Linksome commited on
Commit
3d3eea5
·
verified ·
1 Parent(s): b7293cc

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
.ipynb_checkpoints/README-checkpoint.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: Llama3.1-8B
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: Configuration_M
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
+ # Configuration_M
18
+
19
+ This model is a fine-tuned version of [/workspace/meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co//workspace/meta-llama/Llama-3.1-8B-Instruct) on the BL_SFT dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-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: 8
45
+ - total_train_batch_size: 256
46
+ - total_eval_batch_size: 32
47
+ - optimizer: Use OptimizerNames.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
+ - num_epochs: 5.0
50
+
51
+ ### Training results
52
+
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - Transformers 4.50.0
58
+ - Pytorch 2.8.0+cu128
59
+ - Datasets 3.6.0
60
+ - Tokenizers 0.21.1
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: Llama3.1-8B
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: Configuration_M
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
+ # Configuration_M
18
+
19
+ This model is a fine-tuned version of [/workspace/meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co//workspace/meta-llama/Llama-3.1-8B-Instruct) on the BL_SFT dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-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: 8
45
+ - total_train_batch_size: 256
46
+ - total_eval_batch_size: 32
47
+ - optimizer: Use OptimizerNames.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
+ - num_epochs: 5.0
50
+
51
+ ### Training results
52
+
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - Transformers 4.50.0
58
+ - Pytorch 2.8.0+cu128
59
+ - Datasets 3.6.0
60
+ - Tokenizers 0.21.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.953191489361702,
3
+ "num_input_tokens_seen": 114425856,
4
+ "total_flos": 182736094494720.0,
5
+ "train_loss": 0.6214238642672585,
6
+ "train_runtime": 10972.3782,
7
+ "train_samples_per_second": 10.27,
8
+ "train_steps_per_second": 0.04
9
+ }
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "head_dim": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 4096,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 14336,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 8,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": {
27
+ "factor": 8.0,
28
+ "high_freq_factor": 4.0,
29
+ "low_freq_factor": 1.0,
30
+ "original_max_position_embeddings": 8192,
31
+ "rope_type": "llama3"
32
+ },
33
+ "rope_theta": 500000.0,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.50.0",
37
+ "use_cache": false,
38
+ "vocab_size": 128256
39
+ }
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
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.50.0"
12
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f45600167990949147e82848f1b69998e7b503bfbe3cc12f8966d609cb0dd1d5
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8cf0becad10908ce8324c0f629993b64145c7a702a47d010bb6f7af0fdef6e5
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:ecd70653e668fbfe441510affd694e551a20af89ee12226d9fc8bf65032e8b9a
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8948d047a37b8dfc2aa143ed7df7e3292d68d8b81ba505598cede3c934579be6
3
+ size 1168138808
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2069 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
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": "<|eom_id|>",
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": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "additional_special_tokens": [
2053
+ "<|eom_id|>"
2054
+ ],
2055
+ "bos_token": "<|begin_of_text|>",
2056
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2057
+ "clean_up_tokenization_spaces": true,
2058
+ "eos_token": "<|eot_id|>",
2059
+ "extra_special_tokens": {},
2060
+ "model_input_names": [
2061
+ "input_ids",
2062
+ "attention_mask"
2063
+ ],
2064
+ "model_max_length": 131072,
2065
+ "pad_token": "<|eot_id|>",
2066
+ "padding_side": "right",
2067
+ "split_special_tokens": false,
2068
+ "tokenizer_class": "PreTrainedTokenizer"
2069
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.953191489361702,
3
+ "num_input_tokens_seen": 114425856,
4
+ "total_flos": 182736094494720.0,
5
+ "train_loss": 0.6214238642672585,
6
+ "train_runtime": 10972.3782,
7
+ "train_samples_per_second": 10.27,
8
+ "train_steps_per_second": 0.04
9
+ }
trainer_log.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,3564 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.953191489361702,
6
+ "eval_steps": 500,
7
+ "global_step": 440,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.011347517730496455,
14
+ "grad_norm": 28.768582165086425,
15
+ "learning_rate": 4.999936276068748e-05,
16
+ "loss": 2.5462,
17
+ "num_input_tokens_seen": 262144,
18
+ "step": 1
19
+ },
20
+ {
21
+ "epoch": 0.02269503546099291,
22
+ "grad_norm": 93.43249139527468,
23
+ "learning_rate": 4.9997451075235834e-05,
24
+ "loss": 4.367,
25
+ "num_input_tokens_seen": 524288,
26
+ "step": 2
27
+ },
28
+ {
29
+ "epoch": 0.03404255319148936,
30
+ "grad_norm": 27.45199589426381,
31
+ "learning_rate": 4.999426504110115e-05,
32
+ "loss": 3.7754,
33
+ "num_input_tokens_seen": 786432,
34
+ "step": 3
35
+ },
36
+ {
37
+ "epoch": 0.04539007092198582,
38
+ "grad_norm": 21.466687229475028,
39
+ "learning_rate": 4.9989804820704735e-05,
40
+ "loss": 3.4412,
41
+ "num_input_tokens_seen": 1048576,
42
+ "step": 4
43
+ },
44
+ {
45
+ "epoch": 0.05673758865248227,
46
+ "grad_norm": 8.511408964141404,
47
+ "learning_rate": 4.99840706414248e-05,
48
+ "loss": 2.5369,
49
+ "num_input_tokens_seen": 1310720,
50
+ "step": 5
51
+ },
52
+ {
53
+ "epoch": 0.06808510638297872,
54
+ "grad_norm": 17.110148299969282,
55
+ "learning_rate": 4.9977062795584893e-05,
56
+ "loss": 2.531,
57
+ "num_input_tokens_seen": 1572864,
58
+ "step": 6
59
+ },
60
+ {
61
+ "epoch": 0.07943262411347518,
62
+ "grad_norm": 8.528722034783323,
63
+ "learning_rate": 4.9968781640439026e-05,
64
+ "loss": 2.2971,
65
+ "num_input_tokens_seen": 1835008,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.09078014184397164,
70
+ "grad_norm": 7.852506050761374,
71
+ "learning_rate": 4.995922759815339e-05,
72
+ "loss": 2.2175,
73
+ "num_input_tokens_seen": 2097152,
74
+ "step": 8
75
+ },
76
+ {
77
+ "epoch": 0.10212765957446808,
78
+ "grad_norm": 5.024862487166255,
79
+ "learning_rate": 4.9948401155784904e-05,
80
+ "loss": 2.0184,
81
+ "num_input_tokens_seen": 2359296,
82
+ "step": 9
83
+ },
84
+ {
85
+ "epoch": 0.11347517730496454,
86
+ "grad_norm": 5.07110237293465,
87
+ "learning_rate": 4.993630286525634e-05,
88
+ "loss": 1.97,
89
+ "num_input_tokens_seen": 2621440,
90
+ "step": 10
91
+ },
92
+ {
93
+ "epoch": 0.12482269503546099,
94
+ "grad_norm": 3.902962877759486,
95
+ "learning_rate": 4.99229333433282e-05,
96
+ "loss": 1.9201,
97
+ "num_input_tokens_seen": 2883584,
98
+ "step": 11
99
+ },
100
+ {
101
+ "epoch": 0.13617021276595745,
102
+ "grad_norm": 3.6676315365476855,
103
+ "learning_rate": 4.9908293271567286e-05,
104
+ "loss": 1.8835,
105
+ "num_input_tokens_seen": 3145728,
106
+ "step": 12
107
+ },
108
+ {
109
+ "epoch": 0.1475177304964539,
110
+ "grad_norm": 2.929600242853849,
111
+ "learning_rate": 4.9892383396311934e-05,
112
+ "loss": 1.808,
113
+ "num_input_tokens_seen": 3407872,
114
+ "step": 13
115
+ },
116
+ {
117
+ "epoch": 0.15886524822695036,
118
+ "grad_norm": 2.5508693562661717,
119
+ "learning_rate": 4.987520452863399e-05,
120
+ "loss": 1.7956,
121
+ "num_input_tokens_seen": 3670016,
122
+ "step": 14
123
+ },
124
+ {
125
+ "epoch": 0.1702127659574468,
126
+ "grad_norm": 2.2262214099883053,
127
+ "learning_rate": 4.985675754429744e-05,
128
+ "loss": 1.781,
129
+ "num_input_tokens_seen": 3932160,
130
+ "step": 15
131
+ },
132
+ {
133
+ "epoch": 0.18156028368794327,
134
+ "grad_norm": 2.8994102519435656,
135
+ "learning_rate": 4.9837043383713753e-05,
136
+ "loss": 1.7132,
137
+ "num_input_tokens_seen": 4194304,
138
+ "step": 16
139
+ },
140
+ {
141
+ "epoch": 0.19290780141843972,
142
+ "grad_norm": 3.2652620723767845,
143
+ "learning_rate": 4.981606305189401e-05,
144
+ "loss": 1.7316,
145
+ "num_input_tokens_seen": 4456448,
146
+ "step": 17
147
+ },
148
+ {
149
+ "epoch": 0.20425531914893616,
150
+ "grad_norm": 2.588037121879393,
151
+ "learning_rate": 4.979381761839757e-05,
152
+ "loss": 1.7198,
153
+ "num_input_tokens_seen": 4718592,
154
+ "step": 18
155
+ },
156
+ {
157
+ "epoch": 0.21560283687943263,
158
+ "grad_norm": 1.9459781834170677,
159
+ "learning_rate": 4.9770308217277614e-05,
160
+ "loss": 1.6976,
161
+ "num_input_tokens_seen": 4980736,
162
+ "step": 19
163
+ },
164
+ {
165
+ "epoch": 0.22695035460992907,
166
+ "grad_norm": 4.291046579259317,
167
+ "learning_rate": 4.9745536047023324e-05,
168
+ "loss": 1.7159,
169
+ "num_input_tokens_seen": 5242880,
170
+ "step": 20
171
+ },
172
+ {
173
+ "epoch": 0.23829787234042554,
174
+ "grad_norm": 1.9625030923747173,
175
+ "learning_rate": 4.971950237049874e-05,
176
+ "loss": 1.6871,
177
+ "num_input_tokens_seen": 5505024,
178
+ "step": 21
179
+ },
180
+ {
181
+ "epoch": 0.24964539007092199,
182
+ "grad_norm": 3.677910756835627,
183
+ "learning_rate": 4.9692208514878444e-05,
184
+ "loss": 1.641,
185
+ "num_input_tokens_seen": 5767168,
186
+ "step": 22
187
+ },
188
+ {
189
+ "epoch": 0.26099290780141843,
190
+ "grad_norm": 2.2017196904664247,
191
+ "learning_rate": 4.966365587157986e-05,
192
+ "loss": 1.6336,
193
+ "num_input_tokens_seen": 6029312,
194
+ "step": 23
195
+ },
196
+ {
197
+ "epoch": 0.2723404255319149,
198
+ "grad_norm": 2.9082791522352958,
199
+ "learning_rate": 4.963384589619233e-05,
200
+ "loss": 1.6184,
201
+ "num_input_tokens_seen": 6291456,
202
+ "step": 24
203
+ },
204
+ {
205
+ "epoch": 0.28368794326241137,
206
+ "grad_norm": 2.306973394969553,
207
+ "learning_rate": 4.96027801084029e-05,
208
+ "loss": 1.6175,
209
+ "num_input_tokens_seen": 6553600,
210
+ "step": 25
211
+ },
212
+ {
213
+ "epoch": 0.2950354609929078,
214
+ "grad_norm": 1.8276771179473579,
215
+ "learning_rate": 4.957046009191889e-05,
216
+ "loss": 1.6145,
217
+ "num_input_tokens_seen": 6815744,
218
+ "step": 26
219
+ },
220
+ {
221
+ "epoch": 0.30638297872340425,
222
+ "grad_norm": 2.7024583313160213,
223
+ "learning_rate": 4.95368874943871e-05,
224
+ "loss": 1.5905,
225
+ "num_input_tokens_seen": 7077888,
226
+ "step": 27
227
+ },
228
+ {
229
+ "epoch": 0.3177304964539007,
230
+ "grad_norm": 1.8227465911208784,
231
+ "learning_rate": 4.9502064027309836e-05,
232
+ "loss": 1.5847,
233
+ "num_input_tokens_seen": 7340032,
234
+ "step": 28
235
+ },
236
+ {
237
+ "epoch": 0.32907801418439714,
238
+ "grad_norm": 2.189585770318853,
239
+ "learning_rate": 4.946599146595769e-05,
240
+ "loss": 1.5862,
241
+ "num_input_tokens_seen": 7602176,
242
+ "step": 29
243
+ },
244
+ {
245
+ "epoch": 0.3404255319148936,
246
+ "grad_norm": 1.6963880678360608,
247
+ "learning_rate": 4.942867164927899e-05,
248
+ "loss": 1.5856,
249
+ "num_input_tokens_seen": 7864320,
250
+ "step": 30
251
+ },
252
+ {
253
+ "epoch": 0.3517730496453901,
254
+ "grad_norm": 1.884475186213032,
255
+ "learning_rate": 4.9390106479806085e-05,
256
+ "loss": 1.5462,
257
+ "num_input_tokens_seen": 8126464,
258
+ "step": 31
259
+ },
260
+ {
261
+ "epoch": 0.36312056737588655,
262
+ "grad_norm": 1.7633790709929305,
263
+ "learning_rate": 4.935029792355834e-05,
264
+ "loss": 1.5519,
265
+ "num_input_tokens_seen": 8388608,
266
+ "step": 32
267
+ },
268
+ {
269
+ "epoch": 0.37446808510638296,
270
+ "grad_norm": 1.6293655236791516,
271
+ "learning_rate": 4.9309248009941914e-05,
272
+ "loss": 1.5426,
273
+ "num_input_tokens_seen": 8650752,
274
+ "step": 33
275
+ },
276
+ {
277
+ "epoch": 0.38581560283687943,
278
+ "grad_norm": 1.6363171652251638,
279
+ "learning_rate": 4.9266958831646315e-05,
280
+ "loss": 1.5179,
281
+ "num_input_tokens_seen": 8912896,
282
+ "step": 34
283
+ },
284
+ {
285
+ "epoch": 0.3971631205673759,
286
+ "grad_norm": 1.76404697988344,
287
+ "learning_rate": 4.922343254453768e-05,
288
+ "loss": 1.5046,
289
+ "num_input_tokens_seen": 9175040,
290
+ "step": 35
291
+ },
292
+ {
293
+ "epoch": 0.4085106382978723,
294
+ "grad_norm": 1.8922889495300352,
295
+ "learning_rate": 4.917867136754893e-05,
296
+ "loss": 1.5147,
297
+ "num_input_tokens_seen": 9437184,
298
+ "step": 36
299
+ },
300
+ {
301
+ "epoch": 0.4198581560283688,
302
+ "grad_norm": 1.4943749144982619,
303
+ "learning_rate": 4.913267758256658e-05,
304
+ "loss": 1.5326,
305
+ "num_input_tokens_seen": 9699328,
306
+ "step": 37
307
+ },
308
+ {
309
+ "epoch": 0.43120567375886526,
310
+ "grad_norm": 1.652782449680942,
311
+ "learning_rate": 4.9085453534314476e-05,
312
+ "loss": 1.5253,
313
+ "num_input_tokens_seen": 9961472,
314
+ "step": 38
315
+ },
316
+ {
317
+ "epoch": 0.4425531914893617,
318
+ "grad_norm": 1.8558129403608419,
319
