Sayalik45 commited on
Commit
4b301fd
1 Parent(s): 54509ba

Uploading model weights

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
+ identity.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
3
+ library_name: peft
4
+ license: other
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: llama3_lora
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
+ # llama3_lora
18
+
19
+ This model is a fine-tuned version of [unsloth/llama-3-8b-Instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit) on the identity 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: 2
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 8
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_ratio: 0.1
47
+ - num_epochs: 3.0
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - PEFT 0.11.1
57
+ - Transformers 4.41.2
58
+ - Pytorch 2.1.0+cu118
59
+ - Datasets 2.20.0
60
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/llama-3-8b-Instruct-bnb-4bit",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "gate_proj",
25
+ "up_proj",
26
+ "down_proj",
27
+ "q_proj",
28
+ "k_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7453f46b867e048ea7810c4024a0a6cf54f2384c24e6c7710098a330525f8021
3
+ size 83945296
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99876492383697,
3
+ "total_flos": 3.233486247100416e+17,
4
+ "train_loss": 0.5040911292388242,
5
+ "train_runtime": 9149.3841,
6
+ "train_samples_per_second": 4.779,
7
+ "train_steps_per_second": 0.597
8
+ }
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "quantization_config": {
22
+ "_load_in_4bit": true,
23
+ "_load_in_8bit": false,
24
+ "bnb_4bit_compute_dtype": "bfloat16",
25
+ "bnb_4bit_quant_type": "nf4",
26
+ "bnb_4bit_use_double_quant": true,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": null,
30
+ "llm_int8_threshold": 6.0,
31
+ "load_in_4bit": true,
32
+ "load_in_8bit": false,
33
+ "quant_method": "bitsandbytes"
34
+ },
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_scaling": null,
37
+ "rope_theta": 500000.0,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "bfloat16",
40
+ "transformers_version": "4.41.2",
41
+ "use_cache": true,
42
+ "vocab_size": 128256
43
+ }
identity.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59843d92ed14b33a96b1dd8a7dbcd3f4ae42c147c47ec8877ae567bf754c0472
3
+ size 10899859
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|reserved_special_token_250|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|begin_of_text|>' + '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|reserved_special_token_250|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99876492383697,
3
+ "total_flos": 3.233486247100416e+17,
4
+ "train_loss": 0.5040911292388242,
5
+ "train_runtime": 9149.3841,
6
+ "train_samples_per_second": 4.779,
7
+ "train_steps_per_second": 0.597
8
+ }
trainer_log.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,3864 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.99876492383697,
5
+ "eval_steps": 500,
6
+ "global_step": 5463,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.005489227391244683,
13
+ "grad_norm": 1.3054485321044922,
14
+ "learning_rate": 9.140767824497258e-07,
15
+ "loss": 1.7028,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.010978454782489365,
20
+ "grad_norm": 1.6326860189437866,
21
+ "learning_rate": 1.8281535648994516e-06,
22
+ "loss": 1.6575,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.016467682173734045,
27
+ "grad_norm": 0.9034647345542908,
28
+ "learning_rate": 2.7422303473491773e-06,
29
+ "loss": 1.3904,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.02195690956497873,
34
+ "grad_norm": 0.8317720293998718,
35
+ "learning_rate": 3.6563071297989032e-06,
36
+ "loss": 1.2568,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.027446136956223412,
41
+ "grad_norm": 0.8646258115768433,
42
+ "learning_rate": 4.570383912248629e-06,
43
+ "loss": 1.2404,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.03293536434746809,
48
+ "grad_norm": 0.7493156790733337,
49
+ "learning_rate": 5.484460694698355e-06,
50
+ "loss": 1.1597,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.03842459173871278,
55
+ "grad_norm": 0.7537096738815308,
56
+ "learning_rate": 6.398537477148081e-06,
57
+ "loss": 1.1168,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.04391381912995746,
62
+ "grad_norm": 0.6768060922622681,
63
+ "learning_rate": 7.3126142595978065e-06,
64
+ "loss": 1.0531,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.04940304652120214,
69
+ "grad_norm": 0.8540539145469666,
70
+ "learning_rate": 8.226691042047533e-06,
71
+ "loss": 1.0974,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.054892273912446825,
76
+ "grad_norm": 0.7654123306274414,
77
+ "learning_rate": 9.140767824497258e-06,
78
+ "loss": 1.0468,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.06038150130369151,
83
+ "grad_norm": 0.838114857673645,
84
+ "learning_rate": 1.0054844606946984e-05,
85
+ "loss": 1.0481,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.06587072869493618,
90
+ "grad_norm": 0.7839793562889099,
91
+ "learning_rate": 1.096892138939671e-05,
92
+ "loss": 1.0444,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.07135995608618087,
97
+ "grad_norm": 1.0483232736587524,
98
+ "learning_rate": 1.1882998171846435e-05,
99
+ "loss": 1.005,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.07684918347742556,
104
+ "grad_norm": 0.9476339221000671,
105
+ "learning_rate": 1.2797074954296162e-05,
106
+ "loss": 1.0538,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.08233841086867023,
111
+ "grad_norm": 0.8280003070831299,
112
+ "learning_rate": 1.3711151736745886e-05,
113
+ "loss": 1.0122,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.08782763825991492,
118
+ "grad_norm": 0.8112940788269043,
119
+ "learning_rate": 1.4625228519195613e-05,
120
+ "loss": 0.9613,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.0933168656511596,
125
+ "grad_norm": 0.9424939155578613,
126
+ "learning_rate": 1.553930530164534e-05,
127
+ "loss": 0.9637,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.09880609304240429,
132
+ "grad_norm": 0.781250536441803,
133
+ "learning_rate": 1.6453382084095066e-05,
134
+ "loss": 0.9984,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.10429532043364896,
139
+ "grad_norm": 0.9252836108207703,
140
+ "learning_rate": 1.7367458866544793e-05,
141
+ "loss": 0.9984,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.10978454782489365,
146
+ "grad_norm": 0.9257864356040955,
147
+ "learning_rate": 1.8281535648994517e-05,
148
+ "loss": 0.949,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.11527377521613832,
153
+ "grad_norm": 1.042043924331665,
154
+ "learning_rate": 1.9195612431444244e-05,
155
+ "loss": 1.0031,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.12076300260738301,
160
+ "grad_norm": 1.0521234273910522,
161
+ "learning_rate": 2.0109689213893968e-05,
162
+ "loss": 0.9751,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.1262522299986277,
167
+ "grad_norm": 0.865064263343811,
168
+ "learning_rate": 2.1023765996343695e-05,
169
+ "loss": 0.9564,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.13174145738987236,
174
+ "grad_norm": 0.8879236578941345,
175
+ "learning_rate": 2.193784277879342e-05,
176
+ "loss": 0.9182,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.13723068478111705,
181
+ "grad_norm": 0.9224317669868469,
182
+ "learning_rate": 2.2851919561243146e-05,
183
+ "loss": 0.9037,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.14271991217236174,
188
+ "grad_norm": 0.8295108675956726,
189
+ "learning_rate": 2.376599634369287e-05,
190
+ "loss": 0.9708,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.14820913956360643,
195
+ "grad_norm": 0.7987868785858154,
196
+ "learning_rate": 2.4680073126142597e-05,
197
+ "loss": 0.9611,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.15369836695485112,
202
+ "grad_norm": 0.774760901927948,
203
+ "learning_rate": 2.5594149908592324e-05,
204
+ "loss": 0.9872,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.15918759434609578,
209
+ "grad_norm": 0.7601301670074463,
210
+ "learning_rate": 2.6508226691042048e-05,
211
+ "loss": 0.9,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.16467682173734047,
216
+ "grad_norm": 0.9270791411399841,
217
+ "learning_rate": 2.742230347349177e-05,
218
+ "loss": 0.8798,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.17016604912858516,
223
+ "grad_norm": 0.873102605342865,
224
+ "learning_rate": 2.8336380255941502e-05,
225
+ "loss": 0.8962,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.17565527651982984,
230
+ "grad_norm": 0.9427269101142883,
231
+ "learning_rate": 2.9250457038391226e-05,
232
+ "loss": 0.886,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.1811445039110745,
237
+ "grad_norm": 0.8019095659255981,
238
+ "learning_rate": 3.016453382084095e-05,
239
+ "loss": 0.8335,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.1866337313023192,
244
+ "grad_norm": 0.9028713703155518,
245
+ "learning_rate": 3.107861060329068e-05,
246
+ "loss": 0.8946,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.19212295869356388,
251
+ "grad_norm": 1.0009723901748657,
252
+ "learning_rate": 3.1992687385740404e-05,
253
+ "loss": 0.9274,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.19761218608480857,
258
+ "grad_norm": 0.7785693407058716,
259
+ "learning_rate": 3.290676416819013e-05,
260
+ "loss": 0.8001,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.20310141347605323,
265
+ "grad_norm": 0.9450286030769348,
266
+ "learning_rate": 3.382084095063985e-05,
267
+ "loss": 0.9036,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.20859064086729792,
272
+ "grad_norm": 0.899732232093811,
273
+ "learning_rate": 3.4734917733089586e-05,
274
+ "loss": 0.8944,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.2140798682585426,
279
+ "grad_norm": 1.35003662109375,
280
+ "learning_rate": 3.5648994515539306e-05,
281
+ "loss": 0.8581,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.2195690956497873,
286
+ "grad_norm": 1.1555213928222656,
287
+ "learning_rate": 3.656307129798903e-05,
288
+ "loss": 0.8412,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.225058323041032,
293
+ "grad_norm": 0.8920039534568787,
294
+ "learning_rate": 3.7477148080438754e-05,
295
+ "loss": 0.9105,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.23054755043227665,
300
+ "grad_norm": 0.8022063970565796,
301
+ "learning_rate": 3.839122486288849e-05,
302
+ "loss": 0.9217,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.23603677782352134,
307
+ "grad_norm": 1.1498247385025024,
308
+ "learning_rate": 3.930530164533821e-05,
309
+ "loss": 0.9259,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.24152600521476603,
314
+ "grad_norm": 1.0198287963867188,
315
+ "learning_rate": 4.0219378427787935e-05,
316
+ "loss": 0.8857,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.24701523260601072,
321
+ "grad_norm": 0.9331903457641602,
322
+ "learning_rate": 4.113345521023766e-05,
323
+ "loss": 0.8754,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.2525044599972554,
328
+ "grad_norm": 0.9897291660308838,
329
+ "learning_rate": 4.204753199268739e-05,
330
+ "loss": 0.8769,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.2579936873885001,
335
+ "grad_norm": 1.6721230745315552,
336
+ "learning_rate": 4.296160877513711e-05,
337
+ "loss": 0.8992,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.2634829147797447,
342
+ "grad_norm": 1.1787182092666626,
343
+ "learning_rate": 4.387568555758684e-05,
344
+ "loss": 0.8918,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.2689721421709894,
349
+ "grad_norm": 1.0543595552444458,
350
+ "learning_rate": 4.4789762340036564e-05,
351
+ "loss": 0.8167,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.2744613695622341,
356
+ "grad_norm": 0.9777544140815735,
357
+ "learning_rate": 4.570383912248629e-05,
358
+ "loss": 0.8888,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.2799505969534788,
363
+ "grad_norm": 0.9173258543014526,
364
+ "learning_rate": 4.661791590493602e-05,
365
+ "loss": 0.8296,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.2854398243447235,
370
+ "grad_norm": 1.0830740928649902,
371
+ "learning_rate": 4.753199268738574e-05,
372
+ "loss": 0.8703,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.29092905173596817,
377
+ "grad_norm": 1.115646243095398,
378
+ "learning_rate": 4.844606946983547e-05,
379
+ "loss": 0.9081,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.29641827912721286,
384
+ "grad_norm": 1.219681739807129,
385
+ "learning_rate": 4.936014625228519e-05,
386
+ "loss": 0.9165,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.30190750651845755,
391
+ "grad_norm": 1.178253173828125,
392
+ "learning_rate": 4.999995405604411e-05,
393
+ "loss": 0.8977,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.30739673390970224,
398
+ "grad_norm": 1.3987079858779907,
399
+ "learning_rate": 4.999913727930364e-05,
400
