "loss": 0.5848,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.4267425320056899,
427
+ "grad_norm": 5.231106852130435,
428
+ "learning_rate": 9.94645028779028e-06,
429
+ "loss": 0.6117,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.43385490753911804,
434
+ "grad_norm": 6.42206432654939,
435
+ "learning_rate": 9.94024096756221e-06,
436
+ "loss": 0.5831,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.44096728307254623,
441
+ "grad_norm": 7.364483477227342,
442
+ "learning_rate": 9.933693276445588e-06,
443
+ "loss": 0.5741,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.4480796586059744,
448
+ "grad_norm": 5.6944684489072355,
449
+ "learning_rate": 9.92680766291005e-06,
450
+ "loss": 0.5976,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.45519203413940257,
455
+ "grad_norm": 5.6237891453652455,
456
+ "learning_rate": 9.91958459857048e-06,
457
+ "loss": 0.5472,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.4623044096728307,
462
+ "grad_norm": 5.1230807672316505,
463
+ "learning_rate": 9.912024578154706e-06,
464
+ "loss": 0.5302,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.4694167852062589,
469
+ "grad_norm": 6.222140354090307,
470
+ "learning_rate": 9.904128119469625e-06,
471
+ "loss": 0.5292,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.47652916073968704,
476
+ "grad_norm": 5.82908513723418,
477
+ "learning_rate": 9.895895763365722e-06,
478
+ "loss": 0.513,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.48364153627311524,
483
+ "grad_norm": 5.479135634645378,
484
+ "learning_rate": 9.88732807370004e-06,
485
+ "loss": 0.4549,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.4907539118065434,
490
+ "grad_norm": 6.604832724403904,
491
+ "learning_rate": 9.878425637297549e-06,
492
+ "loss": 0.4254,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.49786628733997157,
497
+ "grad_norm": 5.618060296345201,
498
+ "learning_rate": 9.869189063910959e-06,
499
+ "loss": 0.4346,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.5049786628733998,
504
+ "grad_norm": 6.326935885254636,
505
+ "learning_rate": 9.859618986178953e-06,
506
+ "loss": 0.4311,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.5120910384068279,
511
+ "grad_norm": 6.411399143629572,
512
+ "learning_rate": 9.84971605958286e-06,
513
+ "loss": 0.4268,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.519203413940256,
518
+ "grad_norm": 6.244636888029725,
519
+ "learning_rate": 9.839480962401753e-06,
520
+ "loss": 0.3943,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.5263157894736842,
525
+ "grad_norm": 4.9638521174081935,
526
+ "learning_rate": 9.828914395665996e-06,
527
+ "loss": 0.3704,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.5334281650071123,
532
+ "grad_norm": 5.557286789154222,
533
+ "learning_rate": 9.818017083109233e-06,
534
+ "loss": 0.4167,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.5405405405405406,
539
+ "grad_norm": 5.693084707021369,
540
+ "learning_rate": 9.8067897711188e-06,
541
+ "loss": 0.3426,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.5476529160739687,
546
+ "grad_norm": 6.528132775066785,
547
+ "learning_rate": 9.795233228684631e-06,
548
+ "loss": 0.3325,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.5547652916073968,
553
+ "grad_norm": 4.9516616181943744,
554
+ "learning_rate": 9.783348247346558e-06,
555
+ "loss": 0.3526,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.561877667140825,
560
+ "grad_norm": 5.285013263137629,
561
+ "learning_rate": 9.771135641140117e-06,
562
+ "loss": 0.2811,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.5689900426742532,
567
+ "grad_norm": 5.427236432451273,
568
+ "learning_rate": 9.758596246540782e-06,
569
+ "loss": 0.3714,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.5761024182076814,
574
+ "grad_norm": 4.2910836634846135,
575
+ "learning_rate": 9.74573092240668e-06,
576
+ "loss": 0.3484,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.5832147937411095,
581
+ "grad_norm": 5.462486995732004,
582
+ "learning_rate": 9.732540549919758e-06,
583
+ "loss": 0.3275,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.5903271692745377,
588
+ "grad_norm": 5.748493175038991,
589
+ "learning_rate": 9.719026032525432e-06,
590
+ "loss": 0.3134,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.5974395448079659,
595
+ "grad_norm": 5.605839009853595,
596
+ "learning_rate": 9.70518829587071e-06,
597
+ "loss": 0.2918,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.604551920341394,
602
+ "grad_norm": 4.3649770239167305,
603
+ "learning_rate": 9.691028287740783e-06,
604
+ "loss": 0.2941,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.6116642958748222,
609
+ "grad_norm": 6.618364031460492,
610
+ "learning_rate": 9.67654697799412e-06,
611
+ "loss": 0.3041,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.6187766714082503,
616
+ "grad_norm": 4.289539717689249,
617
+ "learning_rate": 9.661745358496033e-06,
618
+ "loss": 0.2691,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.6258890469416786,
623
+ "grad_norm": 4.403362504112069,
624
+ "learning_rate": 9.64662444305074e-06,
625
+ "loss": 0.2789,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.6330014224751067,
630
+ "grad_norm": 5.121206118009773,
631
+ "learning_rate": 9.631185267331937e-06,
632
+ "loss": 0.2585,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.6401137980085349,
637
+ "grad_norm": 4.877490307909731,
638
+ "learning_rate": 9.615428888811842e-06,
639
+ "loss": 0.2499,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.647226173541963,
644
+ "grad_norm": 5.01492577738939,
645
+ "learning_rate": 9.59935638668879e-06,
646
+ "loss": 0.2555,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.6543385490753911,
651
+ "grad_norm": 6.3855818621534555,
652
+ "learning_rate": 9.582968861813295e-06,
653
+ "loss": 0.2193,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.6614509246088194,
658
+ "grad_norm": 4.33698276684028,
659
+ "learning_rate": 9.566267436612662e-06,
660
+ "loss": 0.2533,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.6685633001422475,
665
+ "grad_norm": 4.685807210281303,
666
+ "learning_rate": 9.549253255014105e-06,
667
+ "loss": 0.2141,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.6756756756756757,
672
+ "grad_norm": 5.275159675837076,
673
+ "learning_rate": 9.531927482366398e-06,
674
+ "loss": 0.2121,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.6827880512091038,
679
+ "grad_norm": 4.756073343523271,
680
+ "learning_rate": 9.514291305360053e-06,
681
+ "loss": 0.2187,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.689900426742532,
686
+ "grad_norm": 5.024551500100791,
687
+ "learning_rate": 9.496345931946039e-06,
688
+ "loss": 0.1841,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.6970128022759602,
693
+ "grad_norm": 4.283692003797298,
694
+ "learning_rate": 9.47809259125306e-06,
695
+ "loss": 0.225,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.7041251778093883,
700
+ "grad_norm": 5.201732993672687,
701
+ "learning_rate": 9.459532533503347e-06,
702
+ "loss": 0.184,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.7112375533428165,
707
+ "grad_norm": 4.806159299085367,
708
+ "learning_rate": 9.440667029927043e-06,
709
+ "loss": 0.1774,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.7183499288762447,
714
+ "grad_norm": 4.391296680269581,
715
+ "learning_rate": 9.421497372675133e-06,
716
+ "loss": 0.1729,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.7254623044096729,
721
+ "grad_norm": 3.4175211871739792,
722
+ "learning_rate": 9.402024874730928e-06,
723
+ "loss": 0.2066,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.732574679943101,
728
+ "grad_norm": 5.917646407329018,
729
+ "learning_rate": 9.382250869820146e-06,
730
+ "loss": 0.159,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.7396870554765291,
735
+ "grad_norm": 4.5654765488178155,
736
+ "learning_rate": 9.36217671231956e-06,
737
+ "loss": 0.1924,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.7467994310099573,
742
+ "grad_norm": 4.148546026699148,
743
+ "learning_rate": 9.341803777164228e-06,
744
+ "loss": 0.1414,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.7539118065433855,
749
+ "grad_norm": 5.299579387506197,
750
+ "learning_rate": 9.321133459753322e-06,
751
+ "loss": 0.1751,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.7610241820768137,