+ "learning_rate": 4.9037001630234215e-05,
320
+ "loss": 1.5003,
321
+ "num_input_tokens_seen": 10223616,
322
+ "step": 39
323
+ },
324
+ {
325
+ "epoch": 0.45390070921985815,
326
+ "grad_norm": 1.664990274441562,
327
+ "learning_rate": 4.898732434036244e-05,
328
+ "loss": 1.5021,
329
+ "num_input_tokens_seen": 10485760,
330
+ "step": 40
331
+ },
332
+ {
333
+ "epoch": 0.4652482269503546,
334
+ "grad_norm": 1.7198271557244196,
335
+ "learning_rate": 4.893642419720491e-05,
336
+ "loss": 1.4748,
337
+ "num_input_tokens_seen": 10747904,
338
+ "step": 41
339
+ },
340
+ {
341
+ "epoch": 0.4765957446808511,
342
+ "grad_norm": 1.7242786140938589,
343
+ "learning_rate": 4.888430379560742e-05,
344
+ "loss": 1.5064,
345
+ "num_input_tokens_seen": 11010048,
346
+ "step": 42
347
+ },
348
+ {
349
+ "epoch": 0.4879432624113475,
350
+ "grad_norm": 1.289994987213828,
351
+ "learning_rate": 4.883096579262346e-05,
352
+ "loss": 1.4787,
353
+ "num_input_tokens_seen": 11272192,
354
+ "step": 43
355
+ },
356
+ {
357
+ "epoch": 0.49929078014184397,
358
+ "grad_norm": 2.0636727883365693,
359
+ "learning_rate": 4.877641290737884e-05,
360
+ "loss": 1.5032,
361
+ "num_input_tokens_seen": 11534336,
362
+ "step": 44
363
+ },
364
+ {
365
+ "epoch": 0.5106382978723404,
366
+ "grad_norm": 1.50384393546133,
367
+ "learning_rate": 4.872064792093299e-05,
368
+ "loss": 1.5017,
369
+ "num_input_tokens_seen": 11796480,
370
+ "step": 45
371
+ },
372
+ {
373
+ "epoch": 0.5219858156028369,
374
+ "grad_norm": 1.7274141300795698,
375
+ "learning_rate": 4.866367367613725e-05,
376
+ "loss": 1.4899,
377
+ "num_input_tokens_seen": 12058624,
378
+ "step": 46
379
+ },
380
+ {
381
+ "epoch": 0.5333333333333333,
382
+ "grad_norm": 1.4776150452075232,
383
+ "learning_rate": 4.86054930774899e-05,
384
+ "loss": 1.4501,
385
+ "num_input_tokens_seen": 12320768,
386
+ "step": 47
387
+ },
388
+ {
389
+ "epoch": 0.5446808510638298,
390
+ "grad_norm": 2.0772123001061296,
391
+ "learning_rate": 4.854610909098812e-05,
392
+ "loss": 1.4729,
393
+ "num_input_tokens_seen": 12582912,
394
+ "step": 48
395
+ },
396
+ {
397
+ "epoch": 0.5560283687943263,
398
+ "grad_norm": 1.4784518476625488,
399
+ "learning_rate": 4.848552474397676e-05,
400
+ "loss": 1.4639,
401
+ "num_input_tokens_seen": 12845056,
402
+ "step": 49
403
+ },
404
+ {
405
+ "epoch": 0.5673758865248227,
406
+ "grad_norm": 1.5172983637361528,
407
+ "learning_rate": 4.842374312499405e-05,
408
+ "loss": 1.4626,
409
+ "num_input_tokens_seen": 13107200,
410
+ "step": 50
411
+ },
412
+ {
413
+ "epoch": 0.5787234042553191,
414
+ "grad_norm": 1.590645940567932,
415
+ "learning_rate": 4.836076738361408e-05,
416
+ "loss": 1.4767,
417
+ "num_input_tokens_seen": 13369344,
418
+ "step": 51
419
+ },
420
+ {
421
+ "epoch": 0.5900709219858156,
422
+ "grad_norm": 1.5086587054410023,
423
+ "learning_rate": 4.829660073028631e-05,
424
+ "loss": 1.453,
425
+ "num_input_tokens_seen": 13631488,
426
+ "step": 52
427
+ },
428
+ {
429
+ "epoch": 0.601418439716312,
430
+ "grad_norm": 1.4196104282840498,
431
+ "learning_rate": 4.823124643617187e-05,
432
+ "loss": 1.4406,
433
+ "num_input_tokens_seen": 13893632,
434
+ "step": 53
435
+ },
436
+ {
437
+ "epoch": 0.6127659574468085,
438
+ "grad_norm": 1.5140910517728237,
439
+ "learning_rate": 4.8164707832976783e-05,
440
+ "loss": 1.4498,
441
+ "num_input_tokens_seen": 14155776,
442
+ "step": 54
443
+ },
444
+ {
445
+ "epoch": 0.624113475177305,
446
+ "grad_norm": 1.3210319443750393,
447
+ "learning_rate": 4.8096988312782174e-05,
448
+ "loss": 1.4288,
449
+ "num_input_tokens_seen": 14417920,
450
+ "step": 55
451
+ },
452
+ {
453
+ "epoch": 0.6354609929078014,
454
+ "grad_norm": 1.5120891443494813,
455
+ "learning_rate": 4.802809132787125e-05,
456
+ "loss": 1.4267,
457
+ "num_input_tokens_seen": 14680064,
458
+ "step": 56
459
+ },
460
+ {
461
+ "epoch": 0.6468085106382979,
462
+ "grad_norm": 1.7385310877259594,
463
+ "learning_rate": 4.7958020390553426e-05,
464
+ "loss": 1.4775,
465
+ "num_input_tokens_seen": 14942208,
466
+ "step": 57
467
+ },
468
+ {
469
+ "epoch": 0.6581560283687943,
470
+ "grad_norm": 1.3858014810326225,
471
+ "learning_rate": 4.7886779072985156e-05,
472
+ "loss": 1.4387,
473
+ "num_input_tokens_seen": 15204352,
474
+ "step": 58
475
+ },
476
+ {
477
+ "epoch": 0.6695035460992907,
478
+ "grad_norm": 1.8605931025096338,
479
+ "learning_rate": 4.78143710069879e-05,
480
+ "loss": 1.4093,
481
+ "num_input_tokens_seen": 15466496,
482
+ "step": 59
483
+ },
484
+ {
485
+ "epoch": 0.6808510638297872,
486
+ "grad_norm": 1.3831101615966328,
487
+ "learning_rate": 4.774079988386296e-05,
488
+ "loss": 1.421,
489
+ "num_input_tokens_seen": 15728640,
490
+ "step": 60
491
+ },
492
+ {
493
+ "epoch": 0.6921985815602837,
494
+ "grad_norm": 1.6322196763337964,
495
+ "learning_rate": 4.766606945420329e-05,
496
+ "loss": 1.4411,
497
+ "num_input_tokens_seen": 15990784,
498
+ "step": 61
499
+ },
500
+ {
501
+ "epoch": 0.7035460992907802,
502
+ "grad_norm": 1.6072671722268586,
503
+ "learning_rate": 4.759018352770229e-05,
504
+ "loss": 1.4283,
505
+ "num_input_tokens_seen": 16252928,
506
+ "step": 62
507
+ },
508
+ {
509
+ "epoch": 0.7148936170212766,
510
+ "grad_norm": 1.2535166201622518,
511
+ "learning_rate": 4.751314597295963e-05,
512
+ "loss": 1.4526,
513
+ "num_input_tokens_seen": 16515072,
514
+ "step": 63
515
+ },
516
+ {
517
+ "epoch": 0.7262411347517731,
518
+ "grad_norm": 1.5543521846201784,
519
+ "learning_rate": 4.743496071728396e-05,
520
+ "loss": 1.4148,
521
+ "num_input_tokens_seen": 16777216,
522
+ "step": 64
523
+ },
524
+ {
525
+ "epoch": 0.7375886524822695,
526
+ "grad_norm": 1.3594873685564324,
527
+ "learning_rate": 4.735563174649278e-05,
528
+ "loss": 1.3976,
529
+ "num_input_tokens_seen": 17039360,
530
+ "step": 65
531
+ },
532
+ {
533
+ "epoch": 0.7489361702127659,
534
+ "grad_norm": 1.3662132975871213,
535
+ "learning_rate": 4.72751631047092e-05,
536
+ "loss": 1.4137,
537
+ "num_input_tokens_seen": 17301504,
538
+ "step": 66
539
+ },
540
+ {
541
+ "epoch": 0.7602836879432624,
542
+ "grad_norm": 1.2729255728645377,
543
+ "learning_rate": 4.719355889415576e-05,
544
+ "loss": 1.3951,
545
+ "num_input_tokens_seen": 17563648,
546
+ "step": 67
547
+ },
548
+ {
549
+ "epoch": 0.7716312056737589,
550
+ "grad_norm": 1.2598405597617752,
551
+ "learning_rate": 4.711082327494536e-05,
552
+ "loss": 1.4049,
553
+ "num_input_tokens_seen": 17825792,
554
+ "step": 68
555
+ },
556
+ {
557
+ "epoch": 0.7829787234042553,
558
+ "grad_norm": 1.336014117151041,
559
+ "learning_rate": 4.7026960464869116e-05,
560
+ "loss": 1.4167,
561
+ "num_input_tokens_seen": 18087936,
562
+ "step": 69
563
+ },
564
+ {
565
+ "epoch": 0.7943262411347518,
566
+ "grad_norm": 1.4872379534302926,
567
+ "learning_rate": 4.6941974739181395e-05,
568
+ "loss": 1.4048,
569
+ "num_input_tokens_seen": 18350080,
570
+ "step": 70
571
+ },
572
+ {
573
+ "epoch": 0.8056737588652483,
574
+ "grad_norm": 1.2920324415831732,
575
+ "learning_rate": 4.6855870430381816e-05,
576
+ "loss": 1.4083,
577
+ "num_input_tokens_seen": 18612224,
578
+ "step": 71
579
+ },
580
+ {
581
+ "epoch": 0.8170212765957446,
582
+ "grad_norm": 1.6143627607763888,
583
+ "learning_rate": 4.6768651927994434e-05,
584
+ "loss": 1.3906,
585
+ "num_input_tokens_seen": 18874368,
586
+ "step": 72
587
+ },
588
+ {
589
+ "epoch": 0.8283687943262411,
590
+ "grad_norm": 1.2568838039190413,
591
+ "learning_rate": 4.668032367834392e-05,
592
+ "loss": 1.3973,
593
+ "num_input_tokens_seen": 19136512,
594
+ "step": 73
595
+ },
596
+ {
597
+ "epoch": 0.8397163120567376,
598
+ "grad_norm": 1.5547346669542705,
599
+ "learning_rate": 4.6590890184328925e-05,
600
+ "loss": 1.3918,
601
+ "num_input_tokens_seen": 19398656,
602
+ "step": 74
603
+ },
604
+ {
605
+ "epoch": 0.851063829787234,
606
+ "grad_norm": 1.4356818846930628,
607
+ "learning_rate": 4.6500356005192514e-05,
608
+ "loss": 1.3819,
609
+ "num_input_tokens_seen": 19660800,
610
+ "step": 75
611
+ },
612
+ {
613
+ "epoch": 0.8624113475177305,
614
+ "grad_norm": 1.3284920385369607,
615
+ "learning_rate": 4.640872575628973e-05,
616
+ "loss": 1.3933,
617
+ "num_input_tokens_seen": 19922944,
618
+ "step": 76
619
+ },
620
+ {
621
+ "epoch": 0.873758865248227,
622
+ "grad_norm": 1.107701469460885,
623
+ "learning_rate": 4.6316004108852305e-05,
624
+ "loss": 1.4081,
625
+ "num_input_tokens_seen": 20185088,
626
+ "step": 77
627
+ },
628
+ {
629
+ "epoch": 0.8851063829787233,
630
+ "grad_norm": 1.2529354895940894,
631
+ "learning_rate": 4.622219578975057e-05,
632
+ "loss": 1.3801,
633
+ "num_input_tokens_seen": 20447232,
634
+ "step": 78
635
+ },
636
+ {
637
+ "epoch": 0.8964539007092198,
638
+ "grad_norm": 1.3380392380500745,
639
+ "learning_rate": 4.6127305581252414e-05,
640
+ "loss": 1.3655,
641
+ "num_input_tokens_seen": 20709376,
642
+ "step": 79
643
+ },
644
+ {
645
+ "epoch": 0.9078014184397163,
646
+ "grad_norm": 1.2047088627238154,
647
+ "learning_rate": 4.6031338320779534e-05,
648
+ "loss": 1.3896,
649
+ "num_input_tokens_seen": 20971520,
650
+ "step": 80
651
+ },
652
+ {
653
+ "epoch": 0.9191489361702128,
654
+ "grad_norm": 1.4991837815250253,
655
+ "learning_rate": 4.593429890066082e-05,
656
+ "loss": 1.405,
657
+ "num_input_tokens_seen": 21233664,
658
+ "step": 81
659
+ },
660
+ {
661
+ "epoch": 0.9304964539007092,
662
+ "grad_norm": 1.1414547231387788,
663
+ "learning_rate": 4.583619226788294e-05,
664
+ "loss": 1.3843,
665
+ "num_input_tokens_seen": 21495808,
666
+ "step": 82
667
+ },
668
+ {
669
+ "epoch": 0.9418439716312057,
670
+ "grad_norm": 1.4695936511434455,
671
+ "learning_rate": 4.573702342383816e-05,
672
+ "loss": 1.3698,
673
+ "num_input_tokens_seen": 21757952,
674
+ "step": 83
675
+ },
676
+ {
677
+ "epoch": 0.9531914893617022,
678
+ "grad_norm": 1.2845207314880724,
679
+ "learning_rate": 4.563679742406935e-05,
680
+ "loss": 1.3806,
681
+ "num_input_tokens_seen": 22020096,
682
+ "step": 84
683
+ },
684
+ {
685
+ "epoch": 0.9645390070921985,
686
+ "grad_norm": 1.4475613066375035,
687
+ "learning_rate": 4.5535519378012295e-05,
688
+ "loss": 1.3715,
689
+ "num_input_tokens_seen": 22282240,
690
+ "step": 85
691
+ },
692
+ {
693
+ "epoch": 0.975886524822695,
694
+ "grad_norm": 1.4999411758550487,
695
+ "learning_rate": 4.543319444873517e-05,
696
+ "loss": 1.3718,
697
+ "num_input_tokens_seen": 22544384,
698
+ "step": 86
699
+ },
700
+ {
701
+ "epoch": 0.9872340425531915,
702
+ "grad_norm": 1.261663898483524,
703
+ "learning_rate": 4.532982785267541e-05,
704
+ "loss": 1.3564,
705
+ "num_input_tokens_seen": 22806528,
706
+ "step": 87
707
+ },
708
+ {
709
+ "epoch": 0.9985815602836879,
710
+ "grad_norm": 1.3464933652070896,
711
+ "learning_rate": 4.522542485937369e-05,
712
+ "loss": 1.3744,
713
+ "num_input_tokens_seen": 23068672,
714
+ "step": 88
715
+ },
716
+ {
717
+ "epoch": 1.0,
718
+ "grad_norm": 1.3464933652070896,
719
+ "learning_rate": 4.511999079120534e-05,
720
+ "loss": 1.2363,
721
+ "num_input_tokens_seen": 23101440,
722
+ "step": 89
723
+ },
724
+ {
725
+ "epoch": 1.0113475177304965,
726
+ "grad_norm": 3.3795576075508627,
727
+ "learning_rate": 4.5013531023109014e-05,
728
+ "loss": 1.0013,
729
+ "num_input_tokens_seen": 23363584,
730
+ "step": 90
731
+ },
732
+ {
733
+ "epoch": 1.022695035460993,
734
+ "grad_norm": 1.98501369471366,
735
+ "learning_rate": 4.4906050982312664e-05,
736
+ "loss": 1.0396,
737
+ "num_input_tokens_seen": 23625728,
738
+ "step": 91
739
+ },
740
+ {
741
+ "epoch": 1.0340425531914894,
742
+ "grad_norm": 1.7550611786324055,
743
+ "learning_rate": 4.479755614805688e-05,
744
+ "loss": 0.967,
745
+ "num_input_tokens_seen": 23887872,
746
+ "step": 92
747
+ },
748
+ {
749
+ "epoch": 1.0453900709219859,
750
+ "grad_norm": 2.3047442852698063,
751
+ "learning_rate": 4.4688052051315545e-05,
752
+ "loss": 1.0097,
753
+ "num_input_tokens_seen": 24150016,
754
+ "step": 93
755
+ },
756
+ {
757
+ "epoch": 1.0567375886524824,
758
+ "grad_norm": 1.4568858521127028,
759
+ "learning_rate": 4.457754427451389e-05,
760
+ "loss": 0.9699,
761
+ "num_input_tokens_seen": 24412160,
762
+ "step": 94
763
+ },
764
+ {
765
+ "epoch": 1.0680851063829788,
766
+ "grad_norm": 1.9193925592577146,
767
+ "learning_rate": 4.446603845124388e-05,
768
+ "loss": 0.9548,
769
+ "num_input_tokens_seen": 24674304,
770
+ "step": 95
771
+ },
772
+ {
773
+ "epoch": 1.0794326241134753,
774
+ "grad_norm": 1.3493703965773043,
775
+ "learning_rate": 4.4353540265977064e-05,
776
+ "loss": 0.9504,
777
+ "num_input_tokens_seen": 24936448,
778
+ "step": 96
779
+ },
780
+ {
781
+ "epoch": 1.0907801418439715,
782
+ "grad_norm": 1.7615744346425224,
783
+ "learning_rate": 4.4240055453774734e-05,
784
+ "loss": 0.9807,
785
+ "num_input_tokens_seen": 25198592,
786
+ "step": 97
787
+ },
788
+ {
789
+ "epoch": 1.102127659574468,
790
+ "grad_norm": 1.8062764758660264,
791
+ "learning_rate": 4.412558979999558e-05,
792
+ "loss": 0.9363,
793
+ "num_input_tokens_seen": 25460736,
794
+ "step": 98
795
+ },
796
+ {
797
+ "epoch": 1.1134751773049645,
798
+ "grad_norm": 1.7426430146262821,