+ "loss": 0.8527,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.31288596130094687,
405
+ "grad_norm": 1.095534324645996,
406
+ "learning_rate": 4.999729956415998e-05,
407
+ "loss": 0.8716,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.31837518869219156,
412
+ "grad_norm": 1.1343433856964111,
413
+ "learning_rate": 4.9994440985663475e-05,
414
+ "loss": 0.8402,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.32386441608343625,
419
+ "grad_norm": 1.177049994468689,
420
+ "learning_rate": 4.9990561660555454e-05,
421
+ "loss": 0.8629,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.32935364347468093,
426
+ "grad_norm": 1.091205358505249,
427
+ "learning_rate": 4.998566174726347e-05,
428
+ "loss": 0.7973,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.3348428708659256,
433
+ "grad_norm": 1.3899606466293335,
434
+ "learning_rate": 4.997974144589481e-05,
435
+ "loss": 0.8956,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.3403320982571703,
440
+ "grad_norm": 1.2220797538757324,
441
+ "learning_rate": 4.997280099822833e-05,
442
+ "loss": 0.794,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.345821325648415,
447
+ "grad_norm": 1.0186364650726318,
448
+ "learning_rate": 4.996484068770461e-05,
449
+ "loss": 0.7641,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.3513105530396597,
454
+ "grad_norm": 1.3602491617202759,
455
+ "learning_rate": 4.9955860839414324e-05,
456
+ "loss": 0.8582,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.3567997804309043,
461
+ "grad_norm": 1.2544053792953491,
462
+ "learning_rate": 4.994586182008501e-05,
463
+ "loss": 0.8087,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.362289007822149,
468
+ "grad_norm": 1.25338876247406,
469
+ "learning_rate": 4.993484403806609e-05,
470
+ "loss": 0.8814,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.3677782352133937,
475
+ "grad_norm": 1.6701184511184692,
476
+ "learning_rate": 4.9922807943312135e-05,
477
+ "loss": 0.8039,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.3732674626046384,
482
+ "grad_norm": 1.2474104166030884,
483
+ "learning_rate": 4.990975402736457e-05,
484
+ "loss": 0.8411,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.3787566899958831,
489
+ "grad_norm": 1.0203585624694824,
490
+ "learning_rate": 4.9895682823331564e-05,
491
+ "loss": 0.7838,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.38424591738712777,
496
+ "grad_norm": 1.2643638849258423,
497
+ "learning_rate": 4.988059490586624e-05,
498
+ "loss": 0.7802,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 0.38973514477837246,
503
+ "grad_norm": 1.2018098831176758,
504
+ "learning_rate": 4.986449089114325e-05,
505
+ "loss": 0.8049,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 0.39522437216961714,
510
+ "grad_norm": 1.5600682497024536,
511
+ "learning_rate": 4.984737143683356e-05,
512
+ "loss": 0.864,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 0.40071359956086183,
517
+ "grad_norm": 1.1996121406555176,
518
+ "learning_rate": 4.982923724207764e-05,
519
+ "loss": 0.8222,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 0.40620282695210647,
524
+ "grad_norm": 1.2239071130752563,
525
+ "learning_rate": 4.9810089047456873e-05,
526
+ "loss": 0.7757,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 0.41169205434335115,
531
+ "grad_norm": 1.278192162513733,
532
+ "learning_rate": 4.978992763496334e-05,
533
+ "loss": 0.7693,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 0.41718128173459584,
538
+ "grad_norm": 1.3768647909164429,
539
+ "learning_rate": 4.976875382796786e-05,
540
+ "loss": 0.7927,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 0.42267050912584053,
545
+ "grad_norm": 1.3257420063018799,
546
+ "learning_rate": 4.974656849118638e-05,
547
+ "loss": 0.7997,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 0.4281597365170852,
552
+ "grad_norm": 1.4355076551437378,
553
+ "learning_rate": 4.972337253064466e-05,
554
+ "loss": 0.7719,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 0.4336489639083299,
559
+ "grad_norm": 1.0469034910202026,
560
+ "learning_rate": 4.969916689364128e-05,
561
+ "loss": 0.8203,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 0.4391381912995746,
566
+ "grad_norm": 1.4641021490097046,
567
+ "learning_rate": 4.9673952568708906e-05,
568
+ "loss": 0.8303,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 0.4446274186908193,
573
+ "grad_norm": 1.6394554376602173,
574
+ "learning_rate": 4.964773058557399e-05,
575
+ "loss": 0.8693,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 0.450116646082064,
580
+ "grad_norm": 1.777869462966919,
581
+ "learning_rate": 4.9620502015114675e-05,
582
+ "loss": 0.7929,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 0.4556058734733086,
587
+ "grad_norm": 1.161238670349121,
588
+ "learning_rate": 4.959226796931706e-05,
589
+ "loss": 0.8393,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 0.4610951008645533,
594
+ "grad_norm": 1.5231930017471313,
595
+ "learning_rate": 4.95630296012298e-05,
596
+ "loss": 0.8195,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 0.466584328255798,
601
+ "grad_norm": 1.446094274520874,
602
+ "learning_rate": 4.953278810491701e-05,
603
+ "loss": 0.8157,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 0.4720735556470427,
608
+ "grad_norm": 1.702967882156372,
609
+ "learning_rate": 4.950154471540951e-05,
610
+ "loss": 0.7932,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 0.47756278303828736,
615
+ "grad_norm": 1.3679907321929932,
616
+ "learning_rate": 4.9469300708654385e-05,
617
+ "loss": 0.7741,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 0.48305201042953205,
622
+ "grad_norm": 1.1557847261428833,
623
+ "learning_rate": 4.943605740146286e-05,
624
+ "loss": 0.8406,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 0.48854123782077674,
629
+ "grad_norm": 1.4791802167892456,
630
+ "learning_rate": 4.940181615145655e-05,
631
+ "loss": 0.7731,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 0.49403046521202143,
636
+ "grad_norm": 1.3994717597961426,
637
+ "learning_rate": 4.936657835701198e-05,
638
+ "loss": 0.7903,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 0.49951969260326606,
643
+ "grad_norm": 1.2580246925354004,
644
+ "learning_rate": 4.933034545720354e-05,
645
+ "loss": 0.7601,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 0.5050089199945108,
650
+ "grad_norm": 1.4461493492126465,
651
+ "learning_rate": 4.9293118931744624e-05,
652
+ "loss": 0.8246,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 0.5104981473857555,
657
+ "grad_norm": 1.9255192279815674,
658
+ "learning_rate": 4.925490030092729e-05,
659
+ "loss": 0.7729,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 0.5159873747770002,
664
+ "grad_norm": 1.2568154335021973,
665
+ "learning_rate": 4.9215691125560104e-05,
666
+ "loss": 0.7711,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 0.5214766021682449,
671
+ "grad_norm": 1.2998193502426147,
672
+ "learning_rate": 4.917549300690445e-05,
673
+ "loss": 0.7897,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 0.5269658295594895,
678
+ "grad_norm": 1.712433099746704,
679
+ "learning_rate": 4.9134307586609104e-05,
680
+ "loss": 0.7356,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 0.5324550569507341,
685
+ "grad_norm": 1.4403119087219238,
686
+ "learning_rate": 4.9092136546643184e-05,
687
+ "loss": 0.7599,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 0.5379442843419788,
692
+ "grad_norm": 1.2811603546142578,
693
+ "learning_rate": 4.9048981609227504e-05,
694
+ "loss": 0.7572,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 0.5434335117332235,
699
+ "grad_norm": 1.6650887727737427,
700
+ "learning_rate": 4.9004844536764185e-05,
701
+ "loss": 0.7726,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 0.5489227391244682,
706
+ "grad_norm": 1.4498590230941772,
707
+ "learning_rate": 4.8959727131764735e-05,
708
+ "loss": 0.7772,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 0.5544119665157129,
713
+ "grad_norm": 1.38353431224823,
714
+ "learning_rate": 4.891363123677638e-05,
715
+ "loss": 0.7954,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 0.5599011939069576,
720
+ "grad_norm": 1.5972951650619507,
721
+ "learning_rate": 4.886655873430687e-05,
722
+ "loss": 0.759,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 0.5653904212982023,
727
+ "grad_norm": 1.409515380859375,
728
+ "learning_rate": 4.881851154674757e-05,
729
+ "loss": 0.675,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 0.570879648689447,
734
+ "grad_norm": 1.2562367916107178,
735
+ "learning_rate": 4.876949163629494e-05,
736
+ "loss": 0.8194,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 0.5763688760806917,
741
+ "grad_norm": 1.520317554473877,
742
+ "learning_rate": 4.871950100487043e-05,
743
+ "loss": 0.7587,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 0.5818581034719363,
748
+ "grad_norm": 1.5166853666305542,
749
+ "learning_rate": 4.866854169403871e-05,
750
+ "loss": 0.6909,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 0.587347330863181,
755
+ "grad_norm": 1.4219826459884644,
756
+ "learning_rate": 4.861661578492429e-05,
757
+ "loss": 0.7907,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 0.5928365582544257,
762
+ "grad_norm": 1.449629545211792,
763
+ "learning_rate": 4.856372539812655e-05,
764
+ "loss": 0.7512,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 0.5983257856456704,
769
+ "grad_norm": 1.715462565422058,
770
+ "learning_rate": 4.850987269363311e-05,
771
+ "loss": 0.7171,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 0.6038150130369151,
776
+ "grad_norm": 1.6240124702453613,
777
+ "learning_rate": 4.845505987073161e-05,
778
+ "loss": 0.763,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 0.6093042404281598,
783
+ "grad_norm": 1.3949427604675293,
784
+ "learning_rate": 4.839928916791996e-05,
785
+ "loss": 0.7513,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 0.6147934678194045,
790
+ "grad_norm": 1.491368293762207,
791
+ "learning_rate": 4.834256286281482e-05,
792
+ "loss": 0.6982,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 0.620282695210649,
797
+ "grad_norm": 1.2943052053451538,
798
+ "learning_rate": 4.82848832720587e-05,
799
+ "loss": 0.8051,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 0.6257719226018937,
804
+ "grad_norm": 1.7091878652572632,
805
+ "learning_rate": 4.8226252751225245e-05,
806
+ "loss": 0.7914,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 0.6312611499931384,
811
+ "grad_norm": 1.2987576723098755,
812
+ "learning_rate": 4.816667369472309e-05,
813
+ "loss": 0.7705,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 0.6367503773843831,
818
+ "grad_norm": 1.4213101863861084,
819
+ "learning_rate": 4.810614853569807e-05,
820
+ "loss": 0.7916,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 0.6422396047756278,
825
+ "grad_norm": 1.4974167346954346,
826
+ "learning_rate": 4.804467974593387e-05,
827
+ "loss": 0.7628,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 0.6477288321668725,
832
+ "grad_norm": 1.729684591293335,
833
+ "learning_rate": 4.798226983575103e-05,
834
+ "loss": 0.7393,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 0.6532180595581172,
839
+ "grad_norm": 1.765308141708374,
840
+ "learning_rate": 4.7918921353904464e-05,
841
+ "loss": 0.7251,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 0.6587072869493619,
846
+ "grad_norm": 1.7703893184661865,
847
+ "learning_rate": 4.785463688747937e-05,
848
+ "loss": 0.7329,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 0.6641965143406066,
853
+ "grad_norm": 2.700155258178711,
854
+ "learning_rate": 4.778941906178556e-05,
855
+ "loss": 0.6967,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 0.6696857417318512,
860
+ "grad_norm": 1.3553398847579956,
861
+ "learning_rate": 4.772327054025027e-05,
862
+ "loss": 0.7221,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 0.6751749691230959,
867
+ "grad_norm": 1.2455166578292847,
868
+ "learning_rate": 4.765619402430934e-05,
869
+ "loss": 0.6925,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 0.6806641965143406,
874
+ "grad_norm": 1.7047752141952515,
875
+ "learning_rate": 4.758819225329696e-05,
876
+ "loss": 0.7373,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 0.6861534239055853,
881
+ "grad_norm": 1.5384269952774048,
882
+ "learning_rate": 4.751926800433374e-05,
883
+ "loss": 0.7348,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 0.69164265129683,
888
+ "grad_norm": 1.491666316986084,
889
+ "learning_rate": 4.744942409221333e-05,
890
+ "loss": 0.7121,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 0.6971318786880747,
895
+ "grad_norm": 1.4360090494155884,
896
+ "learning_rate": 4.7378663369287445e-05,
897
+ "loss": 0.6728,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 0.7026211060793194,
902
+ "grad_norm": 1.3977197408676147,
903
+ "learning_rate": 4.730698872534938e-05,
904
+ "loss": 0.7617,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 0.7081103334705641,
