Hugging Face's logo

axel-datos
/
Llama-3.2-1B_gsm8k_lisa

Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
axel-datos commited on
Commit
6f0733e
•
1 Parent(s): 513356b

Upload folder using huggingface_hub

Browse files
Files changed (35) hide show
  1. .gitattributes +3 -0
  2. README.md +55 -0
  3. all_results.json +9 -0
  4. checkpoint-5000/config.json +37 -0
  5. checkpoint-5000/generation_config.json +9 -0
  6. checkpoint-5000/model.safetensors +3 -0
  7. checkpoint-5000/optimizer.pt +3 -0
  8. checkpoint-5000/rng_state.pth +3 -0
  9. checkpoint-5000/scheduler.pt +3 -0
  10. checkpoint-5000/special_tokens_map.json +17 -0
  11. checkpoint-5000/tokenizer.json +3 -0
  12. checkpoint-5000/tokenizer_config.json +2063 -0
  13. checkpoint-5000/trainer_state.json +1783 -0
  14. checkpoint-5000/training_args.bin +3 -0
  15. checkpoint-7473/config.json +37 -0
  16. checkpoint-7473/generation_config.json +9 -0
  17. checkpoint-7473/model.safetensors +3 -0
  18. checkpoint-7473/optimizer.pt +3 -0
  19. checkpoint-7473/rng_state.pth +3 -0
  20. checkpoint-7473/scheduler.pt +3 -0
  21. checkpoint-7473/special_tokens_map.json +17 -0
  22. checkpoint-7473/tokenizer.json +3 -0
  23. checkpoint-7473/tokenizer_config.json +2063 -0
  24. checkpoint-7473/trainer_state.json +2644 -0
  25. checkpoint-7473/training_args.bin +3 -0
  26. config.json +37 -0
  27. generation_config.json +9 -0
  28. model.safetensors +3 -0
  29. runs/Dec11_18-18-09_a559b199d359/events.out.tfevents.1733941102.a559b199d359.172128.0 +3 -0
  30. special_tokens_map.json +17 -0
  31. tokenizer.json +3 -0
  32. tokenizer_config.json +2063 -0
  33. train_results.json +9 -0
  34. trainer_state.json +2653 -0
  35. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ 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
+ checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-7473/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: llama3.2
4
+ base_model: meta-llama/Llama-3.2-1B
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - customized
9
+ model-index:
10
+ - name: Llama-3.2-1B_gsm8k_lisa
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Llama-3.2-1B_gsm8k_lisa
18
+
19
+ This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on the customized dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 1e-05
39
+ - train_batch_size: 1
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Use paged_adamw_32bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 1.0
45
+
46
+ ### Training results
47
+
48
+
49
+
50
+ ### Framework versions
51
+
52
+ - Transformers 4.46.3
53
+ - Pytorch 2.5.1+cu121
54
+ - Datasets 3.2.0
55
+ - Tokenizers 0.20.3
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 1.1170284894683136e+16,
4
+ "train_loss": 0.7570252240493756,
5
+ "train_runtime": 920.0938,
6
+ "train_samples": 7473,
7
+ "train_samples_per_second": 8.122,
8
+ "train_steps_per_second": 8.122
9
+ }
checkpoint-5000/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.2-1B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 16,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 128001,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": {
25
+ "factor": 32.0,
26
+ "high_freq_factor": 4.0,
27
+ "low_freq_factor": 1.0,
28
+ "original_max_position_embeddings": 8192,
29
+ "rope_type": "llama3"
30
+ },
31
+ "rope_theta": 500000.0,
32
+ "tie_word_embeddings": true,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.46.3",
35
+ "use_cache": true,
36
+ "vocab_size": 128256
37
+ }
checkpoint-5000/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.46.3"
9
+ }
checkpoint-5000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eba234299520e0c91c083ce4af0c3fc4573de2ae245474f88216becc88339db6
3
+ size 2471645608
checkpoint-5000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c95bf2a0c0bce42b9c48fdb44f92cad5d0b720d4143711400f5e373a3e7644b
3
+ size 9886607746
checkpoint-5000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8032fb0ab64df02e1deef729f91f8e5d3bc739ede6ab6ac750b5fc1e3cdb27bc
3
+ size 14244
checkpoint-5000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e40cd8e4d69ee47267ed784149c5e82b9cd023eb1f595f3fe2f45e60e594f3fe
3
+ size 1064
checkpoint-5000/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|end_of_text|>"
17
+ }
checkpoint-5000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-5000/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "model_input_names": [
2056
+ "input_ids",
2057
+ "attention_mask"
2058
+ ],
2059
+ "model_max_length": 131072,
2060
+ "pad_token": "<|end_of_text|>",
2061
+ "padding_side": "right",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
checkpoint-5000/trainer_state.json ADDED
@@ -0,0 +1,1783 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.6690753378830456,
5
+ "eval_steps": 500,
6
+ "global_step": 5000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0026763013515321826,
13
+ "grad_norm": 21.75,
14
+ "learning_rate": 9.973236986484679e-06,
15
+ "loss": 1.9581,
16
+ "step": 20
17
+ },
18
+ {
19
+ "epoch": 0.005352602703064365,
20
+ "grad_norm": 11.0625,
21
+ "learning_rate": 9.946473972969357e-06,
22
+ "loss": 1.8767,
23
+ "step": 40
24
+ },
25
+ {
26
+ "epoch": 0.008028904054596548,
27
+ "grad_norm": 20.875,
28
+ "learning_rate": 9.919710959454035e-06,
29
+ "loss": 1.729,
30
+ "step": 60
31
+ },
32
+ {
33
+ "epoch": 0.01070520540612873,
34
+ "grad_norm": 11.8125,
35
+ "learning_rate": 9.892947945938713e-06,
36
+ "loss": 1.4764,
37
+ "step": 80
38
+ },
39
+ {
40
+ "epoch": 0.013381506757660913,
41
+ "grad_norm": 20.375,
42
+ "learning_rate": 9.86618493242339e-06,
43
+ "loss": 1.4558,
44
+ "step": 100
45
+ },
46
+ {
47
+ "epoch": 0.016057808109193095,
48
+ "grad_norm": 9.8125,
49
+ "learning_rate": 9.83942191890807e-06,
50
+ "loss": 1.1101,
51
+ "step": 120
52
+ },
53
+ {
54
+ "epoch": 0.018734109460725276,
55
+ "grad_norm": 14.8125,
56
+ "learning_rate": 9.812658905392748e-06,
57
+ "loss": 1.2423,
58
+ "step": 140
59
+ },
60
+ {
61
+ "epoch": 0.02141041081225746,
62
+ "grad_norm": 15.3125,
63
+ "learning_rate": 9.785895891877426e-06,
64
+ "loss": 1.3871,
65
+ "step": 160
66
+ },
67
+ {
68
+ "epoch": 0.02408671216378964,
69
+ "grad_norm": 11.8125,
70
+ "learning_rate": 9.759132878362104e-06,
71
+ "loss": 1.2922,
72
+ "step": 180
73
+ },
74
+ {
75
+ "epoch": 0.026763013515321826,
76
+ "grad_norm": 9.25,
77
+ "learning_rate": 9.732369864846782e-06,
78
+ "loss": 1.3144,
79
+ "step": 200
80
+ },
81
+ {
82
+ "epoch": 0.029439314866854006,
83
+ "grad_norm": 18.625,
84
+ "learning_rate": 9.70560685133146e-06,
85
+ "loss": 1.0756,
86
+ "step": 220
87
+ },
88
+ {
89
+ "epoch": 0.03211561621838619,
90
+ "grad_norm": 43.25,
91
+ "learning_rate": 9.678843837816138e-06,
92
+ "loss": 1.2612,
93
+ "step": 240
94
+ },
95
+ {
96
+ "epoch": 0.034791917569918375,
97
+ "grad_norm": 9.4375,
98
+ "learning_rate": 9.652080824300816e-06,
99
+ "loss": 1.0856,
100
+ "step": 260
101
+ },
102
+ {
103
+ "epoch": 0.03746821892145055,
104
+ "grad_norm": 17.5,
105
+ "learning_rate": 9.625317810785494e-06,
106
+ "loss": 1.0375,
107
+ "step": 280
108
+ },
109
+ {
110
+ "epoch": 0.04014452027298274,
111
+ "grad_norm": 7.75,
112
+ "learning_rate": 9.598554797270172e-06,
113
+ "loss": 0.9578,
114
+ "step": 300
115
+ },
116
+ {
117
+ "epoch": 0.04282082162451492,
118
+ "grad_norm": 12.875,
119
+ "learning_rate": 9.571791783754852e-06,
120
+ "loss": 0.9921,
121
+ "step": 320
122
+ },
123
+ {
124
+ "epoch": 0.045497122976047105,
125
+ "grad_norm": 14.4375,
126
+ "learning_rate": 9.54502877023953e-06,
127
+ "loss": 0.8984,
128
+ "step": 340
129
+ },
130
+ {
131
+ "epoch": 0.04817342432757928,
132
+ "grad_norm": 11.9375,
133
+ "learning_rate": 9.518265756724208e-06,
134
+ "loss": 1.0139,
135
+ "step": 360
136
+ },
137
+ {
138
+ "epoch": 0.05084972567911147,
139
+ "grad_norm": 8.1875,
140
+ "learning_rate": 9.491502743208886e-06,
141
+ "loss": 0.9266,
142
+ "step": 380
143
+ },
144
+ {
145
+ "epoch": 0.05352602703064365,
146
+ "grad_norm": 33.0,
147
+ "learning_rate": 9.464739729693564e-06,
148
+ "loss": 0.8922,
149
+ "step": 400
150
+ },
151
+ {
152
+ "epoch": 0.056202328382175835,
153
+ "grad_norm": 20.375,
154
+ "learning_rate": 9.437976716178242e-06,
155
+ "loss": 0.9903,
156
+ "step": 420
157
+ },
158
+ {
159
+ "epoch": 0.05887862973370801,
160
+ "grad_norm": 18.625,
161
+ "learning_rate": 9.41121370266292e-06,
162
+ "loss": 0.8287,
163
+ "step": 440
164
+ },
165
+ {
166
+ "epoch": 0.0615549310852402,
167
+ "grad_norm": 8.75,
168
+ "learning_rate": 9.384450689147598e-06,
169
+ "loss": 0.9283,
170
+ "step": 460
171
+ },
172
+ {
173
+ "epoch": 0.06423123243677238,
174
+ "grad_norm": 21.75,
175
+ "learning_rate": 9.357687675632276e-06,
176
+ "loss": 0.9585,
177
+ "step": 480
178
+ },
179
+ {
180
+ "epoch": 0.06690753378830457,
181
+ "grad_norm": 13.9375,
182
+ "learning_rate": 9.330924662116954e-06,
183
+ "loss": 0.8412,
184
+ "step": 500
185
+ },
186
+ {
187
+ "epoch": 0.06958383513983675,
188
+ "grad_norm": 25.0,
189
+ "learning_rate": 9.304161648601634e-06,
190
+ "loss": 0.9743,
191
+ "step": 520
192
+ },
193
+ {
194
+ "epoch": 0.07226013649136893,
195
+ "grad_norm": 18.625,
196
+ "learning_rate": 9.277398635086312e-06,
197
+ "loss": 0.869,
198
+ "step": 540
199
+ },
200
+ {
201
+ "epoch": 0.0749364378429011,
202
+ "grad_norm": 11.625,
203
+ "learning_rate": 9.25063562157099e-06,
204
+ "loss": 0.7945,
205
+ "step": 560
206
+ },
207
+ {
208
+ "epoch": 0.07761273919443329,
209
+ "grad_norm": 7.1875,
210
+ "learning_rate": 9.223872608055667e-06,
211
+ "loss": 0.8359,
212
+ "step": 580
213
+ },
214
+ {
215
+ "epoch": 0.08028904054596547,
216
+ "grad_norm": 14.3125,
217
+ "learning_rate": 9.197109594540345e-06,
218
+ "loss": 0.7731,
219
+ "step": 600
220
+ },
221
+ {
222
+ "epoch": 0.08296534189749766,
223
+ "grad_norm": 12.9375,
224
+ "learning_rate": 9.170346581025023e-06,
225
+ "loss": 0.8352,
226
+ "step": 620
227
+ },
228
+ {
229
+ "epoch": 0.08564164324902984,
230
+ "grad_norm": 19.75,
231
+ "learning_rate": 9.143583567509703e-06,
232
+ "loss": 0.8792,
233
+ "step": 640
234
+ },
235
+ {
236
+ "epoch": 0.08831794460056203,
237
+ "grad_norm": 8.25,
238
+ "learning_rate": 9.116820553994381e-06,
239
+ "loss": 0.8651,
240
+ "step": 660
241
+ },
242
+ {
243
+ "epoch": 0.09099424595209421,
244
+ "grad_norm": 12.125,
245
+ "learning_rate": 9.090057540479059e-06,
246
+ "loss": 0.812,
247
+ "step": 680
248
+ },
249
+ {
250
+ "epoch": 0.0936705473036264,
251
+ "grad_norm": 15.75,
252
+ "learning_rate": 9.063294526963737e-06,
253
+ "loss": 0.8949,
254
+ "step": 700
255
+ },
256
+ {
257
+ "epoch": 0.09634684865515857,
258
+ "grad_norm": 11.5625,
259
+ "learning_rate": 9.036531513448415e-06,
260
+ "loss": 0.8752,
261
+ "step": 720
262
+ },
263
+ {
264
+ "epoch": 0.09902315000669075,
265
+ "grad_norm": 14.6875,
266
+ "learning_rate": 9.009768499933093e-06,
267
+ "loss": 0.8544,
268
+ "step": 740
269
+ },
270
+ {
271
+ "epoch": 0.10169945135822293,
272
+ "grad_norm": 9.9375,
273
+ "learning_rate": 8.983005486417771e-06,
274
+ "loss": 0.8414,
275
+ "step": 760
276
+ },
277
+ {
278
+ "epoch": 0.10437575270975512,
279
+ "grad_norm": 11.5,
280
+ "learning_rate": 8.95624247290245e-06,
281
+ "loss": 0.8796,
282
+ "step": 780
283
+ },
284
+ {
285
+ "epoch": 0.1070520540612873,
286
+ "grad_norm": 13.0625,
287
+ "learning_rate": 8.929479459387129e-06,
288
+ "loss": 0.853,
289
+ "step": 800
290
+ },
291
+ {
292
+ "epoch": 0.10972835541281949,
293
+ "grad_norm": 12.1875,
294
+ "learning_rate": 8.902716445871807e-06,
295
+ "loss": 0.8864,
296
+ "step": 820
297
+ },
298
+ {
299
+ "epoch": 0.11240465676435167,
300
+ "grad_norm": 60.0,
301
+ "learning_rate": 8.875953432356485e-06,
302
+ "loss": 0.7659,
303
+ "step": 840
304
+ },
305
+ {
306
+ "epoch": 0.11508095811588386,
307
+ "grad_norm": 30.0,
308
+ "learning_rate": 8.849190418841163e-06,
309
+ "loss": 0.9269,
310
+ "step": 860
311
+ },
312
+ {
313
+ "epoch": 0.11775725946741603,
314
+ "grad_norm": 9.125,
315
+ "learning_rate": 8.82242740532584e-06,
316
+ "loss": 0.7939,
317
+ "step": 880
318
+ },
319
+ {
320
+ "epoch": 0.12043356081894821,
321
+ "grad_norm": 9.0,
322
+ "learning_rate": 8.795664391810519e-06,
323
+ "loss": 0.8343,
324
+ "step": 900
325
+ },
326
+ {
327
+ "epoch": 0.1231098621704804,
328
+ "grad_norm": 18.25,
329
+ "learning_rate": 8.768901378295197e-06,
330
+ "loss": 0.7588,
331
+ "step": 920
332
+ },
333
+ {
334
+ "epoch": 0.12578616352201258,
335
+ "grad_norm": 6.34375,
336
+ "learning_rate": 8.742138364779875e-06,
337
+ "loss": 0.8424,
338
+ "step": 940
339
+ },
340
+ {
341
+ "epoch": 0.12846246487354476,
342
+ "grad_norm": 11.875,
343
+ "learning_rate": 8.715375351264553e-06,
344
+ "loss": 0.7666,
345
+ "step": 960
346
+ },
347
+ {
348
+ "epoch": 0.13113876622507695,
349
+ "grad_norm": 10.0,
350
+ "learning_rate": 8.688612337749232e-06,
351
+ "loss": 0.7019,
352
+ "step": 980
353
+ },
354
+ {
355
+ "epoch": 0.13381506757660913,
356
+ "grad_norm": 8.25,
357
+ "learning_rate": 8.66184932423391e-06,
358
+ "loss": 0.7036,
359
+ "step": 1000
360
+ },
361
+ {
362
+ "epoch": 0.13649136892814132,
363
+ "grad_norm": 10.75,
364
+ "learning_rate": 8.635086310718588e-06,
365
+ "loss": 0.7355,
366
+ "step": 1020
367
+ },
368
+ {
369
+ "epoch": 0.1391676702796735,
370
+ "grad_norm": 14.3125,
371
+ "learning_rate": 8.608323297203266e-06,
372
+ "loss": 0.737,
373
+ "step": 1040
374
+ },
375
+ {
376
+ "epoch": 0.14184397163120568,
377
+ "grad_norm": 9.5,
378
+ "learning_rate": 8.581560283687944e-06,
379
+ "loss": 0.7999,
380
+ "step": 1060
381
+ },
382
+ {
383
+ "epoch": 0.14452027298273787,
384
+ "grad_norm": 10.125,
385
+ "learning_rate": 8.554797270172622e-06,
386
+ "loss": 0.7613,
387
+ "step": 1080
388
+ },
389
+ {
390
+ "epoch": 0.14719657433427003,
391
+ "grad_norm": 22.625,
392
+ "learning_rate": 8.5280342566573e-06,
393
+ "loss": 0.8093,
394
+ "step": 1100
395
+ },
396
+ {
397
+ "epoch": 0.1498728756858022,
398
+ "grad_norm": 45.0,
399
+ "learning_rate": 8.501271243141978e-06,
400
+ "loss": 0.8385,
401
+ "step": 1120
402
+ },
403
+ {
404
+ "epoch": 0.1525491770373344,
405
+ "grad_norm": 12.5625,
406
+ "learning_rate": 8.474508229626656e-06,
407
+ "loss": 0.8014,
408
+ "step": 1140
409
+ },
410
+ {
411
+ "epoch": 0.15522547838886658,
412
+ "grad_norm": 12.625,
413
+ "learning_rate": 8.447745216111334e-06,
414
+ "loss": 0.8474,
415
+ "step": 1160
416
+ },
417
+ {
418
+ "epoch": 0.15790177974039876,
419
+ "grad_norm": 11.875,
420
+ "learning_rate": 8.420982202596014e-06,
421
+ "loss": 0.8009,
422
+ "step": 1180
423
+ },
424
+ {
425
+ "epoch": 0.16057808109193095,
426
+ "grad_norm": 20.625,
427
+ "learning_rate": 8.394219189080692e-06,
428
+ "loss": 0.8726,
429
+ "step": 1200
430
+ },
431
+ {
432
+ "epoch": 0.16325438244346313,
433
+ "grad_norm": 11.9375,
434
+ "learning_rate": 8.36745617556537e-06,