799
+ "learning_rate": 4.401014914000078e-05,
800
+ "loss": 0.968,
801
+ "num_input_tokens_seen": 25722880,
802
+ "step": 99
803
+ },
804
+ {
805
+ "epoch": 1.124822695035461,
806
+ "grad_norm": 1.5389141278391227,
807
+ "learning_rate": 4.389373935885646e-05,
808
+ "loss": 0.9428,
809
+ "num_input_tokens_seen": 25985024,
810
+ "step": 100
811
+ },
812
+ {
813
+ "epoch": 1.1361702127659574,
814
+ "grad_norm": 1.4116557578228721,
815
+ "learning_rate": 4.3776366391033746e-05,
816
+ "loss": 0.921,
817
+ "num_input_tokens_seen": 26247168,
818
+ "step": 101
819
+ },
820
+ {
821
+ "epoch": 1.147517730496454,
822
+ "grad_norm": 1.4555202749322727,
823
+ "learning_rate": 4.365803622010618e-05,
824
+ "loss": 0.9368,
825
+ "num_input_tokens_seen": 26509312,
826
+ "step": 102
827
+ },
828
+ {
829
+ "epoch": 1.1588652482269504,
830
+ "grad_norm": 1.51393536895009,
831
+ "learning_rate": 4.35387548784447e-05,
832
+ "loss": 0.9424,
833
+ "num_input_tokens_seen": 26771456,
834
+ "step": 103
835
+ },
836
+ {
837
+ "epoch": 1.1702127659574468,
838
+ "grad_norm": 1.3497959200668166,
839
+ "learning_rate": 4.341852844691012e-05,
840
+ "loss": 0.9395,
841
+ "num_input_tokens_seen": 27033600,
842
+ "step": 104
843
+ },
844
+ {
845
+ "epoch": 1.1815602836879433,
846
+ "grad_norm": 1.963720316682781,
847
+ "learning_rate": 4.329736305454314e-05,
848
+ "loss": 0.9575,
849
+ "num_input_tokens_seen": 27295744,
850
+ "step": 105
851
+ },
852
+ {
853
+ "epoch": 1.1929078014184398,
854
+ "grad_norm": 1.5398810468770388,
855
+ "learning_rate": 4.3175264878251845e-05,
856
+ "loss": 0.9087,
857
+ "num_input_tokens_seen": 27557888,
858
+ "step": 106
859
+ },
860
+ {
861
+ "epoch": 1.2042553191489362,
862
+ "grad_norm": 2.249980638617661,
863
+ "learning_rate": 4.305224014249688e-05,
864
+ "loss": 0.9613,
865
+ "num_input_tokens_seen": 27820032,
866
+ "step": 107
867
+ },
868
+ {
869
+ "epoch": 1.2156028368794327,
870
+ "grad_norm": 1.7994413618778806,
871
+ "learning_rate": 4.292829511897409e-05,
872
+ "loss": 0.9336,
873
+ "num_input_tokens_seen": 28082176,
874
+ "step": 108
875
+ },
876
+ {
877
+ "epoch": 1.226950354609929,
878
+ "grad_norm": 2.1172062063526695,
879
+ "learning_rate": 4.280343612629479e-05,
880
+ "loss": 0.9444,
881
+ "num_input_tokens_seen": 28344320,
882
+ "step": 109
883
+ },
884
+ {
885
+ "epoch": 1.2382978723404254,
886
+ "grad_norm": 1.689025623361111,
887
+ "learning_rate": 4.267766952966369e-05,
888
+ "loss": 0.9054,
889
+ "num_input_tokens_seen": 28606464,
890
+ "step": 110
891
+ },
892
+ {
893
+ "epoch": 1.249645390070922,
894
+ "grad_norm": 1.7237793371868935,
895
+ "learning_rate": 4.255100174055434e-05,
896
+ "loss": 0.9391,
897
+ "num_input_tokens_seen": 28868608,
898
+ "step": 111
899
+ },
900
+ {
901
+ "epoch": 1.2609929078014184,
902
+ "grad_norm": 1.5807920095324717,
903
+ "learning_rate": 4.242343921638234e-05,
904
+ "loss": 0.9232,
905
+ "num_input_tokens_seen": 29130752,
906
+ "step": 112
907
+ },
908
+ {
909
+ "epoch": 1.2723404255319148,
910
+ "grad_norm": 1.5455548794679541,
911
+ "learning_rate": 4.22949884601761e-05,
912
+ "loss": 0.9383,
913
+ "num_input_tokens_seen": 29392896,
914
+ "step": 113
915
+ },
916
+ {
917
+ "epoch": 1.2836879432624113,
918
+ "grad_norm": 1.505150180088299,
919
+ "learning_rate": 4.2165656020245336e-05,
920
+ "loss": 0.921,
921
+ "num_input_tokens_seen": 29655040,
922
+ "step": 114
923
+ },
924
+ {
925
+ "epoch": 1.2950354609929078,
926
+ "grad_norm": 1.7329578957192628,
927
+ "learning_rate": 4.2035448489847284e-05,
928
+ "loss": 0.9525,
929
+ "num_input_tokens_seen": 29917184,
930
+ "step": 115
931
+ },
932
+ {
933
+ "epoch": 1.3063829787234043,
934
+ "grad_norm": 1.4120446620663845,
935
+ "learning_rate": 4.1904372506850484e-05,
936
+ "loss": 0.8843,
937
+ "num_input_tokens_seen": 30179328,
938
+ "step": 116
939
+ },
940
+ {
941
+ "epoch": 1.3177304964539007,
942
+ "grad_norm": 1.440521563342665,
943
+ "learning_rate": 4.1772434753396504e-05,
944
+ "loss": 0.9295,
945
+ "num_input_tokens_seen": 30441472,
946
+ "step": 117
947
+ },
948
+ {
949
+ "epoch": 1.3290780141843972,
950
+ "grad_norm": 1.2751014560476446,
951
+ "learning_rate": 4.1639641955559205e-05,
952
+ "loss": 0.965,
953
+ "num_input_tokens_seen": 30703616,
954
+ "step": 118
955
+ },
956
+ {
957
+ "epoch": 1.3404255319148937,
958
+ "grad_norm": 1.353326348573935,
959
+ "learning_rate": 4.1506000883001875e-05,
960
+ "loss": 0.9193,
961
+ "num_input_tokens_seen": 30965760,
962
+ "step": 119
963
+ },
964
+ {
965
+ "epoch": 1.3517730496453901,
966
+ "grad_norm": 1.3458043729465723,
967
+ "learning_rate": 4.137151834863213e-05,
968
+ "loss": 0.9418,
969
+ "num_input_tokens_seen": 31227904,
970
+ "step": 120
971
+ },
972
+ {
973
+ "epoch": 1.3631205673758866,
974
+ "grad_norm": 1.3301133192597863,
975
+ "learning_rate": 4.123620120825459e-05,
976
+ "loss": 0.9139,
977
+ "num_input_tokens_seen": 31490048,
978
+ "step": 121
979
+ },
980
+ {
981
+ "epoch": 1.374468085106383,
982
+ "grad_norm": 1.519558123717531,
983
+ "learning_rate": 4.1100056360221384e-05,
984
+ "loss": 0.9378,
985
+ "num_input_tokens_seen": 31752192,
986
+ "step": 122
987
+ },
988
+ {
989
+ "epoch": 1.3858156028368795,
990
+ "grad_norm": 1.2225151449916911,
991
+ "learning_rate": 4.096309074508046e-05,
992
+ "loss": 0.9334,
993
+ "num_input_tokens_seen": 32014336,
994
+ "step": 123
995
+ },
996
+ {
997
+ "epoch": 1.397163120567376,
998
+ "grad_norm": 1.3505855040891415,
999
+ "learning_rate": 4.082531134522176e-05,
1000
+ "loss": 0.9227,
1001
+ "num_input_tokens_seen": 32276480,
1002
+ "step": 124
1003
+ },
1004
+ {
1005
+ "epoch": 1.4085106382978723,
1006
+ "grad_norm": 1.1984405892159349,
1007
+ "learning_rate": 4.06867251845213e-05,
1008
+ "loss": 0.9232,
1009
+ "num_input_tokens_seen": 32538624,
1010
+ "step": 125
1011
+ },
1012
+ {
1013
+ "epoch": 1.4198581560283687,
1014
+ "grad_norm": 1.2105780592446167,
1015
+ "learning_rate": 4.054733932798306e-05,
1016
+ "loss": 0.9126,
1017
+ "num_input_tokens_seen": 32800768,
1018
+ "step": 126
1019
+ },
1020
+ {
1021
+ "epoch": 1.4312056737588652,
1022
+ "grad_norm": 1.4082252271919538,
1023
+ "learning_rate": 4.0407160881378824e-05,
1024
+ "loss": 0.9026,
1025
+ "num_input_tokens_seen": 33062912,
1026
+ "step": 127
1027
+ },
1028
+ {
1029
+ "epoch": 1.4425531914893617,
1030
+ "grad_norm": 1.242226249471717,
1031
+ "learning_rate": 4.0266196990885955e-05,
1032
+ "loss": 0.9329,
1033
+ "num_input_tokens_seen": 33325056,
1034
+ "step": 128
1035
+ },
1036
+ {
1037
+ "epoch": 1.4539007092198581,
1038
+ "grad_norm": 1.2320327101088704,
1039
+ "learning_rate": 4.012445484272307e-05,
1040
+ "loss": 0.9055,
1041
+ "num_input_tokens_seen": 33587200,
1042
+ "step": 129
1043
+ },
1044
+ {
1045
+ "epoch": 1.4652482269503546,
1046
+ "grad_norm": 1.097364604214534,
1047
+ "learning_rate": 3.9981941662783674e-05,
1048
+ "loss": 0.9505,
1049
+ "num_input_tokens_seen": 33849344,
1050
+ "step": 130
1051
+ },
1052
+ {
1053
+ "epoch": 1.476595744680851,
1054
+ "grad_norm": 1.287506918091485,
1055
+ "learning_rate": 3.9838664716267855e-05,
1056
+ "loss": 0.9205,
1057
+ "num_input_tokens_seen": 34111488,
1058
+ "step": 131
1059
+ },
1060
+ {
1061
+ "epoch": 1.4879432624113476,
1062
+ "grad_norm": 1.1710856488092862,
1063
+ "learning_rate": 3.969463130731183e-05,
1064
+ "loss": 0.9757,
1065
+ "num_input_tokens_seen": 34373632,
1066
+ "step": 132
1067
+ },
1068
+ {
1069
+ "epoch": 1.499290780141844,
1070
+ "grad_norm": 1.1761537048031911,
1071
+ "learning_rate": 3.954984877861565e-05,
1072
+ "loss": 0.9375,
1073
+ "num_input_tokens_seen": 34635776,
1074
+ "step": 133
1075
+ },
1076
+ {
1077
+ "epoch": 1.5106382978723403,
1078
+ "grad_norm": 1.211479891065261,
1079
+ "learning_rate": 3.9404324511068825e-05,
1080
+ "loss": 0.9631,
1081
+ "num_input_tokens_seen": 34897920,
1082
+ "step": 134
1083
+ },
1084
+ {
1085
+ "epoch": 1.5219858156028367,
1086
+ "grad_norm": 1.1227811129578062,
1087
+ "learning_rate": 3.92580659233741e-05,
1088
+ "loss": 0.9413,
1089
+ "num_input_tokens_seen": 35160064,
1090
+ "step": 135
1091
+ },
1092
+ {
1093
+ "epoch": 1.5333333333333332,
1094
+ "grad_norm": 1.2565270122423726,
1095
+ "learning_rate": 3.911108047166924e-05,
1096
+ "loss": 0.9436,
1097
+ "num_input_tokens_seen": 35422208,
1098
+ "step": 136
1099
+ },
1100
+ {
1101
+ "epoch": 1.5446808510638297,
1102
+ "grad_norm": 1.194511509764168,
1103
+ "learning_rate": 3.8963375649146866e-05,
1104
+ "loss": 0.9537,
1105
+ "num_input_tokens_seen": 35684352,
1106
+ "step": 137
1107
+ },
1108
+ {
1109
+ "epoch": 1.5560283687943262,
1110
+ "grad_norm": 1.147953601769395,
1111
+ "learning_rate": 3.881495898567257e-05,
1112
+ "loss": 0.9279,
1113
+ "num_input_tokens_seen": 35946496,
1114
+ "step": 138
1115
+ },
1116
+ {
1117
+ "epoch": 1.5673758865248226,
1118
+ "grad_norm": 1.128582567310139,
1119
+ "learning_rate": 3.866583804740095e-05,
1120
+ "loss": 0.9053,
1121
+ "num_input_tokens_seen": 36208640,
1122
+ "step": 139
1123
+ },
1124
+ {
1125
+ "epoch": 1.578723404255319,
1126
+ "grad_norm": 1.1883091515233541,
1127
+ "learning_rate": 3.851602043638994e-05,
1128
+ "loss": 0.9499,
1129
+ "num_input_tokens_seen": 36470784,
1130
+ "step": 140
1131
+ },
1132
+ {
1133
+ "epoch": 1.5900709219858156,
1134
+ "grad_norm": 1.154451792017842,
1135
+ "learning_rate": 3.8365513790213265e-05,
1136
+ "loss": 0.9262,
1137
+ "num_input_tokens_seen": 36732928,
1138
+ "step": 141
1139
+ },
1140
+ {
1141
+ "epoch": 1.601418439716312,
1142
+ "grad_norm": 1.2185944157116932,
1143
+ "learning_rate": 3.821432578157105e-05,
1144
+ "loss": 0.934,
1145
+ "num_input_tokens_seen": 36995072,
1146
+ "step": 142
1147
+ },
1148
+ {
1149
+ "epoch": 1.6127659574468085,
1150
+ "grad_norm": 1.1779364162194832,
1151
+ "learning_rate": 3.8062464117898724e-05,
1152
+ "loss": 0.9588,
1153
+ "num_input_tokens_seen": 37257216,
1154
+ "step": 143
1155
+ },
1156
+ {
1157
+ "epoch": 1.624113475177305,
1158
+ "grad_norm": 1.1736568320305454,
1159
+ "learning_rate": 3.790993654097405e-05,
1160
+ "loss": 0.9616,
1161
+ "num_input_tokens_seen": 37519360,
1162
+ "step": 144
1163
+ },
1164
+ {
1165
+ "epoch": 1.6354609929078014,
1166
+ "grad_norm": 1.174721701784409,
1167
+ "learning_rate": 3.77567508265225e-05,
1168
+ "loss": 0.9551,
1169
+ "num_input_tokens_seen": 37781504,
1170
+ "step": 145
1171
+ },
1172
+ {
1173
+ "epoch": 1.646808510638298,
1174
+ "grad_norm": 1.1583059430503744,
1175
+ "learning_rate": 3.76029147838208e-05,
1176
+ "loss": 0.9636,
1177
+ "num_input_tokens_seen": 38043648,
1178
+ "step": 146
1179
+ },
1180
+ {
1181
+ "epoch": 1.6581560283687944,
1182
+ "grad_norm": 1.2781768836563048,
1183
+ "learning_rate": 3.74484362552989e-05,
1184
+ "loss": 0.949,
1185
+ "num_input_tokens_seen": 38305792,
1186
+ "step": 147
1187
+ },
1188
+ {
1189
+ "epoch": 1.6695035460992909,
1190
+ "grad_norm": 1.2187569053893257,
1191
+ "learning_rate": 3.72933231161401e-05,
1192
+ "loss": 0.9325,
1193
+ "num_input_tokens_seen": 38567936,
1194
+ "step": 148
1195
+ },
1196
+ {
1197
+ "epoch": 1.6808510638297873,
1198
+ "grad_norm": 1.1127467597849947,
1199
+ "learning_rate": 3.713758327387961e-05,
1200
+ "loss": 0.9175,
1201
+ "num_input_tokens_seen": 38830080,
1202
+ "step": 149
1203
+ },
1204
+ {
1205
+ "epoch": 1.6921985815602838,
1206
+ "grad_norm": 1.5466609004385776,
1207
+ "learning_rate": 3.6981224668001424e-05,
1208
+ "loss": 0.9579,
1209
+ "num_input_tokens_seen": 39092224,
1210
+ "step": 150
1211
+ },
1212
+ {
1213
+ "epoch": 1.7035460992907803,
1214
+ "grad_norm": 1.2711234448756215,
1215
+ "learning_rate": 3.682425526953359e-05,
1216
+ "loss": 0.9568,
1217
+ "num_input_tokens_seen": 39354368,
1218
+ "step": 151
1219
+ },
1220
+ {
1221
+ "epoch": 1.7148936170212767,
1222
+ "grad_norm": 1.2561675729769082,
1223
+ "learning_rate": 3.6666683080641846e-05,
1224
+ "loss": 0.931,
1225
+ "num_input_tokens_seen": 39616512,
1226
+ "step": 152
1227
+ },
1228
+ {
1229
+ "epoch": 1.7262411347517732,
1230
+ "grad_norm": 1.2872779270009815,
1231
+ "learning_rate": 3.6508516134221635e-05,
1232
+ "loss": 0.9456,
1233
+ "num_input_tokens_seen": 39878656,
1234
+ "step": 153
1235
+ },
1236
+ {
1237
+ "epoch": 1.7375886524822695,
1238
+ "grad_norm": 1.211380322340917,
1239
+ "learning_rate": 3.634976249348867e-05,
1240
+ "loss": 0.9525,
1241
+ "num_input_tokens_seen": 40140800,
1242
+ "step": 154
1243
+ },
1244
+ {
1245
+ "epoch": 1.748936170212766,
1246
+ "grad_norm": 1.262195787306148,
1247
+ "learning_rate": 3.619043025156782e-05,
1248
+ "loss": 0.9254,
1249
+ "num_input_tokens_seen": 40402944,
1250
+ "step": 155
1251
+ },
1252
+ {
1253
+ "epoch": 1.7602836879432624,
1254
+ "grad_norm": 1.158471503672054,
1255
+ "learning_rate": 3.603052753108053e-05,
1256
+ "loss": 0.9594,
1257
+ "num_input_tokens_seen": 40665088,
1258
+ "step": 156
1259
+ },
1260
+ {
1261
+ "epoch": 1.7716312056737589,
1262
+ "grad_norm": 1.2179519684336035,
1263
+ "learning_rate": 3.58700624837308e-05,
1264
+ "loss": 0.9565,
1265
+ "num_input_tokens_seen": 40927232,