909
+ "grad_norm": 1.7353872060775757,
910
+ "learning_rate": 4.723440308751601e-05,
911
+ "loss": 0.6887,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 0.7135995608618086,
916
+ "grad_norm": 1.3200151920318604,
917
+ "learning_rate": 4.716090942010823e-05,
918
+ "loss": 0.752,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 0.7190887882530533,
923
+ "grad_norm": 1.333355188369751,
924
+ "learning_rate": 4.708651072452993e-05,
925
+ "loss": 0.7336,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 0.724578015644298,
930
+ "grad_norm": 1.6440070867538452,
931
+ "learning_rate": 4.701121003914537e-05,
932
+ "loss": 0.7333,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 0.7300672430355427,
937
+ "grad_norm": 1.848791480064392,
938
+ "learning_rate": 4.693501043915514e-05,
939
+ "loss": 0.7648,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 0.7355564704267874,
944
+ "grad_norm": 1.593891978263855,
945
+ "learning_rate": 4.685791503647052e-05,
946
+ "loss": 0.787,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 0.7410456978180321,
951
+ "grad_norm": 1.6957751512527466,
952
+ "learning_rate": 4.6779926979586475e-05,
953
+ "loss": 0.7212,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 0.7465349252092768,
958
+ "grad_norm": 1.3588330745697021,
959
+ "learning_rate": 4.6701049453453e-05,
960
+ "loss": 0.7175,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 0.7520241526005215,
965
+ "grad_norm": 1.462112307548523,
966
+ "learning_rate": 4.662128567934509e-05,
967
+ "loss": 0.7133,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 0.7575133799917662,
972
+ "grad_norm": 1.5633749961853027,
973
+ "learning_rate": 4.654063891473115e-05,
974
+ "loss": 0.6978,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 0.7630026073830108,
979
+ "grad_norm": 1.7605217695236206,
980
+ "learning_rate": 4.645911245314e-05,
981
+ "loss": 0.7019,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 0.7684918347742555,
986
+ "grad_norm": 1.6843842267990112,
987
+ "learning_rate": 4.637670962402636e-05,
988
+ "loss": 0.7483,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 0.7739810621655002,
993
+ "grad_norm": 2.015845537185669,
994
+ "learning_rate": 4.629343379263487e-05,
995
+ "loss": 0.7208,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 0.7794702895567449,
1000
+ "grad_norm": 1.8158447742462158,
1001
+ "learning_rate": 4.620928835986267e-05,
1002
+ "loss": 0.7733,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 0.7849595169479896,
1007
+ "grad_norm": 1.7793387174606323,
1008
+ "learning_rate": 4.6124276762120485e-05,
1009
+ "loss": 0.7111,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 0.7904487443392343,
1014
+ "grad_norm": 1.6674373149871826,
1015
+ "learning_rate": 4.603840247119233e-05,
1016
+ "loss": 0.6663,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 0.795937971730479,
1021
+ "grad_norm": 1.4028520584106445,
1022
+ "learning_rate": 4.595166899409368e-05,
1023
+ "loss": 0.7692,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 0.8014271991217237,
1028
+ "grad_norm": 1.6022142171859741,
1029
+ "learning_rate": 4.5864079872928265e-05,
1030
+ "loss": 0.7305,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 0.8069164265129684,
1035
+ "grad_norm": 1.4971508979797363,
1036
+ "learning_rate": 4.577563868474344e-05,
1037
+ "loss": 0.6875,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 0.8124056539042129,
1042
+ "grad_norm": 1.8490726947784424,
1043
+ "learning_rate": 4.5686349041384055e-05,
1044
+ "loss": 0.6849,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 0.8178948812954576,
1049
+ "grad_norm": 1.9100017547607422,
1050
+ "learning_rate": 4.559621458934498e-05,
1051
+ "loss": 0.6506,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 0.8233841086867023,
1056
+ "grad_norm": 1.6782461404800415,
1057
+ "learning_rate": 4.550523900962219e-05,
1058
+ "loss": 0.704,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 0.828873336077947,
1063
+ "grad_norm": 2.1226425170898438,
1064
+ "learning_rate": 4.541342601756242e-05,
1065
+ "loss": 0.6988,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 0.8343625634691917,
1070
+ "grad_norm": 1.658097267150879,
1071
+ "learning_rate": 4.532077936271144e-05,
1072
+ "loss": 0.705,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 0.8398517908604364,
1077
+ "grad_norm": 1.8850988149642944,
1078
+ "learning_rate": 4.522730282866093e-05,
1079
+ "loss": 0.6801,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 0.8453410182516811,
1084
+ "grad_norm": 1.5480940341949463,
1085
+ "learning_rate": 4.513300023289397e-05,
1086
+ "loss": 0.6308,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 0.8508302456429258,
1091
+ "grad_norm": 1.7652947902679443,
1092
+ "learning_rate": 4.503787542662912e-05,
1093
+ "loss": 0.6731,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 0.8563194730341704,
1098
+ "grad_norm": 1.902155876159668,
1099
+ "learning_rate": 4.494193229466314e-05,
1100
+ "loss": 0.7404,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 0.8618087004254151,
1105
+ "grad_norm": 2.1436920166015625,
1106
+ "learning_rate": 4.4845174755212385e-05,
1107
+ "loss": 0.6884,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 0.8672979278166598,
1112
+ "grad_norm": 1.6139538288116455,
1113
+ "learning_rate": 4.47476067597527e-05,
1114
+ "loss": 0.6947,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 0.8727871552079045,
1119
+ "grad_norm": 1.5919870138168335,
1120
+ "learning_rate": 4.464923229285816e-05,
1121
+ "loss": 0.6982,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 0.8782763825991492,
1126
+ "grad_norm": 1.6209038496017456,
1127
+ "learning_rate": 4.4550055372038225e-05,
1128
+ "loss": 0.7124,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 0.8837656099903939,
1133
+ "grad_norm": 1.631515383720398,
1134
+ "learning_rate": 4.445008004757376e-05,
1135
+ "loss": 0.6771,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 0.8892548373816386,
1140
+ "grad_norm": 1.4836645126342773,
1141
+ "learning_rate": 4.434931040235159e-05,
1142
+ "loss": 0.6272,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 0.8947440647728833,
1147
+ "grad_norm": 1.3640625476837158,
1148
+ "learning_rate": 4.4247750551697756e-05,
1149
+ "loss": 0.6477,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 0.900233292164128,
1154
+ "grad_norm": 1.5562537908554077,
1155
+ "learning_rate": 4.414540464320945e-05,
1156
+ "loss": 0.7128,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 0.9057225195553725,
1161
+ "grad_norm": 1.548048973083496,
1162
+ "learning_rate": 4.404227685658565e-05,
1163
+ "loss": 0.7098,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 0.9112117469466172,
1168
+ "grad_norm": 1.613368034362793,
1169
+ "learning_rate": 4.39383714034564e-05,
1170
+ "loss": 0.6926,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 0.9167009743378619,
1175
+ "grad_norm": 1.789654016494751,
1176
+ "learning_rate": 4.383369252721084e-05,
1177
+ "loss": 0.6398,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 0.9221902017291066,
1182
+ "grad_norm": 1.625928282737732,
1183
+ "learning_rate": 4.372824450282388e-05,
1184
+ "loss": 0.7087,
1185
+ "step": 1680
1186
+ },
1187
+ {
1188
+ "epoch": 0.9276794291203513,
1189
+ "grad_norm": 1.686936855316162,
1190
+ "learning_rate": 4.362203163668164e-05,
1191
+ "loss": 0.6764,
1192
+ "step": 1690
1193
+ },
1194
+ {
1195
+ "epoch": 0.933168656511596,
1196
+ "grad_norm": 1.6460559368133545,
1197
+ "learning_rate": 4.351505826640555e-05,
1198
+ "loss": 0.6969,
1199
+ "step": 1700
1200
+ },
1201
+ {
1202
+ "epoch": 0.9386578839028407,
1203
+ "grad_norm": 1.6267837285995483,
1204
+ "learning_rate": 4.3407328760675245e-05,
1205
+ "loss": 0.672,
1206
+ "step": 1710
1207
+ },
1208
+ {
1209
+ "epoch": 0.9441471112940854,
1210
+ "grad_norm": 1.5070548057556152,
1211
+ "learning_rate": 4.329884751905014e-05,
1212
+ "loss": 0.6586,
1213
+ "step": 1720
1214
+ },
1215
+ {
1216
+ "epoch": 0.94963633868533,
1217
+ "grad_norm": 1.8759193420410156,
1218
+ "learning_rate": 4.3189618971789747e-05,
1219
+ "loss": 0.6601,
1220
+ "step": 1730
1221
+ },
1222
+ {
1223
+ "epoch": 0.9551255660765747,
1224
+ "grad_norm": 1.6111549139022827,
1225
+ "learning_rate": 4.307964757967273e-05,
1226
+ "loss": 0.7042,
1227
+ "step": 1740
1228
+ },
1229
+ {
1230
+ "epoch": 0.9606147934678194,
1231
+ "grad_norm": 1.3748118877410889,
1232
+ "learning_rate": 4.2968937833814784e-05,
1233
+ "loss": 0.6573,
1234
+ "step": 1750
1235
+ },
1236
+ {
1237
+ "epoch": 0.9661040208590641,
1238
+ "grad_norm": 1.7284533977508545,
1239
+ "learning_rate": 4.285749425548518e-05,
1240
+ "loss": 0.619,
1241
+ "step": 1760
1242
+ },
1243
+ {
1244
+ "epoch": 0.9715932482503088,
1245
+ "grad_norm": 1.5528743267059326,
1246
+ "learning_rate": 4.274532139592211e-05,
1247
+ "loss": 0.6601,
1248
+ "step": 1770
1249
+ },
1250
+ {
1251
+ "epoch": 0.9770824756415535,
1252
+ "grad_norm": 1.6220190525054932,
1253
+ "learning_rate": 4.2632423836146885e-05,
1254
+ "loss": 0.6449,
1255
+ "step": 1780
1256
+ },
1257
+ {
1258
+ "epoch": 0.9825717030327982,
1259
+ "grad_norm": 2.00435471534729,
1260
+ "learning_rate": 4.251880618677678e-05,
1261
+ "loss": 0.6404,
1262
+ "step": 1790
1263
+ },
1264
+ {
1265
+ "epoch": 0.9880609304240429,
1266
+ "grad_norm": 1.8456660509109497,
1267
+ "learning_rate": 4.240447308783679e-05,
1268
+ "loss": 0.7124,
1269
+ "step": 1800
1270
+ },
1271
+ {
1272
+ "epoch": 0.9935501578152875,
1273
+ "grad_norm": 1.8724040985107422,
1274
+ "learning_rate": 4.2289429208570094e-05,
1275
+ "loss": 0.7138,
1276
+ "step": 1810
1277
+ },
1278
+ {
1279
+ "epoch": 0.9990393852065321,
1280
+ "grad_norm": 1.441105842590332,
1281
+ "learning_rate": 4.217367924724741e-05,
1282
+ "loss": 0.7439,
1283
+ "step": 1820
1284
+ },
1285
+ {
1286
+ "epoch": 1.0045286125977768,
1287
+ "grad_norm": 1.392276406288147,
1288
+ "learning_rate": 4.2057227930975066e-05,
1289
+ "loss": 0.4876,
1290
+ "step": 1830
1291
+ },
1292
+ {
1293
+ "epoch": 1.0100178399890216,
1294
+ "grad_norm": 1.4682689905166626,
1295
+ "learning_rate": 4.194008001550204e-05,
1296
+ "loss": 0.4949,
1297
+ "step": 1840
1298
+ },
1299
+ {
1300
+ "epoch": 1.0155070673802662,
1301
+ "grad_norm": 1.7317707538604736,
1302
+ "learning_rate": 4.1822240285025635e-05,
1303
+ "loss": 0.5329,
1304
+ "step": 1850
1305
+ },
1306
+ {
1307
+ "epoch": 1.020996294771511,
1308
+ "grad_norm": 1.9328278303146362,
1309
+ "learning_rate": 4.170371355199621e-05,
1310
+ "loss": 0.5068,
1311
+ "step": 1860
1312
+ },
1313
+ {
1314
+ "epoch": 1.0264855221627556,
1315
+ "grad_norm": 1.7879178524017334,
1316
+ "learning_rate": 4.158450465692051e-05,
1317
+ "loss": 0.5112,
1318
+ "step": 1870
1319
+ },
1320
+ {
1321
+ "epoch": 1.0319747495540004,
1322
+ "grad_norm": 1.6801658868789673,
1323
+ "learning_rate": 4.146461846816411e-05,
1324
+ "loss": 0.4826,
1325
+ "step": 1880
1326
+ },
1327
+ {
1328
+ "epoch": 1.037463976945245,
1329
+ "grad_norm": 1.6541537046432495,
1330
+ "learning_rate": 4.1344059881752534e-05,
1331
+ "loss": 0.4522,
1332
+ "step": 1890
1333
+ },
1334
+ {
1335
+ "epoch": 1.0429532043364897,
1336
+ "grad_norm": 2.27681303024292,
1337
+ "learning_rate": 4.1222833821171315e-05,
1338
+ "loss": 0.4726,
1339
+ "step": 1900
1340
+ },
1341
+ {
1342
+ "epoch": 1.0484424317277343,
1343
+ "grad_norm": 1.6335279941558838,
1344
+ "learning_rate": 4.110094523716492e-05,
1345
+ "loss": 0.469,
1346
+ "step": 1910
1347
+ },
1348
+ {
1349
+ "epoch": 1.053931659118979,
1350
+ "grad_norm": 1.730760931968689,
1351
+ "learning_rate": 4.0978399107534584e-05,
1352
+ "loss": 0.4554,
1353
+ "step": 1920
1354
+ },
1355
+ {
1356
+ "epoch": 1.0594208865102237,
1357
+ "grad_norm": 1.636106014251709,
1358
+ "learning_rate": 4.0855200436935e-05,
1359
+ "loss": 0.4914,
1360
+ "step": 1930
1361
+ },
1362
+ {
1363
+ "epoch": 1.0649101139014683,
1364
+ "grad_norm": 1.855231523513794,
1365
+ "learning_rate": 4.073135425666997e-05,
1366
+ "loss": 0.4609,
1367
+ "step": 1940
1368
+ },
1369
+ {
1370
+ "epoch": 1.070399341292713,
1371
+ "grad_norm": 2.0908730030059814,
1372
+ "learning_rate": 4.0606865624486875e-05,
1373
+ "loss": 0.472,
1374
+ "step": 1950
1375
+ },
1376
+ {
1377
+ "epoch": 1.0758885686839577,
1378
+ "grad_norm": 1.7960741519927979,
1379
+ "learning_rate": 4.048173962437019e-05,
1380
+ "loss": 0.5072,
1381
+ "step": 1960
1382
+ },
1383
+ {
1384
+ "epoch": 1.0813777960752025,
1385
+ "grad_norm": 1.6274662017822266,
1386
+ "learning_rate": 4.035598136633378e-05,
1387
+ "loss": 0.455,
1388
+ "step": 1970
1389
+ },
1390
+ {
1391
+ "epoch": 1.086867023466447,
1392
+ "grad_norm": 1.898768663406372,
1393
+ "learning_rate": 4.0229595986212304e-05,
1394
+ "loss": 0.5023,
1395
+ "step": 1980
1396
+ },
1397
+ {
1398
+ "epoch": 1.0923562508576918,
1399
+ "grad_norm": 1.6245406866073608,
1400
+ "learning_rate": 4.0102588645451396e-05,
1401
+ "loss": 0.4863,
1402
+ "step": 1990
1403
+ },
1404
+ {
1405
+ "epoch": 1.0978454782489364,