756
+ "grad_norm": 3.9468784531968426,
757
+ "learning_rate": 9.300167175854564e-06,
758
+ "loss": 0.1642,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.7681365576102418,
763
+ "grad_norm": 4.258905236243376,
764
+ "learning_rate": 9.278906361507238e-06,
765
+ "loss": 0.1362,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.7752489331436699,
770
+ "grad_norm": 4.177714057989964,
771
+ "learning_rate": 9.257352472923842e-06,
772
+ "loss": 0.1375,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.7823613086770982,
777
+ "grad_norm": 4.631019052366409,
778
+ "learning_rate": 9.235506986390346e-06,
779
+ "loss": 0.1282,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.7894736842105263,
784
+ "grad_norm": 4.025666581154786,
785
+ "learning_rate": 9.213371398165077e-06,
786
+ "loss": 0.1341,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.7965860597439545,
791
+ "grad_norm": 5.312761237015971,
792
+ "learning_rate": 9.190947224376238e-06,
793
+ "loss": 0.1624,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.8036984352773826,
798
+ "grad_norm": 4.847580150934388,
799
+ "learning_rate": 9.168236000918063e-06,
800
+ "loss": 0.1228,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.8108108108108109,
805
+ "grad_norm": 3.681304323084205,
806
+ "learning_rate": 9.145239283345618e-06,
807
+ "loss": 0.1295,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.817923186344239,
812
+ "grad_norm": 2.856809444870011,
813
+ "learning_rate": 9.121958646768251e-06,
814
+ "loss": 0.1239,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.8250355618776671,
819
+ "grad_norm": 3.8759882864356574,
820
+ "learning_rate": 9.09839568574173e-06,
821
+ "loss": 0.1058,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.8321479374110953,
826
+ "grad_norm": 3.520732889394545,
827
+ "learning_rate": 9.074552014158994e-06,
828
+ "loss": 0.1085,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.8392603129445235,
833
+ "grad_norm": 3.343174269734267,
834
+ "learning_rate": 9.050429265139647e-06,
835
+ "loss": 0.1158,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.8463726884779517,
840
+ "grad_norm": 4.5226917893573475,
841
+ "learning_rate": 9.026029090918076e-06,
842
+ "loss": 0.1222,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.8534850640113798,
847
+ "grad_norm": 3.7945492207672564,
848
+ "learning_rate": 9.001353162730297e-06,
849
+ "loss": 0.1112,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.8605974395448079,
854
+ "grad_norm": 4.30755037317223,
855
+ "learning_rate": 8.976403170699486e-06,
856
+ "loss": 0.1065,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.8677098150782361,
861
+ "grad_norm": 2.8075717567217033,
862
+ "learning_rate": 8.951180823720212e-06,
863
+ "loss": 0.0936,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.8748221906116643,
868
+ "grad_norm": 4.173272966405032,
869
+ "learning_rate": 8.925687849341398e-06,
870
+ "loss": 0.0794,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.8819345661450925,
875
+ "grad_norm": 3.41589130381316,
876
+ "learning_rate": 8.899925993647994e-06,
877
+ "loss": 0.0897,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.8890469416785206,
882
+ "grad_norm": 4.346956823329345,
883
+ "learning_rate": 8.873897021141378e-06,
884
+ "loss": 0.0887,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.8961593172119487,
889
+ "grad_norm": 3.51891817822506,
890
+ "learning_rate": 8.847602714618504e-06,
891
+ "loss": 0.0846,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.903271692745377,
896
+ "grad_norm": 3.106657795276442,
897
+ "learning_rate": 8.821044875049796e-06,
898
+ "loss": 0.0883,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.9103840682788051,
903
+ "grad_norm": 3.469975395363045,
904
+ "learning_rate": 8.794225321455788e-06,
905
+ "loss": 0.0893,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.9174964438122333,
910
+ "grad_norm": 4.092170025970377,
911
+ "learning_rate": 8.767145890782542e-06,
912
+ "loss": 0.0912,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.9246088193456614,
917
+ "grad_norm": 3.970701793851334,
918
+ "learning_rate": 8.739808437775825e-06,
919
+ "loss": 0.0759,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.9317211948790897,
924
+ "grad_norm": 4.338458399102716,
925
+ "learning_rate": 8.71221483485407e-06,
926
+ "loss": 0.0938,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.9388335704125178,
931
+ "grad_norm": 3.4360396182886963,
932
+ "learning_rate": 8.684366971980139e-06,
933
+ "loss": 0.0804,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.9459459459459459,
938
+ "grad_norm": 3.3921438457695654,
939
+ "learning_rate": 8.656266756531857e-06,
940
+ "loss": 0.0734,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.9530583214793741,
945
+ "grad_norm": 3.6703934299551126,
946
+ "learning_rate": 8.627916113171396e-06,
947
+ "loss": 0.0794,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.9601706970128022,
952
+ "grad_norm": 3.0528739658231823,
953
+ "learning_rate": 8.599316983713419e-06,
954
+ "loss": 0.0729,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.9672830725462305,
959
+ "grad_norm": 3.205301205746107,
960
+ "learning_rate": 8.570471326992105e-06,
961
+ "loss": 0.0776,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.9743954480796586,
966
+ "grad_norm": 3.39755647080461,
967
+ "learning_rate": 8.54138111872697e-06,
968
+ "loss": 0.0801,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.9815078236130867,
973
+ "grad_norm": 2.5637363679350056,
974
+ "learning_rate": 8.512048351387551e-06,
975
+ "loss": 0.0698,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.9886201991465149,
980
+ "grad_norm": 2.5368692351882367,
981
+ "learning_rate": 8.482475034056927e-06,
982
+ "loss": 0.0719,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.9957325746799431,
987
+ "grad_norm": 2.729862342028922,
988
+ "learning_rate": 8.452663192294121e-06,
989
+ "loss": 0.0704,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 1.0028449502133712,
994
+ "grad_norm": 3.2434913299704524,
995
+ "learning_rate": 8.42261486799536e-06,
996
+ "loss": 0.0619,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 1.0099573257467995,
1001
+ "grad_norm": 2.7769965300793844,
1002
+ "learning_rate": 8.392332119254214e-06,
1003
+ "loss": 0.0498,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 1.0170697012802277,
1008
+ "grad_norm": 2.824241471905449,
1009
+ "learning_rate": 8.361817020220647e-06,
1010
+ "loss": 0.0468,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 1.0241820768136558,
1015
+ "grad_norm": 2.9150859408507794,
1016
+ "learning_rate": 8.331071660958936e-06,
1017
+ "loss": 0.0556,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 1.031294452347084,
1022
+ "grad_norm": 1.907604048350405,
1023
+ "learning_rate": 8.300098147304523e-06,
1024
+ "loss": 0.047,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 1.038406827880512,
1029
+ "grad_norm": 3.404202261022711,
1030
+ "learning_rate": 8.268898600719785e-06,
1031
+ "loss": 0.0553,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 1.0455192034139402,
1036
+ "grad_norm": 3.931120264062831,
1037
+ "learning_rate": 8.237475158148724e-06,
1038
+ "loss": 0.0536,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 1.0526315789473684,
1043
+ "grad_norm": 3.1620958675587403,
1044
+ "learning_rate": 8.205829971870602e-06,
1045
+ "loss": 0.0479,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 1.0597439544807965,
1050
+ "grad_norm": 2.7429804696608935,
1051
+ "learning_rate": 8.173965209352524e-06,
1052
+ "loss": 0.048,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 1.0668563300142249,
1057
+ "grad_norm": 3.6303992768842437,
1058
+ "learning_rate": 8.14188305310099e-06,
1059
+ "loss": 0.0582,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 1.073968705547653,
1064
+ "grad_norm": 3.293723594586508,
1065
+ "learning_rate": 8.109585700512395e-06,
1066
+ "loss": 0.0507,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 1.0810810810810811,
1071
+ "grad_norm": 3.4841344851942755,
1072
+ "learning_rate": 8.077075363722542e-06,
1073
+ "loss": 0.0492,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 1.0881934566145093,
1078
+ "grad_norm": 3.7536302337999277,
1079
+ "learning_rate": 8.044354269455109e-06,
1080
+ "loss": 0.059,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 1.0953058321479374,