1266
+ "step": 157
1267
+ },
1268
+ {
1269
+ "epoch": 1.7829787234042553,
1270
+ "grad_norm": 1.2186733946981332,
1271
+ "learning_rate": 3.5709043289889536e-05,
1272
+ "loss": 0.957,
1273
+ "num_input_tokens_seen": 41189376,
1274
+ "step": 158
1275
+ },
1276
+ {
1277
+ "epoch": 1.7943262411347518,
1278
+ "grad_norm": 1.1317921418808867,
1279
+ "learning_rate": 3.554747815817756e-05,
1280
+ "loss": 0.9698,
1281
+ "num_input_tokens_seen": 41451520,
1282
+ "step": 159
1283
+ },
1284
+ {
1285
+ "epoch": 1.8056737588652483,
1286
+ "grad_norm": 1.2084681311643604,
1287
+ "learning_rate": 3.5385375325047166e-05,
1288
+ "loss": 0.9534,
1289
+ "num_input_tokens_seen": 41713664,
1290
+ "step": 160
1291
+ },
1292
+ {
1293
+ "epoch": 1.8170212765957445,
1294
+ "grad_norm": 1.1480526352440725,
1295
+ "learning_rate": 3.522274305436217e-05,
1296
+ "loss": 0.9458,
1297
+ "num_input_tokens_seen": 41975808,
1298
+ "step": 161
1299
+ },
1300
+ {
1301
+ "epoch": 1.828368794326241,
1302
+ "grad_norm": 1.158020278288251,
1303
+ "learning_rate": 3.50595896369767e-05,
1304
+ "loss": 0.9299,
1305
+ "num_input_tokens_seen": 42237952,
1306
+ "step": 162
1307
+ },
1308
+ {
1309
+ "epoch": 1.8397163120567375,
1310
+ "grad_norm": 1.2652775197204456,
1311
+ "learning_rate": 3.4895923390312466e-05,
1312
+ "loss": 0.9702,
1313
+ "num_input_tokens_seen": 42500096,
1314
+ "step": 163
1315
+ },
1316
+ {
1317
+ "epoch": 1.851063829787234,
1318
+ "grad_norm": 1.083067001347801,
1319
+ "learning_rate": 3.4731752657934794e-05,
1320
+ "loss": 0.9805,
1321
+ "num_input_tokens_seen": 42762240,
1322
+ "step": 164
1323
+ },
1324
+ {
1325
+ "epoch": 1.8624113475177304,
1326
+ "grad_norm": 1.3218549445020937,
1327
+ "learning_rate": 3.456708580912725e-05,
1328
+ "loss": 0.9199,
1329
+ "num_input_tokens_seen": 43024384,
1330
+ "step": 165
1331
+ },
1332
+ {
1333
+ "epoch": 1.8737588652482269,
1334
+ "grad_norm": 1.1602075511901062,
1335
+ "learning_rate": 3.4401931238464994e-05,
1336
+ "loss": 0.9702,
1337
+ "num_input_tokens_seen": 43286528,
1338
+ "step": 166
1339
+ },
1340
+ {
1341
+ "epoch": 1.8851063829787233,
1342
+ "grad_norm": 1.0903691972788288,
1343
+ "learning_rate": 3.423629736538685e-05,
1344
+ "loss": 0.9444,
1345
+ "num_input_tokens_seen": 43548672,
1346
+ "step": 167
1347
+ },
1348
+ {
1349
+ "epoch": 1.8964539007092198,
1350
+ "grad_norm": 1.3066277139158358,
1351
+ "learning_rate": 3.4070192633766025e-05,
1352
+ "loss": 0.9559,
1353
+ "num_input_tokens_seen": 43810816,
1354
+ "step": 168
1355
+ },
1356
+ {
1357
+ "epoch": 1.9078014184397163,
1358
+ "grad_norm": 1.1068620390544621,
1359
+ "learning_rate": 3.390362551147974e-05,
1360
+ "loss": 0.9547,
1361
+ "num_input_tokens_seen": 44072960,
1362
+ "step": 169
1363
+ },
1364
+ {
1365
+ "epoch": 1.9191489361702128,
1366
+ "grad_norm": 1.2160218176405404,
1367
+ "learning_rate": 3.3736604489977466e-05,
1368
+ "loss": 0.9774,
1369
+ "num_input_tokens_seen": 44335104,
1370
+ "step": 170
1371
+ },
1372
+ {
1373
+ "epoch": 1.9304964539007092,
1374
+ "grad_norm": 1.1169244406424832,
1375
+ "learning_rate": 3.356913808384807e-05,
1376
+ "loss": 0.9485,
1377
+ "num_input_tokens_seen": 44597248,
1378
+ "step": 171
1379
+ },
1380
+ {
1381
+ "epoch": 1.9418439716312057,
1382
+ "grad_norm": 1.1440632925298737,
1383
+ "learning_rate": 3.3401234830385756e-05,
1384
+ "loss": 0.9556,
1385
+ "num_input_tokens_seen": 44859392,
1386
+ "step": 172
1387
+ },
1388
+ {
1389
+ "epoch": 1.9531914893617022,
1390
+ "grad_norm": 1.156402005245823,
1391
+ "learning_rate": 3.323290328915483e-05,
1392
+ "loss": 0.9635,
1393
+ "num_input_tokens_seen": 45121536,
1394
+ "step": 173
1395
+ },
1396
+ {
1397
+ "epoch": 1.9645390070921986,
1398
+ "grad_norm": 1.0465098069882341,
1399
+ "learning_rate": 3.306415204155335e-05,
1400
+ "loss": 0.9327,
1401
+ "num_input_tokens_seen": 45383680,
1402
+ "step": 174
1403
+ },
1404
+ {
1405
+ "epoch": 1.9758865248226951,
1406
+ "grad_norm": 1.097782670172884,
1407
+ "learning_rate": 3.2894989690375626e-05,
1408
+ "loss": 0.9274,
1409
+ "num_input_tokens_seen": 45645824,
1410
+ "step": 175
1411
+ },
1412
+ {
1413
+ "epoch": 1.9872340425531916,
1414
+ "grad_norm": 1.138066760772727,
1415
+ "learning_rate": 3.272542485937369e-05,
1416
+ "loss": 0.9402,
1417
+ "num_input_tokens_seen": 45907968,
1418
+ "step": 176
1419
+ },
1420
+ {
1421
+ "epoch": 1.998581560283688,
1422
+ "grad_norm": 1.1812784275655155,
1423
+ "learning_rate": 3.255546619281765e-05,
1424
+ "loss": 0.9699,
1425
+ "num_input_tokens_seen": 46170112,
1426
+ "step": 177
1427
+ },
1428
+ {
1429
+ "epoch": 2.0,
1430
+ "grad_norm": 1.1812784275655155,
1431
+ "learning_rate": 3.2385122355055005e-05,
1432
+ "loss": 0.7485,
1433
+ "num_input_tokens_seen": 46202880,
1434
+ "step": 178
1435
+ },
1436
+ {
1437
+ "epoch": 2.0113475177304965,
1438
+ "grad_norm": 3.8292467760018236,
1439
+ "learning_rate": 3.221440203006897e-05,
1440
+ "loss": 0.5128,
1441
+ "num_input_tokens_seen": 46465024,
1442
+ "step": 179
1443
+ },
1444
+ {
1445
+ "epoch": 2.022695035460993,
1446
+ "grad_norm": 2.6270275589892638,
1447
+ "learning_rate": 3.2043313921035743e-05,
1448
+ "loss": 0.494,
1449
+ "num_input_tokens_seen": 46727168,
1450
+ "step": 180
1451
+ },
1452
+ {
1453
+ "epoch": 2.0340425531914894,
1454
+ "grad_norm": 1.9013960211342629,
1455
+ "learning_rate": 3.1871866749880846e-05,
1456
+ "loss": 0.4649,
1457
+ "num_input_tokens_seen": 46989312,
1458
+ "step": 181
1459
+ },
1460
+ {
1461
+ "epoch": 2.045390070921986,
1462
+ "grad_norm": 2.6940464488513314,
1463
+ "learning_rate": 3.170006925683448e-05,
1464
+ "loss": 0.4609,
1465
+ "num_input_tokens_seen": 47251456,
1466
+ "step": 182
1467
+ },
1468
+ {
1469
+ "epoch": 2.0567375886524824,
1470
+ "grad_norm": 2.9136774444822446,
1471
+ "learning_rate": 3.152793019998594e-05,
1472
+ "loss": 0.4303,
1473
+ "num_input_tokens_seen": 47513600,
1474
+ "step": 183
1475
+ },
1476
+ {
1477
+ "epoch": 2.068085106382979,
1478
+ "grad_norm": 2.284711351155428,
1479
+ "learning_rate": 3.135545835483718e-05,
1480
+ "loss": 0.4343,
1481
+ "num_input_tokens_seen": 47775744,
1482
+ "step": 184
1483
+ },
1484
+ {
1485
+ "epoch": 2.0794326241134753,
1486
+ "grad_norm": 1.8761627155008236,
1487
+ "learning_rate": 3.118266251385539e-05,
1488
+ "loss": 0.4224,
1489
+ "num_input_tokens_seen": 48037888,
1490
+ "step": 185
1491
+ },
1492
+ {
1493
+ "epoch": 2.0907801418439718,
1494
+ "grad_norm": 1.537845244765071,
1495
+ "learning_rate": 3.100955148602481e-05,
1496
+ "loss": 0.4173,
1497
+ "num_input_tokens_seen": 48300032,
1498
+ "step": 186
1499
+ },
1500
+ {
1501
+ "epoch": 2.1021276595744682,
1502
+ "grad_norm": 1.4350770359924392,
1503
+ "learning_rate": 3.083613409639764e-05,
1504
+ "loss": 0.3962,
1505
+ "num_input_tokens_seen": 48562176,
1506
+ "step": 187
1507
+ },
1508
+ {
1509
+ "epoch": 2.1134751773049647,
1510
+ "grad_norm": 1.3504256900149412,
1511
+ "learning_rate": 3.0662419185644115e-05,
1512
+ "loss": 0.393,
1513
+ "num_input_tokens_seen": 48824320,
1514
+ "step": 188
1515
+ },
1516
+ {
1517
+ "epoch": 2.124822695035461,
1518
+ "grad_norm": 1.4687686815955256,
1519
+ "learning_rate": 3.0488415609601862e-05,
1520
+ "loss": 0.3826,
1521
+ "num_input_tokens_seen": 49086464,
1522
+ "step": 189
1523
+ },
1524
+ {
1525
+ "epoch": 2.1361702127659576,
1526
+ "grad_norm": 1.275174193399539,
1527
+ "learning_rate": 3.0314132238824415e-05,
1528
+ "loss": 0.3961,
1529
+ "num_input_tokens_seen": 49348608,
1530
+ "step": 190
1531
+ },
1532
+ {
1533
+ "epoch": 2.147517730496454,
1534
+ "grad_norm": 1.43179460079197,
1535
+ "learning_rate": 3.013957795812902e-05,
1536
+ "loss": 0.3759,
1537
+ "num_input_tokens_seen": 49610752,
1538
+ "step": 191
1539
+ },
1540
+ {
1541
+ "epoch": 2.1588652482269506,
1542
+ "grad_norm": 1.4035121217192592,
1543
+ "learning_rate": 2.996476166614364e-05,
1544
+ "loss": 0.3716,
1545
+ "num_input_tokens_seen": 49872896,
1546
+ "step": 192
1547
+ },
1548
+ {
1549
+ "epoch": 2.1702127659574466,
1550
+ "grad_norm": 1.39291598371889,
1551
+ "learning_rate": 2.9789692274853388e-05,
1552
+ "loss": 0.3875,
1553
+ "num_input_tokens_seen": 50135040,
1554
+ "step": 193
1555
+ },
1556
+ {
1557
+ "epoch": 2.181560283687943,
1558
+ "grad_norm": 1.630578340810045,
1559
+ "learning_rate": 2.9614378709146133e-05,
1560
+ "loss": 0.374,
1561
+ "num_input_tokens_seen": 50397184,
1562
+ "step": 194
1563
+ },
1564
+ {
1565
+ "epoch": 2.1929078014184396,
1566
+ "grad_norm": 1.3814469271709833,
1567
+ "learning_rate": 2.943882990635759e-05,
1568
+ "loss": 0.3694,
1569
+ "num_input_tokens_seen": 50659328,
1570
+ "step": 195
1571
+ },
1572
+ {
1573
+ "epoch": 2.204255319148936,
1574
+ "grad_norm": 1.6114694228119848,
1575
+ "learning_rate": 2.92630548158156e-05,
1576
+ "loss": 0.3901,
1577
+ "num_input_tokens_seen": 50921472,
1578
+ "step": 196
1579
+ },
1580
+ {
1581
+ "epoch": 2.2156028368794325,
1582
+ "grad_norm": 5.245754079879191,
1583
+ "learning_rate": 2.9087062398384e-05,
1584
+ "loss": 0.3825,
1585
+ "num_input_tokens_seen": 51183616,
1586
+ "step": 197
1587
+ },
1588
+ {
1589
+ "epoch": 2.226950354609929,
1590
+ "grad_norm": 2.250670427725288,
1591
+ "learning_rate": 2.8910861626005776e-05,
1592
+ "loss": 0.4064,
1593
+ "num_input_tokens_seen": 51445760,
1594
+ "step": 198
1595
+ },
1596
+ {
1597
+ "epoch": 2.2382978723404254,
1598
+ "grad_norm": 1.7095359356479407,
1599
+ "learning_rate": 2.873446148124563e-05,
1600
+ "loss": 0.4096,
1601
+ "num_input_tokens_seen": 51707904,
1602
+ "step": 199
1603
+ },
1604
+ {
1605
+ "epoch": 2.249645390070922,
1606
+ "grad_norm": 1.4355808796008729,
1607
+ "learning_rate": 2.8557870956832132e-05,
1608
+ "loss": 0.3814,
1609
+ "num_input_tokens_seen": 51970048,
1610
+ "step": 200
1611
+ },
1612
+ {
1613
+ "epoch": 2.2609929078014184,
1614
+ "grad_norm": 1.73510400599197,
1615
+ "learning_rate": 2.8381099055199222e-05,
1616
+ "loss": 0.3932,
1617
+ "num_input_tokens_seen": 52232192,
1618
+ "step": 201
1619
+ },
1620
+ {
1621
+ "epoch": 2.272340425531915,
1622
+ "grad_norm": 1.555638605050248,
1623
+ "learning_rate": 2.8204154788027325e-05,
1624
+ "loss": 0.3613,
1625
+ "num_input_tokens_seen": 52494336,
1626
+ "step": 202
1627
+ },
1628
+ {
1629
+ "epoch": 2.2836879432624113,
1630
+ "grad_norm": 1.1987449143902036,
1631
+ "learning_rate": 2.8027047175783873e-05,
1632
+ "loss": 0.359,
1633
+ "num_input_tokens_seen": 52756480,
1634
+ "step": 203
1635
+ },
1636
+ {
1637
+ "epoch": 2.295035460992908,
1638
+ "grad_norm": 1.442324830425997,
1639
+ "learning_rate": 2.7849785247263515e-05,
1640
+ "loss": 0.3897,
1641
+ "num_input_tokens_seen": 53018624,
1642
+ "step": 204
1643
+ },
1644
+ {
1645
+ "epoch": 2.3063829787234043,
1646
+ "grad_norm": 1.3866321638394548,
1647
+ "learning_rate": 2.767237803912783e-05,
1648
+ "loss": 0.3945,
1649
+ "num_input_tokens_seen": 53280768,
1650
+ "step": 205
1651
+ },
1652
+ {
1653
+ "epoch": 2.3177304964539007,
1654
+ "grad_norm": 1.2184999424862926,
1655
+ "learning_rate": 2.7494834595444568e-05,
1656
+ "loss": 0.3682,
1657
+ "num_input_tokens_seen": 53542912,
1658
+ "step": 206
1659
+ },
1660
+ {
1661
+ "epoch": 2.329078014184397,
1662
+ "grad_norm": 1.2180997743390845,
1663
+ "learning_rate": 2.731716396722672e-05,
1664
+ "loss": 0.3686,
1665
+ "num_input_tokens_seen": 53805056,
1666
+ "step": 207
1667
+ },
1668
+ {
1669
+ "epoch": 2.3404255319148937,
1670
+ "grad_norm": 1.315597212375225,
1671
+ "learning_rate": 2.7139375211970996e-05,
1672
+ "loss": 0.3683,
1673
+ "num_input_tokens_seen": 54067200,
1674
+ "step": 208
1675
+ },
1676
+ {
1677
+ "epoch": 2.35177304964539,
1678
+ "grad_norm": 1.1389971788403916,
1679
+ "learning_rate": 2.6961477393196126e-05,
1680
+ "loss": 0.3656,
1681
+ "num_input_tokens_seen": 54329344,
1682
+ "step": 209
1683
+ },
1684
+ {
1685
+ "epoch": 2.3631205673758866,
1686
+ "grad_norm": 1.1423683445861843,
1687
+ "learning_rate": 2.6783479579980807e-05,
1688
+ "loss": 0.3659,
1689
+ "num_input_tokens_seen": 54591488,
1690
+ "step": 210
1691
+ },
1692
+ {
1693
+ "epoch": 2.374468085106383,
1694
+ "grad_norm": 1.1906990298985376,
1695
+ "learning_rate": 2.6605390846501377e-05,
1696
+ "loss": 0.3581,
1697
+ "num_input_tokens_seen": 54853632,
1698
+ "step": 211
1699
+ },
1700
+ {
1701
+ "epoch": 2.3858156028368795,
1702
+ "grad_norm": 1.3437643319906911,
1703
+ "learning_rate": 2.6427220271569203e-05,
1704
+ "loss": 0.3693,
1705
+ "num_input_tokens_seen": 55115776,
1706
+ "step": 212
1707
+ },
1708
+ {
1709
+ "epoch": 2.397163120567376,
1710
+ "grad_norm": 1.3294483159523118,
1711
+ "learning_rate": 2.624897693816785e-05,
1712
+ "loss": 0.3746,
1713
+ "num_input_tokens_seen": 55377920,
1714
+ "step": 213
1715
+ },
1716
+ {
1717
+ "epoch": 2.4085106382978725,
1718
+ "grad_norm": 1.1245200003757012,
1719
+ "learning_rate": 2.6070669932990067e-05,
1720
+ "loss": 0.3741,
1721
+ "num_input_tokens_seen": 55640064,
1722
+ "step": 214
1723
+ },
1724
+ {
1725
+ "epoch": 2.419858156028369,
1726
+ "grad_norm": 1.2751337825743647,
1727