1406
+ "grad_norm": 1.440356731414795,
1407
+ "learning_rate": 3.997496453089692e-05,
1408
+ "loss": 0.4912,
1409
+ "step": 2000
1410
+ },
1411
+ {
1412
+ "epoch": 1.1033347056401812,
1413
+ "grad_norm": 1.9108120203018188,
1414
+ "learning_rate": 3.984672885458312e-05,
1415
+ "loss": 0.4691,
1416
+ "step": 2010
1417
+ },
1418
+ {
1419
+ "epoch": 1.1088239330314258,
1420
+ "grad_norm": 1.7355122566223145,
1421
+ "learning_rate": 3.971788685351978e-05,
1422
+ "loss": 0.4965,
1423
+ "step": 2020
1424
+ },
1425
+ {
1426
+ "epoch": 1.1143131604226706,
1427
+ "grad_norm": 1.7125989198684692,
1428
+ "learning_rate": 3.9588443789478366e-05,
1429
+ "loss": 0.468,
1430
+ "step": 2030
1431
+ },
1432
+ {
1433
+ "epoch": 1.1198023878139152,
1434
+ "grad_norm": 1.8434703350067139,
1435
+ "learning_rate": 3.945840494877709e-05,
1436
+ "loss": 0.4886,
1437
+ "step": 2040
1438
+ },
1439
+ {
1440
+ "epoch": 1.12529161520516,
1441
+ "grad_norm": 2.302004337310791,
1442
+ "learning_rate": 3.934086499185402e-05,
1443
+ "loss": 0.4932,
1444
+ "step": 2050
1445
+ },
1446
+ {
1447
+ "epoch": 1.1307808425964045,
1448
+ "grad_norm": 1.931429147720337,
1449
+ "learning_rate": 3.9209708826272075e-05,
1450
+ "loss": 0.5121,
1451
+ "step": 2060
1452
+ },
1453
+ {
1454
+ "epoch": 1.1362700699876491,
1455
+ "grad_norm": 1.889414668083191,
1456
+ "learning_rate": 3.907797235116677e-05,
1457
+ "loss": 0.5094,
1458
+ "step": 2070
1459
+ },
1460
+ {
1461
+ "epoch": 1.141759297378894,
1462
+ "grad_norm": 2.243352174758911,
1463
+ "learning_rate": 3.894566094651682e-05,
1464
+ "loss": 0.488,
1465
+ "step": 2080
1466
+ },
1467
+ {
1468
+ "epoch": 1.1472485247701387,
1469
+ "grad_norm": 1.6855474710464478,
1470
+ "learning_rate": 3.881278001578046e-05,
1471
+ "loss": 0.531,
1472
+ "step": 2090
1473
+ },
1474
+ {
1475
+ "epoch": 1.1527377521613833,
1476
+ "grad_norm": 2.328468084335327,
1477
+ "learning_rate": 3.8679334985674786e-05,
1478
+ "loss": 0.5397,
1479
+ "step": 2100
1480
+ },
1481
+ {
1482
+ "epoch": 1.1582269795526279,
1483
+ "grad_norm": 1.8057246208190918,
1484
+ "learning_rate": 3.854533130595408e-05,
1485
+ "loss": 0.4964,
1486
+ "step": 2110
1487
+ },
1488
+ {
1489
+ "epoch": 1.1637162069438727,
1490
+ "grad_norm": 1.6702812910079956,
1491
+ "learning_rate": 3.8410774449187315e-05,
1492
+ "loss": 0.5011,
1493
+ "step": 2120
1494
+ },
1495
+ {
1496
+ "epoch": 1.1692054343351173,
1497
+ "grad_norm": 1.4972355365753174,
1498
+ "learning_rate": 3.827566991053461e-05,
1499
+ "loss": 0.4922,
1500
+ "step": 2130
1501
+ },
1502
+ {
1503
+ "epoch": 1.174694661726362,
1504
+ "grad_norm": 1.739022970199585,
1505
+ "learning_rate": 3.814002320752287e-05,
1506
+ "loss": 0.4309,
1507
+ "step": 2140
1508
+ },
1509
+ {
1510
+ "epoch": 1.1801838891176066,
1511
+ "grad_norm": 1.8909087181091309,
1512
+ "learning_rate": 3.8003839879820377e-05,
1513
+ "loss": 0.4761,
1514
+ "step": 2150
1515
+ },
1516
+ {
1517
+ "epoch": 1.1856731165088514,
1518
+ "grad_norm": 1.9765682220458984,
1519
+ "learning_rate": 3.786712548901064e-05,
1520
+ "loss": 0.4895,
1521
+ "step": 2160
1522
+ },
1523
+ {
1524
+ "epoch": 1.191162343900096,
1525
+ "grad_norm": 2.1266307830810547,
1526
+ "learning_rate": 3.772988561836517e-05,
1527
+ "loss": 0.4894,
1528
+ "step": 2170
1529
+ },
1530
+ {
1531
+ "epoch": 1.1966515712913408,
1532
+ "grad_norm": 1.7856028079986572,
1533
+ "learning_rate": 3.759212587261559e-05,
1534
+ "loss": 0.4812,
1535
+ "step": 2180
1536
+ },
1537
+ {
1538
+ "epoch": 1.2021407986825854,
1539
+ "grad_norm": 1.8546531200408936,
1540
+ "learning_rate": 3.745385187772463e-05,
1541
+ "loss": 0.4928,
1542
+ "step": 2190
1543
+ },
1544
+ {
1545
+ "epoch": 1.2076300260738302,
1546
+ "grad_norm": 1.8596118688583374,
1547
+ "learning_rate": 3.731506928065641e-05,
1548
+ "loss": 0.512,
1549
+ "step": 2200
1550
+ },
1551
+ {
1552
+ "epoch": 1.2131192534650748,
1553
+ "grad_norm": 2.024635076522827,
1554
+ "learning_rate": 3.717578374914585e-05,
1555
+ "loss": 0.4715,
1556
+ "step": 2210
1557
+ },
1558
+ {
1559
+ "epoch": 1.2186084808563196,
1560
+ "grad_norm": 2.1620028018951416,
1561
+ "learning_rate": 3.703600097146718e-05,
1562
+ "loss": 0.4754,
1563
+ "step": 2220
1564
+ },
1565
+ {
1566
+ "epoch": 1.2240977082475641,
1567
+ "grad_norm": 1.9437251091003418,
1568
+ "learning_rate": 3.68957266562016e-05,
1569
+ "loss": 0.475,
1570
+ "step": 2230
1571
+ },
1572
+ {
1573
+ "epoch": 1.229586935638809,
1574
+ "grad_norm": 2.7284131050109863,
1575
+ "learning_rate": 3.675496653200425e-05,
1576
+ "loss": 0.4901,
1577
+ "step": 2240
1578
+ },
1579
+ {
1580
+ "epoch": 1.2350761630300535,
1581
+ "grad_norm": 2.2666921615600586,
1582
+ "learning_rate": 3.661372634737013e-05,
1583
+ "loss": 0.4694,
1584
+ "step": 2250
1585
+ },
1586
+ {
1587
+ "epoch": 1.240565390421298,
1588
+ "grad_norm": 1.5657079219818115,
1589
+ "learning_rate": 3.647201187039946e-05,
1590
+ "loss": 0.4809,
1591
+ "step": 2260
1592
+ },
1593
+ {
1594
+ "epoch": 1.246054617812543,
1595
+ "grad_norm": 2.3592708110809326,
1596
+ "learning_rate": 3.632982888856202e-05,
1597
+ "loss": 0.4539,
1598
+ "step": 2270
1599
+ },
1600
+ {
1601
+ "epoch": 1.2515438452037877,
1602
+ "grad_norm": 1.7647560834884644,
1603
+ "learning_rate": 3.6187183208460844e-05,
1604
+ "loss": 0.4945,
1605
+ "step": 2280
1606
+ },
1607
+ {
1608
+ "epoch": 1.2570330725950323,
1609
+ "grad_norm": 2.0273566246032715,
1610
+ "learning_rate": 3.604408065559508e-05,
1611
+ "loss": 0.4853,
1612
+ "step": 2290
1613
+ },
1614
+ {
1615
+ "epoch": 1.2625222999862769,
1616
+ "grad_norm": 2.0692555904388428,
1617
+ "learning_rate": 3.590052707412208e-05,
1618
+ "loss": 0.498,
1619
+ "step": 2300
1620
+ },
1621
+ {
1622
+ "epoch": 1.2680115273775217,
1623
+ "grad_norm": 2.35859751701355,
1624
+ "learning_rate": 3.575652832661872e-05,
1625
+ "loss": 0.5287,
1626
+ "step": 2310
1627
+ },
1628
+ {
1629
+ "epoch": 1.2735007547687662,
1630
+ "grad_norm": 1.8455514907836914,
1631
+ "learning_rate": 3.5612090293841994e-05,
1632
+ "loss": 0.5035,
1633
+ "step": 2320
1634
+ },
1635
+ {
1636
+ "epoch": 1.278989982160011,
1637
+ "grad_norm": 2.233416795730591,
1638
+ "learning_rate": 3.5467218874488837e-05,
1639
+ "loss": 0.5078,
1640
+ "step": 2330
1641
+ },
1642
+ {
1643
+ "epoch": 1.2844792095512556,
1644
+ "grad_norm": 1.7934064865112305,
1645
+ "learning_rate": 3.5321919984955244e-05,
1646
+ "loss": 0.5015,
1647
+ "step": 2340
1648
+ },
1649
+ {
1650
+ "epoch": 1.2899684369425004,
1651
+ "grad_norm": 1.753578543663025,
1652
+ "learning_rate": 3.517619955909463e-05,
1653
+ "loss": 0.4556,
1654
+ "step": 2350
1655
+ },
1656
+ {
1657
+ "epoch": 1.295457664333745,
1658
+ "grad_norm": 1.9207135438919067,
1659
+ "learning_rate": 3.5030063547975525e-05,
1660
+ "loss": 0.4417,
1661
+ "step": 2360
1662
+ },
1663
+ {
1664
+ "epoch": 1.3009468917249898,
1665
+ "grad_norm": 1.77664315700531,
1666
+ "learning_rate": 3.488351791963849e-05,
1667
+ "loss": 0.435,
1668
+ "step": 2370
1669
+ },
1670
+ {
1671
+ "epoch": 1.3064361191162344,
1672
+ "grad_norm": 1.5567264556884766,
1673
+ "learning_rate": 3.473656865885248e-05,
1674
+ "loss": 0.4872,
1675
+ "step": 2380
1676
+ },
1677
+ {
1678
+ "epoch": 1.3119253465074792,
1679
+ "grad_norm": 1.9232813119888306,
1680
+ "learning_rate": 3.4589221766870306e-05,
1681
+ "loss": 0.479,
1682
+ "step": 2390
1683
+ },
1684
+ {
1685
+ "epoch": 1.3174145738987237,
1686
+ "grad_norm": 1.6090134382247925,
1687
+ "learning_rate": 3.444148326118366e-05,
1688
+ "loss": 0.577,
1689
+ "step": 2400
1690
+ },
1691
+ {
1692
+ "epoch": 1.3229038012899683,
1693
+ "grad_norm": 1.7962336540222168,
1694
+ "learning_rate": 3.4293359175277314e-05,
1695
+ "loss": 0.4801,
1696
+ "step": 2410
1697
+ },
1698
+ {
1699
+ "epoch": 1.3283930286812131,
1700
+ "grad_norm": 2.1019630432128906,
1701
+ "learning_rate": 3.414485555838273e-05,
1702
+ "loss": 0.4884,
1703
+ "step": 2420
1704
+ },
1705
+ {
1706
+ "epoch": 1.333882256072458,
1707
+ "grad_norm": 1.8056087493896484,
1708
+ "learning_rate": 3.3995978475231024e-05,
1709
+ "loss": 0.4527,
1710
+ "step": 2430
1711
+ },
1712
+ {
1713
+ "epoch": 1.3393714834637025,
1714
+ "grad_norm": 1.7557107210159302,
1715
+ "learning_rate": 3.3846734005805254e-05,
1716
+ "loss": 0.4831,
1717
+ "step": 2440
1718
+ },
1719
+ {
1720
+ "epoch": 1.344860710854947,
1721
+ "grad_norm": 1.7773773670196533,
1722
+ "learning_rate": 3.369712824509217e-05,
1723
+ "loss": 0.4994,
1724
+ "step": 2450
1725
+ },
1726
+ {
1727
+ "epoch": 1.3503499382461919,
1728
+ "grad_norm": 1.7856857776641846,
1729
+ "learning_rate": 3.354716730283327e-05,
1730
+ "loss": 0.4761,
1731
+ "step": 2460
1732
+ },
1733
+ {
1734
+ "epoch": 1.3558391656374364,
1735
+ "grad_norm": 2.119858980178833,
1736
+ "learning_rate": 3.3396857303275296e-05,
1737
+ "loss": 0.4891,
1738
+ "step": 2470
1739
+ },
1740
+ {
1741
+ "epoch": 1.3613283930286812,
1742
+ "grad_norm": 1.9912039041519165,
1743
+ "learning_rate": 3.324620438492011e-05,
1744
+ "loss": 0.4415,
1745
+ "step": 2480
1746
+ },
1747
+ {
1748
+ "epoch": 1.3668176204199258,
1749
+ "grad_norm": 2.347066879272461,
1750
+ "learning_rate": 3.309521470027403e-05,
1751
+ "loss": 0.4733,
1752
+ "step": 2490
1753
+ },
1754
+ {
1755
+ "epoch": 1.3723068478111706,
1756
+ "grad_norm": 1.963139533996582,
1757
+ "learning_rate": 3.294389441559655e-05,
1758
+ "loss": 0.4626,
1759
+ "step": 2500
1760
+ },
1761
+ {
1762
+ "epoch": 1.3777960752024152,
1763
+ "grad_norm": 2.103672742843628,
1764
+ "learning_rate": 3.279224971064851e-05,
1765
+ "loss": 0.5168,
1766
+ "step": 2510
1767
+ },
1768
+ {
1769
+ "epoch": 1.38328530259366,
1770
+ "grad_norm": 1.741493821144104,
1771
+ "learning_rate": 3.2640286778439746e-05,
1772
+ "loss": 0.4687,
1773
+ "step": 2520
1774
+ },
1775
+ {
1776
+ "epoch": 1.3887745299849046,
1777
+ "grad_norm": 1.9451817274093628,
1778
+ "learning_rate": 3.248801182497615e-05,
1779
+ "loss": 0.454,
1780
+ "step": 2530
1781
+ },
1782
+ {
1783
+ "epoch": 1.3942637573761494,
1784
+ "grad_norm": 2.4190995693206787,
1785
+ "learning_rate": 3.233543106900624e-05,
1786
+ "loss": 0.4594,
1787
+ "step": 2540
1788
+ },
1789
+ {
1790
+ "epoch": 1.399752984767394,
1791
+ "grad_norm": 1.543632984161377,
1792
+ "learning_rate": 3.21825507417672e-05,
1793
+ "loss": 0.4408,
1794
+ "step": 2550
1795
+ },
1796
+ {
1797
+ "epoch": 1.4052422121586385,
1798
+ "grad_norm": 2.006373882293701,
1799
+ "learning_rate": 3.202937708673033e-05,
1800
+ "loss": 0.4802,
1801
+ "step": 2560
1802
+ },
1803
+ {
1804
+ "epoch": 1.4107314395498833,
1805
+ "grad_norm": 1.912208914756775,
1806
+ "learning_rate": 3.1875916359346214e-05,
1807
+ "loss": 0.4731,
1808
+ "step": 2570
1809
+ },
1810
+ {
1811
+ "epoch": 1.4162206669411281,
1812
+ "grad_norm": 1.6737933158874512,
1813
+ "learning_rate": 3.17221748267891e-05,
1814
+ "loss": 0.454,
1815
+ "step": 2580
1816
+ },
1817
+ {
1818
+ "epoch": 1.4217098943323727,
1819
+ "grad_norm": 1.9672836065292358,
1820
+ "learning_rate": 3.156815876770105e-05,
1821
+ "loss": 0.4229,
1822
+ "step": 2590
1823
+ },
1824
+ {
1825
+ "epoch": 1.4271991217236173,
1826
+ "grad_norm": 1.512810230255127,
1827
+ "learning_rate": 3.1413874471935496e-05,
1828
+ "loss": 0.4896,
1829
+ "step": 2600
1830
+ },
1831
+ {
1832
+ "epoch": 1.432688349114862,
1833
+ "grad_norm": 1.8552961349487305,
1834
+ "learning_rate": 3.125932824030037e-05,
1835
+ "loss": 0.4808,
1836
+ "step": 2610
1837
+ },
1838
+ {
1839
+ "epoch": 1.438177576506107,
1840
+ "grad_norm": 1.7483348846435547,
1841
+ "learning_rate": 3.110452638430081e-05,
1842
+ "loss": 0.4271,
1843
+ "step": 2620
1844
+ },
1845
+ {
1846
+ "epoch": 1.4436668038973515,
1847
+ "grad_norm": 1.7746537923812866,
1848
+ "learning_rate": 3.094947522588135e-05,
1849
+ "loss": 0.4618,
1850
+ "step": 2630
1851
+ },
1852
+ {
1853
+ "epoch": 1.449156031288596,
1854
+ "grad_norm": 2.1067216396331787,
1855
+ "learning_rate": 3.079418109716778e-05,
1856
+ "loss": 0.4765,
1857
+ "step": 2640
1858
+ },
1859
+ {
1860
+ "epoch": 1.4546452586798408,
1861
+ "grad_norm": 1.6052168607711792,
1862
+ "learning_rate": 3.063865034020857e-05,
1863
+ "loss": 0.4596,
1864
+ "step": 2650
1865
+ },
1866
+ {
1867
+ "epoch": 1.4601344860710854,
1868
+ "grad_norm": 1.6968189477920532,
1869
+ "learning_rate": 3.0482889306715813e-05,
1870
+ "loss": 0.4384,
1871
+ "step": 2660
1872
+ },
1873
+ {
1874
+ "epoch": 1.4656237134623302,
1875
+ "grad_norm": 1.869379997253418,
1876
+ "learning_rate": 3.032690435780584e-05,
1877
+ "loss": 0.4872,
1878
+ "step": 2670
1879
+ },
1880
+ {
1881
+ "epoch": 1.4711129408535748,
1882
+ "grad_norm": 1.8812456130981445,
1883
+ "learning_rate": 3.017070186373949e-05,
1884
+ "loss": 0.4581,
1885
+ "step": 2680
1886
+ },
1887
+ {
1888
+ "epoch": 1.4766021682448196,
1889
+ "grad_norm": 1.99275803565979,
1890
+ "learning_rate": 3.001428820366187e-05,
1891
+ "loss": 0.49,
1892
+ "step": 2690
1893
+ },
1894
+ {
1895
+ "epoch": 1.4820913956360642,
1896
+ "grad_norm": 1.6111352443695068,
1897
+ "learning_rate": 2.9857669765341928e-05,