435
+ "loss": 0.751,
436
+ "step": 1220
437
+ },
438
+ {
439
+ "epoch": 0.16593068379499532,
440
+ "grad_norm": 8.4375,
441
+ "learning_rate": 8.340693162050048e-06,
442
+ "loss": 0.729,
443
+ "step": 1240
444
+ },
445
+ {
446
+ "epoch": 0.1686069851465275,
447
+ "grad_norm": 14.375,
448
+ "learning_rate": 8.313930148534726e-06,
449
+ "loss": 0.7642,
450
+ "step": 1260
451
+ },
452
+ {
453
+ "epoch": 0.17128328649805968,
454
+ "grad_norm": 9.4375,
455
+ "learning_rate": 8.287167135019404e-06,
456
+ "loss": 0.799,
457
+ "step": 1280
458
+ },
459
+ {
460
+ "epoch": 0.17395958784959187,
461
+ "grad_norm": 17.375,
462
+ "learning_rate": 8.260404121504082e-06,
463
+ "loss": 0.7899,
464
+ "step": 1300
465
+ },
466
+ {
467
+ "epoch": 0.17663588920112405,
468
+ "grad_norm": 8.25,
469
+ "learning_rate": 8.23364110798876e-06,
470
+ "loss": 0.8224,
471
+ "step": 1320
472
+ },
473
+ {
474
+ "epoch": 0.17931219055265624,
475
+ "grad_norm": 17.25,
476
+ "learning_rate": 8.206878094473438e-06,
477
+ "loss": 0.7836,
478
+ "step": 1340
479
+ },
480
+ {
481
+ "epoch": 0.18198849190418842,
482
+ "grad_norm": 11.9375,
483
+ "learning_rate": 8.180115080958116e-06,
484
+ "loss": 0.8547,
485
+ "step": 1360
486
+ },
487
+ {
488
+ "epoch": 0.1846647932557206,
489
+ "grad_norm": 11.8125,
490
+ "learning_rate": 8.153352067442795e-06,
491
+ "loss": 0.8314,
492
+ "step": 1380
493
+ },
494
+ {
495
+ "epoch": 0.1873410946072528,
496
+ "grad_norm": 12.25,
497
+ "learning_rate": 8.126589053927473e-06,
498
+ "loss": 0.7372,
499
+ "step": 1400
500
+ },
501
+ {
502
+ "epoch": 0.19001739595878495,
503
+ "grad_norm": 17.625,
504
+ "learning_rate": 8.099826040412151e-06,
505
+ "loss": 0.7241,
506
+ "step": 1420
507
+ },
508
+ {
509
+ "epoch": 0.19269369731031713,
510
+ "grad_norm": 13.25,
511
+ "learning_rate": 8.07306302689683e-06,
512
+ "loss": 0.75,
513
+ "step": 1440
514
+ },
515
+ {
516
+ "epoch": 0.19536999866184931,
517
+ "grad_norm": 9.3125,
518
+ "learning_rate": 8.046300013381507e-06,
519
+ "loss": 0.7802,
520
+ "step": 1460
521
+ },
522
+ {
523
+ "epoch": 0.1980463000133815,
524
+ "grad_norm": 9.1875,
525
+ "learning_rate": 8.019536999866185e-06,
526
+ "loss": 0.8704,
527
+ "step": 1480
528
+ },
529
+ {
530
+ "epoch": 0.20072260136491368,
531
+ "grad_norm": 6.15625,
532
+ "learning_rate": 7.992773986350863e-06,
533
+ "loss": 0.7438,
534
+ "step": 1500
535
+ },
536
+ {
537
+ "epoch": 0.20339890271644587,
538
+ "grad_norm": 9.125,
539
+ "learning_rate": 7.966010972835541e-06,
540
+ "loss": 0.7446,
541
+ "step": 1520
542
+ },
543
+ {
544
+ "epoch": 0.20607520406797805,
545
+ "grad_norm": 21.25,
546
+ "learning_rate": 7.93924795932022e-06,
547
+ "loss": 0.6814,
548
+ "step": 1540
549
+ },
550
+ {
551
+ "epoch": 0.20875150541951024,
552
+ "grad_norm": 6.65625,
553
+ "learning_rate": 7.912484945804897e-06,
554
+ "loss": 0.7361,
555
+ "step": 1560
556
+ },
557
+ {
558
+ "epoch": 0.21142780677104242,
559
+ "grad_norm": 13.125,
560
+ "learning_rate": 7.885721932289577e-06,
561
+ "loss": 0.67,
562
+ "step": 1580
563
+ },
564
+ {
565
+ "epoch": 0.2141041081225746,
566
+ "grad_norm": 15.6875,
567
+ "learning_rate": 7.858958918774255e-06,
568
+ "loss": 0.7145,
569
+ "step": 1600
570
+ },
571
+ {
572
+ "epoch": 0.2167804094741068,
573
+ "grad_norm": 14.1875,
574
+ "learning_rate": 7.832195905258933e-06,
575
+ "loss": 0.818,
576
+ "step": 1620
577
+ },
578
+ {
579
+ "epoch": 0.21945671082563897,
580
+ "grad_norm": 6.53125,
581
+ "learning_rate": 7.805432891743611e-06,
582
+ "loss": 0.7837,
583
+ "step": 1640
584
+ },
585
+ {
586
+ "epoch": 0.22213301217717116,
587
+ "grad_norm": 13.5625,
588
+ "learning_rate": 7.778669878228289e-06,
589
+ "loss": 0.7751,
590
+ "step": 1660
591
+ },
592
+ {
593
+ "epoch": 0.22480931352870334,
594
+ "grad_norm": 15.375,
595
+ "learning_rate": 7.751906864712967e-06,
596
+ "loss": 0.8476,
597
+ "step": 1680
598
+ },
599
+ {
600
+ "epoch": 0.22748561488023553,
601
+ "grad_norm": 7.625,
602
+ "learning_rate": 7.725143851197645e-06,
603
+ "loss": 0.7734,
604
+ "step": 1700
605
+ },
606
+ {
607
+ "epoch": 0.2301619162317677,
608
+ "grad_norm": 14.25,
609
+ "learning_rate": 7.698380837682323e-06,
610
+ "loss": 0.7714,
611
+ "step": 1720
612
+ },
613
+ {
614
+ "epoch": 0.23283821758329987,
615
+ "grad_norm": 18.5,
616
+ "learning_rate": 7.671617824167e-06,
617
+ "loss": 0.7447,
618
+ "step": 1740
619
+ },
620
+ {
621
+ "epoch": 0.23551451893483205,
622
+ "grad_norm": 15.75,
623
+ "learning_rate": 7.644854810651679e-06,
624
+ "loss": 0.7385,
625
+ "step": 1760
626
+ },
627
+ {
628
+ "epoch": 0.23819082028636424,
629
+ "grad_norm": 10.5,
630
+ "learning_rate": 7.618091797136358e-06,
631
+ "loss": 0.7058,
632
+ "step": 1780
633
+ },
634
+ {
635
+ "epoch": 0.24086712163789642,
636
+ "grad_norm": 38.75,
637
+ "learning_rate": 7.591328783621036e-06,
638
+ "loss": 0.737,
639
+ "step": 1800
640
+ },
641
+ {
642
+ "epoch": 0.2435434229894286,
643
+ "grad_norm": 10.5,
644
+ "learning_rate": 7.564565770105714e-06,
645
+ "loss": 0.7831,
646
+ "step": 1820
647
+ },
648
+ {
649
+ "epoch": 0.2462197243409608,
650
+ "grad_norm": 21.0,
651
+ "learning_rate": 7.5378027565903925e-06,
652
+ "loss": 0.8369,
653
+ "step": 1840
654
+ },
655
+ {
656
+ "epoch": 0.24889602569249297,
657
+ "grad_norm": 20.5,
658
+ "learning_rate": 7.5110397430750704e-06,
659
+ "loss": 0.7846,
660
+ "step": 1860
661
+ },
662
+ {
663
+ "epoch": 0.25157232704402516,
664
+ "grad_norm": 6.375,
665
+ "learning_rate": 7.484276729559748e-06,
666
+ "loss": 0.8011,
667
+ "step": 1880
668
+ },
669
+ {
670
+ "epoch": 0.25424862839555734,
671
+ "grad_norm": 9.1875,
672
+ "learning_rate": 7.457513716044428e-06,
673
+ "loss": 0.7536,
674
+ "step": 1900
675
+ },
676
+ {
677
+ "epoch": 0.2569249297470895,
678
+ "grad_norm": 9.0,
679
+ "learning_rate": 7.430750702529106e-06,
680
+ "loss": 0.7622,
681
+ "step": 1920
682
+ },
683
+ {
684
+ "epoch": 0.2596012310986217,
685
+ "grad_norm": 7.875,
686
+ "learning_rate": 7.403987689013784e-06,
687
+ "loss": 0.7059,
688
+ "step": 1940
689
+ },
690
+ {
691
+ "epoch": 0.2622775324501539,
692
+ "grad_norm": 7.46875,
693
+ "learning_rate": 7.377224675498462e-06,
694
+ "loss": 0.7635,
695
+ "step": 1960
696
+ },
697
+ {
698
+ "epoch": 0.2649538338016861,
699
+ "grad_norm": 6.21875,
700
+ "learning_rate": 7.35046166198314e-06,
701
+ "loss": 0.7693,
702
+ "step": 1980
703
+ },
704
+ {
705
+ "epoch": 0.26763013515321826,
706
+ "grad_norm": 9.375,
707
+ "learning_rate": 7.323698648467819e-06,
708
+ "loss": 0.7812,
709
+ "step": 2000
710
+ },
711
+ {
712
+ "epoch": 0.27030643650475045,
713
+ "grad_norm": 13.1875,
714
+ "learning_rate": 7.296935634952497e-06,
715
+ "loss": 0.7372,
716
+ "step": 2020
717
+ },
718
+ {
719
+ "epoch": 0.27298273785628263,
720
+ "grad_norm": 16.75,
721
+ "learning_rate": 7.270172621437175e-06,
722
+ "loss": 0.8489,
723
+ "step": 2040
724
+ },
725
+ {
726
+ "epoch": 0.2756590392078148,
727
+ "grad_norm": 5.40625,
728
+ "learning_rate": 7.243409607921853e-06,
729
+ "loss": 0.6996,
730
+ "step": 2060
731
+ },
732
+ {
733
+ "epoch": 0.278335340559347,
734
+ "grad_norm": 10.875,
735
+ "learning_rate": 7.216646594406531e-06,
736
+ "loss": 0.7596,
737
+ "step": 2080
738
+ },
739
+ {
740
+ "epoch": 0.2810116419108792,
741
+ "grad_norm": 33.5,
742
+ "learning_rate": 7.18988358089121e-06,
743
+ "loss": 0.7819,
744
+ "step": 2100
745
+ },
746
+ {
747
+ "epoch": 0.28368794326241137,
748
+ "grad_norm": 11.4375,
749
+ "learning_rate": 7.163120567375888e-06,
750
+ "loss": 0.8196,
751
+ "step": 2120
752
+ },
753
+ {
754
+ "epoch": 0.28636424461394355,
755
+ "grad_norm": 7.78125,
756
+ "learning_rate": 7.136357553860566e-06,
757
+ "loss": 0.7454,
758
+ "step": 2140
759
+ },
760
+ {
761
+ "epoch": 0.28904054596547574,
762
+ "grad_norm": 14.5625,
763
+ "learning_rate": 7.109594540345244e-06,
764
+ "loss": 0.7306,
765
+ "step": 2160
766
+ },
767
+ {
768
+ "epoch": 0.2917168473170079,
769
+ "grad_norm": 9.5,
770
+ "learning_rate": 7.082831526829922e-06,
771
+ "loss": 0.7076,
772
+ "step": 2180
773
+ },
774
+ {
775
+ "epoch": 0.29439314866854005,
776
+ "grad_norm": 12.875,
777
+ "learning_rate": 7.0560685133146004e-06,
778
+ "loss": 0.7679,
779
+ "step": 2200
780
+ },
781
+ {
782
+ "epoch": 0.29706945002007223,
783
+ "grad_norm": 11.0,
784
+ "learning_rate": 7.029305499799278e-06,
785
+ "loss": 0.6691,
786
+ "step": 2220
787
+ },
788
+ {
789
+ "epoch": 0.2997457513716044,
790
+ "grad_norm": 13.4375,
791
+ "learning_rate": 7.002542486283956e-06,
792
+ "loss": 0.7002,
793
+ "step": 2240
794
+ },
795
+ {
796
+ "epoch": 0.3024220527231366,
797
+ "grad_norm": 13.25,
798
+ "learning_rate": 6.975779472768634e-06,
799
+ "loss": 0.8657,
800
+ "step": 2260
801
+ },
802
+ {
803
+ "epoch": 0.3050983540746688,
804
+ "grad_norm": 16.25,
805
+ "learning_rate": 6.949016459253312e-06,
806
+ "loss": 0.6808,
807
+ "step": 2280
808
+ },
809
+ {
810
+ "epoch": 0.30777465542620097,
811
+ "grad_norm": 11.75,
812
+ "learning_rate": 6.922253445737991e-06,
813
+ "loss": 0.7294,
814
+ "step": 2300
815
+ },
816
+ {
817
+ "epoch": 0.31045095677773316,
818
+ "grad_norm": 12.5,
819
+ "learning_rate": 6.895490432222669e-06,
820
+ "loss": 0.7018,
821
+ "step": 2320
822
+ },
823
+ {
824
+ "epoch": 0.31312725812926534,
825
+ "grad_norm": 11.6875,
826
+ "learning_rate": 6.868727418707347e-06,
827
+ "loss": 0.6812,
828
+ "step": 2340
829
+ },
830
+ {
831
+ "epoch": 0.3158035594807975,
832
+ "grad_norm": 7.625,
833
+ "learning_rate": 6.841964405192025e-06,
834
+ "loss": 0.7062,
835
+ "step": 2360
836
+ },
837
+ {
838
+ "epoch": 0.3184798608323297,
839
+ "grad_norm": 18.125,
840
+ "learning_rate": 6.815201391676703e-06,
841
+ "loss": 0.7192,
842
+ "step": 2380
843
+ },
844
+ {
845
+ "epoch": 0.3211561621838619,
846
+ "grad_norm": 12.75,
847
+ "learning_rate": 6.788438378161382e-06,
848
+ "loss": 0.6406,
849
+ "step": 2400
850
+ },
851
+ {
852
+ "epoch": 0.3238324635353941,
853
+ "grad_norm": 6.75,
854
+ "learning_rate": 6.76167536464606e-06,
855
+ "loss": 0.7128,
856
+ "step": 2420
857
+ },
858
+ {
859
+ "epoch": 0.32650876488692626,
860
+ "grad_norm": 15.6875,
861
+ "learning_rate": 6.734912351130738e-06,
862
+ "loss": 0.6342,
863
+ "step": 2440
864
+ },
865
+ {
866
+ "epoch": 0.32918506623845845,
867
+ "grad_norm": 14.0,
868
+ "learning_rate": 6.708149337615416e-06,
869
+ "loss": 0.7335,
870
+ "step": 2460
871
+ },
872
+ {
873
+ "epoch": 0.33186136758999063,
874
+ "grad_norm": 13.0,
875
+ "learning_rate": 6.681386324100094e-06,
876
+ "loss": 0.629,
877
+ "step": 2480
878
+ },
879
+ {
880
+ "epoch": 0.3345376689415228,
881
+ "grad_norm": 10.3125,
882
+ "learning_rate": 6.654623310584773e-06,
883
+ "loss": 0.7736,
884
+ "step": 2500
885
+ },
886
+ {
887
+ "epoch": 0.337213970293055,
888
+ "grad_norm": 7.84375,
889
+ "learning_rate": 6.627860297069451e-06,
890
+ "loss": 0.826,
891
+ "step": 2520
892
+ },
893
+ {
894
+ "epoch": 0.3398902716445872,
895
+ "grad_norm": 7.09375,
896
+ "learning_rate": 6.601097283554129e-06,
897
+ "loss": 0.6452,
898
+ "step": 2540
899
+ },
900
+ {
901
+ "epoch": 0.34256657299611937,
902
+ "grad_norm": 6.125,
903
+ "learning_rate": 6.574334270038807e-06,
904
+ "loss": 0.705,
905
+ "step": 2560
906
+ },
907
+ {
908
+ "epoch": 0.34524287434765155,
909
+ "grad_norm": 65.0,
910
+ "learning_rate": 6.547571256523485e-06,
911
+ "loss": 0.6926,
912
+ "step": 2580
913
+ },
914
+ {
915
+ "epoch": 0.34791917569918374,
916
+ "grad_norm": 7.125,
917
+ "learning_rate": 6.5208082430081635e-06,
918
+ "loss": 0.6877,
919
+ "step": 2600
920
+ },
921
+ {
922
+ "epoch": 0.3505954770507159,
923
+ "grad_norm": 12.4375,
924
+ "learning_rate": 6.4940452294928415e-06,
925
+ "loss": 0.8122,
926
+ "step": 2620
927
+ },
928
+ {
929
+ "epoch": 0.3532717784022481,
930
+ "grad_norm": 5.75,
931
+ "learning_rate": 6.4672822159775195e-06,
932
+ "loss": 0.7015,
933
+ "step": 2640
934
+ },
935
+ {
936
+ "epoch": 0.3559480797537803,
937
+ "grad_norm": 9.1875,
938
+ "learning_rate": 6.4405192024621975e-06,
939
+ "loss": 0.7502,
940
+ "step": 2660
941
+ },
942
+ {
943
+ "epoch": 0.3586243811053125,
944
+ "grad_norm": 4.6875,
945
+ "learning_rate": 6.4137561889468755e-06,
946
+ "loss": 0.6114,
947
+ "step": 2680
948
+ },
949
+ {
950
+ "epoch": 0.36130068245684466,
951
+ "grad_norm": 12.0,
952
+ "learning_rate": 6.386993175431554e-06,
953
+ "loss": 0.6149,
954
+ "step": 2700
955
+ },
956
+ {
957
+ "epoch": 0.36397698380837684,
958
+ "grad_norm": 7.78125,
959
+ "learning_rate": 6.360230161916232e-06,
960
+ "loss": 0.6908,
961
+ "step": 2720
962
+ },
963
+ {
964
+ "epoch": 0.366653285159909,
965
+ "grad_norm": 7.65625,
966
+ "learning_rate": 6.33346714840091e-06,
967
+ "loss": 0.7734,
968
+ "step": 2740
969
+ },
970
+ {
971
+ "epoch": 0.3693295865114412,
972
+ "grad_norm": 12.0,
973
+ "learning_rate": 6.306704134885588e-06,
974
+ "loss": 0.7201,
975
+ "step": 2760
976
+ },
977
+ {
978
+ "epoch": 0.3720058878629734,
979
+ "grad_norm": 17.875,
980
+ "learning_rate": 6.279941121370266e-06,
981
+ "loss": 0.7441,
982
+ "step": 2780
983
+ },
984
+ {
985
+ "epoch": 0.3746821892145056,
986
+ "grad_norm": 18.375,
987
+ "learning_rate": 6.253178107854945e-06,
988
+ "loss": 0.6822,
989
+ "step": 2800
990
+ },
991
+ {
992
+ "epoch": 0.37735849056603776,
993
+ "grad_norm": 10.125,
994
+ "learning_rate": 6.226415094339623e-06,
995
+ "loss": 0.758,
996
+ "step": 2820
997
+ },
998
+ {
999
+ "epoch": 0.3800347919175699,
1000
+ "grad_norm": 15.125,
1001
+ "learning_rate": 6.199652080824301e-06,
1002
+ "loss": 0.6623,
1003
+ "step": 2840
1004
+ },
1005
+ {
1006
+ "epoch": 0.3827110932691021,
1007
+ "grad_norm": 8.5,
1008
+ "learning_rate": 6.172889067308979e-06,
1009
+ "loss": 0.6744,
1010
+ "step": 2860
1011
+ },
1012
+ {
1013
+ "epoch": 0.38538739462063426,
1014
+ "grad_norm": 10.8125,
1015
+ "learning_rate": 6.146126053793657e-06,
1016
+ "loss": 0.6643,
1017
+ "step": 2880
1018
+ },
1019
+ {
1020
+ "epoch": 0.38806369597216644,
1021
+ "grad_norm": 11.5625,
1022
+ "learning_rate": 6.119363040278336e-06,
1023
+ "loss": 0.7278,
1024
+ "step": 2900
1025
+ },
1026
+ {
1027
+ "epoch": 0.39073999732369863,
1028
+ "grad_norm": 6.65625,
1029
+ "learning_rate": 6.092600026763014e-06,
1030
+ "loss": 0.6364,
1031
+ "step": 2920
1032
+ },
1033
+ {
1034
+ "epoch": 0.3934162986752308,
1035
+ "grad_norm": 8.75,
1036
+ "learning_rate": 6.065837013247692e-06,
1037
+ "loss": 0.7175,
1038
+ "step": 2940
1039
+ },
1040
+ {
1041
+ "epoch": 0.396092600026763,
1042
+ "grad_norm": 10.25,
1043
+ "learning_rate": 6.03907399973237e-06,
1044
+ "loss": 0.6905,
1045
+ "step": 2960
1046
+ },
1047
+ {
1048
+ "epoch": 0.3987689013782952,
1049
+ "grad_norm": 14.0625,
1050
+ "learning_rate": 6.012310986217048e-06,
1051
+ "loss": 0.599,
1052
+ "step": 2980
1053
+ },
1054
+ {
1055
+ "epoch": 0.40144520272982737,
1056
+ "grad_norm": 9.6875,
1057