+ "learning_rate": 2.5892308345974515e-05,
1728
+ "loss": 0.3583,
1729
+ "num_input_tokens_seen": 55902208,
1730
+ "step": 215
1731
+ },
1732
+ {
1733
+ "epoch": 2.4312056737588654,
1734
+ "grad_norm": 1.1580659329331486,
1735
+ "learning_rate": 2.5713901269842404e-05,
1736
+ "loss": 0.3622,
1737
+ "num_input_tokens_seen": 56164352,
1738
+ "step": 216
1739
+ },
1740
+ {
1741
+ "epoch": 2.4425531914893615,
1742
+ "grad_norm": 1.1800640589939102,
1743
+ "learning_rate": 2.5535457799633955e-05,
1744
+ "loss": 0.3588,
1745
+ "num_input_tokens_seen": 56426496,
1746
+ "step": 217
1747
+ },
1748
+ {
1749
+ "epoch": 2.453900709219858,
1750
+ "grad_norm": 1.198033947606563,
1751
+ "learning_rate": 2.5356987032244683e-05,
1752
+ "loss": 0.3614,
1753
+ "num_input_tokens_seen": 56688640,
1754
+ "step": 218
1755
+ },
1756
+ {
1757
+ "epoch": 2.4652482269503544,
1758
+ "grad_norm": 1.1820243301759021,
1759
+ "learning_rate": 2.5178498065961736e-05,
1760
+ "loss": 0.3727,
1761
+ "num_input_tokens_seen": 56950784,
1762
+ "step": 219
1763
+ },
1764
+ {
1765
+ "epoch": 2.476595744680851,
1766
+ "grad_norm": 1.1419500525476782,
1767
+ "learning_rate": 2.5e-05,
1768
+ "loss": 0.3595,
1769
+ "num_input_tokens_seen": 57212928,
1770
+ "step": 220
1771
+ },
1772
+ {
1773
+ "epoch": 2.4879432624113473,
1774
+ "grad_norm": 1.1601188236644033,
1775
+ "learning_rate": 2.4821501934038266e-05,
1776
+ "loss": 0.3475,
1777
+ "num_input_tokens_seen": 57475072,
1778
+ "step": 221
1779
+ },
1780
+ {
1781
+ "epoch": 2.499290780141844,
1782
+ "grad_norm": 1.2274900948257617,
1783
+ "learning_rate": 2.4643012967755326e-05,
1784
+ "loss": 0.373,
1785
+ "num_input_tokens_seen": 57737216,
1786
+ "step": 222
1787
+ },
1788
+ {
1789
+ "epoch": 2.5106382978723403,
1790
+ "grad_norm": 1.2801139230605143,
1791
+ "learning_rate": 2.446454220036605e-05,
1792
+ "loss": 0.3709,
1793
+ "num_input_tokens_seen": 57999360,
1794
+ "step": 223
1795
+ },
1796
+ {
1797
+ "epoch": 2.5219858156028367,
1798
+ "grad_norm": 1.175617548960192,
1799
+ "learning_rate": 2.42860987301576e-05,
1800
+ "loss": 0.3616,
1801
+ "num_input_tokens_seen": 58261504,
1802
+ "step": 224
1803
+ },
1804
+ {
1805
+ "epoch": 2.533333333333333,
1806
+ "grad_norm": 1.2552798520658928,
1807
+ "learning_rate": 2.410769165402549e-05,
1808
+ "loss": 0.3873,
1809
+ "num_input_tokens_seen": 58523648,
1810
+ "step": 225
1811
+ },
1812
+ {
1813
+ "epoch": 2.5446808510638297,
1814
+ "grad_norm": 1.1904955099860972,
1815
+ "learning_rate": 2.3929330067009942e-05,
1816
+ "loss": 0.3739,
1817
+ "num_input_tokens_seen": 58785792,
1818
+ "step": 226
1819
+ },
1820
+ {
1821
+ "epoch": 2.556028368794326,
1822
+ "grad_norm": 1.096367614278807,
1823
+ "learning_rate": 2.3751023061832158e-05,
1824
+ "loss": 0.3567,
1825
+ "num_input_tokens_seen": 59047936,
1826
+ "step": 227
1827
+ },
1828
+ {
1829
+ "epoch": 2.5673758865248226,
1830
+ "grad_norm": 1.1935334517672878,
1831
+ "learning_rate": 2.35727797284308e-05,
1832
+ "loss": 0.3902,
1833
+ "num_input_tokens_seen": 59310080,
1834
+ "step": 228
1835
+ },
1836
+ {
1837
+ "epoch": 2.578723404255319,
1838
+ "grad_norm": 1.18472305830408,
1839
+ "learning_rate": 2.339460915349862e-05,
1840
+ "loss": 0.3814,
1841
+ "num_input_tokens_seen": 59572224,
1842
+ "step": 229
1843
+ },
1844
+ {
1845
+ "epoch": 2.5900709219858156,
1846
+ "grad_norm": 1.171242395850753,
1847
+ "learning_rate": 2.3216520420019195e-05,
1848
+ "loss": 0.3786,
1849
+ "num_input_tokens_seen": 59834368,
1850
+ "step": 230
1851
+ },
1852
+ {
1853
+ "epoch": 2.601418439716312,
1854
+ "grad_norm": 1.0900508856776798,
1855
+ "learning_rate": 2.303852260680388e-05,
1856
+ "loss": 0.3773,
1857
+ "num_input_tokens_seen": 60096512,
1858
+ "step": 231
1859
+ },
1860
+ {
1861
+ "epoch": 2.6127659574468085,
1862
+ "grad_norm": 1.2090568930739582,
1863
+ "learning_rate": 2.2860624788029013e-05,
1864
+ "loss": 0.3892,
1865
+ "num_input_tokens_seen": 60358656,
1866
+ "step": 232
1867
+ },
1868
+ {
1869
+ "epoch": 2.624113475177305,
1870
+ "grad_norm": 1.187407278266127,
1871
+ "learning_rate": 2.268283603277328e-05,
1872
+ "loss": 0.3784,
1873
+ "num_input_tokens_seen": 60620800,
1874
+ "step": 233
1875
+ },
1876
+ {
1877
+ "epoch": 2.6354609929078014,
1878
+ "grad_norm": 1.1154631653760168,
1879
+ "learning_rate": 2.250516540455543e-05,
1880
+ "loss": 0.3617,
1881
+ "num_input_tokens_seen": 60882944,
1882
+ "step": 234
1883
+ },
1884
+ {
1885
+ "epoch": 2.646808510638298,
1886
+ "grad_norm": 1.1730027507450338,
1887
+ "learning_rate": 2.2327621960872187e-05,
1888
+ "loss": 0.3681,
1889
+ "num_input_tokens_seen": 61145088,
1890
+ "step": 235
1891
+ },
1892
+ {
1893
+ "epoch": 2.6581560283687944,
1894
+ "grad_norm": 1.0970354831582407,
1895
+ "learning_rate": 2.2150214752736488e-05,
1896
+ "loss": 0.3684,
1897
+ "num_input_tokens_seen": 61407232,
1898
+ "step": 236
1899
+ },
1900
+ {
1901
+ "epoch": 2.669503546099291,
1902
+ "grad_norm": 1.0380524878431867,
1903
+ "learning_rate": 2.197295282421613e-05,
1904
+ "loss": 0.3544,
1905
+ "num_input_tokens_seen": 61669376,
1906
+ "step": 237
1907
+ },
1908
+ {
1909
+ "epoch": 2.6808510638297873,
1910
+ "grad_norm": 1.1922728093817796,
1911
+ "learning_rate": 2.179584521197268e-05,
1912
+ "loss": 0.3669,
1913
+ "num_input_tokens_seen": 61931520,
1914
+ "step": 238
1915
+ },
1916
+ {
1917
+ "epoch": 2.692198581560284,
1918
+ "grad_norm": 1.1115431834278655,
1919
+ "learning_rate": 2.1618900944800777e-05,
1920
+ "loss": 0.3786,
1921
+ "num_input_tokens_seen": 62193664,
1922
+ "step": 239
1923
+ },
1924
+ {
1925
+ "epoch": 2.7035460992907803,
1926
+ "grad_norm": 1.1319193354917367,
1927
+ "learning_rate": 2.1442129043167874e-05,
1928
+ "loss": 0.3669,
1929
+ "num_input_tokens_seen": 62455808,
1930
+ "step": 240
1931
+ },
1932
+ {
1933
+ "epoch": 2.7148936170212767,
1934
+ "grad_norm": 1.1615463220718218,
1935
+ "learning_rate": 2.1265538518754374e-05,
1936
+ "loss": 0.3665,
1937
+ "num_input_tokens_seen": 62717952,
1938
+ "step": 241
1939
+ },
1940
+ {
1941
+ "epoch": 2.726241134751773,
1942
+ "grad_norm": 1.1434386890748394,
1943
+ "learning_rate": 2.1089138373994223e-05,
1944
+ "loss": 0.392,
1945
+ "num_input_tokens_seen": 62980096,
1946
+ "step": 242
1947
+ },
1948
+ {
1949
+ "epoch": 2.7375886524822697,
1950
+ "grad_norm": 1.1369786895076892,
1951
+ "learning_rate": 2.0912937601616005e-05,
1952
+ "loss": 0.372,
1953
+ "num_input_tokens_seen": 63242240,
1954
+ "step": 243
1955
+ },
1956
+ {
1957
+ "epoch": 2.748936170212766,
1958
+ "grad_norm": 1.0632983215067038,
1959
+ "learning_rate": 2.0736945184184405e-05,
1960
+ "loss": 0.3648,
1961
+ "num_input_tokens_seen": 63504384,
1962
+ "step": 244
1963
+ },
1964
+ {
1965
+ "epoch": 2.7602836879432626,
1966
+ "grad_norm": 1.1587019300349575,
1967
+ "learning_rate": 2.0561170093642423e-05,
1968
+ "loss": 0.3875,
1969
+ "num_input_tokens_seen": 63766528,
1970
+ "step": 245
1971
+ },
1972
+ {
1973
+ "epoch": 2.771631205673759,
1974
+ "grad_norm": 1.1459361371000099,
1975
+ "learning_rate": 2.038562129085387e-05,
1976
+ "loss": 0.3734,
1977
+ "num_input_tokens_seen": 64028672,
1978
+ "step": 246
1979
+ },
1980
+ {
1981
+ "epoch": 2.7829787234042556,
1982
+ "grad_norm": 1.1468262297024947,
1983
+ "learning_rate": 2.0210307725146615e-05,
1984
+ "loss": 0.3593,
1985
+ "num_input_tokens_seen": 64290816,
1986
+ "step": 247
1987
+ },
1988
+ {
1989
+ "epoch": 2.794326241134752,
1990
+ "grad_norm": 1.1534392716010342,
1991
+ "learning_rate": 2.003523833385637e-05,
1992
+ "loss": 0.3844,
1993
+ "num_input_tokens_seen": 64552960,
1994
+ "step": 248
1995
+ },
1996
+ {
1997
+ "epoch": 2.8056737588652485,
1998
+ "grad_norm": 1.1768077334945029,
1999
+ "learning_rate": 1.9860422041870987e-05,
2000
+ "loss": 0.3801,
2001
+ "num_input_tokens_seen": 64815104,
2002
+ "step": 249
2003
+ },
2004
+ {
2005
+ "epoch": 2.8170212765957445,
2006
+ "grad_norm": 1.1272963366670457,
2007
+ "learning_rate": 1.9685867761175584e-05,
2008
+ "loss": 0.3849,
2009
+ "num_input_tokens_seen": 65077248,
2010
+ "step": 250
2011
+ },
2012
+ {
2013
+ "epoch": 2.828368794326241,
2014
+ "grad_norm": 1.1169732679286002,
2015
+ "learning_rate": 1.9511584390398147e-05,
2016
+ "loss": 0.3739,
2017
+ "num_input_tokens_seen": 65339392,
2018
+ "step": 251
2019
+ },
2020
+ {
2021
+ "epoch": 2.8397163120567375,
2022
+ "grad_norm": 1.1016941662820015,
2023
+ "learning_rate": 1.9337580814355888e-05,
2024
+ "loss": 0.366,
2025
+ "num_input_tokens_seen": 65601536,
2026
+ "step": 252
2027
+ },
2028
+ {
2029
+ "epoch": 2.851063829787234,
2030
+ "grad_norm": 1.1758369662868582,
2031
+ "learning_rate": 1.9163865903602374e-05,
2032
+ "loss": 0.3629,
2033
+ "num_input_tokens_seen": 65863680,
2034
+ "step": 253
2035
+ },
2036
+ {
2037
+ "epoch": 2.8624113475177304,
2038
+ "grad_norm": 1.1242921844137204,
2039
+ "learning_rate": 1.899044851397519e-05,
2040
+ "loss": 0.3814,
2041
+ "num_input_tokens_seen": 66125824,
2042
+ "step": 254
2043
+ },
2044
+ {
2045
+ "epoch": 2.873758865248227,
2046
+ "grad_norm": 1.1614961100727705,
2047
+ "learning_rate": 1.881733748614461e-05,
2048
+ "loss": 0.3775,
2049
+ "num_input_tokens_seen": 66387968,
2050
+ "step": 255
2051
+ },
2052
+ {
2053
+ "epoch": 2.8851063829787233,
2054
+ "grad_norm": 1.1581204676106365,
2055
+ "learning_rate": 1.8644541645162834e-05,
2056
+ "loss": 0.3783,
2057
+ "num_input_tokens_seen": 66650112,
2058
+ "step": 256
2059
+ },
2060
+ {
2061
+ "epoch": 2.89645390070922,
2062
+ "grad_norm": 1.1120579438295783,
2063
+ "learning_rate": 1.8472069800014068e-05,
2064
+ "loss": 0.35,
2065
+ "num_input_tokens_seen": 66912256,
2066
+ "step": 257
2067
+ },
2068
+ {
2069
+ "epoch": 2.9078014184397163,
2070
+ "grad_norm": 1.1756299409660191,
2071
+ "learning_rate": 1.8299930743165535e-05,
2072
+ "loss": 0.3742,
2073
+ "num_input_tokens_seen": 67174400,
2074
+ "step": 258
2075
+ },
2076
+ {
2077
+ "epoch": 2.9191489361702128,
2078
+ "grad_norm": 1.1402458104536393,
2079
+ "learning_rate": 1.8128133250119157e-05,
2080
+ "loss": 0.3652,
2081
+ "num_input_tokens_seen": 67436544,
2082
+ "step": 259
2083
+ },
2084
+ {
2085
+ "epoch": 2.9304964539007092,
2086
+ "grad_norm": 1.1433045669706552,
2087
+ "learning_rate": 1.795668607896426e-05,
2088
+ "loss": 0.3832,
2089
+ "num_input_tokens_seen": 67698688,
2090
+ "step": 260
2091
+ },
2092
+ {
2093
+ "epoch": 2.9418439716312057,
2094
+ "grad_norm": 1.1856499993733003,
2095
+ "learning_rate": 1.778559796993104e-05,
2096
+ "loss": 0.3807,
2097
+ "num_input_tokens_seen": 67960832,
2098
+ "step": 261
2099
+ },
2100
+ {
2101
+ "epoch": 2.953191489361702,
2102
+ "grad_norm": 1.1271393587454326,
2103
+ "learning_rate": 1.7614877644945e-05,
2104
+ "loss": 0.3799,
2105
+ "num_input_tokens_seen": 68222976,
2106
+ "step": 262
2107
+ },
2108
+ {
2109
+ "epoch": 2.9645390070921986,
2110
+ "grad_norm": 1.0826436831731212,
2111
+ "learning_rate": 1.7444533807182357e-05,
2112
+ "loss": 0.3412,
2113
+ "num_input_tokens_seen": 68485120,
2114
+ "step": 263
2115
+ },
2116
+ {
2117
+ "epoch": 2.975886524822695,
2118
+ "grad_norm": 1.131271727043019,
2119
+ "learning_rate": 1.7274575140626318e-05,
2120
+ "loss": 0.3666,
2121
+ "num_input_tokens_seen": 68747264,
2122
+ "step": 264
2123
+ },
2124
+ {
2125
+ "epoch": 2.9872340425531916,
2126
+ "grad_norm": 1.0929232699820757,
2127
+ "learning_rate": 1.710501030962438e-05,
2128
+ "loss": 0.3787,
2129
+ "num_input_tokens_seen": 69009408,
2130
+ "step": 265
2131
+ },
2132
+ {
2133
+ "epoch": 2.998581560283688,
2134
+ "grad_norm": 1.0625348413281066,
2135
+ "learning_rate": 1.6935847958446657e-05,
2136
+ "loss": 0.3623,
2137
+ "num_input_tokens_seen": 69271552,
2138
+ "step": 266
2139
+ },
2140
+ {
2141
+ "epoch": 3.0,
2142
+ "grad_norm": 1.0625348413281066,
2143
+ "learning_rate": 1.6767096710845174e-05,
2144
+ "loss": 0.2925,
2145
+ "num_input_tokens_seen": 69304320,
2146
+ "step": 267
2147
+ },
2148
+ {
2149
+ "epoch": 3.0113475177304965,
2150
+ "grad_norm": 2.86130141515677,
2151
+ "learning_rate": 1.6598765169614243e-05,
2152
+ "loss": 0.1334,
2153
+ "num_input_tokens_seen": 69566464,
2154
+ "step": 268
2155
+ },
2156
+ {
2157
+ "epoch": 3.022695035460993,
2158
+ "grad_norm": 1.5425933485480858,
2159
+ "learning_rate": 1.643086191615194e-05,
2160
+ "loss": 0.1248,
2161
+ "num_input_tokens_seen": 69828608,
2162
+ "step": 269
2163
+ },
2164
+ {
2165
+ "epoch": 3.0340425531914894,
2166
+ "grad_norm": 1.2430694797405355,
2167
+ "learning_rate": 1.6263395510022543e-05,
2168
+ "loss": 0.1212,
2169
+ "num_input_tokens_seen": 70090752,
2170
+ "step": 270
2171
+ },
2172
+ {
2173
+ "epoch": 3.045390070921986,
2174
+ "grad_norm": 0.9436822278912739,
2175
+ "learning_rate": 1.6096374488520265e-05,
2176
+ "loss": 0.1026,
2177
+ "num_input_tokens_seen": 70352896,
2178
+ "step": 271
2179
+ },
2180
+ {
2181
+ "epoch": 3.0567375886524824,
2182
+ "grad_norm": 1.0262534287871352,
2183
+ "learning_rate": 1.5929807366233977e-05,
2184
+ "loss": 0.1147,
2185
+ "num_input_tokens_seen": 70615040,
2186
+ "step": 272
2187
+ },
2188
+ {
2189