1898
+ "loss": 0.4262,
1899
+ "step": 2700
1900
+ },
1901
+ {
1902
+ "epoch": 1.487580623027309,
1903
+ "grad_norm": 2.6115357875823975,
1904
+ "learning_rate": 2.9700852944911512e-05,
1905
+ "loss": 0.4774,
1906
+ "step": 2710
1907
+ },
1908
+ {
1909
+ "epoch": 1.4930698504185536,
1910
+ "grad_norm": 1.8144830465316772,
1911
+ "learning_rate": 2.9543844146604195e-05,
1912
+ "loss": 0.4618,
1913
+ "step": 2720
1914
+ },
1915
+ {
1916
+ "epoch": 1.4985590778097984,
1917
+ "grad_norm": 1.7375366687774658,
1918
+ "learning_rate": 2.938664978249372e-05,
1919
+ "loss": 0.4278,
1920
+ "step": 2730
1921
+ },
1922
+ {
1923
+ "epoch": 1.504048305201043,
1924
+ "grad_norm": 1.914023756980896,
1925
+ "learning_rate": 2.9229276272232146e-05,
1926
+ "loss": 0.4706,
1927
+ "step": 2740
1928
+ },
1929
+ {
1930
+ "epoch": 1.5095375325922875,
1931
+ "grad_norm": 1.7386229038238525,
1932
+ "learning_rate": 2.907173004278768e-05,
1933
+ "loss": 0.4308,
1934
+ "step": 2750
1935
+ },
1936
+ {
1937
+ "epoch": 1.5150267599835323,
1938
+ "grad_norm": 1.5574982166290283,
1939
+ "learning_rate": 2.8914017528182185e-05,
1940
+ "loss": 0.4487,
1941
+ "step": 2760
1942
+ },
1943
+ {
1944
+ "epoch": 1.5205159873747771,
1945
+ "grad_norm": 2.144409418106079,
1946
+ "learning_rate": 2.8756145169228432e-05,
1947
+ "loss": 0.4232,
1948
+ "step": 2770
1949
+ },
1950
+ {
1951
+ "epoch": 1.5260052147660217,
1952
+ "grad_norm": 2.5904343128204346,
1953
+ "learning_rate": 2.859811941326709e-05,
1954
+ "loss": 0.4603,
1955
+ "step": 2780
1956
+ },
1957
+ {
1958
+ "epoch": 1.5314944421572663,
1959
+ "grad_norm": 2.3824493885040283,
1960
+ "learning_rate": 2.8439946713903354e-05,
1961
+ "loss": 0.4649,
1962
+ "step": 2790
1963
+ },
1964
+ {
1965
+ "epoch": 1.536983669548511,
1966
+ "grad_norm": 2.1540448665618896,
1967
+ "learning_rate": 2.8281633530743497e-05,
1968
+ "loss": 0.4988,
1969
+ "step": 2800
1970
+ },
1971
+ {
1972
+ "epoch": 1.5424728969397559,
1973
+ "grad_norm": 2.121973752975464,
1974
+ "learning_rate": 2.8123186329130942e-05,
1975
+ "loss": 0.4795,
1976
+ "step": 2810
1977
+ },
1978
+ {
1979
+ "epoch": 1.5479621243310004,
1980
+ "grad_norm": 1.8560881614685059,
1981
+ "learning_rate": 2.7964611579882317e-05,
1982
+ "loss": 0.427,
1983
+ "step": 2820
1984
+ },
1985
+ {
1986
+ "epoch": 1.553451351722245,
1987
+ "grad_norm": 2.625507354736328,
1988
+ "learning_rate": 2.7805915759023153e-05,
1989
+ "loss": 0.4982,
1990
+ "step": 2830
1991
+ },
1992
+ {
1993
+ "epoch": 1.5589405791134898,
1994
+ "grad_norm": 1.8594845533370972,
1995
+ "learning_rate": 2.764710534752342e-05,
1996
+ "loss": 0.4489,
1997
+ "step": 2840
1998
+ },
1999
+ {
2000
+ "epoch": 1.5644298065047346,
2001
+ "grad_norm": 1.9746872186660767,
2002
+ "learning_rate": 2.748818683103285e-05,
2003
+ "loss": 0.4177,
2004
+ "step": 2850
2005
+ },
2006
+ {
2007
+ "epoch": 1.569919033895979,
2008
+ "grad_norm": 1.9741085767745972,
2009
+ "learning_rate": 2.7329166699616064e-05,
2010
+ "loss": 0.4816,
2011
+ "step": 2860
2012
+ },
2013
+ {
2014
+ "epoch": 1.5754082612872238,
2015
+ "grad_norm": 1.9904859066009521,
2016
+ "learning_rate": 2.7170051447487532e-05,
2017
+ "loss": 0.4392,
2018
+ "step": 2870
2019
+ },
2020
+ {
2021
+ "epoch": 1.5808974886784686,
2022
+ "grad_norm": 1.9376888275146484,
2023
+ "learning_rate": 2.7010847572746356e-05,
2024
+ "loss": 0.5002,
2025
+ "step": 2880
2026
+ },
2027
+ {
2028
+ "epoch": 1.5863867160697132,
2029
+ "grad_norm": 1.6673862934112549,
2030
+ "learning_rate": 2.6851561577110874e-05,
2031
+ "loss": 0.437,
2032
+ "step": 2890
2033
+ },
2034
+ {
2035
+ "epoch": 1.5918759434609577,
2036
+ "grad_norm": 1.8041437864303589,
2037
+ "learning_rate": 2.6692199965653185e-05,
2038
+ "loss": 0.4565,
2039
+ "step": 2900
2040
+ },
2041
+ {
2042
+ "epoch": 1.5973651708522025,
2043
+ "grad_norm": 1.6648041009902954,
2044
+ "learning_rate": 2.6532769246533435e-05,
2045
+ "loss": 0.4755,
2046
+ "step": 2910
2047
+ },
2048
+ {
2049
+ "epoch": 1.6028543982434473,
2050
+ "grad_norm": 2.290234088897705,
2051
+ "learning_rate": 2.6373275930734075e-05,
2052
+ "loss": 0.4603,
2053
+ "step": 2920
2054
+ },
2055
+ {
2056
+ "epoch": 1.608343625634692,
2057
+ "grad_norm": 2.1882123947143555,
2058
+ "learning_rate": 2.621372653179391e-05,
2059
+ "loss": 0.4551,
2060
+ "step": 2930
2061
+ },
2062
+ {
2063
+ "epoch": 1.6138328530259365,
2064
+ "grad_norm": 1.7908653020858765,
2065
+ "learning_rate": 2.6054127565542146e-05,
2066
+ "loss": 0.5062,
2067
+ "step": 2940
2068
+ },
2069
+ {
2070
+ "epoch": 1.6193220804171813,
2071
+ "grad_norm": 2.1407206058502197,
2072
+ "learning_rate": 2.5894485549832254e-05,
2073
+ "loss": 0.5046,
2074
+ "step": 2950
2075
+ },
2076
+ {
2077
+ "epoch": 1.624811307808426,
2078
+ "grad_norm": 1.8676074743270874,
2079
+ "learning_rate": 2.57348070042758e-05,
2080
+ "loss": 0.4685,
2081
+ "step": 2960
2082
+ },
2083
+ {
2084
+ "epoch": 1.6303005351996707,
2085
+ "grad_norm": 2.0238535404205322,
2086
+ "learning_rate": 2.5575098449976204e-05,
2087
+ "loss": 0.4836,
2088
+ "step": 2970
2089
+ },
2090
+ {
2091
+ "epoch": 1.6357897625909152,
2092
+ "grad_norm": 2.1416938304901123,
2093
+ "learning_rate": 2.541536640926238e-05,
2094
+ "loss": 0.4146,
2095
+ "step": 2980
2096
+ },
2097
+ {
2098
+ "epoch": 1.64127898998216,
2099
+ "grad_norm": 2.006524085998535,
2100
+ "learning_rate": 2.5255617405422443e-05,
2101
+ "loss": 0.441,
2102
+ "step": 2990
2103
+ },
2104
+ {
2105
+ "epoch": 1.6467682173734048,
2106
+ "grad_norm": 2.2434608936309814,
2107
+ "learning_rate": 2.5095857962437226e-05,
2108
+ "loss": 0.4932,
2109
+ "step": 3000
2110
+ },
2111
+ {
2112
+ "epoch": 1.6522574447646494,
2113
+ "grad_norm": 2.113938093185425,
2114
+ "learning_rate": 2.4936094604713918e-05,
2115
+ "loss": 0.4324,
2116
+ "step": 3010
2117
+ },
2118
+ {
2119
+ "epoch": 1.657746672155894,
2120
+ "grad_norm": 1.8772289752960205,
2121
+ "learning_rate": 2.4776333856819565e-05,
2122
+ "loss": 0.4655,
2123
+ "step": 3020
2124
+ },
2125
+ {
2126
+ "epoch": 1.6632358995471388,
2127
+ "grad_norm": 2.1245956420898438,
2128
+ "learning_rate": 2.4616582243214623e-05,
2129
+ "loss": 0.4631,
2130
+ "step": 3030
2131
+ },
2132
+ {
2133
+ "epoch": 1.6687251269383834,
2134
+ "grad_norm": 2.2539162635803223,
2135
+ "learning_rate": 2.4456846287986525e-05,
2136
+ "loss": 0.4492,
2137
+ "step": 3040
2138
+ },
2139
+ {
2140
+ "epoch": 1.674214354329628,
2141
+ "grad_norm": 2.4101765155792236,
2142
+ "learning_rate": 2.429713251458323e-05,
2143
+ "loss": 0.4326,
2144
+ "step": 3050
2145
+ },
2146
+ {
2147
+ "epoch": 1.6797035817208728,
2148
+ "grad_norm": 2.1554176807403564,
2149
+ "learning_rate": 2.4137447445546837e-05,
2150
+ "loss": 0.4527,
2151
+ "step": 3060
2152
+ },
2153
+ {
2154
+ "epoch": 1.6851928091121176,
2155
+ "grad_norm": 2.0779566764831543,
2156
+ "learning_rate": 2.397779760224713e-05,
2157
+ "loss": 0.4331,
2158
+ "step": 3070
2159
+ },
2160
+ {
2161
+ "epoch": 1.6906820365033621,
2162
+ "grad_norm": 2.3145909309387207,
2163
+ "learning_rate": 2.3818189504615367e-05,
2164
+ "loss": 0.4159,
2165
+ "step": 3080
2166
+ },
2167
+ {
2168
+ "epoch": 1.6961712638946067,
2169
+ "grad_norm": 2.1414687633514404,
2170
+ "learning_rate": 2.3658629670877938e-05,
2171
+ "loss": 0.4996,
2172
+ "step": 3090
2173
+ },
2174
+ {
2175
+ "epoch": 1.7016604912858515,
2176
+ "grad_norm": 1.6377606391906738,
2177
+ "learning_rate": 2.3499124617290187e-05,
2178
+ "loss": 0.4827,
2179
+ "step": 3100
2180
+ },
2181
+ {
2182
+ "epoch": 1.7071497186770963,
2183
+ "grad_norm": 2.27193546295166,
2184
+ "learning_rate": 2.3339680857870288e-05,
2185
+ "loss": 0.5358,
2186
+ "step": 3110
2187
+ },
2188
+ {
2189
+ "epoch": 1.7126389460683409,
2190
+ "grad_norm": 1.6943323612213135,
2191
+ "learning_rate": 2.318030490413323e-05,
2192
+ "loss": 0.4584,
2193
+ "step": 3120
2194
+ },
2195
+ {
2196
+ "epoch": 1.7181281734595855,
2197
+ "grad_norm": 2.1574575901031494,
2198
+ "learning_rate": 2.30210032648249e-05,
2199
+ "loss": 0.4366,
2200
+ "step": 3130
2201
+ },
2202
+ {
2203
+ "epoch": 1.7236174008508303,
2204
+ "grad_norm": 1.805962085723877,
2205
+ "learning_rate": 2.286178244565625e-05,
2206
+ "loss": 0.4633,
2207
+ "step": 3140
2208
+ },
2209
+ {
2210
+ "epoch": 1.729106628242075,
2211
+ "grad_norm": 2.4552011489868164,
2212
+ "learning_rate": 2.2702648949037618e-05,
2213
+ "loss": 0.4861,
2214
+ "step": 3150
2215
+ },
2216
+ {
2217
+ "epoch": 1.7345958556333196,
2218
+ "grad_norm": 1.9455459117889404,
2219
+ "learning_rate": 2.2543609273813195e-05,
2220
+ "loss": 0.4881,
2221
+ "step": 3160
2222
+ },
2223
+ {
2224
+ "epoch": 1.7400850830245642,
2225
+ "grad_norm": 1.8050341606140137,
2226
+ "learning_rate": 2.2384669914995592e-05,
2227
+ "loss": 0.418,
2228
+ "step": 3170
2229
+ },
2230
+ {
2231
+ "epoch": 1.745574310415809,
2232
+ "grad_norm": 2.0198020935058594,
2233
+ "learning_rate": 2.2225837363500636e-05,
2234
+ "loss": 0.472,
2235
+ "step": 3180
2236
+ },
2237
+ {
2238
+ "epoch": 1.7510635378070538,
2239
+ "grad_norm": 2.245699167251587,
2240
+ "learning_rate": 2.2067118105882195e-05,
2241
+ "loss": 0.4718,
2242
+ "step": 3190
2243
+ },
2244
+ {
2245
+ "epoch": 1.7565527651982984,
2246
+ "grad_norm": 2.3782804012298584,
2247
+ "learning_rate": 2.190851862406739e-05,
2248
+ "loss": 0.4318,
2249
+ "step": 3200
2250
+ },
2251
+ {
2252
+ "epoch": 1.762041992589543,
2253
+ "grad_norm": 1.766295075416565,
2254
+ "learning_rate": 2.17500453950918e-05,
2255
+ "loss": 0.4728,
2256
+ "step": 3210
2257
+ },
2258
+ {
2259
+ "epoch": 1.7675312199807878,
2260
+ "grad_norm": 1.883118987083435,
2261
+ "learning_rate": 2.159170489083498e-05,
2262
+ "loss": 0.4229,
2263
+ "step": 3220
2264
+ },
2265
+ {
2266
+ "epoch": 1.7730204473720323,
2267
+ "grad_norm": 2.2457189559936523,
2268
+ "learning_rate": 2.1433503577756137e-05,
2269
+ "loss": 0.3906,
2270
+ "step": 3230
2271
+ },
2272
+ {
2273
+ "epoch": 1.778509674763277,
2274
+ "grad_norm": 1.66023850440979,
2275
+ "learning_rate": 2.1275447916630055e-05,
2276
+ "loss": 0.379,
2277
+ "step": 3240
2278
+ },
2279
+ {
2280
+ "epoch": 1.7839989021545217,
2281
+ "grad_norm": 2.2401814460754395,
2282
+ "learning_rate": 2.1117544362283286e-05,
2283
+ "loss": 0.4173,
2284
+ "step": 3250
2285
+ },
2286
+ {
2287
+ "epoch": 1.7894881295457665,
2288
+ "grad_norm": 2.2202141284942627,
2289
+ "learning_rate": 2.0959799363330425e-05,
2290
+ "loss": 0.426,
2291
+ "step": 3260
2292
+ },
2293
+ {
2294
+ "epoch": 1.794977356937011,
2295
+ "grad_norm": 2.292778253555298,
2296
+ "learning_rate": 2.0802219361910908e-05,
2297
+ "loss": 0.4165,
2298
+ "step": 3270
2299
+ },
2300
+ {
2301
+ "epoch": 1.8004665843282557,
2302
+ "grad_norm": 2.025392770767212,
2303
+ "learning_rate": 2.0644810793425807e-05,
2304
+ "loss": 0.4216,
2305
+ "step": 3280
2306
+ },
2307
+ {
2308
+ "epoch": 1.8059558117195005,
2309
+ "grad_norm": 1.669911503791809,
2310
+ "learning_rate": 2.048758008627506e-05,
2311
+ "loss": 0.4745,
2312
+ "step": 3290
2313
+ },
2314
+ {
2315
+ "epoch": 1.8114450391107453,
2316
+ "grad_norm": 2.2425777912139893,
2317
+ "learning_rate": 2.033053366159493e-05,
2318
+ "loss": 0.4314,
2319
+ "step": 3300
2320
+ },
2321
+ {
2322
+ "epoch": 1.8169342665019899,
2323
+ "grad_norm": 2.065985679626465,
2324
+ "learning_rate": 2.0173677932995787e-05,
2325
+ "loss": 0.4882,
2326
+ "step": 3310
2327
+ },
2328
+ {
2329
+ "epoch": 1.8224234938932344,
2330
+ "grad_norm": 1.8231384754180908,
2331
+ "learning_rate": 2.0017019306300182e-05,
2332
+ "loss": 0.4346,
2333
+ "step": 3320
2334
+ },
2335
+ {
2336
+ "epoch": 1.8279127212844792,
2337
+ "grad_norm": 2.203216075897217,
2338
+ "learning_rate": 1.9860564179281217e-05,
2339
+ "loss": 0.515,
2340
+ "step": 3330
2341
+ },
2342
+ {
2343
+ "epoch": 1.833401948675724,
2344
+ "grad_norm": 1.8703504800796509,
2345
+ "learning_rate": 1.970431894140128e-05,
2346
+ "loss": 0.4268,
2347
+ "step": 3340
2348
+ },
2349
+ {
2350
+ "epoch": 1.8388911760669686,
2351
+ "grad_norm": 2.13779616355896,
2352
+ "learning_rate": 1.954828997355112e-05,
2353
+ "loss": 0.4324,
2354
+ "step": 3350
2355
+ },
2356
+ {
2357
+ "epoch": 1.8443804034582132,
2358
+ "grad_norm": 2.4620044231414795,
2359
+ "learning_rate": 1.939248364778924e-05,
2360
+ "loss": 0.4542,
2361
+ "step": 3360
2362
+ },
2363
+ {
2364
+ "epoch": 1.849869630849458,
2365
+ "grad_norm": 2.0297598838806152,
2366
+ "learning_rate": 1.923690632708169e-05,
2367
+ "loss": 0.4695,
2368
+ "step": 3370
2369
+ },
2370
+ {
2371
+ "epoch": 1.8553588582407026,
2372
+ "grad_norm": 2.2314670085906982,
2373
+ "learning_rate": 1.908156436504215e-05,
2374
+ "loss": 0.4433,
2375
+ "step": 3380
2376
+ },
2377
+ {
2378
+ "epoch": 1.8608480856319471,
2379
+ "grad_norm": 1.7243778705596924,
2380
+ "learning_rate": 1.892646410567255e-05,
2381
+ "loss": 0.4257,
2382
+ "step": 3390
2383
+ },
2384
+ {
2385
+ "epoch": 1.866337313023192,
2386
+ "grad_norm": 1.6004356145858765,
2387
+ "learning_rate": 1.877161188310392e-05,
2388
+ "loss": 0.3585,
2389
+ "step": 3400
2390