+ "learning_rate": 5.985547972701727e-06,
1058
+ "loss": 0.7629,
1059
+ "step": 3000
1060
+ },
1061
+ {
1062
+ "epoch": 0.40412150408135955,
1063
+ "grad_norm": 19.125,
1064
+ "learning_rate": 5.958784959186405e-06,
1065
+ "loss": 0.7624,
1066
+ "step": 3020
1067
+ },
1068
+ {
1069
+ "epoch": 0.40679780543289173,
1070
+ "grad_norm": 9.0625,
1071
+ "learning_rate": 5.932021945671083e-06,
1072
+ "loss": 0.7122,
1073
+ "step": 3040
1074
+ },
1075
+ {
1076
+ "epoch": 0.4094741067844239,
1077
+ "grad_norm": 12.0625,
1078
+ "learning_rate": 5.905258932155761e-06,
1079
+ "loss": 0.711,
1080
+ "step": 3060
1081
+ },
1082
+ {
1083
+ "epoch": 0.4121504081359561,
1084
+ "grad_norm": 8.4375,
1085
+ "learning_rate": 5.878495918640439e-06,
1086
+ "loss": 0.685,
1087
+ "step": 3080
1088
+ },
1089
+ {
1090
+ "epoch": 0.4148267094874883,
1091
+ "grad_norm": 23.5,
1092
+ "learning_rate": 5.851732905125117e-06,
1093
+ "loss": 0.7422,
1094
+ "step": 3100
1095
+ },
1096
+ {
1097
+ "epoch": 0.41750301083902047,
1098
+ "grad_norm": 8.9375,
1099
+ "learning_rate": 5.824969891609795e-06,
1100
+ "loss": 0.7546,
1101
+ "step": 3120
1102
+ },
1103
+ {
1104
+ "epoch": 0.42017931219055266,
1105
+ "grad_norm": 10.375,
1106
+ "learning_rate": 5.798206878094474e-06,
1107
+ "loss": 0.7204,
1108
+ "step": 3140
1109
+ },
1110
+ {
1111
+ "epoch": 0.42285561354208484,
1112
+ "grad_norm": 7.3125,
1113
+ "learning_rate": 5.771443864579152e-06,
1114
+ "loss": 0.7457,
1115
+ "step": 3160
1116
+ },
1117
+ {
1118
+ "epoch": 0.425531914893617,
1119
+ "grad_norm": 10.9375,
1120
+ "learning_rate": 5.744680851063831e-06,
1121
+ "loss": 0.7411,
1122
+ "step": 3180
1123
+ },
1124
+ {
1125
+ "epoch": 0.4282082162451492,
1126
+ "grad_norm": 12.3125,
1127
+ "learning_rate": 5.717917837548509e-06,
1128
+ "loss": 0.7036,
1129
+ "step": 3200
1130
+ },
1131
+ {
1132
+ "epoch": 0.4308845175966814,
1133
+ "grad_norm": 10.0625,
1134
+ "learning_rate": 5.691154824033187e-06,
1135
+ "loss": 0.7014,
1136
+ "step": 3220
1137
+ },
1138
+ {
1139
+ "epoch": 0.4335608189482136,
1140
+ "grad_norm": 6.875,
1141
+ "learning_rate": 5.664391810517865e-06,
1142
+ "loss": 0.73,
1143
+ "step": 3240
1144
+ },
1145
+ {
1146
+ "epoch": 0.43623712029974576,
1147
+ "grad_norm": 8.375,
1148
+ "learning_rate": 5.637628797002543e-06,
1149
+ "loss": 0.6942,
1150
+ "step": 3260
1151
+ },
1152
+ {
1153
+ "epoch": 0.43891342165127795,
1154
+ "grad_norm": 13.125,
1155
+ "learning_rate": 5.610865783487222e-06,
1156
+ "loss": 0.6773,
1157
+ "step": 3280
1158
+ },
1159
+ {
1160
+ "epoch": 0.44158972300281013,
1161
+ "grad_norm": 10.5,
1162
+ "learning_rate": 5.5841027699719e-06,
1163
+ "loss": 0.6452,
1164
+ "step": 3300
1165
+ },
1166
+ {
1167
+ "epoch": 0.4442660243543423,
1168
+ "grad_norm": 7.59375,
1169
+ "learning_rate": 5.557339756456578e-06,
1170
+ "loss": 0.7561,
1171
+ "step": 3320
1172
+ },
1173
+ {
1174
+ "epoch": 0.4469423257058745,
1175
+ "grad_norm": 10.4375,
1176
+ "learning_rate": 5.530576742941256e-06,
1177
+ "loss": 0.7064,
1178
+ "step": 3340
1179
+ },
1180
+ {
1181
+ "epoch": 0.4496186270574067,
1182
+ "grad_norm": 6.90625,
1183
+ "learning_rate": 5.503813729425934e-06,
1184
+ "loss": 0.6614,
1185
+ "step": 3360
1186
+ },
1187
+ {
1188
+ "epoch": 0.45229492840893887,
1189
+ "grad_norm": 11.125,
1190
+ "learning_rate": 5.477050715910613e-06,
1191
+ "loss": 0.7513,
1192
+ "step": 3380
1193
+ },
1194
+ {
1195
+ "epoch": 0.45497122976047105,
1196
+ "grad_norm": 16.875,
1197
+ "learning_rate": 5.450287702395291e-06,
1198
+ "loss": 0.6785,
1199
+ "step": 3400
1200
+ },
1201
+ {
1202
+ "epoch": 0.45764753111200324,
1203
+ "grad_norm": 12.1875,
1204
+ "learning_rate": 5.4235246888799686e-06,
1205
+ "loss": 0.8056,
1206
+ "step": 3420
1207
+ },
1208
+ {
1209
+ "epoch": 0.4603238324635354,
1210
+ "grad_norm": 19.125,
1211
+ "learning_rate": 5.3967616753646466e-06,
1212
+ "loss": 0.7518,
1213
+ "step": 3440
1214
+ },
1215
+ {
1216
+ "epoch": 0.46300013381506755,
1217
+ "grad_norm": 9.8125,
1218
+ "learning_rate": 5.3699986618493245e-06,
1219
+ "loss": 0.6852,
1220
+ "step": 3460
1221
+ },
1222
+ {
1223
+ "epoch": 0.46567643516659973,
1224
+ "grad_norm": 7.59375,
1225
+ "learning_rate": 5.343235648334003e-06,
1226
+ "loss": 0.7327,
1227
+ "step": 3480
1228
+ },
1229
+ {
1230
+ "epoch": 0.4683527365181319,
1231
+ "grad_norm": 19.0,
1232
+ "learning_rate": 5.316472634818681e-06,
1233
+ "loss": 0.7463,
1234
+ "step": 3500
1235
+ },
1236
+ {
1237
+ "epoch": 0.4710290378696641,
1238
+ "grad_norm": 8.6875,
1239
+ "learning_rate": 5.289709621303359e-06,
1240
+ "loss": 0.6091,
1241
+ "step": 3520
1242
+ },
1243
+ {
1244
+ "epoch": 0.4737053392211963,
1245
+ "grad_norm": 14.0,
1246
+ "learning_rate": 5.262946607788037e-06,
1247
+ "loss": 0.6896,
1248
+ "step": 3540
1249
+ },
1250
+ {
1251
+ "epoch": 0.47638164057272847,
1252
+ "grad_norm": 8.5,
1253
+ "learning_rate": 5.236183594272715e-06,
1254
+ "loss": 0.7641,
1255
+ "step": 3560
1256
+ },
1257
+ {
1258
+ "epoch": 0.47905794192426066,
1259
+ "grad_norm": 12.3125,
1260
+ "learning_rate": 5.209420580757394e-06,
1261
+ "loss": 0.6582,
1262
+ "step": 3580
1263
+ },
1264
+ {
1265
+ "epoch": 0.48173424327579284,
1266
+ "grad_norm": 11.0625,
1267
+ "learning_rate": 5.182657567242072e-06,
1268
+ "loss": 0.7291,
1269
+ "step": 3600
1270
+ },
1271
+ {
1272
+ "epoch": 0.484410544627325,
1273
+ "grad_norm": 12.9375,
1274
+ "learning_rate": 5.15589455372675e-06,
1275
+ "loss": 0.7209,
1276
+ "step": 3620
1277
+ },
1278
+ {
1279
+ "epoch": 0.4870868459788572,
1280
+ "grad_norm": 14.625,
1281
+ "learning_rate": 5.129131540211428e-06,
1282
+ "loss": 0.7259,
1283
+ "step": 3640
1284
+ },
1285
+ {
1286
+ "epoch": 0.4897631473303894,
1287
+ "grad_norm": 9.4375,
1288
+ "learning_rate": 5.102368526696106e-06,
1289
+ "loss": 0.7259,
1290
+ "step": 3660
1291
+ },
1292
+ {
1293
+ "epoch": 0.4924394486819216,
1294
+ "grad_norm": 7.53125,
1295
+ "learning_rate": 5.075605513180785e-06,
1296
+ "loss": 0.6947,
1297
+ "step": 3680
1298
+ },
1299
+ {
1300
+ "epoch": 0.49511575003345376,
1301
+ "grad_norm": 6.59375,
1302
+ "learning_rate": 5.048842499665463e-06,
1303
+ "loss": 0.7026,
1304
+ "step": 3700
1305
+ },
1306
+ {
1307
+ "epoch": 0.49779205138498595,
1308
+ "grad_norm": 22.125,
1309
+ "learning_rate": 5.022079486150141e-06,
1310
+ "loss": 0.7332,
1311
+ "step": 3720
1312
+ },
1313
+ {
1314
+ "epoch": 0.5004683527365181,
1315
+ "grad_norm": 9.625,
1316
+ "learning_rate": 4.995316472634819e-06,
1317
+ "loss": 0.7487,
1318
+ "step": 3740
1319
+ },
1320
+ {
1321
+ "epoch": 0.5031446540880503,
1322
+ "grad_norm": 8.9375,
1323
+ "learning_rate": 4.968553459119497e-06,
1324
+ "loss": 0.6364,
1325
+ "step": 3760
1326
+ },
1327
+ {
1328
+ "epoch": 0.5058209554395825,
1329
+ "grad_norm": 10.125,
1330
+ "learning_rate": 4.941790445604176e-06,
1331
+ "loss": 0.7261,
1332
+ "step": 3780
1333
+ },
1334
+ {
1335
+ "epoch": 0.5084972567911147,
1336
+ "grad_norm": 19.0,
1337
+ "learning_rate": 4.915027432088854e-06,
1338
+ "loss": 0.725,
1339
+ "step": 3800
1340
+ },
1341
+ {
1342
+ "epoch": 0.5111735581426469,
1343
+ "grad_norm": 11.6875,
1344
+ "learning_rate": 4.888264418573532e-06,
1345
+ "loss": 0.6957,
1346
+ "step": 3820
1347
+ },
1348
+ {
1349
+ "epoch": 0.513849859494179,
1350
+ "grad_norm": 9.75,
1351
+ "learning_rate": 4.86150140505821e-06,
1352
+ "loss": 0.6555,
1353
+ "step": 3840
1354
+ },
1355
+ {
1356
+ "epoch": 0.5165261608457112,
1357
+ "grad_norm": 8.875,
1358
+ "learning_rate": 4.834738391542888e-06,
1359
+ "loss": 0.7902,
1360
+ "step": 3860
1361
+ },
1362
+ {
1363
+ "epoch": 0.5192024621972434,
1364
+ "grad_norm": 10.5625,
1365
+ "learning_rate": 4.8079753780275665e-06,
1366
+ "loss": 0.7535,
1367
+ "step": 3880
1368
+ },
1369
+ {
1370
+ "epoch": 0.5218787635487756,
1371
+ "grad_norm": 6.71875,
1372
+ "learning_rate": 4.7812123645122445e-06,
1373
+ "loss": 0.84,
1374
+ "step": 3900
1375
+ },
1376
+ {
1377
+ "epoch": 0.5245550649003078,
1378
+ "grad_norm": 8.3125,
1379
+ "learning_rate": 4.7544493509969225e-06,
1380
+ "loss": 0.6911,
1381
+ "step": 3920
1382
+ },
1383
+ {
1384
+ "epoch": 0.52723136625184,
1385
+ "grad_norm": 9.4375,
1386
+ "learning_rate": 4.7276863374816004e-06,
1387
+ "loss": 0.7435,
1388
+ "step": 3940
1389
+ },
1390
+ {
1391
+ "epoch": 0.5299076676033722,
1392
+ "grad_norm": 12.875,
1393
+ "learning_rate": 4.7009233239662784e-06,
1394
+ "loss": 0.7176,
1395
+ "step": 3960
1396
+ },
1397
+ {
1398
+ "epoch": 0.5325839689549043,
1399
+ "grad_norm": 6.6875,
1400
+ "learning_rate": 4.674160310450957e-06,
1401
+ "loss": 0.6389,
1402
+ "step": 3980
1403
+ },
1404
+ {
1405
+ "epoch": 0.5352602703064365,
1406
+ "grad_norm": 17.0,
1407
+ "learning_rate": 4.647397296935635e-06,
1408
+ "loss": 0.6902,
1409
+ "step": 4000
1410
+ },
1411
+ {
1412
+ "epoch": 0.5379365716579687,
1413
+ "grad_norm": 15.5,
1414
+ "learning_rate": 4.620634283420313e-06,
1415
+ "loss": 0.7835,
1416
+ "step": 4020
1417
+ },
1418
+ {
1419
+ "epoch": 0.5406128730095009,
1420
+ "grad_norm": 14.0625,
1421
+ "learning_rate": 4.593871269904991e-06,
1422
+ "loss": 0.7667,
1423
+ "step": 4040
1424
+ },
1425
+ {
1426
+ "epoch": 0.5432891743610331,
1427
+ "grad_norm": 15.5625,
1428
+ "learning_rate": 4.567108256389669e-06,
1429
+ "loss": 0.7173,
1430
+ "step": 4060
1431
+ },
1432
+ {
1433
+ "epoch": 0.5459654757125653,
1434
+ "grad_norm": 7.6875,
1435
+ "learning_rate": 4.540345242874348e-06,
1436
+ "loss": 0.6364,
1437
+ "step": 4080
1438
+ },
1439
+ {
1440
+ "epoch": 0.5486417770640974,
1441
+ "grad_norm": 8.0625,
1442
+ "learning_rate": 4.513582229359027e-06,
1443
+ "loss": 0.6644,
1444
+ "step": 4100
1445
+ },
1446
+ {
1447
+ "epoch": 0.5513180784156296,
1448
+ "grad_norm": 8.6875,
1449
+ "learning_rate": 4.486819215843705e-06,
1450
+ "loss": 0.6862,
1451
+ "step": 4120
1452
+ },
1453
+ {
1454
+ "epoch": 0.5539943797671618,
1455
+ "grad_norm": 16.875,
1456
+ "learning_rate": 4.460056202328383e-06,
1457
+ "loss": 0.6885,
1458
+ "step": 4140
1459
+ },
1460
+ {
1461
+ "epoch": 0.556670681118694,
1462
+ "grad_norm": 8.125,
1463
+ "learning_rate": 4.433293188813061e-06,
1464
+ "loss": 0.7585,
1465
+ "step": 4160
1466
+ },
1467
+ {
1468
+ "epoch": 0.5593469824702262,
1469
+ "grad_norm": 13.375,
1470
+ "learning_rate": 4.406530175297739e-06,
1471
+ "loss": 0.7361,
1472
+ "step": 4180
1473
+ },
1474
+ {
1475
+ "epoch": 0.5620232838217584,
1476
+ "grad_norm": 9.875,
1477
+ "learning_rate": 4.379767161782418e-06,
1478
+ "loss": 0.6836,
1479
+ "step": 4200
1480
+ },
1481
+ {
1482
+ "epoch": 0.5646995851732906,
1483
+ "grad_norm": 10.75,
1484
+ "learning_rate": 4.353004148267096e-06,
1485
+ "loss": 0.7238,
1486
+ "step": 4220
1487
+ },
1488
+ {
1489
+ "epoch": 0.5673758865248227,
1490
+ "grad_norm": 10.5625,
1491
+ "learning_rate": 4.326241134751774e-06,
1492
+ "loss": 0.7354,
1493
+ "step": 4240
1494
+ },
1495
+ {
1496
+ "epoch": 0.5700521878763549,
1497
+ "grad_norm": 8.125,
1498
+ "learning_rate": 4.299478121236452e-06,
1499
+ "loss": 0.7141,
1500
+ "step": 4260
1501
+ },
1502
+ {
1503
+ "epoch": 0.5727284892278871,
1504
+ "grad_norm": 9.9375,
1505
+ "learning_rate": 4.27271510772113e-06,
1506
+ "loss": 0.7113,
1507
+ "step": 4280
1508
+ },
1509
+ {
1510
+ "epoch": 0.5754047905794193,
1511
+ "grad_norm": 13.75,
1512
+ "learning_rate": 4.245952094205808e-06,
1513
+ "loss": 0.7338,
1514
+ "step": 4300
1515
+ },
1516
+ {
1517
+ "epoch": 0.5780810919309515,
1518
+ "grad_norm": 14.375,
1519
+ "learning_rate": 4.219189080690486e-06,
1520
+ "loss": 0.7292,
1521
+ "step": 4320
1522
+ },
1523
+ {
1524
+ "epoch": 0.5807573932824837,
1525
+ "grad_norm": 10.3125,
1526
+ "learning_rate": 4.192426067175164e-06,
1527
+ "loss": 0.6675,
1528
+ "step": 4340
1529
+ },
1530
+ {
1531
+ "epoch": 0.5834336946340158,
1532
+ "grad_norm": 27.375,
1533
+ "learning_rate": 4.165663053659842e-06,
1534
+ "loss": 0.6879,
1535
+ "step": 4360
1536
+ },
1537
+ {
1538
+ "epoch": 0.586109995985548,
1539
+ "grad_norm": 11.8125,
1540
+ "learning_rate": 4.13890004014452e-06,
1541
+ "loss": 0.5935,
1542
+ "step": 4380
1543
+ },
1544
+ {
1545
+ "epoch": 0.5887862973370801,
1546
+ "grad_norm": 7.46875,
1547
+ "learning_rate": 4.112137026629199e-06,
1548
+ "loss": 0.7692,
1549
+ "step": 4400
1550
+ },
1551
+ {
1552
+ "epoch": 0.5914625986886123,
1553
+ "grad_norm": 13.875,
1554
+ "learning_rate": 4.085374013113877e-06,
1555
+ "loss": 0.7598,
1556
+ "step": 4420
1557
+ },
1558
+ {
1559
+ "epoch": 0.5941389000401445,
1560
+ "grad_norm": 14.6875,
1561
+ "learning_rate": 4.058610999598555e-06,
1562
+ "loss": 0.63,
1563
+ "step": 4440
1564
+ },
1565
+ {
1566
+ "epoch": 0.5968152013916767,
1567
+ "grad_norm": 17.75,
1568
+ "learning_rate": 4.031847986083233e-06,
1569
+ "loss": 0.7506,
1570
+ "step": 4460
1571
+ },
1572
+ {
1573
+ "epoch": 0.5994915027432088,
1574
+ "grad_norm": 9.625,
1575
+ "learning_rate": 4.005084972567911e-06,
1576
+ "loss": 0.6189,
1577
+ "step": 4480
1578
+ },
1579
+ {
1580
+ "epoch": 0.602167804094741,
1581
+ "grad_norm": 8.875,
1582
+ "learning_rate": 3.97832195905259e-06,
1583
+ "loss": 0.7193,
1584
+ "step": 4500
1585
+ },
1586
+ {
1587
+ "epoch": 0.6048441054462732,
1588
+ "grad_norm": 12.8125,
1589
+ "learning_rate": 3.951558945537268e-06,
1590
+ "loss": 0.7936,
1591
+ "step": 4520
1592
+ },
1593
+ {
1594
+ "epoch": 0.6075204067978054,
1595
+ "grad_norm": 8.3125,
1596
+ "learning_rate": 3.924795932021946e-06,
1597
+ "loss": 0.7412,
1598
+ "step": 4540
1599
+ },
1600
+ {
1601
+ "epoch": 0.6101967081493376,
1602
+ "grad_norm": 13.75,
1603
+ "learning_rate": 3.898032918506624e-06,
1604
+ "loss": 0.6437,
1605
+ "step": 4560
1606
+ },
1607
+ {
1608
+ "epoch": 0.6128730095008698,
1609
+ "grad_norm": 12.1875,
1610
+ "learning_rate": 3.871269904991302e-06,
1611
+ "loss": 0.6643,
1612
+ "step": 4580
1613
+ },
1614
+ {
1615
+ "epoch": 0.6155493108524019,
1616
+ "grad_norm": 14.5,
1617
+ "learning_rate": 3.844506891475981e-06,
1618
+ "loss": 0.6438,
1619
+ "step": 4600
1620
+ },
1621
+ {
1622
+ "epoch": 0.6182256122039341,
1623
+ "grad_norm": 8.6875,
1624
+ "learning_rate": 3.817743877960659e-06,
1625
+ "loss": 0.6731,
1626
+ "step": 4620
1627
+ },
1628
+ {
1629
+ "epoch": 0.6209019135554663,
1630
+ "grad_norm": 23.0,
1631
+ "learning_rate": 3.7909808644453367e-06,
1632
+ "loss": 0.6498,
1633
+ "step": 4640
1634
+ },
1635
+ {
1636
+ "epoch": 0.6235782149069985,
1637
+ "grad_norm": 7.3125,
1638
+ "learning_rate": 3.7642178509300147e-06,
1639
+ "loss": 0.7402,
1640
+ "step": 4660
1641
+ },
1642
+ {
1643
+ "epoch": 0.6262545162585307,
1644
+ "grad_norm": 16.625,
1645
+ "learning_rate": 3.737454837414693e-06,
1646
+ "loss": 0.7464,
1647
+ "step": 4680
1648
+ },
1649
+ {
1650
+ "epoch": 0.6289308176100629,
1651
+ "grad_norm": 8.5625,
1652
+ "learning_rate": 3.710691823899371e-06,
1653
+ "loss": 0.7294,
1654
+ "step": 4700
1655
+ },
1656