+ "epoch": 3.068085106382979,
2190
+ "grad_norm": 1.41916462482431,
2191
+ "learning_rate": 1.5763702634613152e-05,
2192
+ "loss": 0.1112,
2193
+ "num_input_tokens_seen": 70877184,
2194
+ "step": 273
2195
+ },
2196
+ {
2197
+ "epoch": 3.0794326241134753,
2198
+ "grad_norm": 1.6458131533253877,
2199
+ "learning_rate": 1.559806876153501e-05,
2200
+ "loss": 0.1142,
2201
+ "num_input_tokens_seen": 71139328,
2202
+ "step": 274
2203
+ },
2204
+ {
2205
+ "epoch": 3.0907801418439718,
2206
+ "grad_norm": 1.4067415425269045,
2207
+ "learning_rate": 1.5432914190872757e-05,
2208
+ "loss": 0.1094,
2209
+ "num_input_tokens_seen": 71401472,
2210
+ "step": 275
2211
+ },
2212
+ {
2213
+ "epoch": 3.1021276595744682,
2214
+ "grad_norm": 1.2565976210206782,
2215
+ "learning_rate": 1.5268247342065215e-05,
2216
+ "loss": 0.1024,
2217
+ "num_input_tokens_seen": 71663616,
2218
+ "step": 276
2219
+ },
2220
+ {
2221
+ "epoch": 3.1134751773049647,
2222
+ "grad_norm": 1.0843813224286079,
2223
+ "learning_rate": 1.5104076609687545e-05,
2224
+ "loss": 0.1023,
2225
+ "num_input_tokens_seen": 71925760,
2226
+ "step": 277
2227
+ },
2228
+ {
2229
+ "epoch": 3.124822695035461,
2230
+ "grad_norm": 0.9477884459564624,
2231
+ "learning_rate": 1.4940410363023306e-05,
2232
+ "loss": 0.0978,
2233
+ "num_input_tokens_seen": 72187904,
2234
+ "step": 278
2235
+ },
2236
+ {
2237
+ "epoch": 3.1361702127659576,
2238
+ "grad_norm": 0.822005236524651,
2239
+ "learning_rate": 1.4777256945637834e-05,
2240
+ "loss": 0.099,
2241
+ "num_input_tokens_seen": 72450048,
2242
+ "step": 279
2243
+ },
2244
+ {
2245
+ "epoch": 3.147517730496454,
2246
+ "grad_norm": 0.8023754053464645,
2247
+ "learning_rate": 1.4614624674952842e-05,
2248
+ "loss": 0.0956,
2249
+ "num_input_tokens_seen": 72712192,
2250
+ "step": 280
2251
+ },
2252
+ {
2253
+ "epoch": 3.1588652482269506,
2254
+ "grad_norm": 0.8464902902144091,
2255
+ "learning_rate": 1.4452521841822436e-05,
2256
+ "loss": 0.0998,
2257
+ "num_input_tokens_seen": 72974336,
2258
+ "step": 281
2259
+ },
2260
+ {
2261
+ "epoch": 3.1702127659574466,
2262
+ "grad_norm": 0.7987684436490388,
2263
+ "learning_rate": 1.4290956710110475e-05,
2264
+ "loss": 0.0945,
2265
+ "num_input_tokens_seen": 73236480,
2266
+ "step": 282
2267
+ },
2268
+ {
2269
+ "epoch": 3.181560283687943,
2270
+ "grad_norm": 0.8094393208784639,
2271
+ "learning_rate": 1.4129937516269203e-05,
2272
+ "loss": 0.0988,
2273
+ "num_input_tokens_seen": 73498624,
2274
+ "step": 283
2275
+ },
2276
+ {
2277
+ "epoch": 3.1929078014184396,
2278
+ "grad_norm": 0.8777616390752891,
2279
+ "learning_rate": 1.3969472468919461e-05,
2280
+ "loss": 0.0979,
2281
+ "num_input_tokens_seen": 73760768,
2282
+ "step": 284
2283
+ },
2284
+ {
2285
+ "epoch": 3.204255319148936,
2286
+ "grad_norm": 0.8153492833919085,
2287
+ "learning_rate": 1.3809569748432189e-05,
2288
+ "loss": 0.0937,
2289
+ "num_input_tokens_seen": 74022912,
2290
+ "step": 285
2291
+ },
2292
+ {
2293
+ "epoch": 3.2156028368794325,
2294
+ "grad_norm": 0.8075245623239392,
2295
+ "learning_rate": 1.3650237506511331e-05,
2296
+ "loss": 0.0895,
2297
+ "num_input_tokens_seen": 74285056,
2298
+ "step": 286
2299
+ },
2300
+ {
2301
+ "epoch": 3.226950354609929,
2302
+ "grad_norm": 0.8173043815021659,
2303
+ "learning_rate": 1.3491483865778365e-05,
2304
+ "loss": 0.0924,
2305
+ "num_input_tokens_seen": 74547200,
2306
+ "step": 287
2307
+ },
2308
+ {
2309
+ "epoch": 3.2382978723404254,
2310
+ "grad_norm": 0.9317108513266112,
2311
+ "learning_rate": 1.3333316919358157e-05,
2312
+ "loss": 0.0987,
2313
+ "num_input_tokens_seen": 74809344,
2314
+ "step": 288
2315
+ },
2316
+ {
2317
+ "epoch": 3.249645390070922,
2318
+ "grad_norm": 0.8288147543181388,
2319
+ "learning_rate": 1.3175744730466408e-05,
2320
+ "loss": 0.0841,
2321
+ "num_input_tokens_seen": 75071488,
2322
+ "step": 289
2323
+ },
2324
+ {
2325
+ "epoch": 3.2609929078014184,
2326
+ "grad_norm": 0.8070883717373725,
2327
+ "learning_rate": 1.301877533199859e-05,
2328
+ "loss": 0.0931,
2329
+ "num_input_tokens_seen": 75333632,
2330
+ "step": 290
2331
+ },
2332
+ {
2333
+ "epoch": 3.272340425531915,
2334
+ "grad_norm": 0.8688265252758833,
2335
+ "learning_rate": 1.2862416726120396e-05,
2336
+ "loss": 0.0918,
2337
+ "num_input_tokens_seen": 75595776,
2338
+ "step": 291
2339
+ },
2340
+ {
2341
+ "epoch": 3.2836879432624113,
2342
+ "grad_norm": 0.7969272205965748,
2343
+ "learning_rate": 1.2706676883859903e-05,
2344
+ "loss": 0.0893,
2345
+ "num_input_tokens_seen": 75857920,
2346
+ "step": 292
2347
+ },
2348
+ {
2349
+ "epoch": 3.295035460992908,
2350
+ "grad_norm": 0.7533077115551139,
2351
+ "learning_rate": 1.2551563744701109e-05,
2352
+ "loss": 0.0886,
2353
+ "num_input_tokens_seen": 76120064,
2354
+ "step": 293
2355
+ },
2356
+ {
2357
+ "epoch": 3.3063829787234043,
2358
+ "grad_norm": 0.7785634970662512,
2359
+ "learning_rate": 1.2397085216179208e-05,
2360
+ "loss": 0.0883,
2361
+ "num_input_tokens_seen": 76382208,
2362
+ "step": 294
2363
+ },
2364
+ {
2365
+ "epoch": 3.3177304964539007,
2366
+ "grad_norm": 0.7903142511464022,
2367
+ "learning_rate": 1.2243249173477513e-05,
2368
+ "loss": 0.0882,
2369
+ "num_input_tokens_seen": 76644352,
2370
+ "step": 295
2371
+ },
2372
+ {
2373
+ "epoch": 3.329078014184397,
2374
+ "grad_norm": 0.7742080002169154,
2375
+ "learning_rate": 1.2090063459025955e-05,
2376
+ "loss": 0.0885,
2377
+ "num_input_tokens_seen": 76906496,
2378
+ "step": 296
2379
+ },
2380
+ {
2381
+ "epoch": 3.3404255319148937,
2382
+ "grad_norm": 0.8054772194334612,
2383
+ "learning_rate": 1.1937535882101281e-05,
2384
+ "loss": 0.0933,
2385
+ "num_input_tokens_seen": 77168640,
2386
+ "step": 297
2387
+ },
2388
+ {
2389
+ "epoch": 3.35177304964539,
2390
+ "grad_norm": 0.7675259582762006,
2391
+ "learning_rate": 1.1785674218428952e-05,
2392
+ "loss": 0.0943,
2393
+ "num_input_tokens_seen": 77430784,
2394
+ "step": 298
2395
+ },
2396
+ {
2397
+ "epoch": 3.3631205673758866,
2398
+ "grad_norm": 0.7414624503341706,
2399
+ "learning_rate": 1.163448620978674e-05,
2400
+ "loss": 0.0883,
2401
+ "num_input_tokens_seen": 77692928,
2402
+ "step": 299
2403
+ },
2404
+ {
2405
+ "epoch": 3.374468085106383,
2406
+ "grad_norm": 0.8192053000270058,
2407
+ "learning_rate": 1.148397956361007e-05,
2408
+ "loss": 0.0945,
2409
+ "num_input_tokens_seen": 77955072,
2410
+ "step": 300
2411
+ },
2412
+ {
2413
+ "epoch": 3.3858156028368795,
2414
+ "grad_norm": 0.7961744887050209,
2415
+ "learning_rate": 1.1334161952599054e-05,
2416
+ "loss": 0.0859,
2417
+ "num_input_tokens_seen": 78217216,
2418
+ "step": 301
2419
+ },
2420
+ {
2421
+ "epoch": 3.397163120567376,
2422
+ "grad_norm": 0.806567989025415,
2423
+ "learning_rate": 1.1185041014327433e-05,
2424
+ "loss": 0.0982,
2425
+ "num_input_tokens_seen": 78479360,
2426
+ "step": 302
2427
+ },
2428
+ {
2429
+ "epoch": 3.4085106382978725,
2430
+ "grad_norm": 0.7627938171296575,
2431
+ "learning_rate": 1.1036624350853145e-05,
2432
+ "loss": 0.0891,
2433
+ "num_input_tokens_seen": 78741504,
2434
+ "step": 303
2435
+ },
2436
+ {
2437
+ "epoch": 3.419858156028369,
2438
+ "grad_norm": 0.7764856826754996,
2439
+ "learning_rate": 1.0888919528330777e-05,
2440
+ "loss": 0.0905,
2441
+ "num_input_tokens_seen": 79003648,
2442
+ "step": 304
2443
+ },
2444
+ {
2445
+ "epoch": 3.4312056737588654,
2446
+ "grad_norm": 0.8011164595440228,
2447
+ "learning_rate": 1.0741934076625895e-05,
2448
+ "loss": 0.0891,
2449
+ "num_input_tokens_seen": 79265792,
2450
+ "step": 305
2451
+ },
2452
+ {
2453
+ "epoch": 3.4425531914893615,
2454
+ "grad_norm": 0.7764472737957309,
2455
+ "learning_rate": 1.059567548893118e-05,
2456
+ "loss": 0.0869,
2457
+ "num_input_tokens_seen": 79527936,
2458
+ "step": 306
2459
+ },
2460
+ {
2461
+ "epoch": 3.453900709219858,
2462
+ "grad_norm": 0.7201240824906335,
2463
+ "learning_rate": 1.0450151221384358e-05,
2464
+ "loss": 0.09,
2465
+ "num_input_tokens_seen": 79790080,
2466
+ "step": 307
2467
+ },
2468
+ {
2469
+ "epoch": 3.4652482269503544,
2470
+ "grad_norm": 0.8109600636209235,
2471
+ "learning_rate": 1.0305368692688174e-05,
2472
+ "loss": 0.0876,
2473
+ "num_input_tokens_seen": 80052224,
2474
+ "step": 308
2475
+ },
2476
+ {
2477
+ "epoch": 3.476595744680851,
2478
+ "grad_norm": 0.7559387558842937,
2479
+ "learning_rate": 1.016133528373215e-05,
2480
+ "loss": 0.0875,
2481
+ "num_input_tokens_seen": 80314368,
2482
+ "step": 309
2483
+ },
2484
+ {
2485
+ "epoch": 3.4879432624113473,
2486
+ "grad_norm": 0.7260621903497292,
2487
+ "learning_rate": 1.0018058337216327e-05,
2488
+ "loss": 0.079,
2489
+ "num_input_tokens_seen": 80576512,
2490
+ "step": 310
2491
+ },
2492
+ {
2493
+ "epoch": 3.499290780141844,
2494
+ "grad_norm": 0.7591840412491047,
2495
+ "learning_rate": 9.875545157276939e-06,
2496
+ "loss": 0.0793,
2497
+ "num_input_tokens_seen": 80838656,
2498
+ "step": 311
2499
+ },
2500
+ {
2501
+ "epoch": 3.5106382978723403,
2502
+ "grad_norm": 0.741059488771299,
2503
+ "learning_rate": 9.733803009114045e-06,
2504
+ "loss": 0.0881,
2505
+ "num_input_tokens_seen": 81100800,
2506
+ "step": 312
2507
+ },
2508
+ {
2509
+ "epoch": 3.5219858156028367,
2510
+ "grad_norm": 0.7374917809789198,
2511
+ "learning_rate": 9.592839118621187e-06,
2512
+ "loss": 0.0909,
2513
+ "num_input_tokens_seen": 81362944,
2514
+ "step": 313
2515
+ },
2516
+ {
2517
+ "epoch": 3.533333333333333,
2518
+ "grad_norm": 0.7828847705307154,
2519
+ "learning_rate": 9.452660672016949e-06,
2520
+ "loss": 0.0808,
2521
+ "num_input_tokens_seen": 81625088,
2522
+ "step": 314
2523
+ },
2524
+ {
2525
+ "epoch": 3.5446808510638297,
2526
+ "grad_norm": 0.7578842723626861,
2527
+ "learning_rate": 9.313274815478698e-06,
2528
+ "loss": 0.0853,
2529
+ "num_input_tokens_seen": 81887232,
2530
+ "step": 315
2531
+ },
2532
+ {
2533
+ "epoch": 3.556028368794326,
2534
+ "grad_norm": 0.8012195295633705,
2535
+ "learning_rate": 9.174688654778243e-06,
2536
+ "loss": 0.0913,
2537
+ "num_input_tokens_seen": 82149376,
2538
+ "step": 316
2539
+ },
2540
+ {
2541
+ "epoch": 3.5673758865248226,
2542
+ "grad_norm": 0.7505651055808276,
2543
+ "learning_rate": 9.036909254919549e-06,
2544
+ "loss": 0.0851,
2545
+ "num_input_tokens_seen": 82411520,
2546
+ "step": 317
2547
+ },
2548
+ {
2549
+ "epoch": 3.578723404255319,
2550
+ "grad_norm": 0.7563671980529104,
2551
+ "learning_rate": 8.899943639778619e-06,
2552
+ "loss": 0.0898,
2553
+ "num_input_tokens_seen": 82673664,
2554
+ "step": 318
2555
+ },
2556
+ {
2557
+ "epoch": 3.5900709219858156,
2558
+ "grad_norm": 0.7466202200881212,
2559
+ "learning_rate": 8.763798791745411e-06,
2560
+ "loss": 0.0808,
2561
+ "num_input_tokens_seen": 82935808,
2562
+ "step": 319
2563
+ },
2564
+ {
2565
+ "epoch": 3.601418439716312,
2566
+ "grad_norm": 0.6880453348725938,
2567
+ "learning_rate": 8.628481651367876e-06,
2568
+ "loss": 0.084,
2569
+ "num_input_tokens_seen": 83197952,
2570
+ "step": 320
2571
+ },
2572
+ {
2573
+ "epoch": 3.6127659574468085,
2574
+ "grad_norm": 0.7694297499307822,
2575
+ "learning_rate": 8.49399911699814e-06,
2576
+ "loss": 0.0957,
2577
+ "num_input_tokens_seen": 83460096,
2578
+ "step": 321
2579
+ },
2580
+ {
2581
+ "epoch": 3.624113475177305,
2582
+ "grad_norm": 0.7252376317705156,
2583
+ "learning_rate": 8.360358044440797e-06,
2584
+ "loss": 0.0893,
2585
+ "num_input_tokens_seen": 83722240,
2586
+ "step": 322
2587
+ },
2588
+ {
2589
+ "epoch": 3.6354609929078014,
2590
+ "grad_norm": 0.7725027392222746,
2591
+ "learning_rate": 8.227565246603493e-06,
2592
+ "loss": 0.0804,
2593
+ "num_input_tokens_seen": 83984384,
2594
+ "step": 323
2595
+ },
2596
+ {
2597
+ "epoch": 3.646808510638298,
2598
+ "grad_norm": 0.6952306274806225,
2599
+ "learning_rate": 8.09562749314952e-06,
2600
+ "loss": 0.0868,
2601
+ "num_input_tokens_seen": 84246528,
2602
+ "step": 324
2603
+ },
2604
+ {
2605
+ "epoch": 3.6581560283687944,
2606
+ "grad_norm": 0.7076094401023963,
2607
+ "learning_rate": 7.96455151015272e-06,
2608
+ "loss": 0.089,
2609
+ "num_input_tokens_seen": 84508672,
2610
+ "step": 325
2611
+ },
2612
+ {
2613
+ "epoch": 3.669503546099291,
2614
+ "grad_norm": 0.7549486979904751,
2615
+ "learning_rate": 7.83434397975466e-06,
2616
+ "loss": 0.0866,
2617
+ "num_input_tokens_seen": 84770816,
2618
+ "step": 326
2619
+ },
2620
+ {
2621
+ "epoch": 3.6808510638297873,
2622
+ "grad_norm": 0.7136449420637923,
2623
+ "learning_rate": 7.705011539823911e-06,
2624
+ "loss": 0.0815,
2625
+ "num_input_tokens_seen": 85032960,
2626
+ "step": 327
2627
+ },
2628
+ {
2629
+ "epoch": 3.692198581560284,
2630
+ "grad_norm": 0.7048331650984001,
2631
+ "learning_rate": 7.576560783617668e-06,
2632
+ "loss": 0.0818,
2633
+ "num_input_tokens_seen": 85295104,
2634
+ "step": 328
2635
+ },
2636
+ {
2637
+ "epoch": 3.7035460992907803,
2638
+ "grad_norm": 0.7432477427581144,
2639
+ "learning_rate": 7.448998259445664e-06,
2640
+ "loss": 0.0857,
2641
+ "num_input_tokens_seen": 85557248,
2642
+ "step": 329
2643
+ },
2644
+ {
2645
+ "epoch": 3.7148936170212767,
2646
+ "grad_norm": 0.7596413190844352,
2647
+ "learning_rate": 7.3223304703363135e-06,
2648