1085
+ "grad_norm": 3.261925658312736,
1086
+ "learning_rate": 8.011424658869142e-06,
1087
+ "loss": 0.0496,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 1.1024182076813656,
1092
+ "grad_norm": 3.2649673226199503,
1093
+ "learning_rate": 7.978288787405556e-06,
1094
+ "loss": 0.0428,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 1.1095305832147937,
1099
+ "grad_norm": 3.1908862790356185,
1100
+ "learning_rate": 7.944948924632643e-06,
1101
+ "loss": 0.0484,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 1.1166429587482218,
1106
+ "grad_norm": 2.980091794093968,
1107
+ "learning_rate": 7.911407354090634e-06,
1108
+ "loss": 0.0485,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 1.12375533428165,
1113
+ "grad_norm": 2.6098085172978287,
1114
+ "learning_rate": 7.877666373135287e-06,
1115
+ "loss": 0.0441,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 1.1308677098150781,
1120
+ "grad_norm": 2.6329214221965485,
1121
+ "learning_rate": 7.84372829278053e-06,
1122
+ "loss": 0.052,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 1.1379800853485065,
1127
+ "grad_norm": 2.9828411095241862,
1128
+ "learning_rate": 7.809595437540189e-06,
1129
+ "loss": 0.0444,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 1.1450924608819346,
1134
+ "grad_norm": 2.8256209003189183,
1135
+ "learning_rate": 7.775270145268755e-06,
1136
+ "loss": 0.0405,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 1.1522048364153628,
1141
+ "grad_norm": 2.1852050342228053,
1142
+ "learning_rate": 7.740754767001278e-06,
1143
+ "loss": 0.0443,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 1.159317211948791,
1148
+ "grad_norm": 2.9459065182368223,
1149
+ "learning_rate": 7.706051666792318e-06,
1150
+ "loss": 0.044,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 1.166429587482219,
1155
+ "grad_norm": 1.8756599971066235,
1156
+ "learning_rate": 7.671163221554043e-06,
1157
+ "loss": 0.0443,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 1.1735419630156472,
1162
+ "grad_norm": 2.546613866229381,
1163
+ "learning_rate": 7.636091820893417e-06,
1164
+ "loss": 0.0485,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 1.1806543385490753,
1169
+ "grad_norm": 2.6687368539976215,
1170
+ "learning_rate": 7.600839866948528e-06,
1171
+ "loss": 0.0479,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 1.1877667140825037,
1176
+ "grad_norm": 3.1352891064330235,
1177
+ "learning_rate": 7.565409774224066e-06,
1178
+ "loss": 0.0478,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 1.1948790896159318,
1183
+ "grad_norm": 2.840525979100908,
1184
+ "learning_rate": 7.529803969425941e-06,
1185
+ "loss": 0.0402,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 1.20199146514936,
1190
+ "grad_norm": 2.6839166671210015,
1191
+ "learning_rate": 7.494024891295075e-06,
1192
+ "loss": 0.0456,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 1.209103840682788,
1197
+ "grad_norm": 2.5400915247833513,
1198
+ "learning_rate": 7.458074990440363e-06,
1199
+ "loss": 0.0399,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 1.2162162162162162,
1204
+ "grad_norm": 2.4640207101809923,
1205
+ "learning_rate": 7.421956729170823e-06,
1206
+ "loss": 0.0408,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 1.2233285917496444,
1211
+ "grad_norm": 2.9057910772118296,
1212
+ "learning_rate": 7.385672581326954e-06,
1213
+ "loss": 0.0532,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 1.2304409672830725,
1218
+ "grad_norm": 2.2101614324462004,
1219
+ "learning_rate": 7.34922503211128e-06,
1220
+ "loss": 0.0412,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 1.2375533428165006,
1225
+ "grad_norm": 2.778141590898155,
1226
+ "learning_rate": 7.312616577918149e-06,
1227
+ "loss": 0.0383,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 1.2446657183499288,
1232
+ "grad_norm": 1.9995919460370448,
1233
+ "learning_rate": 7.2758497261627345e-06,
1234
+ "loss": 0.0357,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 1.251778093883357,
1239
+ "grad_norm": 2.9469506417904725,
1240
+ "learning_rate": 7.238926995109306e-06,
1241
+ "loss": 0.0421,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 1.2588904694167853,
1246
+ "grad_norm": 2.916214854110651,
1247
+ "learning_rate": 7.201850913698736e-06,
1248
+ "loss": 0.0433,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 1.2660028449502134,
1253
+ "grad_norm": 2.4356023661651935,
1254
+ "learning_rate": 7.164624021375294e-06,
1255
+ "loss": 0.0381,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 1.2731152204836416,
1260
+ "grad_norm": 2.9191479958429705,
1261
+ "learning_rate": 7.12724886791271e-06,
1262
+ "loss": 0.0347,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 1.2802275960170697,
1267
+ "grad_norm": 2.7350905980602964,
1268
+ "learning_rate": 7.08972801323953e-06,
1269
+ "loss": 0.042,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 1.2873399715504978,
1274
+ "grad_norm": 1.8638175145049911,
1275
+ "learning_rate": 7.052064027263785e-06,
1276
+ "loss": 0.0358,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 1.294452347083926,
1281
+ "grad_norm": 2.518215951733799,
1282
+ "learning_rate": 7.014259489696968e-06,
1283
+ "loss": 0.0313,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 1.3015647226173541,
1288
+ "grad_norm": 2.7073773489335435,
1289
+ "learning_rate": 6.976316989877343e-06,
1290
+ "loss": 0.0315,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 1.3086770981507825,
1295
+ "grad_norm": 2.1307550105530932,
1296
+ "learning_rate": 6.938239126592592e-06,
1297
+ "loss": 0.0305,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 1.3157894736842106,
1302
+ "grad_norm": 2.5312376788572957,
1303
+ "learning_rate": 6.90002850790182e-06,
1304
+ "loss": 0.0441,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 1.3229018492176388,
1309
+ "grad_norm": 2.5163550627582523,
1310
+ "learning_rate": 6.861687750956922e-06,
1311
+ "loss": 0.0363,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 1.330014224751067,
1316
+ "grad_norm": 2.121254806907021,
1317
+ "learning_rate": 6.823219481823318e-06,
1318
+ "loss": 0.035,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 1.337126600284495,
1323
+ "grad_norm": 1.6219365468690443,
1324
+ "learning_rate": 6.784626335300102e-06,
1325
+ "loss": 0.0211,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 1.3442389758179232,
1330
+ "grad_norm": 2.53112733146716,
1331
+ "learning_rate": 6.745910954739563e-06,
1332
+ "loss": 0.0368,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 1.3513513513513513,
1337
+ "grad_norm": 2.262886209479993,
1338
+ "learning_rate": 6.707075991866143e-06,
1339
+ "loss": 0.0337,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 1.3584637268847795,
1344
+ "grad_norm": 2.2016920030917126,
1345
+ "learning_rate": 6.668124106594813e-06,
1346
+ "loss": 0.0323,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 1.3655761024182076,
1351
+ "grad_norm": 2.503481715381616,
1352
+ "learning_rate": 6.629057966848879e-06,
1353
+ "loss": 0.0374,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 1.3726884779516357,
1358
+ "grad_norm": 2.282735039659182,
1359
+ "learning_rate": 6.589880248377258e-06,
1360
+ "loss": 0.0293,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 1.379800853485064,
1365
+ "grad_norm": 2.2077630603832223,
1366
+ "learning_rate": 6.550593634571205e-06,
1367
+ "loss": 0.0326,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 1.3869132290184922,
1372
+ "grad_norm": 2.4581246568090167,
1373
+ "learning_rate": 6.511200816280523e-06,
1374
+ "loss": 0.0279,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 1.3940256045519204,
1379
+ "grad_norm": 1.9826120506712706,
1380
+ "learning_rate": 6.471704491629251e-06,
1381
+ "loss": 0.0348,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 1.4011379800853485,
1386
+ "grad_norm": 2.0571244476045187,
1387
+ "learning_rate": 6.432107365830872e-06,
1388
+ "loss": 0.0303,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 1.4082503556187767,
1393
+ "grad_norm": 2.5505998895912594,
1394
+ "learning_rate": 6.392412151003019e-06,
1395
+ "loss": 0.0379,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 1.4153627311522048,
1400
+ "grad_norm": 2.764733651901472,
1401
+ "learning_rate": 6.3526215659817156e-06,
1402
+ "loss": 0.0346,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 1.422475106685633,