+ {
1657
+ "epoch": 0.631607118961595,
1658
+ "grad_norm": 7.1875,
1659
+ "learning_rate": 3.68392881038405e-06,
1660
+ "loss": 0.7184,
1661
+ "step": 4720
1662
+ },
1663
+ {
1664
+ "epoch": 0.6342834203131272,
1665
+ "grad_norm": 8.0625,
1666
+ "learning_rate": 3.657165796868728e-06,
1667
+ "loss": 0.6361,
1668
+ "step": 4740
1669
+ },
1670
+ {
1671
+ "epoch": 0.6369597216646594,
1672
+ "grad_norm": 10.6875,
1673
+ "learning_rate": 3.6304027833534063e-06,
1674
+ "loss": 0.6732,
1675
+ "step": 4760
1676
+ },
1677
+ {
1678
+ "epoch": 0.6396360230161916,
1679
+ "grad_norm": 10.1875,
1680
+ "learning_rate": 3.6036397698380843e-06,
1681
+ "loss": 0.6091,
1682
+ "step": 4780
1683
+ },
1684
+ {
1685
+ "epoch": 0.6423123243677238,
1686
+ "grad_norm": 10.75,
1687
+ "learning_rate": 3.5768767563227623e-06,
1688
+ "loss": 0.6382,
1689
+ "step": 4800
1690
+ },
1691
+ {
1692
+ "epoch": 0.644988625719256,
1693
+ "grad_norm": 10.6875,
1694
+ "learning_rate": 3.5501137428074407e-06,
1695
+ "loss": 0.7222,
1696
+ "step": 4820
1697
+ },
1698
+ {
1699
+ "epoch": 0.6476649270707882,
1700
+ "grad_norm": 16.5,
1701
+ "learning_rate": 3.5233507292921187e-06,
1702
+ "loss": 0.6297,
1703
+ "step": 4840
1704
+ },
1705
+ {
1706
+ "epoch": 0.6503412284223203,
1707
+ "grad_norm": 12.375,
1708
+ "learning_rate": 3.496587715776797e-06,
1709
+ "loss": 0.709,
1710
+ "step": 4860
1711
+ },
1712
+ {
1713
+ "epoch": 0.6530175297738525,
1714
+ "grad_norm": 15.8125,
1715
+ "learning_rate": 3.469824702261475e-06,
1716
+ "loss": 0.6754,
1717
+ "step": 4880
1718
+ },
1719
+ {
1720
+ "epoch": 0.6556938311253847,
1721
+ "grad_norm": 32.5,
1722
+ "learning_rate": 3.443061688746153e-06,
1723
+ "loss": 0.9194,
1724
+ "step": 4900
1725
+ },
1726
+ {
1727
+ "epoch": 0.6583701324769169,
1728
+ "grad_norm": 7.75,
1729
+ "learning_rate": 3.4162986752308315e-06,
1730
+ "loss": 0.6851,
1731
+ "step": 4920
1732
+ },
1733
+ {
1734
+ "epoch": 0.6610464338284491,
1735
+ "grad_norm": 24.5,
1736
+ "learning_rate": 3.3895356617155095e-06,
1737
+ "loss": 0.728,
1738
+ "step": 4940
1739
+ },
1740
+ {
1741
+ "epoch": 0.6637227351799813,
1742
+ "grad_norm": 13.3125,
1743
+ "learning_rate": 3.362772648200188e-06,
1744
+ "loss": 0.6899,
1745
+ "step": 4960
1746
+ },
1747
+ {
1748
+ "epoch": 0.6663990365315134,
1749
+ "grad_norm": 12.4375,
1750
+ "learning_rate": 3.336009634684866e-06,
1751
+ "loss": 0.714,
1752
+ "step": 4980
1753
+ },
1754
+ {
1755
+ "epoch": 0.6690753378830456,
1756
+ "grad_norm": 11.0625,
1757
+ "learning_rate": 3.309246621169544e-06,
1758
+ "loss": 0.721,
1759
+ "step": 5000
1760
+ }
1761
+ ],
1762
+ "logging_steps": 20,
1763
+ "max_steps": 7473,
1764
+ "num_input_tokens_seen": 0,
1765
+ "num_train_epochs": 1,
1766
+ "save_steps": 5000,
1767
+ "stateful_callbacks": {
1768
+ "TrainerControl": {
1769
+ "args": {
1770
+ "should_epoch_stop": false,
1771
+ "should_evaluate": false,
1772
+ "should_log": false,
1773
+ "should_save": true,
1774
+ "should_training_stop": false
1775
+ },
1776
+ "attributes": {}
1777
+ }
1778
+ },
1779
+ "total_flos": 7473762140160000.0,
1780
+ "train_batch_size": 1,
1781
+ "trial_name": null,
1782
+ "trial_params": null
1783
+ }
checkpoint-5000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5192ed7d4caa2f74e975a410893b27550adcd92c93eb22def9cf35fa3c6a5484
3
+ size 6008
checkpoint-7473/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.2-1B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 16,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 128001,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": {
25
+ "factor": 32.0,
26
+ "high_freq_factor": 4.0,
27
+ "low_freq_factor": 1.0,
28
+ "original_max_position_embeddings": 8192,
29
+ "rope_type": "llama3"
30
+ },
31
+ "rope_theta": 500000.0,
32
+ "tie_word_embeddings": true,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.46.3",
35
+ "use_cache": true,
36
+ "vocab_size": 128256
37
+ }
checkpoint-7473/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.46.3"
9
+ }
checkpoint-7473/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09383ac745175f35de75477e5652cfdc1249ff1273fad0ccad70da6c4a04c19c
3
+ size 2471645608
checkpoint-7473/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea991beaa785c167159089df91e40219293e57e9383beffc7a15c20ecdd35a3e
3
+ size 9886607810
checkpoint-7473/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d2fbed01562860fa8e564c08d5ec3b4ac9b08c0ac799929877b47c4e2d6d030
3
+ size 14308
checkpoint-7473/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4d52a309cfb117056fd85a2737bc20b13a6b1106e546913e701b8e7ff1f318e
3
+ size 1064
checkpoint-7473/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|end_of_text|>"
17
+ }
checkpoint-7473/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-7473/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "model_input_names": [
2056
+ "input_ids",
2057
+ "attention_mask"
2058
+ ],
2059
+ "model_max_length": 131072,
2060
+ "pad_token": "<|end_of_text|>",
2061
+ "padding_side": "right",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
checkpoint-7473/trainer_state.json ADDED
@@ -0,0 +1,2644 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 7473,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0026763013515321826,
13
+ "grad_norm": 21.75,
14
+ "learning_rate": 9.973236986484679e-06,
15
+ "loss": 1.9581,
16
+ "step": 20
17
+ },
18
+ {
19
+ "epoch": 0.005352602703064365,
20
+ "grad_norm": 11.0625,
21
+ "learning_rate": 9.946473972969357e-06,
22
+ "loss": 1.8767,
23
+ "step": 40
24
+ },
25
+ {
26
+ "epoch": 0.008028904054596548,
27
+ "grad_norm": 20.875,
28
+ "learning_rate": 9.919710959454035e-06,
29
+ "loss": 1.729,
30
+ "step": 60
31
+ },
32
+ {
33
+ "epoch": 0.01070520540612873,
34
+ "grad_norm": 11.8125,
35
+ "learning_rate": 9.892947945938713e-06,
36
+ "loss": 1.4764,
37
+ "step": 80
38
+ },
39
+ {
40
+ "epoch": 0.013381506757660913,
41
+ "grad_norm": 20.375,
42
+ "learning_rate": 9.86618493242339e-06,
43
+ "loss": 1.4558,
44
+ "step": 100
45
+ },
46
+ {
47
+ "epoch": 0.016057808109193095,
48
+ "grad_norm": 9.8125,
49
+ "learning_rate": 9.83942191890807e-06,
50
+ "loss": 1.1101,
51
+ "step": 120
52
+ },
53
+ {
54
+ "epoch": 0.018734109460725276,
55
+ "grad_norm": 14.8125,
56
+ "learning_rate": 9.812658905392748e-06,
57
+ "loss": 1.2423,
58
+ "step": 140
59
+ },
60
+ {
61
+ "epoch": 0.02141041081225746,
62
+ "grad_norm": 15.3125,
63
+ "learning_rate": 9.785895891877426e-06,
64
+ "loss": 1.3871,
65
+ "step": 160
66
+ },
67
+ {
68
+ "epoch": 0.02408671216378964,
69
+ "grad_norm": 11.8125,
70
+ "learning_rate": 9.759132878362104e-06,
71
+ "loss": 1.2922,
72
+ "step": 180
73
+ },
74
+ {
75
+ "epoch": 0.026763013515321826,
76
+ "grad_norm": 9.25,
77
+ "learning_rate": 9.732369864846782e-06,
78
+ "loss": 1.3144,
79
+ "step": 200
80
+ },
81
+ {
82
+ "epoch": 0.029439314866854006,
83
+ "grad_norm": 18.625,
84
+ "learning_rate": 9.70560685133146e-06,
85
+ "loss": 1.0756,
86
+ "step": 220
87
+ },
88
+ {
89
+ "epoch": 0.03211561621838619,
90
+ "grad_norm": 43.25,
91
+ "learning_rate": 9.678843837816138e-06,
92
+ "loss": 1.2612,
93
+ "step": 240
94
+ },
95
+ {
96
+ "epoch": 0.034791917569918375,
97
+ "grad_norm": 9.4375,
98
+ "learning_rate": 9.652080824300816e-06,
99
+ "loss": 1.0856,
100
+ "step": 260
101
+ },
102
+ {
103
+ "epoch": 0.03746821892145055,
104
+ "grad_norm": 17.5,
105
+ "learning_rate": 9.625317810785494e-06,
106
+ "loss": 1.0375,
107
+ "step": 280
108
+ },
109
+ {
110
+ "epoch": 0.04014452027298274,
111
+ "grad_norm": 7.75,
112
+ "learning_rate": 9.598554797270172e-06,
113
+ "loss": 0.9578,
114
+ "step": 300
115
+ },
116
+ {
117
+ "epoch": 0.04282082162451492,
118
+ "grad_norm": 12.875,
119
+ "learning_rate": 9.571791783754852e-06,
120
+ "loss": 0.9921,
121
+ "step": 320
122
+ },
123
+ {
124
+ "epoch": 0.045497122976047105,
125
+ "grad_norm": 14.4375,
126
+ "learning_rate": 9.54502877023953e-06,
127
+ "loss": 0.8984,
128
+ "step": 340
129
+ },
130
+ {
131
+ "epoch": 0.04817342432757928,
132
+ "grad_norm": 11.9375,
133
+ "learning_rate": 9.518265756724208e-06,
134
+ "loss": 1.0139,
135
+ "step": 360
136
+ },
137
+ {
138
+ "epoch": 0.05084972567911147,
139
+ "grad_norm": 8.1875,
140
+ "learning_rate": 9.491502743208886e-06,
141
+ "loss": 0.9266,
142
+ "step": 380
143
+ },
144
+ {
145
+ "epoch": 0.05352602703064365,
146
+ "grad_norm": 33.0,
147
+ "learning_rate": 9.464739729693564e-06,
148
+ "loss": 0.8922,
149
+ "step": 400
150
+ },
151
+ {
152
+ "epoch": 0.056202328382175835,
153
+ "grad_norm": 20.375,
154
+ "learning_rate": 9.437976716178242e-06,
155
+ "loss": 0.9903,
156
+ "step": 420
157
+ },
158
+ {
159
+ "epoch": 0.05887862973370801,
160
+ "grad_norm": 18.625,
161
+ "learning_rate": 9.41121370266292e-06,
162
+ "loss": 0.8287,
163
+ "step": 440
164
+ },
165
+ {
166
+ "epoch": 0.0615549310852402,
167
+ "grad_norm": 8.75,
168
+ "learning_rate": 9.384450689147598e-06,
169
+ "loss": 0.9283,
170
+ "step": 460
171
+ },
172
+ {
173
+ "epoch": 0.06423123243677238,
174
+ "grad_norm": 21.75,
175
+ "learning_rate": 9.357687675632276e-06,
176
+ "loss": 0.9585,
177
+ "step": 480
178
+ },
179
+ {
180
+ "epoch": 0.06690753378830457,
181
+ "grad_norm": 13.9375,
182
+ "learning_rate": 9.330924662116954e-06,
183
+ "loss": 0.8412,
184
+ "step": 500
185
+ },
186
+ {
187
+ "epoch": 0.06958383513983675,
188
+ "grad_norm": 25.0,
189
+ "learning_rate": 9.304161648601634e-06,
190
+ "loss": 0.9743,
191
+ "step": 520
192
+ },
193
+ {
194
+ "epoch": 0.07226013649136893,
195
+ "grad_norm": 18.625,
196
+ "learning_rate": 9.277398635086312e-06,
197
+ "loss": 0.869,
198
+ "step": 540
199
+ },
200
+ {
201
+ "epoch": 0.0749364378429011,
202
+ "grad_norm": 11.625,
203
+ "learning_rate": 9.25063562157099e-06,
204
+ "loss": 0.7945,
205
+ "step": 560
206
+ },
207
+ {
208
+ "epoch": 0.07761273919443329,
209
+ "grad_norm": 7.1875,
210
+ "learning_rate": 9.223872608055667e-06,
211
+ "loss": 0.8359,
212
+ "step": 580
213
+ },
214
+ {
215
+ "epoch": 0.08028904054596547,
216
+ "grad_norm": 14.3125,
217
+ "learning_rate": 9.197109594540345e-06,
218
+ "loss": 0.7731,
219
+ "step": 600
220
+ },
221
+ {
222
+ "epoch": 0.08296534189749766,
223
+ "grad_norm": 12.9375,
224
+ "learning_rate": 9.170346581025023e-06,
225
+ "loss": 0.8352,
226
+ "step": 620
227
+ },
228
+ {
229
+ "epoch": 0.08564164324902984,
230
+ "grad_norm": 19.75,
231
+ "learning_rate": 9.143583567509703e-06,
232
+ "loss": 0.8792,
233
+ "step": 640
234
+ },
235
+ {
236
+ "epoch": 0.08831794460056203,
237
+ "grad_norm": 8.25,
238
+ "learning_rate": 9.116820553994381e-06,
239
+ "loss": 0.8651,
240
+ "step": 660
241
+ },
242
+ {
243
+ "epoch": 0.09099424595209421,
244
+ "grad_norm": 12.125,
245
+ "learning_rate": 9.090057540479059e-06,
246
+ "loss": 0.812,
247
+ "step": 680
248
+ },
249
+ {
250
+ "epoch": 0.0936705473036264,
251
+ "grad_norm": 15.75,
252
+ "learning_rate": 9.063294526963737e-06,
253
+ "loss": 0.8949,
254
+ "step": 700
255
+ },
256
+ {
257
+ "epoch": 0.09634684865515857,
258
+ "grad_norm": 11.5625,
259
+ "learning_rate": 9.036531513448415e-06,
260
+ "loss": 0.8752,
261
+ "step": 720
262
+ },
263
+ {
264
+ "epoch": 0.09902315000669075,
265
+ "grad_norm": 14.6875,
266
+ "learning_rate": 9.009768499933093e-06,
267
+ "loss": 0.8544,
268
+ "step": 740
269
+ },
270
+ {
271
+ "epoch": 0.10169945135822293,
272
+ "grad_norm": 9.9375,
273
+ "learning_rate": 8.983005486417771e-06,
274
+ "loss": 0.8414,
275
+ "step": 760
276
+ },
277
+ {
278
+ "epoch": 0.10437575270975512,
279
+ "grad_norm": 11.5,
280
+ "learning_rate": 8.95624247290245e-06,
281
+ "loss": 0.8796,
282
+ "step": 780
283
+ },
284
+ {
285
+ "epoch": 0.1070520540612873,
286
+ "grad_norm": 13.0625,
287
+ "learning_rate": 8.929479459387129e-06,
288
+ "loss": 0.853,
289
+ "step": 800
290
+ },
291
+ {
292
+ "epoch": 0.10972835541281949,
293
+ "grad_norm": 12.1875,
294
+ "learning_rate": 8.902716445871807e-06,
295
+ "loss": 0.8864,
296
+ "step": 820
297
+ },
298
+ {
299
+ "epoch": 0.11240465676435167,
300
+ "grad_norm": 60.0,
301
+ "learning_rate": 8.875953432356485e-06,
302
+ "loss": 0.7659,
303
+ "step": 840
304
+ },
305
+ {
306
+ "epoch": 0.11508095811588386,
307
+ "grad_norm": 30.0,
308
+ "learning_rate": 8.849190418841163e-06,
309
+ "loss": 0.9269,
310
+ "step": 860
311
+ },
312
+ {
313
+ "epoch": 0.11775725946741603,
314
+ "grad_norm": 9.125,
315
+ "learning_rate": 8.82242740532584e-06,
316
+ "loss": 0.7939,
317
+ "step": 880
318
+ },
319
+ {
320
+ "epoch": 0.12043356081894821,
321
+ "grad_norm": 9.0,
322
+ "learning_rate": 8.795664391810519e-06,
323
+ "loss": 0.8343,
324
+ "step": 900
325
+ },
326
+ {
327
+ "epoch": 0.1231098621704804,
328
+ "grad_norm": 18.25,
329
+ "learning_rate": 8.768901378295197e-06,
330
+ "loss": 0.7588,
331
+ "step": 920
332
+ },
333
+ {
334
+ "epoch": 0.12578616352201258,
335
+ "grad_norm": 6.34375,
336
+ "learning_rate": 8.742138364779875e-06,
337
+ "loss": 0.8424,
338
+ "step": 940
339
+ },
340
+ {
341
+ "epoch": 0.12846246487354476,
342
+ "grad_norm": 11.875,
343
+ "learning_rate": 8.715375351264553e-06,
344
+ "loss": 0.7666,
345
+ "step": 960
346
+ },
347
+ {
348
+ "epoch": 0.13113876622507695,
349
+ "grad_norm": 10.0,
350
+ "learning_rate": 8.688612337749232e-06,
351
+ "loss": 0.7019,
352
+ "step": 980
353
+ },
354
+ {
355
+ "epoch": 0.13381506757660913,
356
+ "grad_norm": 8.25,
357
+ "learning_rate": 8.66184932423391e-06,
358
+ "loss": 0.7036,
359
+ "step": 1000
360
+ },
361
+ {
362
+ "epoch": 0.13649136892814132,
363
+ "grad_norm": 10.75,
364
+ "learning_rate": 8.635086310718588e-06,
365
+ "loss": 0.7355,
366
+ "step": 1020
367
+ },
368
+ {
369
+ "epoch": 0.1391676702796735,
370
+ "grad_norm": 14.3125,
371
+ "learning_rate": 8.608323297203266e-06,
372
+ "loss": 0.737,
373
+ "step": 1040
374
+ },
375
+ {
376
+ "epoch": 0.14184397163120568,
377
+ "grad_norm": 9.5,
378
+ "learning_rate": 8.581560283687944e-06,
379
+ "loss": 0.7999,
380
+ "step": 1060
381
+ },
382
+ {
383
+ "epoch": 0.14452027298273787,
384
+ "grad_norm": 10.125,
385
+ "learning_rate": 8.554797270172622e-06,
386
+ "loss": 0.7613,
387
+ "step": 1080
388
+ },
389
+ {
390
+ "epoch": 0.14719657433427003,
391
+ "grad_norm": 22.625,
392
+ "learning_rate": 8.5280342566573e-06,
393
+ "loss": 0.8093,
394
+ "step": 1100
395
+ },
396
+ {
397
+ "epoch": 0.1498728756858022,
398
+ "grad_norm": 45.0,
399
+ "learning_rate": 8.501271243141978e-06,
400
+ "loss": 0.8385,
401
+ "step": 1120
402
+ },
403
+ {
404
+ "epoch": 0.1525491770373344,
405
+ "grad_norm": 12.5625,
406
+ "learning_rate": 8.474508229626656e-06,
407
+ "loss": 0.8014,
408
+ "step": 1140
409
+ },
410
+ {
411
+ "epoch": 0.15522547838886658,
412
+ "grad_norm": 12.625,
413
+ "learning_rate": 8.447745216111334e-06,
414
+ "loss": 0.8474,
415
+ "step": 1160
416
+ },
417
+ {
418
+ "epoch": 0.15790177974039876,
419
+ "grad_norm": 11.875,
420