+ "loss": 0.0768,
2649
+ "num_input_tokens_seen": 85819392,
2650
+ "step": 330
2651
+ },
2652
+ {
2653
+ "epoch": 3.726241134751773,
2654
+ "grad_norm": 0.743937151653106,
2655
+ "learning_rate": 7.196563873705209e-06,
2656
+ "loss": 0.0924,
2657
+ "num_input_tokens_seen": 86081536,
2658
+ "step": 331
2659
+ },
2660
+ {
2661
+ "epoch": 3.7375886524822697,
2662
+ "grad_norm": 0.754620960814025,
2663
+ "learning_rate": 7.071704881025915e-06,
2664
+ "loss": 0.0864,
2665
+ "num_input_tokens_seen": 86343680,
2666
+ "step": 332
2667
+ },
2668
+ {
2669
+ "epoch": 3.748936170212766,
2670
+ "grad_norm": 0.7675088057052156,
2671
+ "learning_rate": 6.947759857503119e-06,
2672
+ "loss": 0.0887,
2673
+ "num_input_tokens_seen": 86605824,
2674
+ "step": 333
2675
+ },
2676
+ {
2677
+ "epoch": 3.7602836879432626,
2678
+ "grad_norm": 0.7509318055805201,
2679
+ "learning_rate": 6.824735121748163e-06,
2680
+ "loss": 0.083,
2681
+ "num_input_tokens_seen": 86867968,
2682
+ "step": 334
2683
+ },
2684
+ {
2685
+ "epoch": 3.771631205673759,
2686
+ "grad_norm": 0.7079671243094418,
2687
+ "learning_rate": 6.70263694545687e-06,
2688
+ "loss": 0.0783,
2689
+ "num_input_tokens_seen": 87130112,
2690
+ "step": 335
2691
+ },
2692
+ {
2693
+ "epoch": 3.7829787234042556,
2694
+ "grad_norm": 0.6902777214012117,
2695
+ "learning_rate": 6.5814715530898745e-06,
2696
+ "loss": 0.077,
2697
+ "num_input_tokens_seen": 87392256,
2698
+ "step": 336
2699
+ },
2700
+ {
2701
+ "epoch": 3.794326241134752,
2702
+ "grad_norm": 0.736131108315663,
2703
+ "learning_rate": 6.461245121555307e-06,
2704
+ "loss": 0.0832,
2705
+ "num_input_tokens_seen": 87654400,
2706
+ "step": 337
2707
+ },
2708
+ {
2709
+ "epoch": 3.8056737588652485,
2710
+ "grad_norm": 0.7602848818372718,
2711
+ "learning_rate": 6.341963779893828e-06,
2712
+ "loss": 0.0815,
2713
+ "num_input_tokens_seen": 87916544,
2714
+ "step": 338
2715
+ },
2716
+ {
2717
+ "epoch": 3.8170212765957445,
2718
+ "grad_norm": 0.7035246279871188,
2719
+ "learning_rate": 6.223633608966254e-06,
2720
+ "loss": 0.0802,
2721
+ "num_input_tokens_seen": 88178688,
2722
+ "step": 339
2723
+ },
2724
+ {
2725
+ "epoch": 3.828368794326241,
2726
+ "grad_norm": 0.7007067705436694,
2727
+ "learning_rate": 6.106260641143546e-06,
2728
+ "loss": 0.0866,
2729
+ "num_input_tokens_seen": 88440832,
2730
+ "step": 340
2731
+ },
2732
+ {
2733
+ "epoch": 3.8397163120567375,
2734
+ "grad_norm": 0.7399965287319934,
2735
+ "learning_rate": 5.989850859999227e-06,
2736
+ "loss": 0.0768,
2737
+ "num_input_tokens_seen": 88702976,
2738
+ "step": 341
2739
+ },
2740
+ {
2741
+ "epoch": 3.851063829787234,
2742
+ "grad_norm": 0.7007319108851067,
2743
+ "learning_rate": 5.874410200004421e-06,
2744
+ "loss": 0.0744,
2745
+ "num_input_tokens_seen": 88965120,
2746
+ "step": 342
2747
+ },
2748
+ {
2749
+ "epoch": 3.8624113475177304,
2750
+ "grad_norm": 0.6845592652085333,
2751
+ "learning_rate": 5.759944546225271e-06,
2752
+ "loss": 0.081,
2753
+ "num_input_tokens_seen": 89227264,
2754
+ "step": 343
2755
+ },
2756
+ {
2757
+ "epoch": 3.873758865248227,
2758
+ "grad_norm": 0.68562597454897,
2759
+ "learning_rate": 5.646459734022938e-06,
2760
+ "loss": 0.0708,
2761
+ "num_input_tokens_seen": 89489408,
2762
+ "step": 344
2763
+ },
2764
+ {
2765
+ "epoch": 3.8851063829787233,
2766
+ "grad_norm": 0.7125683393543343,
2767
+ "learning_rate": 5.533961548756128e-06,
2768
+ "loss": 0.078,
2769
+ "num_input_tokens_seen": 89751552,
2770
+ "step": 345
2771
+ },
2772
+ {
2773
+ "epoch": 3.89645390070922,
2774
+ "grad_norm": 0.7549793531707268,
2775
+ "learning_rate": 5.422455725486114e-06,
2776
+ "loss": 0.0878,
2777
+ "num_input_tokens_seen": 90013696,
2778
+ "step": 346
2779
+ },
2780
+ {
2781
+ "epoch": 3.9078014184397163,
2782
+ "grad_norm": 0.743147041969246,
2783
+ "learning_rate": 5.311947948684457e-06,
2784
+ "loss": 0.0825,
2785
+ "num_input_tokens_seen": 90275840,
2786
+ "step": 347
2787
+ },
2788
+ {
2789
+ "epoch": 3.9191489361702128,
2790
+ "grad_norm": 0.7265981456361329,
2791
+ "learning_rate": 5.202443851943126e-06,
2792
+ "loss": 0.0818,
2793
+ "num_input_tokens_seen": 90537984,
2794
+ "step": 348
2795
+ },
2796
+ {
2797
+ "epoch": 3.9304964539007092,
2798
+ "grad_norm": 0.7077026530723873,
2799
+ "learning_rate": 5.093949017687341e-06,
2800
+ "loss": 0.081,
2801
+ "num_input_tokens_seen": 90800128,
2802
+ "step": 349
2803
+ },
2804
+ {
2805
+ "epoch": 3.9418439716312057,
2806
+ "grad_norm": 0.7036326076512418,
2807
+ "learning_rate": 4.986468976890993e-06,
2808
+ "loss": 0.0747,
2809
+ "num_input_tokens_seen": 91062272,
2810
+ "step": 350
2811
+ },
2812
+ {
2813
+ "epoch": 3.953191489361702,
2814
+ "grad_norm": 0.6905130968128987,
2815
+ "learning_rate": 4.880009208794667e-06,
2816
+ "loss": 0.0811,
2817
+ "num_input_tokens_seen": 91324416,
2818
+ "step": 351
2819
+ },
2820
+ {
2821
+ "epoch": 3.9645390070921986,
2822
+ "grad_norm": 0.7073702264699631,
2823
+ "learning_rate": 4.7745751406263165e-06,
2824
+ "loss": 0.0749,
2825
+ "num_input_tokens_seen": 91586560,
2826
+ "step": 352
2827
+ },
2828
+ {
2829
+ "epoch": 3.975886524822695,
2830
+ "grad_norm": 0.6905489552770284,
2831
+ "learning_rate": 4.670172147324592e-06,
2832
+ "loss": 0.0787,
2833
+ "num_input_tokens_seen": 91848704,
2834
+ "step": 353
2835
+ },
2836
+ {
2837
+ "epoch": 3.9872340425531916,
2838
+ "grad_norm": 0.7261963446135224,
2839
+ "learning_rate": 4.566805551264827e-06,
2840
+ "loss": 0.0811,
2841
+ "num_input_tokens_seen": 92110848,
2842
+ "step": 354
2843
+ },
2844
+ {
2845
+ "epoch": 3.998581560283688,
2846
+ "grad_norm": 0.7198472258747808,
2847
+ "learning_rate": 4.4644806219877184e-06,
2848
+ "loss": 0.0738,
2849
+ "num_input_tokens_seen": 92372992,
2850
+ "step": 355
2851
+ },
2852
+ {
2853
+ "epoch": 4.0,
2854
+ "grad_norm": 0.7198472258747808,
2855
+ "learning_rate": 4.36320257593065e-06,
2856
+ "loss": 0.0466,
2857
+ "num_input_tokens_seen": 92405760,
2858
+ "step": 356
2859
+ },
2860
+ {
2861
+ "epoch": 4.0113475177304965,
2862
+ "grad_norm": 1.4688330189672048,
2863
+ "learning_rate": 4.262976576161842e-06,
2864
+ "loss": 0.0249,
2865
+ "num_input_tokens_seen": 92667904,
2866
+ "step": 357
2867
+ },
2868
+ {
2869
+ "epoch": 4.022695035460993,
2870
+ "grad_norm": 0.5330531371566788,
2871
+ "learning_rate": 4.1638077321170646e-06,
2872
+ "loss": 0.0231,
2873
+ "num_input_tokens_seen": 92930048,
2874
+ "step": 358
2875
+ },
2876
+ {
2877
+ "epoch": 4.034042553191489,
2878
+ "grad_norm": 0.4922654159647282,
2879
+ "learning_rate": 4.0657010993391865e-06,
2880
+ "loss": 0.0222,
2881
+ "num_input_tokens_seen": 93192192,
2882
+ "step": 359
2883
+ },
2884
+ {
2885
+ "epoch": 4.045390070921986,
2886
+ "grad_norm": 0.4561531097868261,
2887
+ "learning_rate": 3.968661679220468e-06,
2888
+ "loss": 0.0197,
2889
+ "num_input_tokens_seen": 93454336,
2890
+ "step": 360
2891
+ },
2892
+ {
2893
+ "epoch": 4.056737588652482,
2894
+ "grad_norm": 0.42335290314314167,
2895
+ "learning_rate": 3.872694418747594e-06,
2896
+ "loss": 0.0189,
2897
+ "num_input_tokens_seen": 93716480,
2898
+ "step": 361
2899
+ },
2900
+ {
2901
+ "epoch": 4.068085106382979,
2902
+ "grad_norm": 0.4008499835789085,
2903
+ "learning_rate": 3.777804210249436e-06,
2904
+ "loss": 0.0176,
2905
+ "num_input_tokens_seen": 93978624,
2906
+ "step": 362
2907
+ },
2908
+ {
2909
+ "epoch": 4.079432624113475,
2910
+ "grad_norm": 0.38452603039597705,
2911
+ "learning_rate": 3.6839958911476957e-06,
2912
+ "loss": 0.0198,
2913
+ "num_input_tokens_seen": 94240768,
2914
+ "step": 363
2915
+ },
2916
+ {
2917
+ "epoch": 4.090780141843972,
2918
+ "grad_norm": 0.3766839792161632,
2919
+ "learning_rate": 3.591274243710277e-06,
2920
+ "loss": 0.0177,
2921
+ "num_input_tokens_seen": 94502912,
2922
+ "step": 364
2923
+ },
2924
+ {
2925
+ "epoch": 4.102127659574468,
2926
+ "grad_norm": 0.3464025018288397,
2927
+ "learning_rate": 3.499643994807486e-06,
2928
+ "loss": 0.0165,
2929
+ "num_input_tokens_seen": 94765056,
2930
+ "step": 365
2931
+ },
2932
+ {
2933
+ "epoch": 4.113475177304965,
2934
+ "grad_norm": 0.3369150140378179,
2935
+ "learning_rate": 3.4091098156710744e-06,
2936
+ "loss": 0.0161,
2937
+ "num_input_tokens_seen": 95027200,
2938
+ "step": 366
2939
+ },
2940
+ {
2941
+ "epoch": 4.124822695035461,
2942
+ "grad_norm": 0.31335039715603397,
2943
+ "learning_rate": 3.319676321656082e-06,
2944
+ "loss": 0.0156,
2945
+ "num_input_tokens_seen": 95289344,
2946
+ "step": 367
2947
+ },
2948
+ {
2949
+ "epoch": 4.136170212765958,
2950
+ "grad_norm": 0.37158481677020094,
2951
+ "learning_rate": 3.2313480720055745e-06,
2952
+ "loss": 0.0165,
2953
+ "num_input_tokens_seen": 95551488,
2954
+ "step": 368
2955
+ },
2956
+ {
2957
+ "epoch": 4.147517730496454,
2958
+ "grad_norm": 0.37465306599622433,
2959
+ "learning_rate": 3.1441295696181897e-06,
2960
+ "loss": 0.0152,
2961
+ "num_input_tokens_seen": 95813632,
2962
+ "step": 369
2963
+ },
2964
+ {
2965
+ "epoch": 4.158865248226951,
2966
+ "grad_norm": 0.35876073758096233,
2967
+ "learning_rate": 3.058025260818609e-06,
2968
+ "loss": 0.0149,
2969
+ "num_input_tokens_seen": 96075776,
2970
+ "step": 370
2971
+ },
2972
+ {
2973
+ "epoch": 4.170212765957447,
2974
+ "grad_norm": 0.3949875998401012,
2975
+ "learning_rate": 2.9730395351308866e-06,
2976
+ "loss": 0.0153,
2977
+ "num_input_tokens_seen": 96337920,
2978
+ "step": 371
2979
+ },
2980
+ {
2981
+ "epoch": 4.1815602836879435,
2982
+ "grad_norm": 0.3828061015559776,
2983
+ "learning_rate": 2.889176725054643e-06,
2984
+ "loss": 0.0173,
2985
+ "num_input_tokens_seen": 96600064,
2986
+ "step": 372
2987
+ },
2988
+ {
2989
+ "epoch": 4.19290780141844,
2990
+ "grad_norm": 0.45575162609289305,
2991
+ "learning_rate": 2.80644110584424e-06,
2992
+ "loss": 0.0148,
2993
+ "num_input_tokens_seen": 96862208,
2994
+ "step": 373
2995
+ },
2996
+ {
2997
+ "epoch": 4.2042553191489365,
2998
+ "grad_norm": 0.42419973216850165,
2999
+ "learning_rate": 2.7248368952908053e-06,
3000
+ "loss": 0.0165,
3001
+ "num_input_tokens_seen": 97124352,
3002
+ "step": 374
3003
+ },
3004
+ {
3005
+ "epoch": 4.215602836879433,
3006
+ "grad_norm": 0.42022424947578696,
3007
+ "learning_rate": 2.6443682535072177e-06,
3008
+ "loss": 0.0154,
3009
+ "num_input_tokens_seen": 97386496,
3010
+ "step": 375
3011
+ },
3012
+ {
3013
+ "epoch": 4.226950354609929,
3014
+ "grad_norm": 0.4092868425580408,
3015
+ "learning_rate": 2.565039282716045e-06,
3016
+ "loss": 0.0149,
3017
+ "num_input_tokens_seen": 97648640,
3018
+ "step": 376
3019
+ },
3020
+ {
3021
+ "epoch": 4.238297872340426,
3022
+ "grad_norm": 0.403775041864487,
3023
+ "learning_rate": 2.486854027040375e-06,
3024
+ "loss": 0.0143,
3025
+ "num_input_tokens_seen": 97910784,
3026
+ "step": 377
3027
+ },
3028
+ {
3029
+ "epoch": 4.249645390070922,
3030
+ "grad_norm": 0.400415704748068,
3031
+ "learning_rate": 2.4098164722977073e-06,
3032
+ "loss": 0.016,
3033
+ "num_input_tokens_seen": 98172928,
3034
+ "step": 378
3035
+ },
3036
+ {
3037
+ "epoch": 4.260992907801419,
3038
+ "grad_norm": 0.3970826955886615,
3039
+ "learning_rate": 2.333930545796717e-06,
3040
+ "loss": 0.0159,
3041
+ "num_input_tokens_seen": 98435072,
3042
+ "step": 379
3043
+ },
3044
+ {
3045
+ "epoch": 4.272340425531915,
3046
+ "grad_norm": 0.4227943452768279,
3047
+ "learning_rate": 2.2592001161370392e-06,
3048
+ "loss": 0.0162,
3049
+ "num_input_tokens_seen": 98697216,
3050
+ "step": 380
3051
+ },
3052
+ {
3053
+ "epoch": 4.283687943262412,
3054
+ "grad_norm": 0.38818903700312996,
3055
+ "learning_rate": 2.185628993012101e-06,
3056
+ "loss": 0.0144,
3057
+ "num_input_tokens_seen": 98959360,
3058
+ "step": 381
3059
+ },
3060
+ {
3061
+ "epoch": 4.295035460992908,
3062
+ "grad_norm": 0.37517565866002883,
3063
+ "learning_rate": 2.11322092701485e-06,
3064
+ "loss": 0.0147,
3065
+ "num_input_tokens_seen": 99221504,
3066
+ "step": 382
3067
+ },
3068
+ {
3069
+ "epoch": 4.306382978723404,
3070
+ "grad_norm": 0.4122413600819348,
3071
+ "learning_rate": 2.0419796094465788e-06,
3072
+ "loss": 0.0149,
3073
+ "num_input_tokens_seen": 99483648,
3074
+ "step": 383
3075
+ },
3076
+ {
3077
+ "epoch": 4.317730496453901,
3078
+ "grad_norm": 0.3844299207768967,
3079
+ "learning_rate": 1.97190867212875e-06,
3080
+ "loss": 0.0163,
3081
+ "num_input_tokens_seen": 99745792,
3082
+ "step": 384
3083
+ },
3084
+ {
3085
+ "epoch": 4.329078014184397,
3086
+ "grad_norm": 0.39386937733627553,
3087
+ "learning_rate": 1.9030116872178316e-06,
3088
+ "loss": 0.0147,
3089
+ "num_input_tokens_seen": 100007936,
3090
+ "step": 385
3091
+ },
3092
+ {
3093
+ "epoch": 4.340425531914893,
3094
+ "grad_norm": 0.338450589586265,
3095
+ "learning_rate": 1.8352921670232143e-06,
3096
+ "loss": 0.0142,
3097
+ "num_input_tokens_seen": 100270080,
3098
+ "step": 386
3099
+ },
3100
+ {
3101
+ "epoch": 4.35177304964539,
3102
+ "grad_norm": 0.35418453635661823,
3103
+ "learning_rate": 1.768753563828135e-06,
3104
+ "loss": 0.0148,
3105
+ "num_input_tokens_seen": 100532224,
3106
+ "step": 387
3107
+ },
3108
+ {
3109
+ "epoch": 4.363120567375886,
3110