1407
+ "grad_norm": 2.093793772844917,
1408
+ "learning_rate": 6.312738336135159e-06,
1409
+ "loss": 0.0277,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 1.4295874822190613,
1414
+ "grad_norm": 2.36946856664872,
1415
+ "learning_rate": 6.272765193177044e-06,
1416
+ "loss": 0.0272,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 1.4366998577524894,
1421
+ "grad_norm": 1.6148755839195088,
1422
+ "learning_rate": 6.23270487497947e-06,
1423
+ "loss": 0.0286,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 1.4438122332859176,
1428
+ "grad_norm": 2.2679584601673284,
1429
+ "learning_rate": 6.192560125385412e-06,
1430
+ "loss": 0.0267,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 1.4509246088193457,
1435
+ "grad_norm": 2.0895836816165927,
1436
+ "learning_rate": 6.152333694020781e-06,
1437
+ "loss": 0.0263,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 1.4580369843527738,
1442
+ "grad_norm": 2.2843465595467625,
1443
+ "learning_rate": 6.112028336106108e-06,
1444
+ "loss": 0.0328,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 1.465149359886202,
1449
+ "grad_norm": 2.223353990512444,
1450
+ "learning_rate": 6.071646812267817e-06,
1451
+ "loss": 0.0268,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 1.4722617354196301,
1456
+ "grad_norm": 3.2498269359064613,
1457
+ "learning_rate": 6.031191888349155e-06,
1458
+ "loss": 0.0272,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 1.4793741109530583,
1463
+ "grad_norm": 2.1334409386725577,
1464
+ "learning_rate": 5.990666335220738e-06,
1465
+ "loss": 0.027,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 1.4864864864864864,
1470
+ "grad_norm": 1.1837205419905095,
1471
+ "learning_rate": 5.950072928590781e-06,
1472
+ "loss": 0.024,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 1.4935988620199145,
1477
+ "grad_norm": 2.3246109475669043,
1478
+ "learning_rate": 5.909414448814971e-06,
1479
+ "loss": 0.0254,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 1.5007112375533427,
1484
+ "grad_norm": 2.172355872063245,
1485
+ "learning_rate": 5.8686936807060335e-06,
1486
+ "loss": 0.0275,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 1.5078236130867708,
1491
+ "grad_norm": 2.0037575574912725,
1492
+ "learning_rate": 5.827913413343003e-06,
1493
+ "loss": 0.0268,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 1.5149359886201992,
1498
+ "grad_norm": 2.052997877430725,
1499
+ "learning_rate": 5.787076439880177e-06,
1500
+ "loss": 0.0265,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 1.5220483641536273,
1505
+ "grad_norm": 2.6412414518353535,
1506
+ "learning_rate": 5.746185557355814e-06,
1507
+ "loss": 0.0254,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 1.5291607396870555,
1512
+ "grad_norm": 2.037688763456784,
1513
+ "learning_rate": 5.70524356650056e-06,
1514
+ "loss": 0.022,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 1.5362731152204836,
1519
+ "grad_norm": 1.8060364636807138,
1520
+ "learning_rate": 5.664253271545603e-06,
1521
+ "loss": 0.0196,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 1.543385490753912,
1526
+ "grad_norm": 2.8659848398210994,
1527
+ "learning_rate": 5.623217480030622e-06,
1528
+ "loss": 0.0225,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 1.55049786628734,
1533
+ "grad_norm": 1.7576344300050144,
1534
+ "learning_rate": 5.58213900261148e-06,
1535
+ "loss": 0.0209,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 1.5576102418207682,
1540
+ "grad_norm": 2.4388617988676353,
1541
+ "learning_rate": 5.541020652867713e-06,
1542
+ "loss": 0.0272,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 1.5647226173541964,
1547
+ "grad_norm": 1.8297232039252016,
1548
+ "learning_rate": 5.49986524710983e-06,
1549
+ "loss": 0.022,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 1.5718349928876245,
1554
+ "grad_norm": 3.07701649104599,
1555
+ "learning_rate": 5.4586756041864065e-06,
1556
+ "loss": 0.0226,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 1.5789473684210527,
1561
+ "grad_norm": 2.0923369231599502,
1562
+ "learning_rate": 5.417454545291017e-06,
1563
+ "loss": 0.0267,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 1.5860597439544808,
1568
+ "grad_norm": 1.7648644786729606,
1569
+ "learning_rate": 5.376204893769e-06,
1570
+ "loss": 0.0226,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 1.593172119487909,
1575
+ "grad_norm": 2.7349839796479705,
1576
+ "learning_rate": 5.334929474924093e-06,
1577
+ "loss": 0.0241,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 1.600284495021337,
1582
+ "grad_norm": 1.220625942007617,
1583
+ "learning_rate": 5.293631115824897e-06,
1584
+ "loss": 0.0229,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 1.6073968705547652,
1589
+ "grad_norm": 2.048027464288667,
1590
+ "learning_rate": 5.252312645111266e-06,
1591
+ "loss": 0.0244,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 1.6145092460881934,
1596
+ "grad_norm": 1.807589998784463,
1597
+ "learning_rate": 5.2109768928005454e-06,
1598
+ "loss": 0.0186,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 1.6216216216216215,
1603
+ "grad_norm": 1.8200396071062714,
1604
+ "learning_rate": 5.169626690093751e-06,
1605
+ "loss": 0.0217,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 1.6287339971550496,
1610
+ "grad_norm": 3.162567751879996,
1611
+ "learning_rate": 5.128264869181646e-06,
1612
+ "loss": 0.0214,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 1.635846372688478,
1617
+ "grad_norm": 1.819589839229396,
1618
+ "learning_rate": 5.086894263050755e-06,
1619
+ "loss": 0.0199,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 1.6429587482219061,
1624
+ "grad_norm": 2.432299659362288,
1625
+ "learning_rate": 5.045517705289328e-06,
1626
+ "loss": 0.0184,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 1.6500711237553343,
1631
+ "grad_norm": 1.3210052417654967,
1632
+ "learning_rate": 5.004138029893257e-06,
1633
+ "loss": 0.0189,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 1.6571834992887624,
1638
+ "grad_norm": 2.1820820539792005,
1639
+ "learning_rate": 4.9627580710719734e-06,
1640
+ "loss": 0.0184,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 1.6642958748221908,
1645
+ "grad_norm": 1.824213025460573,
1646
+ "learning_rate": 4.921380663054318e-06,
1647
+ "loss": 0.0195,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 1.671408250355619,
1652
+ "grad_norm": 1.5395595832036817,
1653
+ "learning_rate": 4.880008639894421e-06,
1654
+ "loss": 0.0182,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 1.678520625889047,
1659
+ "grad_norm": 2.1765686448734898,
1660
+ "learning_rate": 4.838644835277585e-06,
1661
+ "loss": 0.0216,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 1.6856330014224752,
1666
+ "grad_norm": 1.6870995721298556,
1667
+ "learning_rate": 4.79729208232621e-06,
1668
+ "loss": 0.0172,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 1.6927453769559033,
1673
+ "grad_norm": 0.7966147079317253,
1674
+ "learning_rate": 4.75595321340573e-06,
1675
+ "loss": 0.0115,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 1.6998577524893315,
1680
+ "grad_norm": 2.172012245299623,
1681
+ "learning_rate": 4.714631059930622e-06,
1682
+ "loss": 0.0161,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 1.7069701280227596,
1687
+ "grad_norm": 1.6833896185427781,
1688
+ "learning_rate": 4.6733284521704816e-06,
1689
+ "loss": 0.0184,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 1.7140825035561877,
1694
+ "grad_norm": 1.943733582718135,
1695
+ "learning_rate": 4.632048219056159e-06,
1696
+ "loss": 0.0201,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 1.7211948790896159,
1701
+ "grad_norm": 0.9592772600888013,
1702
+ "learning_rate": 4.590793187986003e-06,
1703
+ "loss": 0.0154,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 1.728307254623044,
1708
+ "grad_norm": 2.418073085794697,
1709
+ "learning_rate": 4.549566184632206e-06,
1710
+ "loss": 0.0182,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 1.7354196301564722,
1715
+ "grad_norm": 2.213535114167178,
1716
+ "learning_rate": 4.508370032747261e-06,
1717
+ "loss": 0.0162,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 1.7425320056899003,
1722
+ "grad_norm": 1.4082214012150884,
1723
+ "learning_rate": 4.467207553970564e-06,
1724
+ "loss": 0.017,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 1.7496443812233284,