+ "learning_rate": 8.420982202596014e-06,
421
+ "loss": 0.8009,
422
+ "step": 1180
423
+ },
424
+ {
425
+ "epoch": 0.16057808109193095,
426
+ "grad_norm": 20.625,
427
+ "learning_rate": 8.394219189080692e-06,
428
+ "loss": 0.8726,
429
+ "step": 1200
430
+ },
431
+ {
432
+ "epoch": 0.16325438244346313,
433
+ "grad_norm": 11.9375,
434
+ "learning_rate": 8.36745617556537e-06,
435
+ "loss": 0.751,
436
+ "step": 1220
437
+ },
438
+ {
439
+ "epoch": 0.16593068379499532,
440
+ "grad_norm": 8.4375,
441
+ "learning_rate": 8.340693162050048e-06,
442
+ "loss": 0.729,
443
+ "step": 1240
444
+ },
445
+ {
446
+ "epoch": 0.1686069851465275,
447
+ "grad_norm": 14.375,
448
+ "learning_rate": 8.313930148534726e-06,
449
+ "loss": 0.7642,
450
+ "step": 1260
451
+ },
452
+ {
453
+ "epoch": 0.17128328649805968,
454
+ "grad_norm": 9.4375,
455
+ "learning_rate": 8.287167135019404e-06,
456
+ "loss": 0.799,
457
+ "step": 1280
458
+ },
459
+ {
460
+ "epoch": 0.17395958784959187,
461
+ "grad_norm": 17.375,
462
+ "learning_rate": 8.260404121504082e-06,
463
+ "loss": 0.7899,
464
+ "step": 1300
465
+ },
466
+ {
467
+ "epoch": 0.17663588920112405,
468
+ "grad_norm": 8.25,
469
+ "learning_rate": 8.23364110798876e-06,
470
+ "loss": 0.8224,
471
+ "step": 1320
472
+ },
473
+ {
474
+ "epoch": 0.17931219055265624,
475
+ "grad_norm": 17.25,
476
+ "learning_rate": 8.206878094473438e-06,
477
+ "loss": 0.7836,
478
+ "step": 1340
479
+ },
480
+ {
481
+ "epoch": 0.18198849190418842,
482
+ "grad_norm": 11.9375,
483
+ "learning_rate": 8.180115080958116e-06,
484
+ "loss": 0.8547,
485
+ "step": 1360
486
+ },
487
+ {
488
+ "epoch": 0.1846647932557206,
489
+ "grad_norm": 11.8125,
490
+ "learning_rate": 8.153352067442795e-06,
491
+ "loss": 0.8314,
492
+ "step": 1380
493
+ },
494
+ {
495
+ "epoch": 0.1873410946072528,
496
+ "grad_norm": 12.25,
497
+ "learning_rate": 8.126589053927473e-06,
498
+ "loss": 0.7372,
499
+ "step": 1400
500
+ },
501
+ {
502
+ "epoch": 0.19001739595878495,
503
+ "grad_norm": 17.625,
504
+ "learning_rate": 8.099826040412151e-06,
505
+ "loss": 0.7241,
506
+ "step": 1420
507
+ },
508
+ {
509
+ "epoch": 0.19269369731031713,
510
+ "grad_norm": 13.25,
511
+ "learning_rate": 8.07306302689683e-06,
512
+ "loss": 0.75,
513
+ "step": 1440
514
+ },
515
+ {
516
+ "epoch": 0.19536999866184931,
517
+ "grad_norm": 9.3125,
518
+ "learning_rate": 8.046300013381507e-06,
519
+ "loss": 0.7802,
520
+ "step": 1460
521
+ },
522
+ {
523
+ "epoch": 0.1980463000133815,
524
+ "grad_norm": 9.1875,
525
+ "learning_rate": 8.019536999866185e-06,
526
+ "loss": 0.8704,
527
+ "step": 1480
528
+ },
529
+ {
530
+ "epoch": 0.20072260136491368,
531
+ "grad_norm": 6.15625,
532
+ "learning_rate": 7.992773986350863e-06,
533
+ "loss": 0.7438,
534
+ "step": 1500
535
+ },
536
+ {
537
+ "epoch": 0.20339890271644587,
538
+ "grad_norm": 9.125,
539
+ "learning_rate": 7.966010972835541e-06,
540
+ "loss": 0.7446,
541
+ "step": 1520
542
+ },
543
+ {
544
+ "epoch": 0.20607520406797805,
545
+ "grad_norm": 21.25,
546
+ "learning_rate": 7.93924795932022e-06,
547
+ "loss": 0.6814,
548
+ "step": 1540
549
+ },
550
+ {
551
+ "epoch": 0.20875150541951024,
552
+ "grad_norm": 6.65625,
553
+ "learning_rate": 7.912484945804897e-06,
554
+ "loss": 0.7361,
555
+ "step": 1560
556
+ },
557
+ {
558
+ "epoch": 0.21142780677104242,
559
+ "grad_norm": 13.125,
560
+ "learning_rate": 7.885721932289577e-06,
561
+ "loss": 0.67,
562
+ "step": 1580
563
+ },
564
+ {
565
+ "epoch": 0.2141041081225746,
566
+ "grad_norm": 15.6875,
567
+ "learning_rate": 7.858958918774255e-06,
568
+ "loss": 0.7145,
569
+ "step": 1600
570
+ },
571
+ {
572
+ "epoch": 0.2167804094741068,
573
+ "grad_norm": 14.1875,
574
+ "learning_rate": 7.832195905258933e-06,
575
+ "loss": 0.818,
576
+ "step": 1620
577
+ },
578
+ {
579
+ "epoch": 0.21945671082563897,
580
+ "grad_norm": 6.53125,
581
+ "learning_rate": 7.805432891743611e-06,
582
+ "loss": 0.7837,
583
+ "step": 1640
584
+ },
585
+ {
586
+ "epoch": 0.22213301217717116,
587
+ "grad_norm": 13.5625,
588
+ "learning_rate": 7.778669878228289e-06,
589
+ "loss": 0.7751,
590
+ "step": 1660
591
+ },
592
+ {
593
+ "epoch": 0.22480931352870334,
594
+ "grad_norm": 15.375,
595
+ "learning_rate": 7.751906864712967e-06,
596
+ "loss": 0.8476,
597
+ "step": 1680
598
+ },
599
+ {
600
+ "epoch": 0.22748561488023553,
601
+ "grad_norm": 7.625,
602
+ "learning_rate": 7.725143851197645e-06,
603
+ "loss": 0.7734,
604
+ "step": 1700
605
+ },
606
+ {
607
+ "epoch": 0.2301619162317677,
608
+ "grad_norm": 14.25,
609
+ "learning_rate": 7.698380837682323e-06,
610
+ "loss": 0.7714,
611
+ "step": 1720
612
+ },
613
+ {
614
+ "epoch": 0.23283821758329987,
615
+ "grad_norm": 18.5,
616
+ "learning_rate": 7.671617824167e-06,
617
+ "loss": 0.7447,
618
+ "step": 1740
619
+ },
620
+ {
621
+ "epoch": 0.23551451893483205,
622
+ "grad_norm": 15.75,
623
+ "learning_rate": 7.644854810651679e-06,
624
+ "loss": 0.7385,
625
+ "step": 1760
626
+ },
627
+ {
628
+ "epoch": 0.23819082028636424,
629
+ "grad_norm": 10.5,
630
+ "learning_rate": 7.618091797136358e-06,
631
+ "loss": 0.7058,
632
+ "step": 1780
633
+ },
634
+ {
635
+ "epoch": 0.24086712163789642,
636
+ "grad_norm": 38.75,
637
+ "learning_rate": 7.591328783621036e-06,
638
+ "loss": 0.737,
639
+ "step": 1800
640
+ },
641
+ {
642
+ "epoch": 0.2435434229894286,
643
+ "grad_norm": 10.5,
644
+ "learning_rate": 7.564565770105714e-06,
645
+ "loss": 0.7831,
646
+ "step": 1820
647
+ },
648
+ {
649
+ "epoch": 0.2462197243409608,
650
+ "grad_norm": 21.0,
651
+ "learning_rate": 7.5378027565903925e-06,
652
+ "loss": 0.8369,
653
+ "step": 1840
654
+ },
655
+ {
656
+ "epoch": 0.24889602569249297,
657
+ "grad_norm": 20.5,
658
+ "learning_rate": 7.5110397430750704e-06,
659
+ "loss": 0.7846,
660
+ "step": 1860
661
+ },
662
+ {
663
+ "epoch": 0.25157232704402516,
664
+ "grad_norm": 6.375,
665
+ "learning_rate": 7.484276729559748e-06,
666
+ "loss": 0.8011,
667
+ "step": 1880
668
+ },
669
+ {
670
+ "epoch": 0.25424862839555734,
671
+ "grad_norm": 9.1875,
672
+ "learning_rate": 7.457513716044428e-06,
673
+ "loss": 0.7536,
674
+ "step": 1900
675
+ },
676
+ {
677
+ "epoch": 0.2569249297470895,
678
+ "grad_norm": 9.0,
679
+ "learning_rate": 7.430750702529106e-06,
680
+ "loss": 0.7622,
681
+ "step": 1920
682
+ },
683
+ {
684
+ "epoch": 0.2596012310986217,
685
+ "grad_norm": 7.875,
686
+ "learning_rate": 7.403987689013784e-06,
687
+ "loss": 0.7059,
688
+ "step": 1940
689
+ },
690
+ {
691
+ "epoch": 0.2622775324501539,
692
+ "grad_norm": 7.46875,
693
+ "learning_rate": 7.377224675498462e-06,
694
+ "loss": 0.7635,
695
+ "step": 1960
696
+ },
697
+ {
698
+ "epoch": 0.2649538338016861,
699
+ "grad_norm": 6.21875,
700
+ "learning_rate": 7.35046166198314e-06,
701
+ "loss": 0.7693,
702
+ "step": 1980
703
+ },
704
+ {
705
+ "epoch": 0.26763013515321826,
706
+ "grad_norm": 9.375,
707
+ "learning_rate": 7.323698648467819e-06,
708
+ "loss": 0.7812,
709
+ "step": 2000
710
+ },
711
+ {
712
+ "epoch": 0.27030643650475045,
713
+ "grad_norm": 13.1875,
714
+ "learning_rate": 7.296935634952497e-06,
715
+ "loss": 0.7372,
716
+ "step": 2020
717
+ },
718
+ {
719
+ "epoch": 0.27298273785628263,
720
+ "grad_norm": 16.75,
721
+ "learning_rate": 7.270172621437175e-06,
722
+ "loss": 0.8489,
723
+ "step": 2040
724
+ },
725
+ {
726
+ "epoch": 0.2756590392078148,
727
+ "grad_norm": 5.40625,
728
+ "learning_rate": 7.243409607921853e-06,
729
+ "loss": 0.6996,
730
+ "step": 2060
731
+ },
732
+ {
733
+ "epoch": 0.278335340559347,
734
+ "grad_norm": 10.875,
735
+ "learning_rate": 7.216646594406531e-06,
736
+ "loss": 0.7596,
737
+ "step": 2080
738
+ },
739
+ {
740
+ "epoch": 0.2810116419108792,
741
+ "grad_norm": 33.5,
742
+ "learning_rate": 7.18988358089121e-06,
743
+ "loss": 0.7819,
744
+ "step": 2100
745
+ },
746
+ {
747
+ "epoch": 0.28368794326241137,
748
+ "grad_norm": 11.4375,
749
+ "learning_rate": 7.163120567375888e-06,
750
+ "loss": 0.8196,
751
+ "step": 2120
752
+ },
753
+ {
754
+ "epoch": 0.28636424461394355,
755
+ "grad_norm": 7.78125,
756
+ "learning_rate": 7.136357553860566e-06,
757
+ "loss": 0.7454,
758
+ "step": 2140
759
+ },
760
+ {
761
+ "epoch": 0.28904054596547574,
762
+ "grad_norm": 14.5625,
763
+ "learning_rate": 7.109594540345244e-06,
764
+ "loss": 0.7306,
765
+ "step": 2160
766
+ },
767
+ {
768
+ "epoch": 0.2917168473170079,
769
+ "grad_norm": 9.5,
770
+ "learning_rate": 7.082831526829922e-06,
771
+ "loss": 0.7076,
772
+ "step": 2180
773
+ },
774
+ {
775
+ "epoch": 0.29439314866854005,
776
+ "grad_norm": 12.875,
777
+ "learning_rate": 7.0560685133146004e-06,
778
+ "loss": 0.7679,
779
+ "step": 2200
780
+ },
781
+ {
782
+ "epoch": 0.29706945002007223,
783
+ "grad_norm": 11.0,
784
+ "learning_rate": 7.029305499799278e-06,
785
+ "loss": 0.6691,
786
+ "step": 2220
787
+ },
788
+ {
789
+ "epoch": 0.2997457513716044,
790
+ "grad_norm": 13.4375,
791
+ "learning_rate": 7.002542486283956e-06,
792
+ "loss": 0.7002,
793
+ "step": 2240
794
+ },
795
+ {
796
+ "epoch": 0.3024220527231366,
797
+ "grad_norm": 13.25,
798
+ "learning_rate": 6.975779472768634e-06,
799
+ "loss": 0.8657,
800
+ "step": 2260
801
+ },
802
+ {
803
+ "epoch": 0.3050983540746688,
804
+ "grad_norm": 16.25,
805
+ "learning_rate": 6.949016459253312e-06,
806
+ "loss": 0.6808,
807
+ "step": 2280
808
+ },
809
+ {
810
+ "epoch": 0.30777465542620097,
811
+ "grad_norm": 11.75,
812
+ "learning_rate": 6.922253445737991e-06,
813
+ "loss": 0.7294,
814
+ "step": 2300
815
+ },
816
+ {
817
+ "epoch": 0.31045095677773316,
818
+ "grad_norm": 12.5,
819
+ "learning_rate": 6.895490432222669e-06,
820
+ "loss": 0.7018,
821
+ "step": 2320
822
+ },
823
+ {
824
+ "epoch": 0.31312725812926534,
825
+ "grad_norm": 11.6875,
826
+ "learning_rate": 6.868727418707347e-06,
827
+ "loss": 0.6812,
828
+ "step": 2340
829
+ },
830
+ {
831
+ "epoch": 0.3158035594807975,
832
+ "grad_norm": 7.625,
833
+ "learning_rate": 6.841964405192025e-06,
834
+ "loss": 0.7062,
835
+ "step": 2360
836
+ },
837
+ {
838
+ "epoch": 0.3184798608323297,
839
+ "grad_norm": 18.125,
840
+ "learning_rate": 6.815201391676703e-06,
841
+ "loss": 0.7192,
842
+ "step": 2380
843
+ },
844
+ {
845
+ "epoch": 0.3211561621838619,
846
+ "grad_norm": 12.75,
847
+ "learning_rate": 6.788438378161382e-06,
848
+ "loss": 0.6406,
849
+ "step": 2400
850
+ },
851
+ {
852
+ "epoch": 0.3238324635353941,
853
+ "grad_norm": 6.75,
854
+ "learning_rate": 6.76167536464606e-06,
855
+ "loss": 0.7128,
856
+ "step": 2420
857
+ },
858
+ {
859
+ "epoch": 0.32650876488692626,
860
+ "grad_norm": 15.6875,
861
+ "learning_rate": 6.734912351130738e-06,
862
+ "loss": 0.6342,
863
+ "step": 2440
864
+ },
865
+ {
866
+ "epoch": 0.32918506623845845,
867
+ "grad_norm": 14.0,
868
+ "learning_rate": 6.708149337615416e-06,
869
+ "loss": 0.7335,
870
+ "step": 2460
871
+ },
872
+ {
873
+ "epoch": 0.33186136758999063,
874
+ "grad_norm": 13.0,
875
+ "learning_rate": 6.681386324100094e-06,
876
+ "loss": 0.629,
877
+ "step": 2480
878
+ },
879
+ {
880
+ "epoch": 0.3345376689415228,
881
+ "grad_norm": 10.3125,
882
+ "learning_rate": 6.654623310584773e-06,
883
+ "loss": 0.7736,
884
+ "step": 2500
885
+ },
886
+ {
887
+ "epoch": 0.337213970293055,
888
+ "grad_norm": 7.84375,
889
+ "learning_rate": 6.627860297069451e-06,
890
+ "loss": 0.826,
891
+ "step": 2520
892
+ },
893
+ {
894
+ "epoch": 0.3398902716445872,
895
+ "grad_norm": 7.09375,
896
+ "learning_rate": 6.601097283554129e-06,
897
+ "loss": 0.6452,
898
+ "step": 2540
899
+ },
900
+ {
901
+ "epoch": 0.34256657299611937,
902
+ "grad_norm": 6.125,
903
+ "learning_rate": 6.574334270038807e-06,
904
+ "loss": 0.705,
905
+ "step": 2560
906
+ },
907
+ {
908
+ "epoch": 0.34524287434765155,
909
+ "grad_norm": 65.0,
910
+ "learning_rate": 6.547571256523485e-06,
911
+ "loss": 0.6926,
912
+ "step": 2580
913
+ },
914
+ {
915
+ "epoch": 0.34791917569918374,
916
+ "grad_norm": 7.125,
917
+ "learning_rate": 6.5208082430081635e-06,
918
+ "loss": 0.6877,
919
+ "step": 2600
920
+ },
921
+ {
922
+ "epoch": 0.3505954770507159,
923
+ "grad_norm": 12.4375,
924
+ "learning_rate": 6.4940452294928415e-06,
925
+ "loss": 0.8122,
926
+ "step": 2620
927
+ },
928
+ {
929
+ "epoch": 0.3532717784022481,
930
+ "grad_norm": 5.75,
931
+ "learning_rate": 6.4672822159775195e-06,
932
+ "loss": 0.7015,
933
+ "step": 2640
934
+ },
935
+ {
936
+ "epoch": 0.3559480797537803,
937
+ "grad_norm": 9.1875,
938
+ "learning_rate": 6.4405192024621975e-06,
939
+ "loss": 0.7502,
940
+ "step": 2660
941
+ },
942
+ {
943
+ "epoch": 0.3586243811053125,
944
+ "grad_norm": 4.6875,
945
+ "learning_rate": 6.4137561889468755e-06,
946
+ "loss": 0.6114,
947
+ "step": 2680
948
+ },
949
+ {
950
+ "epoch": 0.36130068245684466,
951
+ "grad_norm": 12.0,
952
+ "learning_rate": 6.386993175431554e-06,
953
+ "loss": 0.6149,
954
+ "step": 2700
955
+ },
956
+ {
957
+ "epoch": 0.36397698380837684,
958
+ "grad_norm": 7.78125,
959
+ "learning_rate": 6.360230161916232e-06,
960
+ "loss": 0.6908,
961
+ "step": 2720
962
+ },
963
+ {
964
+ "epoch": 0.366653285159909,
965
+ "grad_norm": 7.65625,
966
+ "learning_rate": 6.33346714840091e-06,
967
+ "loss": 0.7734,
968
+ "step": 2740
969
+ },
970
+ {
971
+ "epoch": 0.3693295865114412,
972
+ "grad_norm": 12.0,
973
+ "learning_rate": 6.306704134885588e-06,
974
+ "loss": 0.7201,
975
+ "step": 2760
976
+ },
977
+ {
978
+ "epoch": 0.3720058878629734,
979
+ "grad_norm": 17.875,
980
+ "learning_rate": 6.279941121370266e-06,
981
+ "loss": 0.7441,
982
+ "step": 2780
983
+ },
984
+ {
985
+ "epoch": 0.3746821892145056,
986
+ "grad_norm": 18.375,
987
+ "learning_rate": 6.253178107854945e-06,
988
+ "loss": 0.6822,
989
+ "step": 2800
990
+ },
991
+ {
992
+ "epoch": 0.37735849056603776,
993
+ "grad_norm": 10.125,
994
+ "learning_rate": 6.226415094339623e-06,
995
+ "loss": 0.758,
996
+ "step": 2820
997
+ },
998
+ {
999
+ "epoch": 0.3800347919175699,
1000
+ "grad_norm": 15.125,
1001
+ "learning_rate": 6.199652080824301e-06,
1002
+ "loss": 0.6623,
1003
+ "step": 2840
1004
+ },
1005
+ {
1006
+ "epoch": 0.3827110932691021,
1007
+ "grad_norm": 8.5,
1008
+ "learning_rate": 6.172889067308979e-06,
1009
+ "loss": 0.6744,
1010
+ "step": 2860
1011
+ },
1012
+ {
1013
+ "epoch": 0.38538739462063426,
1014
+ "grad_norm": 10.8125,
1015
+ "learning_rate": 6.146126053793657e-06,
1016
+ "loss": 0.6643,
1017
+ "step": 2880
1018
+ },
1019
+ {
1020
+ "epoch": 0.38806369597216644,
1021
+ "grad_norm": 11.5625,
1022
+ "learning_rate": 6.119363040278336e-06,
1023
+ "loss": 0.7278,
1024
+ "step": 2900
1025
+ },
1026
+ {
1027
+ "epoch": 0.39073999732369863,
1028
+ "grad_norm": 6.65625,
1029
+ "learning_rate": 6.092600026763014e-06,
1030
+ "loss": 0.6364,
1031
+ "step": 2920
1032
+ },
1033
+ {
1034
+ "epoch": 0.3934162986752308,
1035
+ "grad_norm": 8.75,
1036
+ "learning_rate": 6.065837013247692e-06,
1037
+ "loss": 0.7175,
1038
+ "step": 2940
1039
+ },
1040
+ {
1041
+ "epoch": 0.396092600026763,
1042
+ "grad_norm": 10.25,
1043