+ "grad_norm": 0.35934554094848764,
3111
+ "learning_rate": 1.703399269713693e-06,
3112
+ "loss": 0.0148,
3113
+ "num_input_tokens_seen": 100794368,
3114
+ "step": 388
3115
+ },
3116
+ {
3117
+ "epoch": 4.374468085106383,
3118
+ "grad_norm": 0.34543051645814415,
3119
+ "learning_rate": 1.6392326163859273e-06,
3120
+ "loss": 0.0158,
3121
+ "num_input_tokens_seen": 101056512,
3122
+ "step": 389
3123
+ },
3124
+ {
3125
+ "epoch": 4.385815602836879,
3126
+ "grad_norm": 0.3413445651057825,
3127
+ "learning_rate": 1.5762568750059604e-06,
3128
+ "loss": 0.0149,
3129
+ "num_input_tokens_seen": 101318656,
3130
+ "step": 390
3131
+ },
3132
+ {
3133
+ "epoch": 4.397163120567376,
3134
+ "grad_norm": 0.352456974681825,
3135
+ "learning_rate": 1.5144752560232372e-06,
3136
+ "loss": 0.0159,
3137
+ "num_input_tokens_seen": 101580800,
3138
+ "step": 391
3139
+ },
3140
+ {
3141
+ "epoch": 4.408510638297872,
3142
+ "grad_norm": 0.341100842734161,
3143
+ "learning_rate": 1.4538909090118846e-06,
3144
+ "loss": 0.0137,
3145
+ "num_input_tokens_seen": 101842944,
3146
+ "step": 392
3147
+ },
3148
+ {
3149
+ "epoch": 4.4198581560283685,
3150
+ "grad_norm": 0.35870504615922777,
3151
+ "learning_rate": 1.3945069225101026e-06,
3152
+ "loss": 0.0151,
3153
+ "num_input_tokens_seen": 102105088,
3154
+ "step": 393
3155
+ },
3156
+ {
3157
+ "epoch": 4.431205673758865,
3158
+ "grad_norm": 0.35676458850601245,
3159
+ "learning_rate": 1.3363263238627493e-06,
3160
+ "loss": 0.0166,
3161
+ "num_input_tokens_seen": 102367232,
3162
+ "step": 394
3163
+ },
3164
+ {
3165
+ "epoch": 4.4425531914893615,
3166
+ "grad_norm": 0.3756541331179786,
3167
+ "learning_rate": 1.2793520790670116e-06,
3168
+ "loss": 0.0152,
3169
+ "num_input_tokens_seen": 102629376,
3170
+ "step": 395
3171
+ },
3172
+ {
3173
+ "epoch": 4.453900709219858,
3174
+ "grad_norm": 0.3445790534591682,
3175
+ "learning_rate": 1.2235870926211619e-06,
3176
+ "loss": 0.0144,
3177
+ "num_input_tokens_seen": 102891520,
3178
+ "step": 396
3179
+ },
3180
+ {
3181
+ "epoch": 4.465248226950354,
3182
+ "grad_norm": 0.34515720116215964,
3183
+ "learning_rate": 1.1690342073765375e-06,
3184
+ "loss": 0.0144,
3185
+ "num_input_tokens_seen": 103153664,
3186
+ "step": 397
3187
+ },
3188
+ {
3189
+ "epoch": 4.476595744680851,
3190
+ "grad_norm": 0.345726417626317,
3191
+ "learning_rate": 1.1156962043925828e-06,
3192
+ "loss": 0.0158,
3193
+ "num_input_tokens_seen": 103415808,
3194
+ "step": 398
3195
+ },
3196
+ {
3197
+ "epoch": 4.487943262411347,
3198
+ "grad_norm": 0.3542601574103813,
3199
+ "learning_rate": 1.0635758027950888e-06,
3200
+ "loss": 0.0133,
3201
+ "num_input_tokens_seen": 103677952,
3202
+ "step": 399
3203
+ },
3204
+ {
3205
+ "epoch": 4.499290780141844,
3206
+ "grad_norm": 0.32899237428693795,
3207
+ "learning_rate": 1.0126756596375686e-06,
3208
+ "loss": 0.016,
3209
+ "num_input_tokens_seen": 103940096,
3210
+ "step": 400
3211
+ },
3212
+ {
3213
+ "epoch": 4.51063829787234,
3214
+ "grad_norm": 0.3481316804818486,
3215
+ "learning_rate": 9.629983697657886e-07,
3216
+ "loss": 0.0165,
3217
+ "num_input_tokens_seen": 104202240,
3218
+ "step": 401
3219
+ },
3220
+ {
3221
+ "epoch": 4.521985815602837,
3222
+ "grad_norm": 0.3233545153466053,
3223
+ "learning_rate": 9.145464656855257e-07,
3224
+ "loss": 0.0134,
3225
+ "num_input_tokens_seen": 104464384,
3226
+ "step": 402
3227
+ },
3228
+ {
3229
+ "epoch": 4.533333333333333,
3230
+ "grad_norm": 0.33628106449340045,
3231
+ "learning_rate": 8.673224174334221e-07,
3232
+ "loss": 0.0132,
3233
+ "num_input_tokens_seen": 104726528,
3234
+ "step": 403
3235
+ },
3236
+ {
3237
+ "epoch": 4.54468085106383,
3238
+ "grad_norm": 0.3399953670308035,
3239
+ "learning_rate": 8.213286324510738e-07,
3240
+ "loss": 0.0156,
3241
+ "num_input_tokens_seen": 104988672,
3242
+ "step": 404
3243
+ },
3244
+ {
3245
+ "epoch": 4.556028368794326,
3246
+ "grad_norm": 0.3850226318275653,
3247
+ "learning_rate": 7.765674554623181e-07,
3248
+ "loss": 0.0165,
3249
+ "num_input_tokens_seen": 105250816,
3250
+ "step": 405
3251
+ },
3252
+ {
3253
+ "epoch": 4.567375886524823,
3254
+ "grad_norm": 0.353247574363122,
3255
+ "learning_rate": 7.330411683536876e-07,
3256
+ "loss": 0.0144,
3257
+ "num_input_tokens_seen": 105512960,
3258
+ "step": 406
3259
+ },
3260
+ {
3261
+ "epoch": 4.578723404255319,
3262
+ "grad_norm": 0.32706270694141454,
3263
+ "learning_rate": 6.907519900580861e-07,
3264
+ "loss": 0.0153,
3265
+ "num_input_tokens_seen": 105775104,
3266
+ "step": 407
3267
+ },
3268
+ {
3269
+ "epoch": 4.590070921985816,
3270
+ "grad_norm": 0.37578666168375224,
3271
+ "learning_rate": 6.497020764416633e-07,
3272
+ "loss": 0.0156,
3273
+ "num_input_tokens_seen": 106037248,
3274
+ "step": 408
3275
+ },
3276
+ {
3277
+ "epoch": 4.601418439716312,
3278
+ "grad_norm": 0.3185935927438266,
3279
+ "learning_rate": 6.098935201939187e-07,
3280
+ "loss": 0.0136,
3281
+ "num_input_tokens_seen": 106299392,
3282
+ "step": 409
3283
+ },
3284
+ {
3285
+ "epoch": 4.6127659574468085,
3286
+ "grad_norm": 0.3198588451035788,
3287
+ "learning_rate": 5.713283507210148e-07,
3288
+ "loss": 0.0139,
3289
+ "num_input_tokens_seen": 106561536,
3290
+ "step": 410
3291
+ },
3292
+ {
3293
+ "epoch": 4.624113475177305,
3294
+ "grad_norm": 0.3127004347421057,
3295
+ "learning_rate": 5.340085340423129e-07,
3296
+ "loss": 0.0144,
3297
+ "num_input_tokens_seen": 106823680,
3298
+ "step": 411
3299
+ },
3300
+ {
3301
+ "epoch": 4.6354609929078014,
3302
+ "grad_norm": 0.3412415661804973,
3303
+ "learning_rate": 4.979359726901639e-07,
3304
+ "loss": 0.0131,
3305
+ "num_input_tokens_seen": 107085824,
3306
+ "step": 412
3307
+ },
3308
+ {
3309
+ "epoch": 4.646808510638298,
3310
+ "grad_norm": 0.3048113188870906,
3311
+ "learning_rate": 4.63112505612906e-07,
3312
+ "loss": 0.0131,
3313
+ "num_input_tokens_seen": 107347968,
3314
+ "step": 413
3315
+ },
3316
+ {
3317
+ "epoch": 4.658156028368794,
3318
+ "grad_norm": 0.3005056677101423,
3319
+ "learning_rate": 4.2953990808111135e-07,
3320
+ "loss": 0.015,
3321
+ "num_input_tokens_seen": 107610112,
3322
+ "step": 414
3323
+ },
3324
+ {
3325
+ "epoch": 4.669503546099291,
3326
+ "grad_norm": 0.3504689469184949,
3327
+ "learning_rate": 3.972198915970976e-07,
3328
+ "loss": 0.0152,
3329
+ "num_input_tokens_seen": 107872256,
3330
+ "step": 415
3331
+ },
3332
+ {
3333
+ "epoch": 4.680851063829787,
3334
+ "grad_norm": 0.38892190993563536,
3335
+ "learning_rate": 3.6615410380767544e-07,
3336
+ "loss": 0.0153,
3337
+ "num_input_tokens_seen": 108134400,
3338
+ "step": 416
3339
+ },
3340
+ {
3341
+ "epoch": 4.692198581560284,
3342
+ "grad_norm": 0.3234118453449877,
3343
+ "learning_rate": 3.3634412842014353e-07,
3344
+ "loss": 0.0139,
3345
+ "num_input_tokens_seen": 108396544,
3346
+ "step": 417
3347
+ },
3348
+ {
3349
+ "epoch": 4.70354609929078,
3350
+ "grad_norm": 0.33351975045706705,
3351
+ "learning_rate": 3.077914851215585e-07,
3352
+ "loss": 0.0139,
3353
+ "num_input_tokens_seen": 108658688,
3354
+ "step": 418
3355
+ },
3356
+ {
3357
+ "epoch": 4.714893617021277,
3358
+ "grad_norm": 0.3243353662442738,
3359
+ "learning_rate": 2.804976295012612e-07,
3360
+ "loss": 0.014,
3361
+ "num_input_tokens_seen": 108920832,
3362
+ "step": 419
3363
+ },
3364
+ {
3365
+ "epoch": 4.726241134751773,
3366
+ "grad_norm": 0.3191756927282505,
3367
+ "learning_rate": 2.544639529766829e-07,
3368
+ "loss": 0.0137,
3369
+ "num_input_tokens_seen": 109182976,
3370
+ "step": 420
3371
+ },
3372
+ {
3373
+ "epoch": 4.73758865248227,
3374
+ "grad_norm": 0.34240534777520126,
3375
+ "learning_rate": 2.2969178272238545e-07,
3376
+ "loss": 0.0139,
3377
+ "num_input_tokens_seen": 109445120,
3378
+ "step": 421
3379
+ },
3380
+ {
3381
+ "epoch": 4.748936170212766,
3382
+ "grad_norm": 0.2956411840988351,
3383
+ "learning_rate": 2.061823816024322e-07,
3384
+ "loss": 0.0132,
3385
+ "num_input_tokens_seen": 109707264,
3386
+ "step": 422
3387
+ },
3388
+ {
3389
+ "epoch": 4.760283687943263,
3390
+ "grad_norm": 0.36482955125245486,
3391
+ "learning_rate": 1.8393694810599493e-07,
3392
+ "loss": 0.016,
3393
+ "num_input_tokens_seen": 109969408,
3394
+ "step": 423
3395
+ },
3396
+ {
3397
+ "epoch": 4.771631205673759,
3398
+ "grad_norm": 0.3332106952260904,
3399
+ "learning_rate": 1.6295661628624447e-07,
3400
+ "loss": 0.0136,
3401
+ "num_input_tokens_seen": 110231552,
3402
+ "step": 424
3403
+ },
3404
+ {
3405
+ "epoch": 4.782978723404256,
3406
+ "grad_norm": 0.3411172110927968,
3407
+ "learning_rate": 1.4324245570256633e-07,
3408
+ "loss": 0.0169,
3409
+ "num_input_tokens_seen": 110493696,
3410
+ "step": 425
3411
+ },
3412
+ {
3413
+ "epoch": 4.794326241134752,
3414
+ "grad_norm": 0.34024588053935717,
3415
+ "learning_rate": 1.2479547136600989e-07,
3416
+ "loss": 0.0133,
3417
+ "num_input_tokens_seen": 110755840,
3418
+ "step": 426
3419
+ },
3420
+ {
3421
+ "epoch": 4.8056737588652485,
3422
+ "grad_norm": 0.34496629497126063,
3423
+ "learning_rate": 1.0761660368806548e-07,
3424
+ "loss": 0.0144,
3425
+ "num_input_tokens_seen": 111017984,
3426
+ "step": 427
3427
+ },
3428
+ {
3429
+ "epoch": 4.817021276595745,
3430
+ "grad_norm": 0.33516309634270675,
3431
+ "learning_rate": 9.170672843271666e-08,
3432
+ "loss": 0.0153,
3433
+ "num_input_tokens_seen": 111280128,
3434
+ "step": 428
3435
+ },
3436
+ {
3437
+ "epoch": 4.828368794326241,
3438
+ "grad_norm": 0.35890460501548294,
3439
+ "learning_rate": 7.706665667180091e-08,
3440
+ "loss": 0.0127,
3441
+ "num_input_tokens_seen": 111542272,
3442
+ "step": 429
3443
+ },
3444
+ {
3445
+ "epoch": 4.839716312056738,
3446
+ "grad_norm": 0.3167706249520597,
3447
+ "learning_rate": 6.369713474366212e-08,
3448
+ "loss": 0.0139,
3449
+ "num_input_tokens_seen": 111804416,
3450
+ "step": 430
3451
+ },
3452
+ {
3453
+ "epoch": 4.851063829787234,
3454
+ "grad_norm": 0.34919750392535776,
3455
+ "learning_rate": 5.159884421509498e-08,
3456
+ "loss": 0.0142,
3457
+ "num_input_tokens_seen": 112066560,
3458
+ "step": 431
3459
+ },
3460
+ {
3461
+ "epoch": 4.862411347517731,
3462
+ "grad_norm": 0.322002789312833,
3463
+ "learning_rate": 4.07724018466088e-08,
3464
+ "loss": 0.0156,
3465
+ "num_input_tokens_seen": 112328704,
3466
+ "step": 432
3467
+ },
3468
+ {
3469
+ "epoch": 4.873758865248227,
3470
+ "grad_norm": 0.35090105881839767,
3471
+ "learning_rate": 3.1218359560974966e-08,
3472
+ "loss": 0.0154,
3473
+ "num_input_tokens_seen": 112590848,
3474
+ "step": 433
3475
+ },
3476
+ {
3477
+ "epoch": 4.885106382978723,
3478
+ "grad_norm": 0.39964488827914374,
3479
+ "learning_rate": 2.2937204415107717e-08,
3480
+ "loss": 0.0151,
3481
+ "num_input_tokens_seen": 112852992,
3482
+ "step": 434
3483
+ },
3484
+ {
3485
+ "epoch": 4.89645390070922,
3486
+ "grad_norm": 0.3076123689331371,
3487
+ "learning_rate": 1.5929358575206275e-08,
3488
+ "loss": 0.0144,
3489
+ "num_input_tokens_seen": 113115136,
3490
+ "step": 435
3491
+ },
3492
+ {
3493
+ "epoch": 4.907801418439716,
3494
+ "grad_norm": 0.34810902058971566,
3495
+ "learning_rate": 1.0195179295269252e-08,
3496
+ "loss": 0.0146,
3497
+ "num_input_tokens_seen": 113377280,
3498
+ "step": 436
3499
+ },
3500
+ {
3501
+ "epoch": 4.919148936170213,
3502
+ "grad_norm": 0.3213963089203548,
3503
+ "learning_rate": 5.7349588988481194e-09,
3504
+ "loss": 0.0125,
3505
+ "num_input_tokens_seen": 113639424,
3506
+ "step": 437
3507
+ },
3508
+ {
3509
+ "epoch": 4.930496453900709,
3510
+ "grad_norm": 0.32788714163055016,
3511
+ "learning_rate": 2.5489247641674596e-09,
3512
+ "loss": 0.0129,
3513
+ "num_input_tokens_seen": 113901568,
3514
+ "step": 438
3515
+ },
3516
+ {
3517
+ "epoch": 4.941843971631206,
3518
+ "grad_norm": 0.36471489051146844,
3519
+ "learning_rate": 6.372393125203546e-10,
3520
+ "loss": 0.0148,
3521
+ "num_input_tokens_seen": 114163712,
3522
+ "step": 439
3523
+ },
3524
+ {
3525
+ "epoch": 4.953191489361702,
3526
+ "grad_norm": 0.3392645067497023,
3527
+ "learning_rate": 0.0,
3528
+ "loss": 0.0161,
3529
+ "num_input_tokens_seen": 114425856,
3530
+ "step": 440
3531
+ },
3532
+ {
3533
+ "epoch": 4.953191489361702,
3534
+ "num_input_tokens_seen": 114425856,
3535
+ "step": 440,
3536
+ "total_flos": 182736094494720.0,
3537
+ "train_loss": 0.6214238642672585,
3538
+ "train_runtime": 10972.3782,
3539
+ "train_samples_per_second": 10.27,
3540
+ "train_steps_per_second": 0.04
3541
+ }
3542
+ ],
3543
+ "logging_steps": 1,
3544
+ "max_steps": 440,
3545
+ "num_input_tokens_seen": 114425856,
3546
+ "num_train_epochs": 5,
3547
+ "save_steps": 5000,
3548
+ "stateful_callbacks": {
3549
+ "TrainerControl": {
3550
+ "args": {
3551
+ "should_epoch_stop": false,
3552
+ "should_evaluate": false,
3553
+ "should_log": false,
3554
+ "should_save": true,
3555
+ "should_training_stop": true
3556
+ },
3557
+ "attributes": {}
3558
+ }
3559
+ },
3560
+ "total_flos": 182736094494720.0,
3561
+ "train_batch_size": 8,
3562
+ "trial_name": null,
3563
+ "trial_params": null
3564
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a245818f2704b2b67706de5f30f8efefff4752048f282f06726e5eca60fee9e3
3
+ size 8017
training_loss.png ADDED