+ },
2391
+ {
2392
+ "epoch": 1.8718265404144367,
2393
+ "grad_norm": 2.1382360458374023,
2394
+ "learning_rate": 1.8617014021337732e-05,
2395
+ "loss": 0.4234,
2396
+ "step": 3410
2397
+ },
2398
+ {
2399
+ "epoch": 1.8773157678056813,
2400
+ "grad_norm": 1.9200503826141357,
2401
+ "learning_rate": 1.846267683398761e-05,
2402
+ "loss": 0.4546,
2403
+ "step": 3420
2404
+ },
2405
+ {
2406
+ "epoch": 1.882804995196926,
2407
+ "grad_norm": 1.9421885013580322,
2408
+ "learning_rate": 1.830860662402153e-05,
2409
+ "loss": 0.4505,
2410
+ "step": 3430
2411
+ },
2412
+ {
2413
+ "epoch": 1.8882942225881707,
2414
+ "grad_norm": 2.25044584274292,
2415
+ "learning_rate": 1.8154809683504403e-05,
2416
+ "loss": 0.4684,
2417
+ "step": 3440
2418
+ },
2419
+ {
2420
+ "epoch": 1.8937834499794155,
2421
+ "grad_norm": 1.7311737537384033,
2422
+ "learning_rate": 1.8001292293341087e-05,
2423
+ "loss": 0.4478,
2424
+ "step": 3450
2425
+ },
2426
+ {
2427
+ "epoch": 1.89927267737066,
2428
+ "grad_norm": 1.8768479824066162,
2429
+ "learning_rate": 1.7848060723019894e-05,
2430
+ "loss": 0.4323,
2431
+ "step": 3460
2432
+ },
2433
+ {
2434
+ "epoch": 1.9047619047619047,
2435
+ "grad_norm": 1.617492914199829,
2436
+ "learning_rate": 1.7695121230356566e-05,
2437
+ "loss": 0.4429,
2438
+ "step": 3470
2439
+ },
2440
+ {
2441
+ "epoch": 1.9102511321531495,
2442
+ "grad_norm": 2.0293169021606445,
2443
+ "learning_rate": 1.7542480061238685e-05,
2444
+ "loss": 0.4399,
2445
+ "step": 3480
2446
+ },
2447
+ {
2448
+ "epoch": 1.9157403595443943,
2449
+ "grad_norm": 1.7568955421447754,
2450
+ "learning_rate": 1.7390143449370663e-05,
2451
+ "loss": 0.4029,
2452
+ "step": 3490
2453
+ },
2454
+ {
2455
+ "epoch": 1.9212295869356388,
2456
+ "grad_norm": 1.6997624635696411,
2457
+ "learning_rate": 1.723811761601904e-05,
2458
+ "loss": 0.4072,
2459
+ "step": 3500
2460
+ },
2461
+ {
2462
+ "epoch": 1.9267188143268834,
2463
+ "grad_norm": 2.185622453689575,
2464
+ "learning_rate": 1.708640876975855e-05,
2465
+ "loss": 0.4502,
2466
+ "step": 3510
2467
+ },
2468
+ {
2469
+ "epoch": 1.9322080417181282,
2470
+ "grad_norm": 2.803870439529419,
2471
+ "learning_rate": 1.693502310621848e-05,
2472
+ "loss": 0.4397,
2473
+ "step": 3520
2474
+ },
2475
+ {
2476
+ "epoch": 1.937697269109373,
2477
+ "grad_norm": 2.163422107696533,
2478
+ "learning_rate": 1.6783966807829692e-05,
2479
+ "loss": 0.4562,
2480
+ "step": 3530
2481
+ },
2482
+ {
2483
+ "epoch": 1.9431864965006176,
2484
+ "grad_norm": 1.7700269222259521,
2485
+ "learning_rate": 1.66332460435721e-05,
2486
+ "loss": 0.4332,
2487
+ "step": 3540
2488
+ },
2489
+ {
2490
+ "epoch": 1.9486757238918622,
2491
+ "grad_norm": 1.9938660860061646,
2492
+ "learning_rate": 1.648286696872277e-05,
2493
+ "loss": 0.4392,
2494
+ "step": 3550
2495
+ },
2496
+ {
2497
+ "epoch": 1.954164951283107,
2498
+ "grad_norm": 1.796387791633606,
2499
+ "learning_rate": 1.6332835724604556e-05,
2500
+ "loss": 0.4079,
2501
+ "step": 3560
2502
+ },
2503
+ {
2504
+ "epoch": 1.9596541786743515,
2505
+ "grad_norm": 1.6725765466690063,
2506
+ "learning_rate": 1.6183158438335223e-05,
2507
+ "loss": 0.4156,
2508
+ "step": 3570
2509
+ },
2510
+ {
2511
+ "epoch": 1.9651434060655961,
2512
+ "grad_norm": 2.1465470790863037,
2513
+ "learning_rate": 1.6033841222577312e-05,
2514
+ "loss": 0.4514,
2515
+ "step": 3580
2516
+ },
2517
+ {
2518
+ "epoch": 1.970632633456841,
2519
+ "grad_norm": 2.0636017322540283,
2520
+ "learning_rate": 1.588489017528844e-05,
2521
+ "loss": 0.4107,
2522
+ "step": 3590
2523
+ },
2524
+ {
2525
+ "epoch": 1.9761218608480857,
2526
+ "grad_norm": 2.281461000442505,
2527
+ "learning_rate": 1.573631137947232e-05,
2528
+ "loss": 0.4247,
2529
+ "step": 3600
2530
+ },
2531
+ {
2532
+ "epoch": 1.9816110882393303,
2533
+ "grad_norm": 1.8369041681289673,
2534
+ "learning_rate": 1.5588110902930252e-05,
2535
+ "loss": 0.3993,
2536
+ "step": 3610
2537
+ },
2538
+ {
2539
+ "epoch": 1.9871003156305749,
2540
+ "grad_norm": 1.538087010383606,
2541
+ "learning_rate": 1.5440294798013445e-05,
2542
+ "loss": 0.4032,
2543
+ "step": 3620
2544
+ },
2545
+ {
2546
+ "epoch": 1.9925895430218197,
2547
+ "grad_norm": 1.7788771390914917,
2548
+ "learning_rate": 1.5292869101375718e-05,
2549
+ "loss": 0.4191,
2550
+ "step": 3630
2551
+ },
2552
+ {
2553
+ "epoch": 1.9980787704130645,
2554
+ "grad_norm": 1.663266897201538,
2555
+ "learning_rate": 1.514583983372707e-05,
2556
+ "loss": 0.4065,
2557
+ "step": 3640
2558
+ },
2559
+ {
2560
+ "epoch": 2.003567997804309,
2561
+ "grad_norm": 1.6794120073318481,
2562
+ "learning_rate": 1.4999212999587723e-05,
2563
+ "loss": 0.3012,
2564
+ "step": 3650
2565
+ },
2566
+ {
2567
+ "epoch": 2.0090572251955536,
2568
+ "grad_norm": 2.0947213172912598,
2569
+ "learning_rate": 1.4852994587042957e-05,
2570
+ "loss": 0.2699,
2571
+ "step": 3660
2572
+ },
2573
+ {
2574
+ "epoch": 2.0145464525867984,
2575
+ "grad_norm": 1.647148609161377,
2576
+ "learning_rate": 1.4707190567498552e-05,
2577
+ "loss": 0.256,
2578
+ "step": 3670
2579
+ },
2580
+ {
2581
+ "epoch": 2.0200356799780432,
2582
+ "grad_norm": 1.6485075950622559,
2583
+ "learning_rate": 1.4561806895436907e-05,
2584
+ "loss": 0.2306,
2585
+ "step": 3680
2586
+ },
2587
+ {
2588
+ "epoch": 2.0255249073692876,
2589
+ "grad_norm": 1.5765630006790161,
2590
+ "learning_rate": 1.4416849508173864e-05,
2591
+ "loss": 0.2363,
2592
+ "step": 3690
2593
+ },
2594
+ {
2595
+ "epoch": 2.0310141347605324,
2596
+ "grad_norm": 2.0813677310943604,
2597
+ "learning_rate": 1.4272324325616251e-05,
2598
+ "loss": 0.2407,
2599
+ "step": 3700
2600
+ },
2601
+ {
2602
+ "epoch": 2.036503362151777,
2603
+ "grad_norm": 2.0815207958221436,
2604
+ "learning_rate": 1.4128237250020115e-05,
2605
+ "loss": 0.2525,
2606
+ "step": 3710
2607
+ },
2608
+ {
2609
+ "epoch": 2.041992589543022,
2610
+ "grad_norm": 2.1880548000335693,
2611
+ "learning_rate": 1.3984594165749676e-05,
2612
+ "loss": 0.2371,
2613
+ "step": 3720
2614
+ },
2615
+ {
2616
+ "epoch": 2.0474818169342663,
2617
+ "grad_norm": 1.7031059265136719,
2618
+ "learning_rate": 1.3841400939037013e-05,
2619
+ "loss": 0.241,
2620
+ "step": 3730
2621
+ },
2622
+ {
2623
+ "epoch": 2.052971044325511,
2624
+ "grad_norm": 1.9227020740509033,
2625
+ "learning_rate": 1.3698663417742496e-05,
2626
+ "loss": 0.2509,
2627
+ "step": 3740
2628
+ },
2629
+ {
2630
+ "epoch": 2.058460271716756,
2631
+ "grad_norm": 1.8670146465301514,
2632
+ "learning_rate": 1.3556387431115969e-05,
2633
+ "loss": 0.265,
2634
+ "step": 3750
2635
+ },
2636
+ {
2637
+ "epoch": 2.0639494991080007,
2638
+ "grad_norm": 2.06124210357666,
2639
+ "learning_rate": 1.3414578789558696e-05,
2640
+ "loss": 0.2182,
2641
+ "step": 3760
2642
+ },
2643
+ {
2644
+ "epoch": 2.069438726499245,
2645
+ "grad_norm": 2.2382616996765137,
2646
+ "learning_rate": 1.3273243284386023e-05,
2647
+ "loss": 0.2477,
2648
+ "step": 3770
2649
+ },
2650
+ {
2651
+ "epoch": 2.07492795389049,
2652
+ "grad_norm": 2.178103446960449,
2653
+ "learning_rate": 1.3132386687590958e-05,
2654
+ "loss": 0.2379,
2655
+ "step": 3780
2656
+ },
2657
+ {
2658
+ "epoch": 2.0804171812817347,
2659
+ "grad_norm": 1.947129249572754,
2660
+ "learning_rate": 1.2992014751608372e-05,
2661
+ "loss": 0.2319,
2662
+ "step": 3790
2663
+ },
2664
+ {
2665
+ "epoch": 2.0859064086729795,
2666
+ "grad_norm": 2.0307064056396484,
2667
+ "learning_rate": 1.2852133209080097e-05,
2668
+ "loss": 0.2416,
2669
+ "step": 3800
2670
+ },
2671
+ {
2672
+ "epoch": 2.091395636064224,
2673
+ "grad_norm": 1.988174319267273,
2674
+ "learning_rate": 1.2712747772620801e-05,
2675
+ "loss": 0.2629,
2676
+ "step": 3810
2677
+ },
2678
+ {
2679
+ "epoch": 2.0968848634554687,
2680
+ "grad_norm": 3.22770094871521,
2681
+ "learning_rate": 1.2573864134584718e-05,
2682
+ "loss": 0.2069,
2683
+ "step": 3820
2684
+ },
2685
+ {
2686
+ "epoch": 2.1023740908467135,
2687
+ "grad_norm": 2.0717577934265137,
2688
+ "learning_rate": 1.243548796683319e-05,
2689
+ "loss": 0.237,
2690
+ "step": 3830
2691
+ },
2692
+ {
2693
+ "epoch": 2.107863318237958,
2694
+ "grad_norm": 2.118257522583008,
2695
+ "learning_rate": 1.2297624920502953e-05,
2696
+ "loss": 0.2531,
2697
+ "step": 3840
2698
+ },
2699
+ {
2700
+ "epoch": 2.1133525456292026,
2701
+ "grad_norm": 2.584071636199951,
2702
+ "learning_rate": 1.2160280625775447e-05,
2703
+ "loss": 0.2464,
2704
+ "step": 3850
2705
+ },
2706
+ {
2707
+ "epoch": 2.1188417730204474,
2708
+ "grad_norm": 2.8391823768615723,
2709
+ "learning_rate": 1.2023460691646821e-05,
2710
+ "loss": 0.2344,
2711
+ "step": 3860
2712
+ },
2713
+ {
2714
+ "epoch": 2.124331000411692,
2715
+ "grad_norm": 1.8388172388076782,
2716
+ "learning_rate": 1.1887170705698905e-05,
2717
+ "loss": 0.2191,
2718
+ "step": 3870
2719
+ },
2720
+ {
2721
+ "epoch": 2.1298202278029366,
2722
+ "grad_norm": 2.278942346572876,
2723
+ "learning_rate": 1.1751416233870999e-05,
2724
+ "loss": 0.2303,
2725
+ "step": 3880
2726
+ },
2727
+ {
2728
+ "epoch": 2.1353094551941814,
2729
+ "grad_norm": 2.4428744316101074,
2730
+ "learning_rate": 1.1616202820232567e-05,
2731
+ "loss": 0.2493,
2732
+ "step": 3890
2733
+ },
2734
+ {
2735
+ "epoch": 2.140798682585426,
2736
+ "grad_norm": 2.272839069366455,
2737
+ "learning_rate": 1.1481535986756828e-05,
2738
+ "loss": 0.2527,
2739
+ "step": 3900
2740
+ },
2741
+ {
2742
+ "epoch": 2.146287909976671,
2743
+ "grad_norm": 2.1877167224884033,
2744
+ "learning_rate": 1.134742123309525e-05,
2745
+ "loss": 0.2599,
2746
+ "step": 3910
2747
+ },
2748
+ {
2749
+ "epoch": 2.1517771373679153,
2750
+ "grad_norm": 1.6496747732162476,
2751
+ "learning_rate": 1.1213864036352939e-05,
2752
+ "loss": 0.2457,
2753
+ "step": 3920
2754
+ },
2755
+ {
2756
+ "epoch": 2.15726636475916,
2757
+ "grad_norm": 2.1241507530212402,
2758
+ "learning_rate": 1.1080869850864964e-05,
2759
+ "loss": 0.2532,
2760
+ "step": 3930
2761
+ },
2762
+ {
2763
+ "epoch": 2.162755592150405,
2764
+ "grad_norm": 1.5271326303482056,
2765
+ "learning_rate": 1.094844410797361e-05,
2766
+ "loss": 0.2651,
2767
+ "step": 3940
2768
+ },
2769
+ {
2770
+ "epoch": 2.1682448195416497,
2771
+ "grad_norm": 1.9697147607803345,
2772
+ "learning_rate": 1.0816592215806562e-05,
2773
+ "loss": 0.2171,
2774
+ "step": 3950
2775
+ },
2776
+ {
2777
+ "epoch": 2.173734046932894,
2778
+ "grad_norm": 1.604737401008606,
2779
+ "learning_rate": 1.0685319559056051e-05,
2780
+ "loss": 0.2579,
2781
+ "step": 3960
2782
+ },
2783
+ {
2784
+ "epoch": 2.179223274324139,
2785
+ "grad_norm": 2.053114414215088,
2786
+ "learning_rate": 1.0554631498758943e-05,
2787
+ "loss": 0.2541,
2788
+ "step": 3970
2789
+ },
2790
+ {
2791
+ "epoch": 2.1847125017153837,
2792
+ "grad_norm": 2.424609422683716,
2793
+ "learning_rate": 1.0424533372077803e-05,
2794
+ "loss": 0.2053,
2795
+ "step": 3980
2796
+ },
2797
+ {
2798
+ "epoch": 2.1902017291066285,
2799
+ "grad_norm": 2.34372615814209,
2800
+ "learning_rate": 1.029503049208293e-05,
2801
+ "loss": 0.214,
2802
+ "step": 3990
2803
+ },
2804
+ {
2805
+ "epoch": 2.195690956497873,
2806
+ "grad_norm": 2.1274008750915527,
2807
+ "learning_rate": 1.0166128147535352e-05,
2808
+ "loss": 0.2133,
2809
+ "step": 4000
2810
+ },
2811
+ {
2812
+ "epoch": 2.2011801838891176,
2813
+ "grad_norm": 1.7201030254364014,
2814
+ "learning_rate": 1.003783160267091e-05,
2815
+ "loss": 0.2233,
2816
+ "step": 4010
2817
+ },
2818
+ {
2819
+ "epoch": 2.2066694112803624,
2820
+ "grad_norm": 2.844679832458496,
2821
+ "learning_rate": 9.91014609698519e-06,
2822
+ "loss": 0.2389,
2823
+ "step": 4020
2824
+ },
2825
+ {
2826
+ "epoch": 2.212158638671607,
2827
+ "grad_norm": 1.7438113689422607,
2828
+ "learning_rate": 9.783076845019598e-06,
2829
+ "loss": 0.2297,
2830
+ "step": 4030
2831
+ },
2832
+ {
2833
+ "epoch": 2.2176478660628516,
2834
+ "grad_norm": 2.076685905456543,
2835
+ "learning_rate": 9.656629036148365e-06,
2836
+ "loss": 0.2519,
2837
+ "step": 4040
2838
+ },
2839
+ {
2840
+ "epoch": 2.2231370934540964,
2841
+ "grad_norm": 2.197861671447754,
2842
+ "learning_rate": 9.530807834366658e-06,
2843
+ "loss": 0.2416,
2844
+ "step": 4050
2845
+ },
2846
+ {
2847
+ "epoch": 2.228626320845341,
2848
+ "grad_norm": 1.6589149236679077,
2849
+ "learning_rate": 9.405618378079686e-06,
2850
+ "loss": 0.238,
2851
+ "step": 4060
2852
+ },
2853
+ {
2854
+ "epoch": 2.2341155482365855,
2855
+ "grad_norm": 2.1636011600494385,
2856
+ "learning_rate": 9.281065779892826e-06,
2857
+ "loss": 0.2165,
2858
+ "step": 4070
2859
+ },
2860
+ {
2861
+ "epoch": 2.2396047756278303,
2862
+ "grad_norm": 2.11350679397583,
2863
+ "learning_rate": 9.15715512640282e-06,
2864
+ "loss": 0.2539,
2865
+ "step": 4080
2866
+ },
2867
+ {
2868
+ "epoch": 2.245094003019075,
2869
+ "grad_norm": 2.1883132457733154,
2870
+ "learning_rate": 9.033891477990091e-06,
2871
+ "loss": 0.2392,
2872
+ "step": 4090
2873
+ },
2874
+ {
2875
+ "epoch": 2.25058323041032,
2876
+ "grad_norm": 1.9660489559173584,
2877
+ "learning_rate": 8.923511544874787e-06,
2878
+ "loss": 0.2507,
2879
+ "step": 4100
2880
+ },
2881
+ {
2882
+ "epoch": 2.2560724578015643,
2883