+ "learning_rate": 6.03907399973237e-06,
1044
+ "loss": 0.6905,
1045
+ "step": 2960
1046
+ },
1047
+ {
1048
+ "epoch": 0.3987689013782952,
1049
+ "grad_norm": 14.0625,
1050
+ "learning_rate": 6.012310986217048e-06,
1051
+ "loss": 0.599,
1052
+ "step": 2980
1053
+ },
1054
+ {
1055
+ "epoch": 0.40144520272982737,
1056
+ "grad_norm": 9.6875,
1057
+ "learning_rate": 5.985547972701727e-06,
1058
+ "loss": 0.7629,
1059
+ "step": 3000
1060
+ },
1061
+ {
1062
+ "epoch": 0.40412150408135955,
1063
+ "grad_norm": 19.125,
1064
+ "learning_rate": 5.958784959186405e-06,
1065
+ "loss": 0.7624,
1066
+ "step": 3020
1067
+ },
1068
+ {
1069
+ "epoch": 0.40679780543289173,
1070
+ "grad_norm": 9.0625,
1071
+ "learning_rate": 5.932021945671083e-06,
1072
+ "loss": 0.7122,
1073
+ "step": 3040
1074
+ },
1075
+ {
1076
+ "epoch": 0.4094741067844239,
1077
+ "grad_norm": 12.0625,
1078
+ "learning_rate": 5.905258932155761e-06,
1079
+ "loss": 0.711,
1080
+ "step": 3060
1081
+ },
1082
+ {
1083
+ "epoch": 0.4121504081359561,
1084
+ "grad_norm": 8.4375,
1085
+ "learning_rate": 5.878495918640439e-06,
1086
+ "loss": 0.685,
1087
+ "step": 3080
1088
+ },
1089
+ {
1090
+ "epoch": 0.4148267094874883,
1091
+ "grad_norm": 23.5,
1092
+ "learning_rate": 5.851732905125117e-06,
1093
+ "loss": 0.7422,
1094
+ "step": 3100
1095
+ },
1096
+ {
1097
+ "epoch": 0.41750301083902047,
1098
+ "grad_norm": 8.9375,
1099
+ "learning_rate": 5.824969891609795e-06,
1100
+ "loss": 0.7546,
1101
+ "step": 3120
1102
+ },
1103
+ {
1104
+ "epoch": 0.42017931219055266,
1105
+ "grad_norm": 10.375,
1106
+ "learning_rate": 5.798206878094474e-06,
1107
+ "loss": 0.7204,
1108
+ "step": 3140
1109
+ },
1110
+ {
1111
+ "epoch": 0.42285561354208484,
1112
+ "grad_norm": 7.3125,
1113
+ "learning_rate": 5.771443864579152e-06,
1114
+ "loss": 0.7457,
1115
+ "step": 3160
1116
+ },
1117
+ {
1118
+ "epoch": 0.425531914893617,
1119
+ "grad_norm": 10.9375,
1120
+ "learning_rate": 5.744680851063831e-06,
1121
+ "loss": 0.7411,
1122
+ "step": 3180
1123
+ },
1124
+ {
1125
+ "epoch": 0.4282082162451492,
1126
+ "grad_norm": 12.3125,
1127
+ "learning_rate": 5.717917837548509e-06,
1128
+ "loss": 0.7036,
1129
+ "step": 3200
1130
+ },
1131
+ {
1132
+ "epoch": 0.4308845175966814,
1133
+ "grad_norm": 10.0625,
1134
+ "learning_rate": 5.691154824033187e-06,
1135
+ "loss": 0.7014,
1136
+ "step": 3220
1137
+ },
1138
+ {
1139
+ "epoch": 0.4335608189482136,
1140
+ "grad_norm": 6.875,
1141
+ "learning_rate": 5.664391810517865e-06,
1142
+ "loss": 0.73,
1143
+ "step": 3240
1144
+ },
1145
+ {
1146
+ "epoch": 0.43623712029974576,
1147
+ "grad_norm": 8.375,
1148
+ "learning_rate": 5.637628797002543e-06,
1149
+ "loss": 0.6942,
1150
+ "step": 3260
1151
+ },
1152
+ {
1153
+ "epoch": 0.43891342165127795,
1154
+ "grad_norm": 13.125,
1155
+ "learning_rate": 5.610865783487222e-06,
1156
+ "loss": 0.6773,
1157
+ "step": 3280
1158
+ },
1159
+ {
1160
+ "epoch": 0.44158972300281013,
1161
+ "grad_norm": 10.5,
1162
+ "learning_rate": 5.5841027699719e-06,
1163
+ "loss": 0.6452,
1164
+ "step": 3300
1165
+ },
1166
+ {
1167
+ "epoch": 0.4442660243543423,
1168
+ "grad_norm": 7.59375,
1169
+ "learning_rate": 5.557339756456578e-06,
1170
+ "loss": 0.7561,
1171
+ "step": 3320
1172
+ },
1173
+ {
1174
+ "epoch": 0.4469423257058745,
1175
+ "grad_norm": 10.4375,
1176
+ "learning_rate": 5.530576742941256e-06,
1177
+ "loss": 0.7064,
1178
+ "step": 3340
1179
+ },
1180
+ {
1181
+ "epoch": 0.4496186270574067,
1182
+ "grad_norm": 6.90625,
1183
+ "learning_rate": 5.503813729425934e-06,
1184
+ "loss": 0.6614,
1185
+ "step": 3360
1186
+ },
1187
+ {
1188
+ "epoch": 0.45229492840893887,
1189
+ "grad_norm": 11.125,
1190
+ "learning_rate": 5.477050715910613e-06,
1191
+ "loss": 0.7513,
1192
+ "step": 3380
1193
+ },
1194
+ {
1195
+ "epoch": 0.45497122976047105,
1196
+ "grad_norm": 16.875,
1197
+ "learning_rate": 5.450287702395291e-06,
1198
+ "loss": 0.6785,
1199
+ "step": 3400
1200
+ },
1201
+ {
1202
+ "epoch": 0.45764753111200324,
1203
+ "grad_norm": 12.1875,
1204
+ "learning_rate": 5.4235246888799686e-06,
1205
+ "loss": 0.8056,
1206
+ "step": 3420
1207
+ },
1208
+ {
1209
+ "epoch": 0.4603238324635354,
1210
+ "grad_norm": 19.125,
1211
+ "learning_rate": 5.3967616753646466e-06,
1212
+ "loss": 0.7518,
1213
+ "step": 3440
1214
+ },
1215
+ {
1216
+ "epoch": 0.46300013381506755,
1217
+ "grad_norm": 9.8125,
1218
+ "learning_rate": 5.3699986618493245e-06,
1219
+ "loss": 0.6852,
1220
+ "step": 3460
1221
+ },
1222
+ {
1223
+ "epoch": 0.46567643516659973,
1224
+ "grad_norm": 7.59375,
1225
+ "learning_rate": 5.343235648334003e-06,
1226
+ "loss": 0.7327,
1227
+ "step": 3480
1228
+ },
1229
+ {
1230
+ "epoch": 0.4683527365181319,
1231
+ "grad_norm": 19.0,
1232
+ "learning_rate": 5.316472634818681e-06,
1233
+ "loss": 0.7463,
1234
+ "step": 3500
1235
+ },
1236
+ {
1237
+ "epoch": 0.4710290378696641,
1238
+ "grad_norm": 8.6875,
1239
+ "learning_rate": 5.289709621303359e-06,
1240
+ "loss": 0.6091,
1241
+ "step": 3520
1242
+ },
1243
+ {
1244
+ "epoch": 0.4737053392211963,
1245
+ "grad_norm": 14.0,
1246
+ "learning_rate": 5.262946607788037e-06,
1247
+ "loss": 0.6896,
1248
+ "step": 3540
1249
+ },
1250
+ {
1251
+ "epoch": 0.47638164057272847,
1252
+ "grad_norm": 8.5,
1253
+ "learning_rate": 5.236183594272715e-06,
1254
+ "loss": 0.7641,
1255
+ "step": 3560
1256
+ },
1257
+ {
1258
+ "epoch": 0.47905794192426066,
1259
+ "grad_norm": 12.3125,
1260
+ "learning_rate": 5.209420580757394e-06,
1261
+ "loss": 0.6582,
1262
+ "step": 3580
1263
+ },
1264
+ {
1265
+ "epoch": 0.48173424327579284,
1266
+ "grad_norm": 11.0625,
1267
+ "learning_rate": 5.182657567242072e-06,
1268
+ "loss": 0.7291,
1269
+ "step": 3600
1270
+ },
1271
+ {
1272
+ "epoch": 0.484410544627325,
1273
+ "grad_norm": 12.9375,
1274
+ "learning_rate": 5.15589455372675e-06,
1275
+ "loss": 0.7209,
1276
+ "step": 3620
1277
+ },
1278
+ {
1279
+ "epoch": 0.4870868459788572,
1280
+ "grad_norm": 14.625,
1281
+ "learning_rate": 5.129131540211428e-06,
1282
+ "loss": 0.7259,
1283
+ "step": 3640
1284
+ },
1285
+ {
1286
+ "epoch": 0.4897631473303894,
1287
+ "grad_norm": 9.4375,
1288
+ "learning_rate": 5.102368526696106e-06,
1289
+ "loss": 0.7259,
1290
+ "step": 3660
1291
+ },
1292
+ {
1293
+ "epoch": 0.4924394486819216,
1294
+ "grad_norm": 7.53125,
1295
+ "learning_rate": 5.075605513180785e-06,
1296
+ "loss": 0.6947,
1297
+ "step": 3680
1298
+ },
1299
+ {
1300
+ "epoch": 0.49511575003345376,
1301
+ "grad_norm": 6.59375,
1302
+ "learning_rate": 5.048842499665463e-06,
1303
+ "loss": 0.7026,
1304
+ "step": 3700
1305
+ },
1306
+ {
1307
+ "epoch": 0.49779205138498595,
1308
+ "grad_norm": 22.125,
1309
+ "learning_rate": 5.022079486150141e-06,
1310
+ "loss": 0.7332,
1311
+ "step": 3720
1312
+ },
1313
+ {
1314
+ "epoch": 0.5004683527365181,
1315
+ "grad_norm": 9.625,
1316
+ "learning_rate": 4.995316472634819e-06,
1317
+ "loss": 0.7487,
1318
+ "step": 3740
1319
+ },
1320
+ {
1321
+ "epoch": 0.5031446540880503,
1322
+ "grad_norm": 8.9375,
1323
+ "learning_rate": 4.968553459119497e-06,
1324
+ "loss": 0.6364,
1325
+ "step": 3760
1326
+ },
1327
+ {
1328
+ "epoch": 0.5058209554395825,
1329
+ "grad_norm": 10.125,
1330
+ "learning_rate": 4.941790445604176e-06,
1331
+ "loss": 0.7261,
1332
+ "step": 3780
1333
+ },
1334
+ {
1335
+ "epoch": 0.5084972567911147,
1336
+ "grad_norm": 19.0,
1337
+ "learning_rate": 4.915027432088854e-06,
1338
+ "loss": 0.725,
1339
+ "step": 3800
1340
+ },
1341
+ {
1342
+ "epoch": 0.5111735581426469,
1343
+ "grad_norm": 11.6875,
1344
+ "learning_rate": 4.888264418573532e-06,
1345
+ "loss": 0.6957,
1346
+ "step": 3820
1347
+ },
1348
+ {
1349
+ "epoch": 0.513849859494179,
1350
+ "grad_norm": 9.75,
1351
+ "learning_rate": 4.86150140505821e-06,
1352
+ "loss": 0.6555,
1353
+ "step": 3840
1354
+ },
1355
+ {
1356
+ "epoch": 0.5165261608457112,
1357
+ "grad_norm": 8.875,
1358
+ "learning_rate": 4.834738391542888e-06,
1359
+ "loss": 0.7902,
1360
+ "step": 3860
1361
+ },
1362
+ {
1363
+ "epoch": 0.5192024621972434,
1364
+ "grad_norm": 10.5625,
1365
+ "learning_rate": 4.8079753780275665e-06,
1366
+ "loss": 0.7535,
1367
+ "step": 3880
1368
+ },
1369
+ {
1370
+ "epoch": 0.5218787635487756,
1371
+ "grad_norm": 6.71875,
1372
+ "learning_rate": 4.7812123645122445e-06,
1373
+ "loss": 0.84,
1374
+ "step": 3900
1375
+ },
1376
+ {
1377
+ "epoch": 0.5245550649003078,
1378
+ "grad_norm": 8.3125,
1379
+ "learning_rate": 4.7544493509969225e-06,
1380
+ "loss": 0.6911,
1381
+ "step": 3920
1382
+ },
1383
+ {
1384
+ "epoch": 0.52723136625184,
1385
+ "grad_norm": 9.4375,
1386
+ "learning_rate": 4.7276863374816004e-06,
1387
+ "loss": 0.7435,
1388
+ "step": 3940
1389
+ },
1390
+ {
1391
+ "epoch": 0.5299076676033722,
1392
+ "grad_norm": 12.875,
1393
+ "learning_rate": 4.7009233239662784e-06,
1394
+ "loss": 0.7176,
1395
+ "step": 3960
1396
+ },
1397
+ {
1398
+ "epoch": 0.5325839689549043,
1399
+ "grad_norm": 6.6875,
1400
+ "learning_rate": 4.674160310450957e-06,
1401
+ "loss": 0.6389,
1402
+ "step": 3980
1403
+ },
1404
+ {
1405
+ "epoch": 0.5352602703064365,
1406
+ "grad_norm": 17.0,
1407
+ "learning_rate": 4.647397296935635e-06,
1408
+ "loss": 0.6902,
1409
+ "step": 4000
1410
+ },
1411
+ {
1412
+ "epoch": 0.5379365716579687,
1413
+ "grad_norm": 15.5,
1414
+ "learning_rate": 4.620634283420313e-06,
1415
+ "loss": 0.7835,
1416
+ "step": 4020
1417
+ },
1418
+ {
1419
+ "epoch": 0.5406128730095009,
1420
+ "grad_norm": 14.0625,
1421
+ "learning_rate": 4.593871269904991e-06,
1422
+ "loss": 0.7667,
1423
+ "step": 4040
1424
+ },
1425
+ {
1426
+ "epoch": 0.5432891743610331,
1427
+ "grad_norm": 15.5625,
1428
+ "learning_rate": 4.567108256389669e-06,
1429
+ "loss": 0.7173,
1430
+ "step": 4060
1431
+ },
1432
+ {
1433
+ "epoch": 0.5459654757125653,
1434
+ "grad_norm": 7.6875,
1435
+ "learning_rate": 4.540345242874348e-06,
1436
+ "loss": 0.6364,
1437
+ "step": 4080
1438
+ },
1439
+ {
1440
+ "epoch": 0.5486417770640974,
1441
+ "grad_norm": 8.0625,
1442
+ "learning_rate": 4.513582229359027e-06,
1443
+ "loss": 0.6644,
1444
+ "step": 4100
1445
+ },
1446
+ {
1447
+ "epoch": 0.5513180784156296,
1448
+ "grad_norm": 8.6875,
1449
+ "learning_rate": 4.486819215843705e-06,
1450
+ "loss": 0.6862,
1451
+ "step": 4120
1452
+ },
1453
+ {
1454
+ "epoch": 0.5539943797671618,
1455
+ "grad_norm": 16.875,
1456
+ "learning_rate": 4.460056202328383e-06,
1457
+ "loss": 0.6885,
1458
+ "step": 4140
1459
+ },
1460
+ {
1461
+ "epoch": 0.556670681118694,
1462
+ "grad_norm": 8.125,
1463
+ "learning_rate": 4.433293188813061e-06,
1464
+ "loss": 0.7585,
1465
+ "step": 4160
1466
+ },
1467
+ {
1468
+ "epoch": 0.5593469824702262,
1469
+ "grad_norm": 13.375,
1470
+ "learning_rate": 4.406530175297739e-06,
1471
+ "loss": 0.7361,
1472
+ "step": 4180
1473
+ },
1474
+ {
1475
+ "epoch": 0.5620232838217584,
1476
+ "grad_norm": 9.875,
1477
+ "learning_rate": 4.379767161782418e-06,
1478
+ "loss": 0.6836,
1479
+ "step": 4200
1480
+ },
1481
+ {
1482
+ "epoch": 0.5646995851732906,
1483
+ "grad_norm": 10.75,
1484
+ "learning_rate": 4.353004148267096e-06,
1485
+ "loss": 0.7238,
1486
+ "step": 4220
1487
+ },
1488
+ {
1489
+ "epoch": 0.5673758865248227,
1490
+ "grad_norm": 10.5625,
1491
+ "learning_rate": 4.326241134751774e-06,
1492
+ "loss": 0.7354,
1493
+ "step": 4240
1494
+ },
1495
+ {
1496
+ "epoch": 0.5700521878763549,
1497
+ "grad_norm": 8.125,
1498
+ "learning_rate": 4.299478121236452e-06,
1499
+ "loss": 0.7141,
1500
+ "step": 4260
1501
+ },
1502
+ {
1503
+ "epoch": 0.5727284892278871,
1504
+ "grad_norm": 9.9375,
1505
+ "learning_rate": 4.27271510772113e-06,
1506
+ "loss": 0.7113,
1507
+ "step": 4280
1508
+ },
1509
+ {
1510
+ "epoch": 0.5754047905794193,
1511
+ "grad_norm": 13.75,
1512
+ "learning_rate": 4.245952094205808e-06,
1513
+ "loss": 0.7338,
1514
+ "step": 4300
1515
+ },
1516
+ {
1517
+ "epoch": 0.5780810919309515,
1518
+ "grad_norm": 14.375,
1519
+ "learning_rate": 4.219189080690486e-06,
1520
+ "loss": 0.7292,
1521
+ "step": 4320
1522
+ },
1523
+ {
1524
+ "epoch": 0.5807573932824837,
1525
+ "grad_norm": 10.3125,
1526
+ "learning_rate": 4.192426067175164e-06,
1527
+ "loss": 0.6675,
1528
+ "step": 4340
1529
+ },
1530
+ {
1531
+ "epoch": 0.5834336946340158,
1532
+ "grad_norm": 27.375,
1533
+ "learning_rate": 4.165663053659842e-06,
1534
+ "loss": 0.6879,
1535
+ "step": 4360
1536
+ },
1537
+ {
1538
+ "epoch": 0.586109995985548,
1539
+ "grad_norm": 11.8125,
1540
+ "learning_rate": 4.13890004014452e-06,
1541
+ "loss": 0.5935,
1542
+ "step": 4380
1543
+ },
1544
+ {
1545
+ "epoch": 0.5887862973370801,
1546
+ "grad_norm": 7.46875,
1547
+ "learning_rate": 4.112137026629199e-06,
1548
+ "loss": 0.7692,
1549
+ "step": 4400
1550
+ },
1551
+ {
1552
+ "epoch": 0.5914625986886123,
1553
+ "grad_norm": 13.875,
1554
+ "learning_rate": 4.085374013113877e-06,
1555
+ "loss": 0.7598,
1556
+ "step": 4420
1557
+ },
1558
+ {
1559
+ "epoch": 0.5941389000401445,
1560
+ "grad_norm": 14.6875,
1561
+ "learning_rate": 4.058610999598555e-06,
1562
+ "loss": 0.63,
1563
+ "step": 4440
1564
+ },
1565
+ {
1566
+ "epoch": 0.5968152013916767,
1567
+ "grad_norm": 17.75,
1568
+ "learning_rate": 4.031847986083233e-06,
1569
+ "loss": 0.7506,
1570
+ "step": 4460
1571
+ },
1572
+ {
1573
+ "epoch": 0.5994915027432088,
1574
+ "grad_norm": 9.625,
1575
+ "learning_rate": 4.005084972567911e-06,
1576
+ "loss": 0.6189,
1577
+ "step": 4480
1578
+ },
1579
+ {
1580
+ "epoch": 0.602167804094741,
1581
+ "grad_norm": 8.875,
1582
+ "learning_rate": 3.97832195905259e-06,
1583
+ "loss": 0.7193,
1584
+ "step": 4500
1585
+ },
1586
+ {
1587
+ "epoch": 0.6048441054462732,
1588
+ "grad_norm": 12.8125,
1589
+ "learning_rate": 3.951558945537268e-06,
1590
+ "loss": 0.7936,
1591
+ "step": 4520
1592
+ },
1593
+ {
1594
+ "epoch": 0.6075204067978054,
1595
+ "grad_norm": 8.3125,
1596
+ "learning_rate": 3.924795932021946e-06,
1597
+ "loss": 0.7412,
1598
+ "step": 4540
1599
+ },
1600
+ {
1601
+ "epoch": 0.6101967081493376,
1602
+ "grad_norm": 13.75,
1603
+ "learning_rate": 3.898032918506624e-06,
1604
+ "loss": 0.6437,
1605
+ "step": 4560
1606
+ },
1607
+ {
1608
+ "epoch": 0.6128730095008698,
1609
+ "grad_norm": 12.1875,
1610
+ "learning_rate": 3.871269904991302e-06,
1611
+ "loss": 0.6643,
1612
+ "step": 4580
1613
+ },
1614
+ {
1615
+ "epoch": 0.6155493108524019,
1616
+ "grad_norm": 14.5,
1617
+ "learning_rate": 3.844506891475981e-06,
1618
+ "loss": 0.6438,
1619
+ "step": 4600
1620
+ },
1621
+ {
1622
+ "epoch": 0.6182256122039341,
1623
+ "grad_norm": 8.6875,
1624
+ "learning_rate": 3.817743877960659e-06,
1625
+ "loss": 0.6731,
1626
+ "step": 4620
1627
+ },
1628
+ {
1629
+ "epoch": 0.6209019135554663,
1630
+ "grad_norm": 23.0,
1631
+ "learning_rate": 3.7909808644453367e-06,
1632
+ "loss": 0.6498,
1633
+ "step": 4640
1634
+ },
1635
+ {
1636
+ "epoch": 0.6235782149069985,
1637
+ "grad_norm": 7.3125,
1638
+ "learning_rate": 3.7642178509300147e-06,
1639
+ "loss": 0.7402,
1640
+ "step": 4660
1641
+ },