1729
+ "grad_norm": 1.4580878754754951,
1730
+ "learning_rate": 4.426081567635137e-06,
1731
+ "loss": 0.0144,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 1.7567567567567568,
1736
+ "grad_norm": 1.2997851819162691,
1737
+ "learning_rate": 4.3849948905745385e-06,
1738
+ "loss": 0.014,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 1.763869132290185,
1743
+ "grad_norm": 1.6936376446584087,
1744
+ "learning_rate": 4.343950336929927e-06,
1745
+ "loss": 0.015,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 1.770981507823613,
1750
+ "grad_norm": 0.9659927368936605,
1751
+ "learning_rate": 4.302950717957304e-06,
1752
+ "loss": 0.0144,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 1.7780938833570412,
1757
+ "grad_norm": 0.863368492950506,
1758
+ "learning_rate": 4.261998841834972e-06,
1759
+ "loss": 0.0144,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 1.7852062588904696,
1764
+ "grad_norm": 1.173314517778269,
1765
+ "learning_rate": 4.221097513471199e-06,
1766
+ "loss": 0.0114,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 1.7923186344238977,
1771
+ "grad_norm": 1.2332466621958023,
1772
+ "learning_rate": 4.18024953431209e-06,
1773
+ "loss": 0.0127,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 1.7994310099573259,
1778
+ "grad_norm": 1.1682909598329931,
1779
+ "learning_rate": 4.13945770214971e-06,
1780
+ "loss": 0.0149,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 1.806543385490754,
1785
+ "grad_norm": 1.291108254245667,
1786
+ "learning_rate": 4.098724810930472e-06,
1787
+ "loss": 0.0129,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 1.8136557610241821,
1792
+ "grad_norm": 0.8886518405396012,
1793
+ "learning_rate": 4.058053650563747e-06,
1794
+ "loss": 0.0124,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 1.8207681365576103,
1799
+ "grad_norm": 1.9480002932590483,
1800
+ "learning_rate": 4.017447006730796e-06,
1801
+ "loss": 0.0139,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 1.8278805120910384,
1806
+ "grad_norm": 1.6270472010472303,
1807
+ "learning_rate": 3.976907660693954e-06,
1808
+ "loss": 0.0128,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 1.8349928876244666,
1813
+ "grad_norm": 0.7994173120546909,
1814
+ "learning_rate": 3.936438389106154e-06,
1815
+ "loss": 0.0154,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 1.8421052631578947,
1820
+ "grad_norm": 1.0657933268821647,
1821
+ "learning_rate": 3.896041963820724e-06,
1822
+ "loss": 0.0162,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 1.8492176386913228,
1827
+ "grad_norm": 1.37634738377725,
1828
+ "learning_rate": 3.855721151701548e-06,
1829
+ "loss": 0.0131,
1830
+ "step": 2600
1831
+ },
1832
+ {
1833
+ "epoch": 1.856330014224751,
1834
+ "grad_norm": 1.7544039532579758,
1835
+ "learning_rate": 3.815478714433559e-06,
1836
+ "loss": 0.0129,
1837
+ "step": 2610
1838
+ },
1839
+ {
1840
+ "epoch": 1.863442389758179,
1841
+ "grad_norm": 0.8340685854059343,
1842
+ "learning_rate": 3.775317408333571e-06,
1843
+ "loss": 0.0153,
1844
+ "step": 2620
1845
+ },
1846
+ {
1847
+ "epoch": 1.8705547652916072,
1848
+ "grad_norm": 0.5628132394579408,
1849
+ "learning_rate": 3.7352399841614996e-06,
1850
+ "loss": 0.0116,
1851
+ "step": 2630
1852
+ },
1853
+ {
1854
+ "epoch": 1.8776671408250356,
1855
+ "grad_norm": 0.6225982099610957,
1856
+ "learning_rate": 3.695249186931954e-06,
1857
+ "loss": 0.0126,
1858
+ "step": 2640
1859
+ },
1860
+ {
1861
+ "epoch": 1.8847795163584637,
1862
+ "grad_norm": 1.3019140739354105,
1863
+ "learning_rate": 3.655347755726224e-06,
1864
+ "loss": 0.0111,
1865
+ "step": 2650
1866
+ },
1867
+ {
1868
+ "epoch": 1.8918918918918919,
1869
+ "grad_norm": 1.8784232456646273,
1870
+ "learning_rate": 3.6155384235046674e-06,
1871
+ "loss": 0.0129,
1872
+ "step": 2660
1873
+ },
1874
+ {
1875
+ "epoch": 1.89900426742532,
1876
+ "grad_norm": 1.2419343143332369,
1877
+ "learning_rate": 3.5758239169195276e-06,
1878
+ "loss": 0.0079,
1879
+ "step": 2670
1880
+ },
1881
+ {
1882
+ "epoch": 1.9061166429587484,
1883
+ "grad_norm": 1.327768382551478,
1884
+ "learning_rate": 3.5362069561281764e-06,
1885
+ "loss": 0.0103,
1886
+ "step": 2680
1887
+ },
1888
+ {
1889
+ "epoch": 1.9132290184921765,
1890
+ "grad_norm": 1.9613323508306293,
1891
+ "learning_rate": 3.4966902546068016e-06,
1892
+ "loss": 0.0127,
1893
+ "step": 2690
1894
+ },
1895
+ {
1896
+ "epoch": 1.9203413940256047,
1897
+ "grad_norm": 1.6143025584170387,
1898
+ "learning_rate": 3.4572765189645516e-06,
1899
+ "loss": 0.0101,
1900
+ "step": 2700
1901
+ },
1902
+ {
1903
+ "epoch": 1.9274537695590328,
1904
+ "grad_norm": 1.616056876993894,
1905
+ "learning_rate": 3.4179684487581555e-06,
1906
+ "loss": 0.0137,
1907
+ "step": 2710
1908
+ },
1909
+ {
1910
+ "epoch": 1.934566145092461,
1911
+ "grad_norm": 0.8562390776041625,
1912
+ "learning_rate": 3.3787687363070256e-06,
1913
+ "loss": 0.0109,
1914
+ "step": 2720
1915
+ },
1916
+ {
1917
+ "epoch": 1.941678520625889,
1918
+ "grad_norm": 1.1375907109658978,
1919
+ "learning_rate": 3.3396800665088435e-06,
1920
+ "loss": 0.0105,
1921
+ "step": 2730
1922
+ },
1923
+ {
1924
+ "epoch": 1.9487908961593172,
1925
+ "grad_norm": 1.4045001817445895,
1926
+ "learning_rate": 3.300705116655672e-06,
1927
+ "loss": 0.0092,
1928
+ "step": 2740
1929
+ },
1930
+ {
1931
+ "epoch": 1.9559032716927454,
1932
+ "grad_norm": 1.3938214602230523,
1933
+ "learning_rate": 3.26184655625058e-06,
1934
+ "loss": 0.0074,
1935
+ "step": 2750
1936
+ },
1937
+ {
1938
+ "epoch": 1.9630156472261735,
1939
+ "grad_norm": 1.125496278925233,
1940
+ "learning_rate": 3.2231070468247954e-06,
1941
+ "loss": 0.0108,
1942
+ "step": 2760
1943
+ },
1944
+ {
1945
+ "epoch": 1.9701280227596016,
1946
+ "grad_norm": 1.0938627450279363,
1947
+ "learning_rate": 3.1844892417554102e-06,
1948
+ "loss": 0.0085,
1949
+ "step": 2770
1950
+ },
1951
+ {
1952
+ "epoch": 1.9772403982930298,
1953
+ "grad_norm": 1.0213367474449344,
1954
+ "learning_rate": 3.1459957860836528e-06,
1955
+ "loss": 0.0109,
1956
+ "step": 2780
1957
+ },
1958
+ {
1959
+ "epoch": 1.984352773826458,
1960
+ "grad_norm": 1.4919999851950547,
1961
+ "learning_rate": 3.1076293163337074e-06,
1962
+ "loss": 0.0098,
1963
+ "step": 2790
1964
+ },
1965
+ {
1966
+ "epoch": 1.991465149359886,
1967
+ "grad_norm": 2.7046778198212404,
1968
+ "learning_rate": 3.069392460332141e-06,
1969
+ "loss": 0.0125,
1970
+ "step": 2800
1971
+ },
1972
+ {
1973
+ "epoch": 1.9985775248933144,
1974
+ "grad_norm": 0.7341284079698729,
1975
+ "learning_rate": 3.031287837027911e-06,
1976
+ "loss": 0.0086,
1977
+ "step": 2810
1978
+ },
1979
+ {
1980
+ "epoch": 2.0056899004267423,
1981
+ "grad_norm": 1.5705489322569974,
1982
+ "learning_rate": 2.9933180563129936e-06,
1983
+ "loss": 0.0061,
1984
+ "step": 2820
1985
+ },
1986
+ {
1987
+ "epoch": 2.012802275960171,
1988
+ "grad_norm": 0.31350772488690454,
1989
+ "learning_rate": 2.955485718843616e-06,
1990
+ "loss": 0.0074,
1991
+ "step": 2830
1992
+ },
1993
+ {
1994
+ "epoch": 2.019914651493599,
1995
+ "grad_norm": 0.6018726291077504,
1996
+ "learning_rate": 2.917793415862129e-06,
1997
+ "loss": 0.0082,
1998
+ "step": 2840
1999
+ },
2000
+ {
2001
+ "epoch": 2.027027027027027,
2002
+ "grad_norm": 0.6809782196576207,
2003
+ "learning_rate": 2.880243729019546e-06,
2004
+ "loss": 0.005,
2005
+ "step": 2850
2006
+ },
2007
+ {
2008
+ "epoch": 2.0341394025604553,
2009
+ "grad_norm": 0.520827132094845,
2010
+ "learning_rate": 2.842839230198685e-06,
2011
+ "loss": 0.0072,
2012
+ "step": 2860
2013
+ },
2014
+ {
2015
+ "epoch": 2.0412517780938835,
2016
+ "grad_norm": 1.1302843148069386,
2017
+ "learning_rate": 2.805582481338044e-06,
2018
+ "loss": 0.008,
2019
+ "step": 2870
2020
+ },
2021
+ {
2022
+ "epoch": 2.0483641536273116,
2023
+ "grad_norm": 0.3587179831514039,
2024
+ "learning_rate": 2.7684760342563045e-06,
2025
+ "loss": 0.0063,
2026
+ "step": 2880
2027
+ },
2028
+ {
2029
+ "epoch": 2.0554765291607398,
2030
+ "grad_norm": 1.116585578193006,
2031
+ "learning_rate": 2.731522430477571e-06,
2032
+ "loss": 0.0066,
2033
+ "step": 2890
2034
+ },
2035
+ {
2036
+ "epoch": 2.062588904694168,
2037
+ "grad_norm": 0.9083509287470979,
2038
+ "learning_rate": 2.694724201057273e-06,
2039
+ "loss": 0.0087,
2040
+ "step": 2900
2041
+ },
2042
+ {
2043
+ "epoch": 2.069701280227596,
2044
+ "grad_norm": 0.6955128987380951,
2045
+ "learning_rate": 2.6580838664088214e-06,