+ "grad_norm": 1.596596360206604,
2884
+ "learning_rate": 8.801491052657259e-06,
2885
+ "loss": 0.2205,
2886
+ "step": 4110
2887
+ },
2888
+ {
2889
+ "epoch": 2.261561685192809,
2890
+ "grad_norm": 1.9153178930282593,
2891
+ "learning_rate": 8.680132090462712e-06,
2892
+ "loss": 0.2189,
2893
+ "step": 4120
2894
+ },
2895
+ {
2896
+ "epoch": 2.267050912584054,
2897
+ "grad_norm": 2.2162649631500244,
2898
+ "learning_rate": 8.559439614463177e-06,
2899
+ "loss": 0.2573,
2900
+ "step": 4130
2901
+ },
2902
+ {
2903
+ "epoch": 2.2725401399752982,
2904
+ "grad_norm": 2.1483819484710693,
2905
+ "learning_rate": 8.439418553612105e-06,
2906
+ "loss": 0.2464,
2907
+ "step": 4140
2908
+ },
2909
+ {
2910
+ "epoch": 2.278029367366543,
2911
+ "grad_norm": 2.043180465698242,
2912
+ "learning_rate": 8.320073809443024e-06,
2913
+ "loss": 0.236,
2914
+ "step": 4150
2915
+ },
2916
+ {
2917
+ "epoch": 2.283518594757788,
2918
+ "grad_norm": 1.6839346885681152,
2919
+ "learning_rate": 8.201410255869458e-06,
2920
+ "loss": 0.2596,
2921
+ "step": 4160
2922
+ },
2923
+ {
2924
+ "epoch": 2.2890078221490326,
2925
+ "grad_norm": 2.334520101547241,
2926
+ "learning_rate": 8.083432738985782e-06,
2927
+ "loss": 0.2233,
2928
+ "step": 4170
2929
+ },
2930
+ {
2931
+ "epoch": 2.2944970495402774,
2932
+ "grad_norm": 2.2806715965270996,
2933
+ "learning_rate": 7.966146076869386e-06,
2934
+ "loss": 0.223,
2935
+ "step": 4180
2936
+ },
2937
+ {
2938
+ "epoch": 2.299986276931522,
2939
+ "grad_norm": 2.726118803024292,
2940
+ "learning_rate": 7.849555059383839e-06,
2941
+ "loss": 0.2236,
2942
+ "step": 4190
2943
+ },
2944
+ {
2945
+ "epoch": 2.3054755043227666,
2946
+ "grad_norm": 1.6786760091781616,
2947
+ "learning_rate": 7.733664447983349e-06,
2948
+ "loss": 0.2509,
2949
+ "step": 4200
2950
+ },
2951
+ {
2952
+ "epoch": 2.3109647317140114,
2953
+ "grad_norm": 1.767065405845642,
2954
+ "learning_rate": 7.618478975518292e-06,
2955
+ "loss": 0.2373,
2956
+ "step": 4210
2957
+ },
2958
+ {
2959
+ "epoch": 2.3164539591052558,
2960
+ "grad_norm": 1.5344187021255493,
2961
+ "learning_rate": 7.504003346041871e-06,
2962
+ "loss": 0.2404,
2963
+ "step": 4220
2964
+ },
2965
+ {
2966
+ "epoch": 2.3219431864965006,
2967
+ "grad_norm": 2.3337080478668213,
2968
+ "learning_rate": 7.390242234618075e-06,
2969
+ "loss": 0.1858,
2970
+ "step": 4230
2971
+ },
2972
+ {
2973
+ "epoch": 2.3274324138877454,
2974
+ "grad_norm": 2.3712496757507324,
2975
+ "learning_rate": 7.277200287130728e-06,
2976
+ "loss": 0.2595,
2977
+ "step": 4240
2978
+ },
2979
+ {
2980
+ "epoch": 2.33292164127899,
2981
+ "grad_norm": 2.5574772357940674,
2982
+ "learning_rate": 7.164882120093757e-06,
2983
+ "loss": 0.2419,
2984
+ "step": 4250
2985
+ },
2986
+ {
2987
+ "epoch": 2.3384108686702345,
2988
+ "grad_norm": 2.367032051086426,
2989
+ "learning_rate": 7.053292320462654e-06,
2990
+ "loss": 0.256,
2991
+ "step": 4260
2992
+ },
2993
+ {
2994
+ "epoch": 2.3439000960614793,
2995
+ "grad_norm": 2.3279731273651123,
2996
+ "learning_rate": 6.942435445447159e-06,
2997
+ "loss": 0.2319,
2998
+ "step": 4270
2999
+ },
3000
+ {
3001
+ "epoch": 2.349389323452724,
3002
+ "grad_norm": 2.5082924365997314,
3003
+ "learning_rate": 6.832316022325138e-06,
3004
+ "loss": 0.212,
3005
+ "step": 4280
3006
+ },
3007
+ {
3008
+ "epoch": 2.354878550843969,
3009
+ "grad_norm": 3.303452730178833,
3010
+ "learning_rate": 6.7229385482577065e-06,
3011
+ "loss": 0.2434,
3012
+ "step": 4290
3013
+ },
3014
+ {
3015
+ "epoch": 2.3603677782352133,
3016
+ "grad_norm": 2.3842883110046387,
3017
+ "learning_rate": 6.614307490105557e-06,
3018
+ "loss": 0.2644,
3019
+ "step": 4300
3020
+ },
3021
+ {
3022
+ "epoch": 2.365857005626458,
3023
+ "grad_norm": 2.0827999114990234,
3024
+ "learning_rate": 6.506427284246547e-06,
3025
+ "loss": 0.2327,
3026
+ "step": 4310
3027
+ },
3028
+ {
3029
+ "epoch": 2.371346233017703,
3030
+ "grad_norm": 1.9834315776824951,
3031
+ "learning_rate": 6.3993023363945165e-06,
3032
+ "loss": 0.2206,
3033
+ "step": 4320
3034
+ },
3035
+ {
3036
+ "epoch": 2.376835460408947,
3037
+ "grad_norm": 1.9981067180633545,
3038
+ "learning_rate": 6.2929370214193735e-06,
3039
+ "loss": 0.2736,
3040
+ "step": 4330
3041
+ },
3042
+ {
3043
+ "epoch": 2.382324687800192,
3044
+ "grad_norm": 2.4763762950897217,
3045
+ "learning_rate": 6.1873356831683884e-06,
3046
+ "loss": 0.2344,
3047
+ "step": 4340
3048
+ },
3049
+ {
3050
+ "epoch": 2.387813915191437,
3051
+ "grad_norm": 1.4734795093536377,
3052
+ "learning_rate": 6.082502634288873e-06,
3053
+ "loss": 0.2019,
3054
+ "step": 4350
3055
+ },
3056
+ {
3057
+ "epoch": 2.3933031425826816,
3058
+ "grad_norm": 2.4421563148498535,
3059
+ "learning_rate": 5.978442156051986e-06,
3060
+ "loss": 0.2289,
3061
+ "step": 4360
3062
+ },
3063
+ {
3064
+ "epoch": 2.3987923699739264,
3065
+ "grad_norm": 2.192746162414551,
3066
+ "learning_rate": 5.875158498177921e-06,
3067
+ "loss": 0.2396,
3068
+ "step": 4370
3069
+ },
3070
+ {
3071
+ "epoch": 2.4042815973651708,
3072
+ "grad_norm": 1.9783297777175903,
3073
+ "learning_rate": 5.772655878662339e-06,
3074
+ "loss": 0.2531,
3075
+ "step": 4380
3076
+ },
3077
+ {
3078
+ "epoch": 2.4097708247564156,
3079
+ "grad_norm": 2.5523509979248047,
3080
+ "learning_rate": 5.6709384836041184e-06,
3081
+ "loss": 0.2405,
3082
+ "step": 4390
3083
+ },
3084
+ {
3085
+ "epoch": 2.4152600521476604,
3086
+ "grad_norm": 1.6953893899917603,
3087
+ "learning_rate": 5.570010467034425e-06,
3088
+ "loss": 0.2279,
3089
+ "step": 4400
3090
+ },
3091
+ {
3092
+ "epoch": 2.4207492795389047,
3093
+ "grad_norm": 1.7373918294906616,
3094
+ "learning_rate": 5.469875950747016e-06,
3095
+ "loss": 0.2081,
3096
+ "step": 4410
3097
+ },
3098
+ {
3099
+ "epoch": 2.4262385069301495,
3100
+ "grad_norm": 2.789266347885132,
3101
+ "learning_rate": 5.370539024129928e-06,
3102
+ "loss": 0.2455,
3103
+ "step": 4420
3104
+ },
3105
+ {
3106
+ "epoch": 2.4317277343213943,
3107
+ "grad_norm": 1.8112378120422363,
3108
+ "learning_rate": 5.272003743998489e-06,
3109
+ "loss": 0.256,
3110
+ "step": 4430
3111
+ },
3112
+ {
3113
+ "epoch": 2.437216961712639,
3114
+ "grad_norm": 1.8407344818115234,
3115
+ "learning_rate": 5.1742741344296246e-06,
3116
+ "loss": 0.2481,
3117
+ "step": 4440
3118
+ },
3119
+ {
3120
+ "epoch": 2.4427061891038835,
3121
+ "grad_norm": 2.0232059955596924,
3122
+ "learning_rate": 5.077354186597541e-06,
3123
+ "loss": 0.2213,
3124
+ "step": 4450
3125
+ },
3126
+ {
3127
+ "epoch": 2.4481954164951283,
3128
+ "grad_norm": 2.0662572383880615,
3129
+ "learning_rate": 4.981247858610688e-06,
3130
+ "loss": 0.2064,
3131
+ "step": 4460
3132
+ },
3133
+ {
3134
+ "epoch": 2.453684643886373,
3135
+ "grad_norm": 1.9686827659606934,
3136
+ "learning_rate": 4.885959075350149e-06,
3137
+ "loss": 0.2344,
3138
+ "step": 4470
3139
+ },
3140
+ {
3141
+ "epoch": 2.459173871277618,
3142
+ "grad_norm": 2.095710515975952,
3143
+ "learning_rate": 4.791491728309347e-06,
3144
+ "loss": 0.2727,
3145
+ "step": 4480
3146
+ },
3147
+ {
3148
+ "epoch": 2.4646630986688622,
3149
+ "grad_norm": 2.7409679889678955,
3150
+ "learning_rate": 4.697849675435112e-06,
3151
+ "loss": 0.2449,
3152
+ "step": 4490
3153
+ },
3154
+ {
3155
+ "epoch": 2.470152326060107,
3156
+ "grad_norm": 1.6528655290603638,
3157
+ "learning_rate": 4.605036740970134e-06,
3158
+ "loss": 0.2228,
3159
+ "step": 4500
3160
+ },
3161
+ {
3162
+ "epoch": 2.475641553451352,
3163
+ "grad_norm": 2.210045337677002,
3164
+ "learning_rate": 4.513056715296773e-06,
3165
+ "loss": 0.2399,
3166
+ "step": 4510
3167
+ },
3168
+ {
3169
+ "epoch": 2.481130780842596,
3170
+ "grad_norm": 1.4573155641555786,
3171
+ "learning_rate": 4.4219133547822865e-06,
3172
+ "loss": 0.2133,
3173
+ "step": 4520
3174
+ },
3175
+ {
3176
+ "epoch": 2.486620008233841,
3177
+ "grad_norm": 2.013803482055664,
3178
+ "learning_rate": 4.331610381625395e-06,
3179
+ "loss": 0.2318,
3180
+ "step": 4530
3181
+ },
3182
+ {
3183
+ "epoch": 2.492109235625086,
3184
+ "grad_norm": 2.090888261795044,
3185
+ "learning_rate": 4.242151483704293e-06,
3186
+ "loss": 0.2393,
3187
+ "step": 4540
3188
+ },
3189
+ {
3190
+ "epoch": 2.4975984630163306,
3191
+ "grad_norm": 2.1223104000091553,
3192
+ "learning_rate": 4.153540314426033e-06,
3193
+ "loss": 0.2343,
3194
+ "step": 4550
3195
+ },
3196
+ {
3197
+ "epoch": 2.5030876904075754,
3198
+ "grad_norm": 2.2379000186920166,
3199
+ "learning_rate": 4.065780492577326e-06,
3200
+ "loss": 0.2608,
3201
+ "step": 4560
3202
+ },
3203
+ {
3204
+ "epoch": 2.5085769177988197,
3205
+ "grad_norm": 1.780354380607605,
3206
+ "learning_rate": 3.978875602176726e-06,
3207
+ "loss": 0.2401,
3208
+ "step": 4570
3209
+ },
3210
+ {
3211
+ "epoch": 2.5140661451900645,
3212
+ "grad_norm": 2.5559253692626953,
3213
+ "learning_rate": 3.892829192328337e-06,
3214
+ "loss": 0.2381,
3215
+ "step": 4580
3216
+ },
3217
+ {
3218
+ "epoch": 2.5195553725813093,
3219
+ "grad_norm": 1.7930986881256104,
3220
+ "learning_rate": 3.8076447770767796e-06,
3221
+ "loss": 0.2712,
3222
+ "step": 4590
3223
+ },
3224
+ {
3225
+ "epoch": 2.5250445999725537,
3226
+ "grad_norm": 2.0700008869171143,
3227
+ "learning_rate": 3.7233258352637553e-06,
3228
+ "loss": 0.2162,
3229
+ "step": 4600
3230
+ },
3231
+ {
3232
+ "epoch": 2.5305338273637985,
3233
+ "grad_norm": 2.3782896995544434,
3234
+ "learning_rate": 3.6398758103859067e-06,
3235
+ "loss": 0.208,
3236
+ "step": 4610
3237
+ },
3238
+ {
3239
+ "epoch": 2.5360230547550433,
3240
+ "grad_norm": 2.345578670501709,
3241
+ "learning_rate": 3.557298110454252e-06,
3242
+ "loss": 0.2231,
3243
+ "step": 4620
3244
+ },
3245
+ {
3246
+ "epoch": 2.5415122821462877,
3247
+ "grad_norm": 1.9046144485473633,
3248
+ "learning_rate": 3.475596107854981e-06,
3249
+ "loss": 0.2359,
3250
+ "step": 4630
3251
+ },
3252
+ {
3253
+ "epoch": 2.5470015095375325,
3254
+ "grad_norm": 2.2235357761383057,
3255
+ "learning_rate": 3.3947731392117237e-06,
3256
+ "loss": 0.2268,
3257
+ "step": 4640
3258
+ },
3259
+ {
3260
+ "epoch": 2.5524907369287773,
3261
+ "grad_norm": 2.3540749549865723,
3262
+ "learning_rate": 3.3148325052492713e-06,
3263
+ "loss": 0.2382,
3264
+ "step": 4650
3265
+ },
3266
+ {
3267
+ "epoch": 2.557979964320022,
3268
+ "grad_norm": 2.550370931625366,
3269
+ "learning_rate": 3.2357774706588157e-06,
3270
+ "loss": 0.2364,
3271
+ "step": 4660
3272
+ },
3273
+ {
3274
+ "epoch": 2.563469191711267,
3275
+ "grad_norm": 2.06571626663208,
3276
+ "learning_rate": 3.1576112639646023e-06,
3277
+ "loss": 0.2379,
3278
+ "step": 4670
3279
+ },
3280
+ {
3281
+ "epoch": 2.568958419102511,
3282
+ "grad_norm": 1.3834680318832397,
3283
+ "learning_rate": 3.08033707739209e-06,
3284
+ "loss": 0.2012,
3285
+ "step": 4680
3286
+ },
3287
+ {
3288
+ "epoch": 2.574447646493756,
3289
+ "grad_norm": 1.7131993770599365,
3290
+ "learning_rate": 3.0039580667375557e-06,
3291
+ "loss": 0.2019,
3292
+ "step": 4690
3293
+ },
3294
+ {
3295
+ "epoch": 2.579936873885001,
3296
+ "grad_norm": 2.2222018241882324,
3297
+ "learning_rate": 2.9284773512392475e-06,
3298
+ "loss": 0.2565,
3299
+ "step": 4700
3300
+ },
3301
+ {
3302
+ "epoch": 2.585426101276245,
3303
+ "grad_norm": 1.8102763891220093,
3304
+ "learning_rate": 2.8538980134499958e-06,
3305
+ "loss": 0.2254,
3306
+ "step": 4710
3307
+ },
3308
+ {
3309
+ "epoch": 2.59091532866749,
3310
+ "grad_norm": 2.4614617824554443,
3311
+ "learning_rate": 2.780223099111298e-06,
3312
+ "loss": 0.2505,
3313
+ "step": 4720
3314
+ },
3315
+ {
3316
+ "epoch": 2.5964045560587348,
3317
+ "grad_norm": 2.120408535003662,
3318
+ "learning_rate": 2.7074556170289674e-06,
3319
+ "loss": 0.1887,
3320
+ "step": 4730
3321
+ },
3322
+ {
3323
+ "epoch": 2.6018937834499796,
3324
+ "grad_norm": 2.1147496700286865,
3325
+ "learning_rate": 2.6355985389502293e-06,
3326
+ "loss": 0.1995,
3327
+ "step": 4740
3328
+ },
3329
+ {
3330
+ "epoch": 2.6073830108412244,
3331
+ "grad_norm": 1.818030595779419,
3332
+ "learning_rate": 2.5646547994423784e-06,
3333
+ "loss": 0.2527,
3334
+ "step": 4750
3335
+ },
3336
+ {
3337
+ "epoch": 2.6128722382324687,
3338
+ "grad_norm": 1.935293197631836,
3339
+ "learning_rate": 2.4946272957729165e-06,
3340
+ "loss": 0.2007,
3341
+ "step": 4760
3342
+ },
3343
+ {
3344
+ "epoch": 2.6183614656237135,
3345
+ "grad_norm": 1.837039589881897,
3346
+ "learning_rate": 2.4255188877912477e-06,
3347
+ "loss": 0.2044,
3348
+ "step": 4770
3349
+ },
3350
+ {
3351
+ "epoch": 2.6238506930149583,
3352
+ "grad_norm": 2.487926721572876,
3353
+ "learning_rate": 2.3573323978118705e-06,
3354
+ "loss": 0.2825,
3355
+ "step": 4780
3356
+ },
3357
+ {
3358
+ "epoch": 2.6293399204062027,
3359
+ "grad_norm": 1.880677342414856,
3360
+ "learning_rate": 2.29007061049914e-06,
3361
+ "loss": 0.209,
3362
+ "step": 4790
3363
+ },
3364
+ {
3365
+ "epoch": 2.6348291477974475,
3366
+ "grad_norm": 2.060526132583618,
3367
+ "learning_rate": 2.2237362727535043e-06,
3368
+ "loss": 0.2069,
3369
+ "step": 4800
3370
+ },
3371
+ {
3372
+ "epoch": 2.6403183751886923,
3373
+ "grad_norm": 1.8091875314712524,
3374
+ "learning_rate": 2.1583320935993605e-06,
3375
+ "loss": 0.2606,