1642
+ {
1643
+ "epoch": 0.6262545162585307,
1644
+ "grad_norm": 16.625,
1645
+ "learning_rate": 3.737454837414693e-06,
1646
+ "loss": 0.7464,
1647
+ "step": 4680
1648
+ },
1649
+ {
1650
+ "epoch": 0.6289308176100629,
1651
+ "grad_norm": 8.5625,
1652
+ "learning_rate": 3.710691823899371e-06,
1653
+ "loss": 0.7294,
1654
+ "step": 4700
1655
+ },
1656
+ {
1657
+ "epoch": 0.631607118961595,
1658
+ "grad_norm": 7.1875,
1659
+ "learning_rate": 3.68392881038405e-06,
1660
+ "loss": 0.7184,
1661
+ "step": 4720
1662
+ },
1663
+ {
1664
+ "epoch": 0.6342834203131272,
1665
+ "grad_norm": 8.0625,
1666
+ "learning_rate": 3.657165796868728e-06,
1667
+ "loss": 0.6361,
1668
+ "step": 4740
1669
+ },
1670
+ {
1671
+ "epoch": 0.6369597216646594,
1672
+ "grad_norm": 10.6875,
1673
+ "learning_rate": 3.6304027833534063e-06,
1674
+ "loss": 0.6732,
1675
+ "step": 4760
1676
+ },
1677
+ {
1678
+ "epoch": 0.6396360230161916,
1679
+ "grad_norm": 10.1875,
1680
+ "learning_rate": 3.6036397698380843e-06,
1681
+ "loss": 0.6091,
1682
+ "step": 4780
1683
+ },
1684
+ {
1685
+ "epoch": 0.6423123243677238,
1686
+ "grad_norm": 10.75,
1687
+ "learning_rate": 3.5768767563227623e-06,
1688
+ "loss": 0.6382,
1689
+ "step": 4800
1690
+ },
1691
+ {
1692
+ "epoch": 0.644988625719256,
1693
+ "grad_norm": 10.6875,
1694
+ "learning_rate": 3.5501137428074407e-06,
1695
+ "loss": 0.7222,
1696
+ "step": 4820
1697
+ },
1698
+ {
1699
+ "epoch": 0.6476649270707882,
1700
+ "grad_norm": 16.5,
1701
+ "learning_rate": 3.5233507292921187e-06,
1702
+ "loss": 0.6297,
1703
+ "step": 4840
1704
+ },
1705
+ {
1706
+ "epoch": 0.6503412284223203,
1707
+ "grad_norm": 12.375,
1708
+ "learning_rate": 3.496587715776797e-06,
1709
+ "loss": 0.709,
1710
+ "step": 4860
1711
+ },
1712
+ {
1713
+ "epoch": 0.6530175297738525,
1714
+ "grad_norm": 15.8125,
1715
+ "learning_rate": 3.469824702261475e-06,
1716
+ "loss": 0.6754,
1717
+ "step": 4880
1718
+ },
1719
+ {
1720
+ "epoch": 0.6556938311253847,
1721
+ "grad_norm": 32.5,
1722
+ "learning_rate": 3.443061688746153e-06,
1723
+ "loss": 0.9194,
1724
+ "step": 4900
1725
+ },
1726
+ {
1727
+ "epoch": 0.6583701324769169,
1728
+ "grad_norm": 7.75,
1729
+ "learning_rate": 3.4162986752308315e-06,
1730
+ "loss": 0.6851,
1731
+ "step": 4920
1732
+ },
1733
+ {
1734
+ "epoch": 0.6610464338284491,
1735
+ "grad_norm": 24.5,
1736
+ "learning_rate": 3.3895356617155095e-06,
1737
+ "loss": 0.728,
1738
+ "step": 4940
1739
+ },
1740
+ {
1741
+ "epoch": 0.6637227351799813,
1742
+ "grad_norm": 13.3125,
1743
+ "learning_rate": 3.362772648200188e-06,
1744
+ "loss": 0.6899,
1745
+ "step": 4960
1746
+ },
1747
+ {
1748
+ "epoch": 0.6663990365315134,
1749
+ "grad_norm": 12.4375,
1750
+ "learning_rate": 3.336009634684866e-06,
1751
+ "loss": 0.714,
1752
+ "step": 4980
1753
+ },
1754
+ {
1755
+ "epoch": 0.6690753378830456,
1756
+ "grad_norm": 11.0625,
1757
+ "learning_rate": 3.309246621169544e-06,
1758
+ "loss": 0.721,
1759
+ "step": 5000
1760
+ },
1761
+ {
1762
+ "epoch": 0.6717516392345778,
1763
+ "grad_norm": 9.3125,
1764
+ "learning_rate": 3.2824836076542223e-06,
1765
+ "loss": 0.7363,
1766
+ "step": 5020
1767
+ },
1768
+ {
1769
+ "epoch": 0.67442794058611,
1770
+ "grad_norm": 3.921875,
1771
+ "learning_rate": 3.2557205941389002e-06,
1772
+ "loss": 0.6483,
1773
+ "step": 5040
1774
+ },
1775
+ {
1776
+ "epoch": 0.6771042419376422,
1777
+ "grad_norm": 6.8125,
1778
+ "learning_rate": 3.2289575806235787e-06,
1779
+ "loss": 0.7267,
1780
+ "step": 5060
1781
+ },
1782
+ {
1783
+ "epoch": 0.6797805432891744,
1784
+ "grad_norm": 8.4375,
1785
+ "learning_rate": 3.2021945671082566e-06,
1786
+ "loss": 0.73,
1787
+ "step": 5080
1788
+ },
1789
+ {
1790
+ "epoch": 0.6824568446407066,
1791
+ "grad_norm": 11.125,
1792
+ "learning_rate": 3.1754315535929346e-06,
1793
+ "loss": 0.7075,
1794
+ "step": 5100
1795
+ },
1796
+ {
1797
+ "epoch": 0.6851331459922387,
1798
+ "grad_norm": 15.0,
1799
+ "learning_rate": 3.148668540077613e-06,
1800
+ "loss": 0.7503,
1801
+ "step": 5120
1802
+ },
1803
+ {
1804
+ "epoch": 0.6878094473437709,
1805
+ "grad_norm": 5.46875,
1806
+ "learning_rate": 3.121905526562291e-06,
1807
+ "loss": 0.6256,
1808
+ "step": 5140
1809
+ },
1810
+ {
1811
+ "epoch": 0.6904857486953031,
1812
+ "grad_norm": 8.875,
1813
+ "learning_rate": 3.0951425130469694e-06,
1814
+ "loss": 0.7156,
1815
+ "step": 5160
1816
+ },
1817
+ {
1818
+ "epoch": 0.6931620500468353,
1819
+ "grad_norm": 9.9375,
1820
+ "learning_rate": 3.0683794995316474e-06,
1821
+ "loss": 0.6339,
1822
+ "step": 5180
1823
+ },
1824
+ {
1825
+ "epoch": 0.6958383513983675,
1826
+ "grad_norm": 6.09375,
1827
+ "learning_rate": 3.0416164860163254e-06,
1828
+ "loss": 0.7028,
1829
+ "step": 5200
1830
+ },
1831
+ {
1832
+ "epoch": 0.6985146527498997,
1833
+ "grad_norm": 7.65625,
1834
+ "learning_rate": 3.014853472501004e-06,
1835
+ "loss": 0.7132,
1836
+ "step": 5220
1837
+ },
1838
+ {
1839
+ "epoch": 0.7011909541014318,
1840
+ "grad_norm": 6.0625,
1841
+ "learning_rate": 2.988090458985682e-06,
1842
+ "loss": 0.6992,
1843
+ "step": 5240
1844
+ },
1845
+ {
1846
+ "epoch": 0.703867255452964,
1847
+ "grad_norm": 7.5625,
1848
+ "learning_rate": 2.96132744547036e-06,
1849
+ "loss": 0.7433,
1850
+ "step": 5260
1851
+ },
1852
+ {
1853
+ "epoch": 0.7065435568044962,
1854
+ "grad_norm": 11.8125,
1855
+ "learning_rate": 2.934564431955038e-06,
1856
+ "loss": 0.6577,
1857
+ "step": 5280
1858
+ },
1859
+ {
1860
+ "epoch": 0.7092198581560284,
1861
+ "grad_norm": 37.0,
1862
+ "learning_rate": 2.907801418439716e-06,
1863
+ "loss": 0.7209,
1864
+ "step": 5300
1865
+ },
1866
+ {
1867
+ "epoch": 0.7118961595075606,
1868
+ "grad_norm": 17.75,
1869
+ "learning_rate": 2.8810384049243946e-06,
1870
+ "loss": 0.6553,
1871
+ "step": 5320
1872
+ },
1873
+ {
1874
+ "epoch": 0.7145724608590928,
1875
+ "grad_norm": 9.8125,
1876
+ "learning_rate": 2.854275391409073e-06,
1877
+ "loss": 0.8166,
1878
+ "step": 5340
1879
+ },
1880
+ {
1881
+ "epoch": 0.717248762210625,
1882
+ "grad_norm": 7.0625,
1883
+ "learning_rate": 2.8275123778937514e-06,
1884
+ "loss": 0.6525,
1885
+ "step": 5360
1886
+ },
1887
+ {
1888
+ "epoch": 0.7199250635621571,
1889
+ "grad_norm": 8.1875,
1890
+ "learning_rate": 2.8007493643784294e-06,
1891
+ "loss": 0.6576,
1892
+ "step": 5380
1893
+ },
1894
+ {
1895
+ "epoch": 0.7226013649136893,
1896
+ "grad_norm": 9.0,
1897
+ "learning_rate": 2.773986350863108e-06,
1898
+ "loss": 0.6565,
1899
+ "step": 5400
1900
+ },
1901
+ {
1902
+ "epoch": 0.7252776662652215,
1903
+ "grad_norm": 12.875,
1904
+ "learning_rate": 2.7472233373477858e-06,
1905
+ "loss": 0.6848,
1906
+ "step": 5420
1907
+ },
1908
+ {
1909
+ "epoch": 0.7279539676167537,
1910
+ "grad_norm": 9.9375,
1911
+ "learning_rate": 2.7204603238324638e-06,
1912
+ "loss": 0.6987,
1913
+ "step": 5440
1914
+ },
1915
+ {
1916
+ "epoch": 0.7306302689682859,
1917
+ "grad_norm": 16.375,
1918
+ "learning_rate": 2.693697310317142e-06,
1919
+ "loss": 0.8492,
1920
+ "step": 5460
1921
+ },
1922
+ {
1923
+ "epoch": 0.733306570319818,
1924
+ "grad_norm": 14.5625,
1925
+ "learning_rate": 2.66693429680182e-06,
1926
+ "loss": 0.6154,
1927
+ "step": 5480
1928
+ },
1929
+ {
1930
+ "epoch": 0.7359828716713502,
1931
+ "grad_norm": 10.3125,
1932
+ "learning_rate": 2.6401712832864986e-06,
1933
+ "loss": 0.6097,
1934
+ "step": 5500
1935
+ },
1936
+ {
1937
+ "epoch": 0.7386591730228824,
1938
+ "grad_norm": 17.5,
1939
+ "learning_rate": 2.6134082697711766e-06,
1940
+ "loss": 0.7904,
1941
+ "step": 5520
1942
+ },
1943
+ {
1944
+ "epoch": 0.7413354743744146,
1945
+ "grad_norm": 10.625,
1946
+ "learning_rate": 2.5866452562558545e-06,
1947
+ "loss": 0.6887,
1948
+ "step": 5540
1949
+ },
1950
+ {
1951
+ "epoch": 0.7440117757259468,
1952
+ "grad_norm": 9.8125,
1953
+ "learning_rate": 2.559882242740533e-06,
1954
+ "loss": 0.6463,
1955
+ "step": 5560
1956
+ },
1957
+ {
1958
+ "epoch": 0.746688077077479,
1959
+ "grad_norm": 12.0625,
1960
+ "learning_rate": 2.533119229225211e-06,
1961
+ "loss": 0.7327,
1962
+ "step": 5580
1963
+ },
1964
+ {
1965
+ "epoch": 0.7493643784290112,
1966
+ "grad_norm": 7.4375,
1967
+ "learning_rate": 2.5063562157098894e-06,
1968
+ "loss": 0.637,
1969
+ "step": 5600
1970
+ },
1971
+ {
1972
+ "epoch": 0.7520406797805433,
1973
+ "grad_norm": 7.78125,
1974
+ "learning_rate": 2.4795932021945673e-06,
1975
+ "loss": 0.7037,
1976
+ "step": 5620
1977
+ },
1978
+ {
1979
+ "epoch": 0.7547169811320755,
1980
+ "grad_norm": 12.625,
1981
+ "learning_rate": 2.4528301886792453e-06,
1982
+ "loss": 0.7834,
1983
+ "step": 5640
1984
+ },
1985
+ {
1986
+ "epoch": 0.7573932824836076,
1987
+ "grad_norm": 7.75,
1988
+ "learning_rate": 2.4260671751639237e-06,
1989
+ "loss": 0.5978,
1990
+ "step": 5660
1991
+ },
1992
+ {
1993
+ "epoch": 0.7600695838351398,
1994
+ "grad_norm": 11.25,
1995
+ "learning_rate": 2.3993041616486017e-06,
1996
+ "loss": 0.6954,
1997
+ "step": 5680
1998
+ },
1999
+ {
2000
+ "epoch": 0.762745885186672,
2001
+ "grad_norm": 22.75,
2002
+ "learning_rate": 2.37254114813328e-06,
2003
+ "loss": 0.6904,
2004
+ "step": 5700
2005
+ },
2006
+ {
2007
+ "epoch": 0.7654221865382042,
2008
+ "grad_norm": 9.8125,
2009
+ "learning_rate": 2.345778134617958e-06,
2010
+ "loss": 0.6372,
2011
+ "step": 5720
2012
+ },
2013
+ {
2014
+ "epoch": 0.7680984878897363,
2015
+ "grad_norm": 9.3125,
2016
+ "learning_rate": 2.319015121102636e-06,
2017
+ "loss": 0.5761,
2018
+ "step": 5740
2019
+ },
2020
+ {
2021
+ "epoch": 0.7707747892412685,
2022
+ "grad_norm": 7.1875,
2023
+ "learning_rate": 2.2922521075873145e-06,
2024
+ "loss": 0.7424,
2025
+ "step": 5760
2026
+ },
2027
+ {
2028
+ "epoch": 0.7734510905928007,
2029
+ "grad_norm": 7.3125,
2030
+ "learning_rate": 2.2654890940719925e-06,
2031
+ "loss": 0.6615,
2032
+ "step": 5780
2033
+ },
2034
+ {
2035
+ "epoch": 0.7761273919443329,
2036
+ "grad_norm": 6.5625,
2037
+ "learning_rate": 2.238726080556671e-06,
2038
+ "loss": 0.7074,
2039
+ "step": 5800
2040
+ },
2041
+ {
2042
+ "epoch": 0.7788036932958651,
2043
+ "grad_norm": 14.0,
2044
+ "learning_rate": 2.2119630670413493e-06,
2045
+ "loss": 0.7508,
2046
+ "step": 5820
2047
+ },
2048
+ {
2049
+ "epoch": 0.7814799946473973,
2050
+ "grad_norm": 24.0,
2051
+ "learning_rate": 2.1852000535260273e-06,
2052
+ "loss": 0.619,
2053
+ "step": 5840
2054
+ },
2055
+ {
2056
+ "epoch": 0.7841562959989294,
2057
+ "grad_norm": 6.21875,
2058
+ "learning_rate": 2.1584370400107053e-06,
2059
+ "loss": 0.7471,
2060
+ "step": 5860
2061
+ },
2062
+ {
2063
+ "epoch": 0.7868325973504616,
2064
+ "grad_norm": 8.9375,
2065
+ "learning_rate": 2.1316740264953837e-06,
2066
+ "loss": 0.6773,
2067
+ "step": 5880
2068
+ },
2069
+ {
2070
+ "epoch": 0.7895088987019938,
2071
+ "grad_norm": 13.375,
2072
+ "learning_rate": 2.1049110129800617e-06,
2073
+ "loss": 0.6566,
2074
+ "step": 5900
2075
+ },
2076
+ {
2077
+ "epoch": 0.792185200053526,
2078
+ "grad_norm": 9.9375,
2079
+ "learning_rate": 2.07814799946474e-06,
2080
+ "loss": 0.8063,
2081
+ "step": 5920
2082
+ },
2083
+ {
2084
+ "epoch": 0.7948615014050582,
2085
+ "grad_norm": 10.625,
2086
+ "learning_rate": 2.051384985949418e-06,
2087
+ "loss": 0.7928,
2088
+ "step": 5940
2089
+ },
2090
+ {
2091
+ "epoch": 0.7975378027565904,
2092
+ "grad_norm": 6.15625,
2093
+ "learning_rate": 2.024621972434096e-06,
2094
+ "loss": 0.714,
2095
+ "step": 5960
2096
+ },
2097
+ {
2098
+ "epoch": 0.8002141041081225,
2099
+ "grad_norm": 4.8125,
2100
+ "learning_rate": 1.9978589589187745e-06,
2101
+ "loss": 0.7086,
2102
+ "step": 5980
2103
+ },
2104
+ {
2105
+ "epoch": 0.8028904054596547,
2106
+ "grad_norm": 8.5,
2107
+ "learning_rate": 1.9710959454034525e-06,
2108
+ "loss": 0.665,
2109
+ "step": 6000
2110
+ },
2111
+ {
2112
+ "epoch": 0.8055667068111869,
2113
+ "grad_norm": 5.21875,
2114
+ "learning_rate": 1.944332931888131e-06,
2115
+ "loss": 0.6577,
2116
+ "step": 6020
2117
+ },
2118
+ {
2119
+ "epoch": 0.8082430081627191,
2120
+ "grad_norm": 10.0625,
2121
+ "learning_rate": 1.917569918372809e-06,
2122
+ "loss": 0.6418,
2123
+ "step": 6040
2124
+ },
2125
+ {
2126
+ "epoch": 0.8109193095142513,
2127
+ "grad_norm": 9.75,
2128
+ "learning_rate": 1.890806904857487e-06,
2129
+ "loss": 0.7353,
2130
+ "step": 6060
2131
+ },
2132
+ {
2133
+ "epoch": 0.8135956108657835,
2134
+ "grad_norm": 9.0625,
2135
+ "learning_rate": 1.8640438913421652e-06,
2136
+ "loss": 0.7601,
2137
+ "step": 6080
2138
+ },
2139
+ {
2140
+ "epoch": 0.8162719122173157,
2141
+ "grad_norm": 13.6875,
2142
+ "learning_rate": 1.8372808778268432e-06,
2143
+ "loss": 0.7325,
2144
+ "step": 6100
2145
+ },
2146
+ {
2147
+ "epoch": 0.8189482135688478,
2148
+ "grad_norm": 13.9375,
2149
+ "learning_rate": 1.8105178643115214e-06,
2150
+ "loss": 0.6905,
2151
+ "step": 6120
2152
+ },
2153
+ {
2154
+ "epoch": 0.82162451492038,
2155
+ "grad_norm": 16.0,
2156
+ "learning_rate": 1.7837548507961998e-06,
2157
+ "loss": 0.6566,
2158
+ "step": 6140
2159
+ },
2160
+ {
2161
+ "epoch": 0.8243008162719122,
2162
+ "grad_norm": 7.59375,
2163
+ "learning_rate": 1.756991837280878e-06,
2164
+ "loss": 0.6967,
2165
+ "step": 6160
2166
+ },
2167
+ {
2168
+ "epoch": 0.8269771176234444,
2169
+ "grad_norm": 18.75,
2170
+ "learning_rate": 1.7302288237655562e-06,
2171
+ "loss": 0.8126,
2172
+ "step": 6180
2173
+ },
2174
+ {
2175
+ "epoch": 0.8296534189749766,
2176
+ "grad_norm": 10.5625,
2177
+ "learning_rate": 1.7034658102502344e-06,
2178
+ "loss": 0.7035,
2179
+ "step": 6200
2180
+ },
2181
+ {
2182
+ "epoch": 0.8323297203265088,
2183
+ "grad_norm": 7.25,
2184
+ "learning_rate": 1.6767027967349126e-06,
2185
+ "loss": 0.7178,
2186
+ "step": 6220
2187
+ },
2188
+ {
2189
+ "epoch": 0.8350060216780409,
2190
+ "grad_norm": 5.0625,
2191
+ "learning_rate": 1.6499397832195906e-06,
2192
+ "loss": 0.7009,
2193
+ "step": 6240
2194
+ },
2195
+ {
2196
+ "epoch": 0.8376823230295731,
2197
+ "grad_norm": 7.28125,
2198
+ "learning_rate": 1.6231767697042688e-06,
2199
+ "loss": 0.65,
2200
+ "step": 6260
2201
+ },
2202
+ {
2203
+ "epoch": 0.8403586243811053,
2204
+ "grad_norm": 8.8125,
2205
+ "learning_rate": 1.596413756188947e-06,
2206
+ "loss": 0.6868,
2207
+ "step": 6280
2208
+ },
2209
+ {
2210
+ "epoch": 0.8430349257326375,
2211
+ "grad_norm": 12.4375,
2212
+ "learning_rate": 1.5696507426736252e-06,
2213
+ "loss": 0.7927,
2214
+ "step": 6300
2215
+ },
2216
+ {
2217
+ "epoch": 0.8457112270841697,
2218
+ "grad_norm": 9.3125,
2219
+ "learning_rate": 1.5428877291583034e-06,
2220
+ "loss": 0.7587,
2221
+ "step": 6320
2222
+ },
2223
+ {
2224
+ "epoch": 0.8483875284357019,
2225
+ "grad_norm": 7.3125,
2226
+ "learning_rate": 1.5161247156429814e-06,
2227
+ "loss": 0.7038,
2228
+ "step": 6340
2229
+ },
2230
+ {
2231
+ "epoch": 0.851063829787234,
2232
+ "grad_norm": 10.9375,
2233
+ "learning_rate": 1.4893617021276596e-06,
2234
+ "loss": 0.8245,
2235
+ "step": 6360
2236
+ },
2237
+ {
2238
+ "epoch": 0.8537401311387662,
2239
+ "grad_norm": 8.375,
2240