2046
+ "loss": 0.0083,
2047
+ "step": 2910
2048
+ },
2049
+ {
2050
+ "epoch": 2.076813655761024,
2051
+ "grad_norm": 2.217810880330465,
2052
+ "learning_rate": 2.6216039361309753e-06,
2053
+ "loss": 0.0084,
2054
+ "step": 2920
2055
+ },
2056
+ {
2057
+ "epoch": 2.0839260312944523,
2058
+ "grad_norm": 0.833769806548182,
2059
+ "learning_rate": 2.5852869088359495e-06,
2060
+ "loss": 0.0066,
2061
+ "step": 2930
2062
+ },
2063
+ {
2064
+ "epoch": 2.0910384068278804,
2065
+ "grad_norm": 0.7464675150972822,
2066
+ "learning_rate": 2.549135271978275e-06,
2067
+ "loss": 0.0051,
2068
+ "step": 2940
2069
+ },
2070
+ {
2071
+ "epoch": 2.0981507823613086,
2072
+ "grad_norm": 0.2874640695250341,
2073
+ "learning_rate": 2.5131515016844345e-06,
2074
+ "loss": 0.0094,
2075
+ "step": 2950
2076
+ },
2077
+ {
2078
+ "epoch": 2.1052631578947367,
2079
+ "grad_norm": 0.5951223484484282,
2080
+ "learning_rate": 2.4773380625832603e-06,
2081
+ "loss": 0.0073,
2082
+ "step": 2960
2083
+ },
2084
+ {
2085
+ "epoch": 2.112375533428165,
2086
+ "grad_norm": 0.8617405032410067,
2087
+ "learning_rate": 2.4416974076371304e-06,
2088
+ "loss": 0.0063,
2089
+ "step": 2970
2090
+ },
2091
+ {
2092
+ "epoch": 2.119487908961593,
2093
+ "grad_norm": 0.20697744879238947,
2094
+ "learning_rate": 2.406231977973942e-06,
2095
+ "loss": 0.0061,
2096
+ "step": 2980
2097
+ },
2098
+ {
2099
+ "epoch": 2.126600284495021,
2100
+ "grad_norm": 1.0179575970597508,
2101
+ "learning_rate": 2.3709442027199387e-06,
2102
+ "loss": 0.0091,
2103
+ "step": 2990
2104
+ },
2105
+ {
2106
+ "epoch": 2.1337126600284497,
2107
+ "grad_norm": 1.0606767583952494,
2108
+ "learning_rate": 2.3358364988333066e-06,
2109
+ "loss": 0.0063,
2110
+ "step": 3000
2111
+ },
2112
+ {
2113
+ "epoch": 2.140825035561878,
2114
+ "grad_norm": 1.2307112817732728,
2115
+ "learning_rate": 2.3009112709386454e-06,
2116
+ "loss": 0.0072,
2117
+ "step": 3010
2118
+ },
2119
+ {
2120
+ "epoch": 2.147937411095306,
2121
+ "grad_norm": 1.1984078867472323,
2122
+ "learning_rate": 2.2661709111622666e-06,
2123
+ "loss": 0.0074,
2124
+ "step": 3020
2125
+ },
2126
+ {
2127
+ "epoch": 2.155049786628734,
2128
+ "grad_norm": 0.1995779664837118,
2129
+ "learning_rate": 2.2316177989683458e-06,
2130
+ "loss": 0.0048,
2131
+ "step": 3030
2132
+ },
2133
+ {
2134
+ "epoch": 2.1621621621621623,
2135
+ "grad_norm": 0.9273305310197127,
2136
+ "learning_rate": 2.197254300995953e-06,
2137
+ "loss": 0.0072,
2138
+ "step": 3040
2139
+ },
2140
+ {
2141
+ "epoch": 2.1692745376955904,
2142
+ "grad_norm": 0.228767885995747,
2143
+ "learning_rate": 2.163082770896943e-06,
2144
+ "loss": 0.006,
2145
+ "step": 3050
2146
+ },
2147
+ {
2148
+ "epoch": 2.1763869132290186,
2149
+ "grad_norm": 1.1353632110102576,
2150
+ "learning_rate": 2.1291055491747643e-06,
2151
+ "loss": 0.0067,
2152
+ "step": 3060
2153
+ },
2154
+ {
2155
+ "epoch": 2.1834992887624467,
2156
+ "grad_norm": 0.909003973479003,
2157
+ "learning_rate": 2.095324963024137e-06,
2158
+ "loss": 0.0063,
2159
+ "step": 3070
2160
+ },
2161
+ {
2162
+ "epoch": 2.190611664295875,
2163
+ "grad_norm": 0.8569150241839785,
2164
+ "learning_rate": 2.061743326171668e-06,
2165
+ "loss": 0.0047,
2166
+ "step": 3080
2167
+ },
2168
+ {
2169
+ "epoch": 2.197724039829303,
2170
+ "grad_norm": 0.5078332905539804,
2171
+ "learning_rate": 2.02836293871736e-06,
2172
+ "loss": 0.0076,
2173
+ "step": 3090
2174
+ },
2175
+ {
2176
+ "epoch": 2.204836415362731,
2177
+ "grad_norm": 0.206100019331658,
2178
+ "learning_rate": 1.9951860869771e-06,
2179
+ "loss": 0.0051,
2180
+ "step": 3100
2181
+ },
2182
+ {
2183
+ "epoch": 2.2119487908961593,
2184
+ "grad_norm": 0.34329585167252463,
2185
+ "learning_rate": 1.962215043326029e-06,
2186
+ "loss": 0.0058,
2187
+ "step": 3110
2188
+ },
2189
+ {
2190
+ "epoch": 2.2190611664295874,
2191
+ "grad_norm": 0.9524416758915172,
2192
+ "learning_rate": 1.9294520660429284e-06,
2193
+ "loss": 0.0057,
2194
+ "step": 3120
2195
+ },
2196
+ {
2197
+ "epoch": 2.2261735419630155,
2198
+ "grad_norm": 0.2901777267550113,
2199
+ "learning_rate": 1.8968993991555301e-06,
2200
+ "loss": 0.0077,
2201
+ "step": 3130
2202
+ },
2203
+ {
2204
+ "epoch": 2.2332859174964437,
2205
+ "grad_norm": 0.22017782629955687,
2206
+ "learning_rate": 1.8645592722868223e-06,
2207
+ "loss": 0.0063,
2208
+ "step": 3140
2209
+ },
2210
+ {
2211
+ "epoch": 2.240398293029872,
2212
+ "grad_norm": 0.38133062392097455,
2213
+ "learning_rate": 1.8324339005023273e-06,
2214
+ "loss": 0.0072,
2215
+ "step": 3150
2216
+ },
2217
+ {
2218
+ "epoch": 2.2475106685633,
2219
+ "grad_norm": 0.17821853650446573,
2220
+ "learning_rate": 1.8005254841584035e-06,
2221
+ "loss": 0.0053,
2222
+ "step": 3160
2223
+ },
2224
+ {
2225
+ "epoch": 2.2546230440967285,
2226
+ "grad_norm": 0.22314200324222835,
2227
+ "learning_rate": 1.768836208751516e-06,
2228
+ "loss": 0.0043,
2229
+ "step": 3170
2230
+ },
2231
+ {
2232
+ "epoch": 2.2617354196301562,
2233
+ "grad_norm": 0.6640226689598476,
2234
+ "learning_rate": 1.7373682447685624e-06,
2235
+ "loss": 0.0051,
2236
+ "step": 3180
2237
+ },
2238
+ {
2239
+ "epoch": 2.268847795163585,
2240
+ "grad_norm": 0.4186199899663268,
2241
+ "learning_rate": 1.706123747538196e-06,
2242
+ "loss": 0.0053,
2243
+ "step": 3190
2244
+ },
2245
+ {
2246
+ "epoch": 2.275960170697013,
2247
+ "grad_norm": 0.2394022704349156,
2248
+ "learning_rate": 1.6751048570832184e-06,
2249
+ "loss": 0.0058,
2250
+ "step": 3200
2251
+ },
2252
+ {
2253
+ "epoch": 2.283072546230441,
2254
+ "grad_norm": 0.4686051788122248,
2255
+ "learning_rate": 1.6443136979739855e-06,
2256
+ "loss": 0.0041,
2257
+ "step": 3210
2258
+ },
2259
+ {
2260
+ "epoch": 2.2901849217638692,
2261
+ "grad_norm": 0.3836913082140705,
2262
+ "learning_rate": 1.6137523791829007e-06,
2263
+ "loss": 0.0041,
2264
+ "step": 3220
2265
+ },
2266
+ {
2267
+ "epoch": 2.2972972972972974,
2268
+ "grad_norm": 0.16170960660071848,
2269
+ "learning_rate": 1.5834229939399637e-06,
2270
+ "loss": 0.0061,
2271
+ "step": 3230
2272
+ },
2273
+ {
2274
+ "epoch": 2.3044096728307255,
2275
+ "grad_norm": 0.18200293554129154,
2276
+ "learning_rate": 1.5533276195893987e-06,
2277
+ "loss": 0.005,
2278
+ "step": 3240
2279
+ },
2280
+ {
2281
+ "epoch": 2.3115220483641536,
2282
+ "grad_norm": 0.23940834550194912,
2283
+ "learning_rate": 1.5234683174473669e-06,
2284
+ "loss": 0.0046,
2285
+ "step": 3250
2286
+ },
2287
+ {
2288
+ "epoch": 2.318634423897582,
2289
+ "grad_norm": 0.24406884268015908,
2290
+ "learning_rate": 1.493847132660789e-06,
2291
+ "loss": 0.0048,
2292
+ "step": 3260
2293
+ },
2294
+ {
2295
+ "epoch": 2.32574679943101,
2296
+ "grad_norm": 0.26509665588494075,
2297
+ "learning_rate": 1.4644660940672628e-06,
2298
+ "loss": 0.0059,
2299
+ "step": 3270
2300
+ },
2301
+ {
2302
+ "epoch": 2.332859174964438,
2303
+ "grad_norm": 0.475162427962314,
2304
+ "learning_rate": 1.435327214056103e-06,
2305
+ "loss": 0.0051,
2306
+ "step": 3280
2307
+ },
2308
+ {
2309
+ "epoch": 2.339971550497866,
2310
+ "grad_norm": 0.30098307863573437,
2311
+ "learning_rate": 1.406432488430508e-06,
2312
+ "loss": 0.005,
2313
+ "step": 3290
2314
+ },
2315
+ {
2316
+ "epoch": 2.3470839260312943,
2317
+ "grad_norm": 0.20931527074041337,
2318
+ "learning_rate": 1.3777838962708602e-06,
2319
+ "loss": 0.0046,
2320
+ "step": 3300
2321
+ },
2322
+ {
2323
+ "epoch": 2.3541963015647225,
2324
+ "grad_norm": 0.22874545442845454,
2325
+ "learning_rate": 1.3493833997991745e-06,
2326
+ "loss": 0.0041,
2327
+ "step": 3310
2328
+ },
2329
+ {
2330
+ "epoch": 2.3613086770981506,
2331
+ "grad_norm": 1.4075066556310636,
2332
+ "learning_rate": 1.3212329442446985e-06,
2333
+ "loss": 0.0058,
2334
+ "step": 3320
2335
+ },
2336
+ {
2337
+ "epoch": 2.3684210526315788,
2338
+ "grad_norm": 0.8975809394063826,
2339
+ "learning_rate": 1.2933344577106822e-06,
2340
+ "loss": 0.005,
2341
+ "step": 3330
2342
+ },
2343
+ {
2344
+ "epoch": 2.3755334281650073,
2345
+ "grad_norm": 0.4148231917835156,
2346
+ "learning_rate": 1.2656898510423122e-06,
2347
+ "loss": 0.0052,
2348
+ "step": 3340
2349
+ },
2350
+ {
2351
+ "epoch": 2.382645803698435,
2352
+ "grad_norm": 0.11195947556497522,
2353
+ "learning_rate": 1.2383010176958372e-06,
2354
+ "loss": 0.0048,
2355
+ "step": 3350
2356
+ },
2357
+ {
2358
+ "epoch": 2.3897581792318636,
2359
+ "grad_norm": 0.26661464526041523,
2360
+ "learning_rate": 1.2111698336088717e-06,
2361
+ "loss": 0.0054,
2362
+ "step": 3360