3376
+ "step": 4810
3377
+ },
3378
+ {
3379
+ "epoch": 2.6458076025799366,
3380
+ "grad_norm": 2.821810483932495,
3381
+ "learning_rate": 2.0938607440744274e-06,
3382
+ "loss": 0.2235,
3383
+ "step": 4820
3384
+ },
3385
+ {
3386
+ "epoch": 2.6512968299711814,
3387
+ "grad_norm": 2.605480194091797,
3388
+ "learning_rate": 2.0303248571206244e-06,
3389
+ "loss": 0.2454,
3390
+ "step": 4830
3391
+ },
3392
+ {
3393
+ "epoch": 2.6567860573624262,
3394
+ "grad_norm": 2.1553428173065186,
3395
+ "learning_rate": 1.967727027476568e-06,
3396
+ "loss": 0.1998,
3397
+ "step": 4840
3398
+ },
3399
+ {
3400
+ "epoch": 2.662275284753671,
3401
+ "grad_norm": 2.485527753829956,
3402
+ "learning_rate": 1.9060698115716063e-06,
3403
+ "loss": 0.2377,
3404
+ "step": 4850
3405
+ },
3406
+ {
3407
+ "epoch": 2.667764512144916,
3408
+ "grad_norm": 1.8272162675857544,
3409
+ "learning_rate": 1.8453557274214162e-06,
3410
+ "loss": 0.2288,
3411
+ "step": 4860
3412
+ },
3413
+ {
3414
+ "epoch": 2.67325373953616,
3415
+ "grad_norm": 2.5798721313476562,
3416
+ "learning_rate": 1.7855872545251757e-06,
3417
+ "loss": 0.2419,
3418
+ "step": 4870
3419
+ },
3420
+ {
3421
+ "epoch": 2.678742966927405,
3422
+ "grad_norm": 2.7085471153259277,
3423
+ "learning_rate": 1.7267668337642761e-06,
3424
+ "loss": 0.222,
3425
+ "step": 4880
3426
+ },
3427
+ {
3428
+ "epoch": 2.68423219431865,
3429
+ "grad_norm": 2.2424449920654297,
3430
+ "learning_rate": 1.6688968673026773e-06,
3431
+ "loss": 0.1913,
3432
+ "step": 4890
3433
+ },
3434
+ {
3435
+ "epoch": 2.689721421709894,
3436
+ "grad_norm": 2.0495047569274902,
3437
+ "learning_rate": 1.6119797184887792e-06,
3438
+ "loss": 0.1905,
3439
+ "step": 4900
3440
+ },
3441
+ {
3442
+ "epoch": 2.695210649101139,
3443
+ "grad_norm": 2.048985242843628,
3444
+ "learning_rate": 1.5560177117589197e-06,
3445
+ "loss": 0.1978,
3446
+ "step": 4910
3447
+ },
3448
+ {
3449
+ "epoch": 2.7006998764923837,
3450
+ "grad_norm": 2.4100003242492676,
3451
+ "learning_rate": 1.5010131325424337e-06,
3452
+ "loss": 0.2575,
3453
+ "step": 4920
3454
+ },
3455
+ {
3456
+ "epoch": 2.7061891038836285,
3457
+ "grad_norm": 2.420525074005127,
3458
+ "learning_rate": 1.4469682271683327e-06,
3459
+ "loss": 0.215,
3460
+ "step": 4930
3461
+ },
3462
+ {
3463
+ "epoch": 2.711678331274873,
3464
+ "grad_norm": 1.7320780754089355,
3465
+ "learning_rate": 1.3938852027735594e-06,
3466
+ "loss": 0.2259,
3467
+ "step": 4940
3468
+ },
3469
+ {
3470
+ "epoch": 2.7171675586661177,
3471
+ "grad_norm": 2.3320376873016357,
3472
+ "learning_rate": 1.3417662272128484e-06,
3473
+ "loss": 0.2514,
3474
+ "step": 4950
3475
+ },
3476
+ {
3477
+ "epoch": 2.7226567860573625,
3478
+ "grad_norm": 2.5615234375,
3479
+ "learning_rate": 1.2906134289701998e-06,
3480
+ "loss": 0.2342,
3481
+ "step": 4960
3482
+ },
3483
+ {
3484
+ "epoch": 2.7281460134486073,
3485
+ "grad_norm": 2.3866004943847656,
3486
+ "learning_rate": 1.240428897071949e-06,
3487
+ "loss": 0.2273,
3488
+ "step": 4970
3489
+ },
3490
+ {
3491
+ "epoch": 2.7336352408398517,
3492
+ "grad_norm": 2.7888448238372803,
3493
+ "learning_rate": 1.191214681001454e-06,
3494
+ "loss": 0.216,
3495
+ "step": 4980
3496
+ },
3497
+ {
3498
+ "epoch": 2.7391244682310965,
3499
+ "grad_norm": 2.318481922149658,
3500
+ "learning_rate": 1.142972790615407e-06,
3501
+ "loss": 0.2053,
3502
+ "step": 4990
3503
+ },
3504
+ {
3505
+ "epoch": 2.7446136956223413,
3506
+ "grad_norm": 1.82982337474823,
3507
+ "learning_rate": 1.095705196061722e-06,
3508
+ "loss": 0.2265,
3509
+ "step": 5000
3510
+ },
3511
+ {
3512
+ "epoch": 2.7501029230135856,
3513
+ "grad_norm": 1.4905016422271729,
3514
+ "learning_rate": 1.0494138276991278e-06,
3515
+ "loss": 0.1784,
3516
+ "step": 5010
3517
+ },
3518
+ {
3519
+ "epoch": 2.7555921504048304,
3520
+ "grad_norm": 1.6236484050750732,
3521
+ "learning_rate": 1.0041005760182853e-06,
3522
+ "loss": 0.1953,
3523
+ "step": 5020
3524
+ },
3525
+ {
3526
+ "epoch": 2.761081377796075,
3527
+ "grad_norm": 1.9028195142745972,
3528
+ "learning_rate": 9.597672915646116e-07,
3529
+ "loss": 0.2076,
3530
+ "step": 5030
3531
+ },
3532
+ {
3533
+ "epoch": 2.76657060518732,
3534
+ "grad_norm": 2.1804606914520264,
3535
+ "learning_rate": 9.164157848626842e-07,
3536
+ "loss": 0.2155,
3537
+ "step": 5040
3538
+ },
3539
+ {
3540
+ "epoch": 2.772059832578565,
3541
+ "grad_norm": 1.961748480796814,
3542
+ "learning_rate": 8.740478263423197e-07,
3543
+ "loss": 0.2072,
3544
+ "step": 5050
3545
+ },
3546
+ {
3547
+ "epoch": 2.777549059969809,
3548
+ "grad_norm": 2.2191579341888428,
3549
+ "learning_rate": 8.32665146266276e-07,
3550
+ "loss": 0.2314,
3551
+ "step": 5060
3552
+ },
3553
+ {
3554
+ "epoch": 2.783038287361054,
3555
+ "grad_norm": 2.2354133129119873,
3556
+ "learning_rate": 7.922694346595511e-07,
3557
+ "loss": 0.2297,
3558
+ "step": 5070
3559
+ },
3560
+ {
3561
+ "epoch": 2.7885275147522988,
3562
+ "grad_norm": 1.8483319282531738,
3563
+ "learning_rate": 7.528623412404179e-07,
3564
+ "loss": 0.214,
3565
+ "step": 5080
3566
+ },
3567
+ {
3568
+ "epoch": 2.794016742143543,
3569
+ "grad_norm": 1.9461801052093506,
3570
+ "learning_rate": 7.144454753530067e-07,
3571
+ "loss": 0.2173,
3572
+ "step": 5090
3573
+ },
3574
+ {
3575
+ "epoch": 2.799505969534788,
3576
+ "grad_norm": 1.8403065204620361,
3577
+ "learning_rate": 6.770204059016127e-07,
3578
+ "loss": 0.2012,
3579
+ "step": 5100
3580
+ },
3581
+ {
3582
+ "epoch": 2.8049951969260327,
3583
+ "grad_norm": 2.654057264328003,
3584
+ "learning_rate": 6.405886612866036e-07,
3585
+ "loss": 0.224,
3586
+ "step": 5110
3587
+ },
3588
+ {
3589
+ "epoch": 2.810484424317277,
3590
+ "grad_norm": 2.0720152854919434,
3591
+ "learning_rate": 6.051517293420101e-07,
3592
+ "loss": 0.1893,
3593
+ "step": 5120
3594
+ },
3595
+ {
3596
+ "epoch": 2.815973651708522,
3597
+ "grad_norm": 1.8411768674850464,
3598
+ "learning_rate": 5.707110572747587e-07,
3599
+ "loss": 0.2351,
3600
+ "step": 5130
3601
+ },
3602
+ {
3603
+ "epoch": 2.8214628790997667,
3604
+ "grad_norm": 1.893263578414917,
3605
+ "learning_rate": 5.3726805160558e-07,
3606
+ "loss": 0.2541,
3607
+ "step": 5140
3608
+ },
3609
+ {
3610
+ "epoch": 2.8269521064910115,
3611
+ "grad_norm": 2.347729206085205,
3612
+ "learning_rate": 5.048240781115571e-07,
3613
+ "loss": 0.2351,
3614
+ "step": 5150
3615
+ },
3616
+ {
3617
+ "epoch": 2.8324413338822563,
3618
+ "grad_norm": 2.2554593086242676,
3619
+ "learning_rate": 4.7338046177035354e-07,
3620
+ "loss": 0.245,
3621
+ "step": 5160
3622
+ },
3623
+ {
3624
+ "epoch": 2.8379305612735006,
3625
+ "grad_norm": 2.649017095565796,
3626
+ "learning_rate": 4.429384867061015e-07,
3627
+ "loss": 0.2444,
3628
+ "step": 5170
3629
+ },
3630
+ {
3631
+ "epoch": 2.8434197886647454,
3632
+ "grad_norm": 2.740800142288208,
3633
+ "learning_rate": 4.1349939613695434e-07,
3634
+ "loss": 0.2354,
3635
+ "step": 5180
3636
+ },
3637
+ {
3638
+ "epoch": 2.8489090160559902,
3639
+ "grad_norm": 2.5310161113739014,
3640
+ "learning_rate": 3.85064392324333e-07,
3641
+ "loss": 0.2086,
3642
+ "step": 5190
3643
+ },
3644
+ {
3645
+ "epoch": 2.8543982434472346,
3646
+ "grad_norm": 2.4969282150268555,
3647
+ "learning_rate": 3.5763463652380146e-07,
3648
+ "loss": 0.2329,
3649
+ "step": 5200
3650
+ },
3651
+ {
3652
+ "epoch": 2.8598874708384794,
3653
+ "grad_norm": 2.0695693492889404,
3654
+ "learning_rate": 3.3121124893766287e-07,
3655
+ "loss": 0.1665,
3656
+ "step": 5210
3657
+ },
3658
+ {
3659
+ "epoch": 2.865376698229724,
3660
+ "grad_norm": 2.0718321800231934,
3661
+ "learning_rate": 3.057953086692017e-07,
3662
+ "loss": 0.2444,
3663
+ "step": 5220
3664
+ },
3665
+ {
3666
+ "epoch": 2.870865925620969,
3667
+ "grad_norm": 2.0257515907287598,
3668
+ "learning_rate": 2.8138785367860796e-07,
3669
+ "loss": 0.2303,
3670
+ "step": 5230
3671
+ },
3672
+ {
3673
+ "epoch": 2.876355153012214,
3674
+ "grad_norm": 2.0960233211517334,
3675
+ "learning_rate": 2.5798988074061394e-07,
3676
+ "loss": 0.2274,
3677
+ "step": 5240
3678
+ },
3679
+ {
3680
+ "epoch": 2.881844380403458,
3681
+ "grad_norm": 2.4282174110412598,
3682
+ "learning_rate": 2.3560234540375424e-07,
3683
+ "loss": 0.1995,
3684
+ "step": 5250
3685
+ },
3686
+ {
3687
+ "epoch": 2.887333607794703,
3688
+ "grad_norm": 1.898910641670227,
3689
+ "learning_rate": 2.1422616195136692e-07,
3690
+ "loss": 0.2002,
3691
+ "step": 5260
3692
+ },
3693
+ {
3694
+ "epoch": 2.8928228351859477,
3695
+ "grad_norm": 1.6507282257080078,
3696
+ "learning_rate": 1.9386220336423678e-07,
3697
+ "loss": 0.1811,
3698
+ "step": 5270
3699
+ },
3700
+ {
3701
+ "epoch": 2.898312062577192,
3702
+ "grad_norm": 2.447411060333252,
3703
+ "learning_rate": 1.7451130128495753e-07,
3704
+ "loss": 0.2376,
3705
+ "step": 5280
3706
+ },
3707
+ {
3708
+ "epoch": 2.903801289968437,
3709
+ "grad_norm": 1.9209644794464111,
3710
+ "learning_rate": 1.5617424598396712e-07,
3711
+ "loss": 0.236,
3712
+ "step": 5290
3713
+ },
3714
+ {
3715
+ "epoch": 2.9092905173596817,
3716
+ "grad_norm": 2.0094797611236572,
3717
+ "learning_rate": 1.3885178632726536e-07,
3718
+ "loss": 0.208,
3719
+ "step": 5300
3720
+ },
3721
+ {
3722
+ "epoch": 2.914779744750926,
3723
+ "grad_norm": 2.3810887336730957,
3724
+ "learning_rate": 1.225446297458327e-07,
3725
+ "loss": 0.2124,
3726
+ "step": 5310
3727
+ },
3728
+ {
3729
+ "epoch": 2.920268972142171,
3730
+ "grad_norm": 2.039491891860962,
3731
+ "learning_rate": 1.0725344220675337e-07,
3732
+ "loss": 0.1983,
3733
+ "step": 5320
3734
+ },
3735
+ {
3736
+ "epoch": 2.9257581995334156,
3737
+ "grad_norm": 2.2363178730010986,
3738
+ "learning_rate": 9.297884818599556e-08,
3739
+ "loss": 0.2173,
3740
+ "step": 5330
3741
+ },
3742
+ {
3743
+ "epoch": 2.9312474269246604,
3744
+ "grad_norm": 2.1318199634552,
3745
+ "learning_rate": 7.972143064292892e-08,
3746
+ "loss": 0.182,
3747
+ "step": 5340
3748
+ },
3749
+ {
3750
+ "epoch": 2.9367366543159052,
3751
+ "grad_norm": 1.9546360969543457,
3752
+ "learning_rate": 6.748173099650202e-08,
3753
+ "loss": 0.1871,
3754
+ "step": 5350
3755
+ },
3756
+ {
3757
+ "epoch": 2.9422258817071496,
3758
+ "grad_norm": 1.8476676940917969,
3759
+ "learning_rate": 5.626024910314609e-08,
3760
+ "loss": 0.1989,
3761
+ "step": 5360
3762
+ },
3763
+ {
3764
+ "epoch": 2.9477151090983944,
3765
+ "grad_norm": 2.1973392963409424,
3766
+ "learning_rate": 4.605744323634142e-08,
3767
+ "loss": 0.2186,
3768
+ "step": 5370
3769
+ },
3770
+ {
3771
+ "epoch": 2.953204336489639,
3772
+ "grad_norm": 1.935354232788086,
3773
+ "learning_rate": 3.687373006792394e-08,
3774
+ "loss": 0.2124,
3775
+ "step": 5380
3776
+ },
3777
+ {
3778
+ "epoch": 2.9586935638808836,
3779
+ "grad_norm": 2.1322507858276367,
3780
+ "learning_rate": 2.870948465105161e-08,
3781
+ "loss": 0.2145,
3782
+ "step": 5390
3783
+ },
3784
+ {
3785
+ "epoch": 2.9641827912721284,
3786
+ "grad_norm": 2.501298189163208,
3787
+ "learning_rate": 2.1565040404902813e-08,
3788
+ "loss": 0.22,
3789
+ "step": 5400
3790
+ },
3791
+ {
3792
+ "epoch": 2.969672018663373,
3793
+ "grad_norm": 1.6250516176223755,
3794
+ "learning_rate": 1.544068910104002e-08,
3795
+ "loss": 0.218,
3796
+ "step": 5410
3797
+ },
3798
+ {
3799
+ "epoch": 2.975161246054618,
3800
+ "grad_norm": 2.794093370437622,
3801
+ "learning_rate": 1.0336680851516512e-08,
3802
+ "loss": 0.257,
3803
+ "step": 5420
3804
+ },
3805
+ {
3806
+ "epoch": 2.9806504734458628,
3807
+ "grad_norm": 2.0987253189086914,
3808
+ "learning_rate": 6.2532240986457044e-09,
3809
+ "loss": 0.2193,
3810
+ "step": 5430
3811
+ },
3812
+ {
3813
+ "epoch": 2.986139700837107,
3814
+ "grad_norm": 2.217175006866455,
3815
+ "learning_rate": 3.1904856064940424e-09,
3816
+ "loss": 0.2392,
3817
+ "step": 5440
3818
+ },
3819
+ {
3820
+ "epoch": 2.991628928228352,
3821
+ "grad_norm": 2.0461556911468506,
3822
+ "learning_rate": 1.1485904540697867e-09,
3823
+ "loss": 0.2137,
3824
+ "step": 5450
3825
+ },
3826
+ {
3827
+ "epoch": 2.9971181556195967,
3828
+ "grad_norm": 1.9249966144561768,
3829
+ "learning_rate": 1.276220302215414e-10,
3830
+ "loss": 0.2132,
3831
+ "step": 5460
3832
+ },
3833
+ {
3834
+ "epoch": 2.99876492383697,
3835
+ "step": 5463,
3836
+ "total_flos": 3.233486247100416e+17,
3837
+ "train_loss": 0.5040911292388242,
3838
+ "train_runtime": 9149.3841,
3839
+ "train_samples_per_second": 4.779,
3840
+ "train_steps_per_second": 0.597
3841
+ }
3842
+ ],
3843
+ "logging_steps": 10,
3844
+ "max_steps": 5463,
3845
+ "num_input_tokens_seen": 0,
3846
+ "num_train_epochs": 3,
3847
+ "save_steps": 1000,
3848
+ "stateful_callbacks": {
3849
+ "TrainerControl": {
3850
+ "args": {
3851
+ "should_epoch_stop": false,
3852
+ "should_evaluate": false,
3853
+ "should_log": false,
3854
+ "should_save": true,
3855
+ "should_training_stop": false
3856
+ },
3857
+ "attributes": {}
3858
+ }
3859
+ },
3860
+ "total_flos": 3.233486247100416e+17,
3861
+ "train_batch_size": 2,
3862
+ "trial_name": null,
3863
+ "trial_params": null
3864
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f9ad635d919ba264023da23c00c4642647d6ce58d3c29a51ae48d5eca1bc556
3
+ size 5240