2363
+ },
2364
+ {
2365
+ "epoch": 2.3968705547652918,
2366
+ "grad_norm": 1.370337214123434,
2367
+ "learning_rate": 1.1842981570719237e-06,
2368
+ "loss": 0.0048,
2369
+ "step": 3370
2370
+ },
2371
+ {
2372
+ "epoch": 2.40398293029872,
2373
+ "grad_norm": 0.26207335784094793,
2374
+ "learning_rate": 1.157687828601094e-06,
2375
+ "loss": 0.0047,
2376
+ "step": 3380
2377
+ },
2378
+ {
2379
+ "epoch": 2.411095305832148,
2380
+ "grad_norm": 0.1752729581013448,
2381
+ "learning_rate": 1.1313406708120327e-06,
2382
+ "loss": 0.0039,
2383
+ "step": 3390
2384
+ },
2385
+ {
2386
+ "epoch": 2.418207681365576,
2387
+ "grad_norm": 0.2700693202909992,
2388
+ "learning_rate": 1.1052584882950896e-06,
2389
+ "loss": 0.0043,
2390
+ "step": 3400
2391
+ },
2392
+ {
2393
+ "epoch": 2.4253200568990043,
2394
+ "grad_norm": 1.3868146763763338,
2395
+ "learning_rate": 1.0794430674917262e-06,
2396
+ "loss": 0.0036,
2397
+ "step": 3410
2398
+ },
2399
+ {
2400
+ "epoch": 2.4324324324324325,
2401
+ "grad_norm": 0.5361814766521613,
2402
+ "learning_rate": 1.0538961765721429e-06,
2403
+ "loss": 0.0049,
2404
+ "step": 3420
2405
+ },
2406
+ {
2407
+ "epoch": 2.4395448079658606,
2408
+ "grad_norm": 0.2257026998579445,
2409
+ "learning_rate": 1.0286195653141822e-06,
2410
+ "loss": 0.0044,
2411
+ "step": 3430
2412
+ },
2413
+ {
2414
+ "epoch": 2.4466571834992887,
2415
+ "grad_norm": 0.28821507076356073,
2416
+ "learning_rate": 1.0036149649834786e-06,
2417
+ "loss": 0.0041,
2418
+ "step": 3440
2419
+ },
2420
+ {
2421
+ "epoch": 2.453769559032717,
2422
+ "grad_norm": 0.20288584422361874,
2423
+ "learning_rate": 9.788840882148803e-07,
2424
+ "loss": 0.0044,
2425
+ "step": 3450
2426
+ },
2427
+ {
2428
+ "epoch": 2.460881934566145,
2429
+ "grad_norm": 0.2961984403628135,
2430
+ "learning_rate": 9.544286288951393e-07,
2431
+ "loss": 0.0035,
2432
+ "step": 3460
2433
+ },
2434
+ {
2435
+ "epoch": 2.467994310099573,
2436
+ "grad_norm": 0.34744720835705395,
2437
+ "learning_rate": 9.302502620469073e-07,
2438
+ "loss": 0.0046,
2439
+ "step": 3470
2440
+ },
2441
+ {
2442
+ "epoch": 2.4751066856330013,
2443
+ "grad_norm": 0.21259678229337609,
2444
+ "learning_rate": 9.063506437139901e-07,
2445
+ "loss": 0.0039,
2446
+ "step": 3480
2447
+ },
2448
+ {
2449
+ "epoch": 2.4822190611664294,
2450
+ "grad_norm": 0.18018604906671717,
2451
+ "learning_rate": 8.827314108479357e-07,
2452
+ "loss": 0.0039,
2453
+ "step": 3490
2454
+ },
2455
+ {
2456
+ "epoch": 2.4893314366998576,
2457
+ "grad_norm": 0.2326353801367776,
2458
+ "learning_rate": 8.593941811959078e-07,
2459
+ "loss": 0.0038,
2460
+ "step": 3500
2461
+ },
2462
+ {
2463
+ "epoch": 2.496443812233286,
2464
+ "grad_norm": 0.1741953097808654,
2465
+ "learning_rate": 8.363405531898833e-07,
2466
+ "loss": 0.004,
2467
+ "step": 3510
2468
+ },
2469
+ {
2470
+ "epoch": 2.503556187766714,
2471
+ "grad_norm": 0.25494195054679114,
2472
+ "learning_rate": 8.135721058371681e-07,
2473
+ "loss": 0.0038,
2474
+ "step": 3520
2475
+ },
2476
+ {
2477
+ "epoch": 2.5106685633001424,
2478
+ "grad_norm": 0.18154830083734025,
2479
+ "learning_rate": 7.910903986122537e-07,
2480
+ "loss": 0.0024,
2481
+ "step": 3530
2482
+ },
2483
+ {
2484
+ "epoch": 2.5177809388335706,
2485
+ "grad_norm": 0.21685694657911553,
2486
+ "learning_rate": 7.688969713499983e-07,
2487
+ "loss": 0.0037,
2488
+ "step": 3540
2489
+ },
2490
+ {
2491
+ "epoch": 2.5248933143669987,
2492
+ "grad_norm": 0.22019585417284554,
2493
+ "learning_rate": 7.469933441401606e-07,
2494
+ "loss": 0.0041,
2495
+ "step": 3550
2496
+ },
2497
+ {
2498
+ "epoch": 2.532005689900427,
2499
+ "grad_norm": 0.12503238568854871,
2500
+ "learning_rate": 7.253810172232867e-07,
2501
+ "loss": 0.0033,
2502
+ "step": 3560
2503
+ },
2504
+ {
2505
+ "epoch": 2.539118065433855,
2506
+ "grad_norm": 0.20164607745958418,
2507
+ "learning_rate": 7.040614708879489e-07,
2508
+ "loss": 0.0036,
2509
+ "step": 3570
2510
+ },
2511
+ {
2512
+ "epoch": 2.546230440967283,
2513
+ "grad_norm": 1.1353152225303087,
2514
+ "learning_rate": 6.830361653693673e-07,
2515
+ "loss": 0.0037,
2516
+ "step": 3580
2517
+ },
2518
+ {
2519
+ "epoch": 2.5533428165007113,
2520
+ "grad_norm": 0.25954463871540623,
2521
+ "learning_rate": 6.623065407493801e-07,
2522
+ "loss": 0.0037,
2523
+ "step": 3590
2524
+ },
2525
+ {
2526
+ "epoch": 2.5604551920341394,
2527
+ "grad_norm": 0.17926285547151083,
2528
+ "learning_rate": 6.418740168578208e-07,
2529
+ "loss": 0.0033,
2530
+ "step": 3600
2531
+ },
2532
+ {
2533
+ "epoch": 2.5675675675675675,
2534
+ "grad_norm": 0.15055900043010326,
2535
+ "learning_rate": 6.217399931752627e-07,
2536
+ "loss": 0.0035,
2537
+ "step": 3610
2538
+ },
2539
+ {
2540
+ "epoch": 2.5746799431009957,
2541
+ "grad_norm": 0.18791412690022857,
2542
+ "learning_rate": 6.019058487371687e-07,
2543
+ "loss": 0.0033,
2544
+ "step": 3620
2545
+ },
2546
+ {
2547
+ "epoch": 2.581792318634424,
2548
+ "grad_norm": 0.11425352927323033,
2549
+ "learning_rate": 5.82372942039432e-07,
2550
+ "loss": 0.0042,
2551
+ "step": 3630
2552
+ },
2553
+ {
2554
+ "epoch": 2.588904694167852,
2555
+ "grad_norm": 0.3824468109713527,
2556
+ "learning_rate": 5.631426109453364e-07,
2557
+ "loss": 0.004,
2558
+ "step": 3640
2559
+ },
2560
+ {
2561
+ "epoch": 2.59601706970128,
2562
+ "grad_norm": 0.15674551917384533,
2563
+ "learning_rate": 5.44216172593916e-07,
2564
+ "loss": 0.0037,
2565
+ "step": 3650
2566
+ },
2567
+ {
2568
+ "epoch": 2.6031294452347082,
2569
+ "grad_norm": 0.2813443939041295,
2570
+ "learning_rate": 5.255949233097451e-07,
2571
+ "loss": 0.0037,
2572
+ "step": 3660
2573
+ },
2574
+ {
2575
+ "epoch": 2.6102418207681364,
2576
+ "grad_norm": 0.18387812179204338,
2577
+ "learning_rate": 5.072801385141429e-07,
2578
+ "loss": 0.0036,
2579
+ "step": 3670
2580
+ },
2581
+ {
2582
+ "epoch": 2.617354196301565,
2583
+ "grad_norm": 0.2156232450844716,
2584
+ "learning_rate": 4.89273072637827e-07,
2585
+ "loss": 0.0032,
2586
+ "step": 3680
2587
+ },
2588
+ {
2589
+ "epoch": 2.6244665718349927,
2590
+ "grad_norm": 0.12440006889757067,
2591
+ "learning_rate": 4.7157495903498105e-07,
2592
+ "loss": 0.0033,
2593
+ "step": 3690
2594
+ },
2595
+ {
2596
+ "epoch": 2.6315789473684212,
2597
+ "grad_norm": 0.17119738387604694,
2598
+ "learning_rate": 4.541870098987911e-07,
2599
+ "loss": 0.0037,
2600
+ "step": 3700
2601
+ },
2602
+ {
2603
+ "epoch": 2.6386913229018494,
2604
+ "grad_norm": 0.1919029589645196,
2605
+ "learning_rate": 4.371104161784073e-07,
2606
+ "loss": 0.0043,
2607
+ "step": 3710
2608
+ },
2609
+ {
2610
+ "epoch": 2.6458036984352775,
2611
+ "grad_norm": 0.23702321107949612,
2612
+ "learning_rate": 4.2034634749738623e-07,
2613
+ "loss": 0.0032,
2614
+ "step": 3720
2615
+ },
2616
+ {
2617
+ "epoch": 2.6529160739687057,
2618
+ "grad_norm": 0.15697463651810808,
2619
+ "learning_rate": 4.038959520735658e-07,
2620
+ "loss": 0.004,
2621
+ "step": 3730
2622
+ },
2623
+ {
2624
+ "epoch": 2.660028449502134,
2625
+ "grad_norm": 0.09125511769820786,
2626
+ "learning_rate": 3.8776035664043033e-07,
2627
+ "loss": 0.0037,
2628
+ "step": 3740
2629
+ },
2630
+ {
2631
+ "epoch": 2.667140825035562,
2632
+ "grad_norm": 0.17251531382162535,
2633
+ "learning_rate": 3.719406663699349e-07,
2634
+ "loss": 0.0042,
2635
+ "step": 3750
2636
+ },
2637
+ {
2638
+ "epoch": 2.67425320056899,
2639
+ "grad_norm": 0.22855108481819528,
2640
+ "learning_rate": 3.564379647968064e-07,
2641
+ "loss": 0.0035,
2642
+ "step": 3760
2643
+ },
2644
+ {
2645
+ "epoch": 2.681365576102418,
2646
+ "grad_norm": 0.1174830009274809,
2647
+ "learning_rate": 3.4125331374433414e-07,
2648
+ "loss": 0.0038,
2649
+ "step": 3770
2650
+ },
2651
+ {
2652
+ "epoch": 2.6884779516358464,
2653
+ "grad_norm": 0.13196615257533414,
2654
+ "learning_rate": 3.2638775325163517e-07,
2655
+ "loss": 0.0029,
2656
+ "step": 3780
2657
+ },
2658
+ {
2659
+ "epoch": 2.6955903271692745,
2660
+ "grad_norm": 0.16568974053657992,
2661
+ "learning_rate": 3.1184230150243025e-07,
2662
+ "loss": 0.0028,
2663
+ "step": 3790
2664
+ },
2665
+ {
2666
+ "epoch": 2.7027027027027026,
2667
+ "grad_norm": 0.16710801427024333,
2668
+ "learning_rate": 2.9761795475529375e-07,
2669
+ "loss": 0.0031,
2670
+ "step": 3800
2671
+ },
2672
+ {
2673
+ "epoch": 2.7098150782361308,
2674
+ "grad_norm": 0.1500941244877554,
2675
+ "learning_rate": 2.8371568727542486e-07,
2676
+ "loss": 0.0036,
2677
+ "step": 3810
2678
+ },
2679
+ {
2680
+ "epoch": 2.716927453769559,
2681
+ "grad_norm": 0.19067715703132965,
2682
+ "learning_rate": 2.7013645126791446e-07,
2683
+ "loss": 0.003,
2684
+ "step": 3820
2685
+ },
2686
+ {
2687
+ "epoch": 2.724039829302987,
2688
+ "grad_norm": 0.15140629484800455,
2689
+ "learning_rate": 2.5688117681252677e-07,
2690
+ "loss": 0.0033,
2691
+ "step": 3830
2692
+ },
2693
+ {
2694
+ "epoch": 2.731152204836415,
2695
+ "grad_norm": 0.17248672811681454,
2696
+ "learning_rate": 2.439507717999945e-07,
2697
+ "loss": 0.003,
2698
+ "step": 3840
2699
+ },
2700
+ {
2701
+ "epoch": 2.7382645803698438,
2702
+ "grad_norm": 0.1782041915340656,
2703
+ "learning_rate": 2.3134612186983817e-07,
2704
+ "loss": 0.0036,
2705
+ "step": 3850
2706
+ },
2707
+ {
2708
+ "epoch": 2.7453769559032715,
2709
+ "grad_norm": 0.3756662666979349,
2710
+ "learning_rate": 2.1906809034970057e-07,
2711
+ "loss": 0.0035,
2712
+ "step": 3860
2713
+ },
2714
+ {
2715
+ "epoch": 2.7524893314367,
2716
+ "grad_norm": 0.2078367449157142,
2717
+ "learning_rate": 2.0711751819622038e-07,
2718
+ "loss": 0.003,
2719
+ "step": 3870
2720
+ },
2721
+ {
2722
+ "epoch": 2.759601706970128,
2723
+ "grad_norm": 0.29097101889612503,
2724
+ "learning_rate": 1.954952239374286e-07,
2725
+ "loss": 0.0042,
2726
+ "step": 3880
2727
+ },
2728
+ {
2729
+ "epoch": 2.7667140825035563,
2730
+ "grad_norm": 0.25963382600527757,
2731
+ "learning_rate": 1.8420200361669137e-07,
2732
+ "loss": 0.0036,
2733
+ "step": 3890
2734
+ },
2735
+ {
2736
+ "epoch": 2.7738264580369845,
2737
+ "grad_norm": 0.1769468548637021,
2738
+ "learning_rate": 1.732386307381767e-07,
2739
+ "loss": 0.0031,
2740
+ "step": 3900
2741
+ },
2742
+ {
2743
+ "epoch": 2.7809388335704126,
2744
+ "grad_norm": 0.15613753091399799,
2745
+ "learning_rate": 1.6260585621388604e-07,
2746
+ "loss": 0.0034,
2747
+ "step": 3910
2748
+ },
2749
+ {
2750
+ "epoch": 2.7880512091038407,
2751
+ "grad_norm": 0.1956972505836662,
2752
+ "learning_rate": 1.523044083122138e-07,
2753
+ "loss": 0.0044,
2754
+ "step": 3920
2755
+ },
2756
+ {
2757
+ "epoch": 2.795163584637269,
2758
+ "grad_norm": 0.23888957121934698,
2759
+ "learning_rate": 1.4233499260807194e-07,
2760
+ "loss": 0.0045,
2761
+ "step": 3930
2762
+ },
2763
+ {
2764
+ "epoch": 2.802275960170697,
2765
+ "grad_norm": 0.20491135818198022,
2766
+ "learning_rate": 1.326982919345582e-07,
2767
+ "loss": 0.0034,
2768
+ "step": 3940
2769
+ },
2770
+ {
2771
+ "epoch": 2.809388335704125,
2772
+ "grad_norm": 0.16904575085328288,
2773
+ "learning_rate": 1.2339496633619218e-07,
2774
+ "loss": 0.0031,
2775
+ "step": 3950
2776
+ },
2777
+ {
2778
+ "epoch": 2.8165007112375533,
2779
+ "grad_norm": 0.1259555532924781,
2780
+ "learning_rate": 1.1442565302370146e-07,
2781
+ "loss": 0.0029,
2782
+ "step": 3960
2783
+ },
2784
+ {
2785
+ "epoch": 2.8236130867709814,
2786
+ "grad_norm": 0.15248025417153557,
2787
+ "learning_rate": 1.0579096633038411e-07,
2788
+ "loss": 0.0037,
2789
+ "step": 3970
2790
+ },
2791
+ {
2792
+ "epoch": 2.8307254623044096,
2793
+ "grad_norm": 0.12827921470857406,
2794
+ "learning_rate": 9.749149767002197e-08,
2795
+ "loss": 0.0032,
2796
+ "step": 3980
2797
+ },
2798
+ {
2799
+ "epoch": 2.8378378378378377,
2800
+ "grad_norm": 0.22583248679646706,
2801
+ "learning_rate": 8.952781549638412e-08,
2802
+ "loss": 0.004,
2803
+ "step": 3990
2804
+ },
2805
+ {
2806
+ "epoch": 2.844950213371266,
2807
+ "grad_norm": 0.18816430934886938,
2808
+ "learning_rate": 8.190046526428241e-08,
2809
+ "loss": 0.0031,
2810
+ "step": 4000
2811
+ },
2812
+ {
2813
+ "epoch": 2.852062588904694,
2814
+ "grad_norm": 0.23202372767680643,
2815
+ "learning_rate": 7.460996939221643e-08,
2816
+ "loss": 0.0039,
2817
+ "step": 4010
2818
+ },
2819
+ {
2820
+ "epoch": 2.8591749644381226,
2821
+ "grad_norm": 0.1623071297031127,
2822
+ "learning_rate": 6.765682722659151e-08,
2823
+ "loss": 0.0039,
2824
+ "step": 4020
2825
+ },
2826
+ {
2827
+ "epoch": 2.8662873399715503,
2828
+ "grad_norm": 0.2130255450940709,
2829
+ "learning_rate": 6.104151500751609e-08,
2830
+ "loss": 0.0028,
2831
+ "step": 4030
2832
+ },
2833
+ {
2834
+ "epoch": 2.873399715504979,
2835
+ "grad_norm": 0.14259971568207008,
2836
+ "learning_rate": 5.476448583618288e-08,
2837
+ "loss": 0.0039,
2838
+ "step": 4040
2839
+ },
2840
+ {
2841
+ "epoch": 2.8805120910384066,
2842
+ "grad_norm": 0.18255687916100874,
2843
+ "learning_rate": 4.8826169643832464e-08,
2844
+ "loss": 0.0028,
2845
+ "step": 4050
2846
+ },
2847
+ {
2848
+ "epoch": 2.887624466571835,
2849
+ "grad_norm": 0.2053446140861889,
2850
+ "learning_rate": 4.322697316231361e-08,
2851
+ "loss": 0.0039,
2852
+ "step": 4060
2853
+ },
2854
+ {
2855
+ "epoch": 2.8947368421052633,
2856
+ "grad_norm": 0.1604377238062154,
2857
+ "learning_rate": 3.796727989621385e-08,
2858
+ "loss": 0.0027,
2859
+ "step": 4070
2860
+ },
2861
+ {
2862
+ "epoch": 2.9018492176386914,
2863
+ "grad_norm": 0.1963367249030138,
2864
+ "learning_rate": 3.304745009660326e-08,
2865
+ "loss": 0.0033,
2866
+ "step": 4080
2867
+ },
2868
+ {
2869
+ "epoch": 2.9089615931721196,
2870
+ "grad_norm": 0.3357461992161217,
2871
+ "learning_rate": 2.8467820736350903e-08,
2872
+ "loss": 0.0031,
2873
+ "step": 4090
2874
+ },
2875
+ {
2876
+ "epoch": 2.9160739687055477,
2877
+ "grad_norm": 0.11268055230811629,
2878
+ "learning_rate": 2.422870548705103e-08,
2879
+ "loss": 0.0032,
2880
+ "step": 4100
2881
+ },
2882
+ {
2883
+ "epoch": 2.923186344238976,
2884
+ "grad_norm": 0.2544008002680536,
2885
+ "learning_rate": 2.0330394697534726e-08,
2886
+ "loss": 0.0037,
2887
+ "step": 4110
2888
+ },
2889
+ {
2890
+ "epoch": 2.930298719772404,
2891
+ "grad_norm": 0.13380581381300227,
2892
+ "learning_rate": 1.677315537398583e-08,
2893
+ "loss": 0.0038,
2894
+ "step": 4120
2895
+ },
2896
+ {
2897
+ "epoch": 2.937411095305832,
2898
+ "grad_norm": 0.18134475982283993,
2899
+ "learning_rate": 1.355723116165164e-08,
2900
+ "loss": 0.0032,
2901
+ "step": 4130
2902
+ },
2903
+ {
2904
+ "epoch": 2.9445234708392602,
2905
+ "grad_norm": 0.26101935700080225,
2906
+ "learning_rate": 1.0682842328154086e-08,
2907
+ "loss": 0.0033,
2908
+ "step": 4140
2909
+ },
2910
+ {
2911
+ "epoch": 2.9516358463726884,
2912
+ "grad_norm": 0.19538728836785646,
2913
+ "learning_rate": 8.150185748405092e-09,
2914
+ "loss": 0.0037,
2915
+ "step": 4150
2916
+ },
2917
+ {
2918
+ "epoch": 2.9587482219061165,
2919
+ "grad_norm": 0.22029377776143994,
2920
+ "learning_rate": 5.959434891121274e-09,
2921
+ "loss": 0.0034,
2922
+ "step": 4160
2923
+ },
2924
+ {
2925
+ "epoch": 2.9658605974395447,
2926
+ "grad_norm": 0.2119562852212782,
2927
+ "learning_rate": 4.110739806940656e-09,
2928
+ "loss": 0.003,
2929
+ "step": 4170
2930
+ },
2931
+ {
2932
+ "epoch": 2.972972972972973,
2933
+ "grad_norm": 0.21084982886316375,
2934
+ "learning_rate": 2.604227118148117e-09,
2935
+ "loss": 0.0027,
2936
+ "step": 4180
2937
+ },
2938
+ {
2939
+ "epoch": 2.9800853485064014,
2940
+ "grad_norm": 0.30515012873944525,
2941
+ "learning_rate": 1.4400000100017741e-09,
2942
+ "loss": 0.0033,
2943
+ "step": 4190
2944
+ },
2945
+ {
2946
+ "epoch": 2.987197724039829,
2947
+ "grad_norm": 0.15412371556633805,
2948
+ "learning_rate": 6.181382236641887e-10,
2949
+ "loss": 0.0028,
2950
+ "step": 4200
2951
+ },
2952
+ {
2953
+ "epoch": 2.9943100995732577,
2954
+ "grad_norm": 0.19260652338114095,
2955
+ "learning_rate": 1.3869805074284704e-10,
2956
+ "loss": 0.0033,
2957
+ "step": 4210
2958
+ },
2959
+ {
2960
+ "epoch": 3.0,
2961
+ "step": 4218,
2962
+ "total_flos": 187524427284480.0,
2963
+ "train_loss": 0.23043089039047898,
2964
+ "train_runtime": 21192.9138,
2965
+ "train_samples_per_second": 12.735,
2966
+ "train_steps_per_second": 0.199
2967
+ }
2968
+ ],
2969
+ "logging_steps": 10,
2970
+ "max_steps": 4218,
2971
+ "num_input_tokens_seen": 0,
2972
+ "num_train_epochs": 3,
2973
+ "save_steps": 500,
2974
+ "stateful_callbacks": {
2975
+ "TrainerControl": {
2976
+ "args": {
2977
+ "should_epoch_stop": false,
2978
+ "should_evaluate": false,
2979
+ "should_log": false,
2980
+ "should_save": false,
2981
+ "should_training_stop": false
2982
+ },
2983
+ "attributes": {}
2984
+ }
2985
+ },
2986
+ "total_flos": 187524427284480.0,
2987
+ "train_batch_size": 8,
2988
+ "trial_name": null,
2989
+ "trial_params": null
2990
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a55d85531e4493089efe8fd76f07a8d1e560db5972bbc88692f78dde42ec48b0
3
+ size 7889
training_loss.png ADDED