+ "learning_rate": 1.4625986886123378e-06,
2241
+ "loss": 0.6673,
2242
+ "step": 6380
2243
+ },
2244
+ {
2245
+ "epoch": 0.8564164324902984,
2246
+ "grad_norm": 7.09375,
2247
+ "learning_rate": 1.435835675097016e-06,
2248
+ "loss": 0.7309,
2249
+ "step": 6400
2250
+ },
2251
+ {
2252
+ "epoch": 0.8590927338418306,
2253
+ "grad_norm": 8.125,
2254
+ "learning_rate": 1.4090726615816942e-06,
2255
+ "loss": 0.725,
2256
+ "step": 6420
2257
+ },
2258
+ {
2259
+ "epoch": 0.8617690351933628,
2260
+ "grad_norm": 8.25,
2261
+ "learning_rate": 1.3823096480663726e-06,
2262
+ "loss": 0.6646,
2263
+ "step": 6440
2264
+ },
2265
+ {
2266
+ "epoch": 0.864445336544895,
2267
+ "grad_norm": 6.4375,
2268
+ "learning_rate": 1.3555466345510506e-06,
2269
+ "loss": 0.7158,
2270
+ "step": 6460
2271
+ },
2272
+ {
2273
+ "epoch": 0.8671216378964272,
2274
+ "grad_norm": 5.71875,
2275
+ "learning_rate": 1.3287836210357288e-06,
2276
+ "loss": 0.6649,
2277
+ "step": 6480
2278
+ },
2279
+ {
2280
+ "epoch": 0.8697979392479593,
2281
+ "grad_norm": 16.875,
2282
+ "learning_rate": 1.302020607520407e-06,
2283
+ "loss": 0.7767,
2284
+ "step": 6500
2285
+ },
2286
+ {
2287
+ "epoch": 0.8724742405994915,
2288
+ "grad_norm": 12.875,
2289
+ "learning_rate": 1.2752575940050852e-06,
2290
+ "loss": 0.6689,
2291
+ "step": 6520
2292
+ },
2293
+ {
2294
+ "epoch": 0.8751505419510237,
2295
+ "grad_norm": 9.5625,
2296
+ "learning_rate": 1.2484945804897634e-06,
2297
+ "loss": 0.6509,
2298
+ "step": 6540
2299
+ },
2300
+ {
2301
+ "epoch": 0.8778268433025559,
2302
+ "grad_norm": 8.625,
2303
+ "learning_rate": 1.2217315669744414e-06,
2304
+ "loss": 0.6574,
2305
+ "step": 6560
2306
+ },
2307
+ {
2308
+ "epoch": 0.8805031446540881,
2309
+ "grad_norm": 12.375,
2310
+ "learning_rate": 1.1949685534591195e-06,
2311
+ "loss": 0.7337,
2312
+ "step": 6580
2313
+ },
2314
+ {
2315
+ "epoch": 0.8831794460056203,
2316
+ "grad_norm": 9.375,
2317
+ "learning_rate": 1.1682055399437977e-06,
2318
+ "loss": 0.6465,
2319
+ "step": 6600
2320
+ },
2321
+ {
2322
+ "epoch": 0.8858557473571524,
2323
+ "grad_norm": 8.8125,
2324
+ "learning_rate": 1.141442526428476e-06,
2325
+ "loss": 0.7548,
2326
+ "step": 6620
2327
+ },
2328
+ {
2329
+ "epoch": 0.8885320487086846,
2330
+ "grad_norm": 11.125,
2331
+ "learning_rate": 1.1146795129131541e-06,
2332
+ "loss": 0.7219,
2333
+ "step": 6640
2334
+ },
2335
+ {
2336
+ "epoch": 0.8912083500602168,
2337
+ "grad_norm": 6.625,
2338
+ "learning_rate": 1.0879164993978321e-06,
2339
+ "loss": 0.8184,
2340
+ "step": 6660
2341
+ },
2342
+ {
2343
+ "epoch": 0.893884651411749,
2344
+ "grad_norm": 6.84375,
2345
+ "learning_rate": 1.0611534858825105e-06,
2346
+ "loss": 0.6956,
2347
+ "step": 6680
2348
+ },
2349
+ {
2350
+ "epoch": 0.8965609527632812,
2351
+ "grad_norm": 7.03125,
2352
+ "learning_rate": 1.0343904723671887e-06,
2353
+ "loss": 0.6756,
2354
+ "step": 6700
2355
+ },
2356
+ {
2357
+ "epoch": 0.8992372541148134,
2358
+ "grad_norm": 8.1875,
2359
+ "learning_rate": 1.007627458851867e-06,
2360
+ "loss": 0.6936,
2361
+ "step": 6720
2362
+ },
2363
+ {
2364
+ "epoch": 0.9019135554663456,
2365
+ "grad_norm": 10.0,
2366
+ "learning_rate": 9.80864445336545e-07,
2367
+ "loss": 0.6416,
2368
+ "step": 6740
2369
+ },
2370
+ {
2371
+ "epoch": 0.9045898568178777,
2372
+ "grad_norm": 8.1875,
2373
+ "learning_rate": 9.541014318212231e-07,
2374
+ "loss": 0.7569,
2375
+ "step": 6760
2376
+ },
2377
+ {
2378
+ "epoch": 0.9072661581694099,
2379
+ "grad_norm": 47.0,
2380
+ "learning_rate": 9.273384183059013e-07,
2381
+ "loss": 0.7972,
2382
+ "step": 6780
2383
+ },
2384
+ {
2385
+ "epoch": 0.9099424595209421,
2386
+ "grad_norm": 7.625,
2387
+ "learning_rate": 9.005754047905794e-07,
2388
+ "loss": 0.6925,
2389
+ "step": 6800
2390
+ },
2391
+ {
2392
+ "epoch": 0.9126187608724743,
2393
+ "grad_norm": 23.875,
2394
+ "learning_rate": 8.738123912752576e-07,
2395
+ "loss": 0.67,
2396
+ "step": 6820
2397
+ },
2398
+ {
2399
+ "epoch": 0.9152950622240065,
2400
+ "grad_norm": 7.6875,
2401
+ "learning_rate": 8.470493777599359e-07,
2402
+ "loss": 0.7114,
2403
+ "step": 6840
2404
+ },
2405
+ {
2406
+ "epoch": 0.9179713635755387,
2407
+ "grad_norm": 8.1875,
2408
+ "learning_rate": 8.202863642446141e-07,
2409
+ "loss": 0.6751,
2410
+ "step": 6860
2411
+ },
2412
+ {
2413
+ "epoch": 0.9206476649270708,
2414
+ "grad_norm": 11.0625,
2415
+ "learning_rate": 7.935233507292922e-07,
2416
+ "loss": 0.6867,
2417
+ "step": 6880
2418
+ },
2419
+ {
2420
+ "epoch": 0.923323966278603,
2421
+ "grad_norm": 15.375,
2422
+ "learning_rate": 7.667603372139704e-07,
2423
+ "loss": 0.7322,
2424
+ "step": 6900
2425
+ },
2426
+ {
2427
+ "epoch": 0.9260002676301351,
2428
+ "grad_norm": 6.15625,
2429
+ "learning_rate": 7.399973236986485e-07,
2430
+ "loss": 0.7396,
2431
+ "step": 6920
2432
+ },
2433
+ {
2434
+ "epoch": 0.9286765689816673,
2435
+ "grad_norm": 18.0,
2436
+ "learning_rate": 7.132343101833267e-07,
2437
+ "loss": 0.7134,
2438
+ "step": 6940
2439
+ },
2440
+ {
2441
+ "epoch": 0.9313528703331995,
2442
+ "grad_norm": 12.125,
2443
+ "learning_rate": 6.864712966680049e-07,
2444
+ "loss": 0.682,
2445
+ "step": 6960
2446
+ },
2447
+ {
2448
+ "epoch": 0.9340291716847317,
2449
+ "grad_norm": 8.5625,
2450
+ "learning_rate": 6.59708283152683e-07,
2451
+ "loss": 0.8207,
2452
+ "step": 6980
2453
+ },
2454
+ {
2455
+ "epoch": 0.9367054730362638,
2456
+ "grad_norm": 5.3125,
2457
+ "learning_rate": 6.329452696373613e-07,
2458
+ "loss": 0.6548,
2459
+ "step": 7000
2460
+ },
2461
+ {
2462
+ "epoch": 0.939381774387796,
2463
+ "grad_norm": 13.0,
2464
+ "learning_rate": 6.061822561220394e-07,
2465
+ "loss": 0.6879,
2466
+ "step": 7020
2467
+ },
2468
+ {
2469
+ "epoch": 0.9420580757393282,
2470
+ "grad_norm": 7.625,
2471
+ "learning_rate": 5.794192426067176e-07,
2472
+ "loss": 0.7555,
2473
+ "step": 7040
2474
+ },
2475
+ {
2476
+ "epoch": 0.9447343770908604,
2477
+ "grad_norm": 6.4375,
2478
+ "learning_rate": 5.526562290913958e-07,
2479
+ "loss": 0.6822,
2480
+ "step": 7060
2481
+ },
2482
+ {
2483
+ "epoch": 0.9474106784423926,
2484
+ "grad_norm": 6.375,
2485
+ "learning_rate": 5.258932155760739e-07,
2486
+ "loss": 0.7273,
2487
+ "step": 7080
2488
+ },
2489
+ {
2490
+ "epoch": 0.9500869797939248,
2491
+ "grad_norm": 9.1875,
2492
+ "learning_rate": 4.99130202060752e-07,
2493
+ "loss": 0.6715,
2494
+ "step": 7100
2495
+ },
2496
+ {
2497
+ "epoch": 0.9527632811454569,
2498
+ "grad_norm": 5.75,
2499
+ "learning_rate": 4.723671885454303e-07,
2500
+ "loss": 0.8109,
2501
+ "step": 7120
2502
+ },
2503
+ {
2504
+ "epoch": 0.9554395824969891,
2505
+ "grad_norm": 13.75,
2506
+ "learning_rate": 4.4560417503010845e-07,
2507
+ "loss": 0.6167,
2508
+ "step": 7140
2509
+ },
2510
+ {
2511
+ "epoch": 0.9581158838485213,
2512
+ "grad_norm": 7.59375,
2513
+ "learning_rate": 4.188411615147866e-07,
2514
+ "loss": 0.6606,
2515
+ "step": 7160
2516
+ },
2517
+ {
2518
+ "epoch": 0.9607921852000535,
2519
+ "grad_norm": 9.1875,
2520
+ "learning_rate": 3.9207814799946473e-07,
2521
+ "loss": 0.7073,
2522
+ "step": 7180
2523
+ },
2524
+ {
2525
+ "epoch": 0.9634684865515857,
2526
+ "grad_norm": 9.75,
2527
+ "learning_rate": 3.65315134484143e-07,
2528
+ "loss": 0.682,
2529
+ "step": 7200
2530
+ },
2531
+ {
2532
+ "epoch": 0.9661447879031179,
2533
+ "grad_norm": 11.8125,
2534
+ "learning_rate": 3.3855212096882113e-07,
2535
+ "loss": 0.7581,
2536
+ "step": 7220
2537
+ },
2538
+ {
2539
+ "epoch": 0.96882108925465,
2540
+ "grad_norm": 8.875,
2541
+ "learning_rate": 3.117891074534993e-07,
2542
+ "loss": 0.6873,
2543
+ "step": 7240
2544
+ },
2545
+ {
2546
+ "epoch": 0.9714973906061822,
2547
+ "grad_norm": 27.375,
2548
+ "learning_rate": 2.8502609393817747e-07,
2549
+ "loss": 0.647,
2550
+ "step": 7260
2551
+ },
2552
+ {
2553
+ "epoch": 0.9741736919577144,
2554
+ "grad_norm": 12.1875,
2555
+ "learning_rate": 2.582630804228556e-07,
2556
+ "loss": 0.6391,
2557
+ "step": 7280
2558
+ },
2559
+ {
2560
+ "epoch": 0.9768499933092466,
2561
+ "grad_norm": 14.1875,
2562
+ "learning_rate": 2.3150006690753381e-07,
2563
+ "loss": 0.8126,
2564
+ "step": 7300
2565
+ },
2566
+ {
2567
+ "epoch": 0.9795262946607788,
2568
+ "grad_norm": 6.4375,
2569
+ "learning_rate": 2.0473705339221198e-07,
2570
+ "loss": 0.7084,
2571
+ "step": 7320
2572
+ },
2573
+ {
2574
+ "epoch": 0.982202596012311,
2575
+ "grad_norm": 25.0,
2576
+ "learning_rate": 1.7797403987689016e-07,
2577
+ "loss": 0.6649,
2578
+ "step": 7340
2579
+ },
2580
+ {
2581
+ "epoch": 0.9848788973638432,
2582
+ "grad_norm": 11.6875,
2583
+ "learning_rate": 1.5121102636156833e-07,
2584
+ "loss": 0.7436,
2585
+ "step": 7360
2586
+ },
2587
+ {
2588
+ "epoch": 0.9875551987153753,
2589
+ "grad_norm": 12.8125,
2590
+ "learning_rate": 1.244480128462465e-07,
2591
+ "loss": 0.6809,
2592
+ "step": 7380
2593
+ },
2594
+ {
2595
+ "epoch": 0.9902315000669075,
2596
+ "grad_norm": 7.125,
2597
+ "learning_rate": 9.768499933092467e-08,
2598
+ "loss": 0.6806,
2599
+ "step": 7400
2600
+ },
2601
+ {
2602
+ "epoch": 0.9929078014184397,
2603
+ "grad_norm": 15.625,
2604
+ "learning_rate": 7.092198581560284e-08,
2605
+ "loss": 0.7224,
2606
+ "step": 7420
2607
+ },
2608
+ {
2609
+ "epoch": 0.9955841027699719,
2610
+ "grad_norm": 7.46875,
2611
+ "learning_rate": 4.415897230028101e-08,
2612
+ "loss": 0.7614,
2613
+ "step": 7440
2614
+ },
2615
+ {
2616
+ "epoch": 0.9982604041215041,
2617
+ "grad_norm": 8.5,
2618
+ "learning_rate": 1.739595878495919e-08,
2619
+ "loss": 0.6988,
2620
+ "step": 7460
2621
+ }
2622
+ ],
2623
+ "logging_steps": 20,
2624
+ "max_steps": 7473,
2625
+ "num_input_tokens_seen": 0,
2626
+ "num_train_epochs": 1,
2627
+ "save_steps": 5000,
2628
+ "stateful_callbacks": {
2629
+ "TrainerControl": {
2630
+ "args": {
2631
+ "should_epoch_stop": false,
2632
+ "should_evaluate": false,
2633
+ "should_log": false,
2634
+ "should_save": true,
2635
+ "should_training_stop": true
2636
+ },
2637
+ "attributes": {}
2638
+ }
2639
+ },
2640
+ "total_flos": 1.1170284894683136e+16,
2641
+ "train_batch_size": 1,
2642
+ "trial_name": null,
2643
+ "trial_params": null
2644
+ }
checkpoint-7473/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5192ed7d4caa2f74e975a410893b27550adcd92c93eb22def9cf35fa3c6a5484
3
+ size 6008
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-3.2-1B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 16,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 128001,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": {
25
+ "factor": 32.0,
26
+ "high_freq_factor": 4.0,
27
+ "low_freq_factor": 1.0,
28
+ "original_max_position_embeddings": 8192,
29
+ "rope_type": "llama3"
30
+ },
31
+ "rope_theta": 500000.0,
32
+ "tie_word_embeddings": true,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.46.3",
35
+ "use_cache": true,
36
+ "vocab_size": 128256
37
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.46.3"
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09383ac745175f35de75477e5652cfdc1249ff1273fad0ccad70da6c4a04c19c
3
+ size 2471645608
runs/Dec11_18-18-09_a559b199d359/events.out.tfevents.1733941102.a559b199d359.172128.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5761951b7e98d3bf28c0448486ec2c76c34c5b36c8e4e16617ff8d0bfd14a2e2
3
+ size 85034
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|end_of_text|>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "model_input_names": [
2056
+ "input_ids",
2057
+ "attention_mask"
2058
+ ],
2059
+ "model_max_length": 131072,
2060
+ "pad_token": "<|end_of_text|>",
2061
+ "padding_side": "right",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 1.1170284894683136e+16,
4
+ "train_loss": 0.7570252240493756,
5
+ "train_runtime": 920.0938,
6
+ "train_samples": 7473,
7
+ "train_samples_per_second": 8.122,
8
+ "train_steps_per_second": 8.122
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,2653 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 7473,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0026763013515321826,
13
+ "grad_norm": 21.75,
14
+ "learning_rate": 9.973236986484679e-06,
15
+ "loss": 1.9581,
16
+ "step": 20
17
+ },
18
+ {
19
+ "epoch": 0.005352602703064365,
20
+ "grad_norm": 11.0625,
21
+ "learning_rate": 9.946473972969357e-06,
22
+ "loss": 1.8767,
23
+ "step": 40
24
+ },
25
+ {
26
+ "epoch": 0.008028904054596548,
27
+ "grad_norm": 20.875,
28
+ "learning_rate": 9.919710959454035e-06,
29
+ "loss": 1.729,
30
+ "step": 60
31
+ },
32
+ {
33
+ "epoch": 0.01070520540612873,
34
+ "grad_norm": 11.8125,
35
+ "learning_rate": 9.892947945938713e-06,
36
+ "loss": 1.4764,
37
+ "step": 80
38
+ },
39
+ {
40
+ "epoch": 0.013381506757660913,
41
+ "grad_norm": 20.375,
42
+ "learning_rate": 9.86618493242339e-06,
43
+ "loss": 1.4558,
44
+ "step": 100
45
+ },
46
+ {
47
+ "epoch": 0.016057808109193095,
48
+ "grad_norm": 9.8125,
49
+ "learning_rate": 9.83942191890807e-06,
50
+ "loss": 1.1101,
51
+ "step": 120
52
+ },
53
+ {
54
+ "epoch": 0.018734109460725276,
55
+ "grad_norm": 14.8125,
56
+ "learning_rate": 9.812658905392748e-06,
57
+ "loss": 1.2423,
58
+ "step": 140
59
+ },
60
+ {
61
+ "epoch": 0.02141041081225746,
62
+ "grad_norm": 15.3125,
63
+ "learning_rate": 9.785895891877426e-06,
64
+ "loss": 1.3871,
65
+ "step": 160
66
+ },
67
+ {
68
+ "epoch": 0.02408671216378964,
69
+ "grad_norm": 11.8125,
70
+ "learning_rate": 9.759132878362104e-06,
71
+ "loss": 1.2922,
72
+ "step": 180
73
+ },
74
+ {
75
+ "epoch": 0.026763013515321826,
76
+ "grad_norm": 9.25,
77
+ "learning_rate": 9.732369864846782e-06,
78
+ "loss": 1.3144,
79
+ "step": 200
80
+ },
81
+ {
82
+ "epoch": 0.029439314866854006,
83
+ "grad_norm": 18.625,
84
+ "learning_rate": 9.70560685133146e-06,
85
+ "loss": 1.0756,
86
+ "step": 220
87
+ },
88
+ {
89
+ "epoch": 0.03211561621838619,
90
+ "grad_norm": 43.25,
91
+ "learning_rate": 9.678843837816138e-06,
92
+ "loss": 1.2612,
93
+ "step": 240
94
+ },
95
+ {
96
+ "epoch": 0.034791917569918375,
97
+ "grad_norm": 9.4375,
98
+ "learning_rate": 9.652080824300816e-06,
99
+ "loss": 1.0856,
100
+ "step": 260
101
+ },
102
+ {
103
+ "epoch": 0.03746821892145055,
104
+ "grad_norm": 17.5,
105
+ "learning_rate": 9.625317810785494e-06,
106
+ "loss": 1.0375,
107
+ "step": 280
108
+ },
109
+ {
110
+ "epoch": 0.04014452027298274,
111
+ "grad_norm": 7.75,
112
+ "learning_rate": 9.598554797270172e-06,
113
+ "loss": 0.9578,
114
+ "step": 300
115
+ },
116
+ {
117
+ "epoch": 0.04282082162451492,
118
+ "grad_norm": 12.875,
119
+ "learning_rate": 9.571791783754852e-06,
120
+ "loss": 0.9921,
121
+ "step": 320
122
+ },
123
+ {
124
+ "epoch": 0.045497122976047105,
125
+ "grad_norm": 14.4375,
126
+ "learning_rate": 9.54502877023953e-06,
127
+ "loss": 0.8984,
128
+ "step": 340
129
+ },
130
+ {
131
+ "epoch": 0.04817342432757928,
132
+ "grad_norm": 11.9375,
133
+ "learning_rate": 9.518265756724208e-06,
134
+ "loss": 1.0139,
135
+ "step": 360
136
+ },
137
+ {
138
+ "epoch": 0.05084972567911147,
139
+ "grad_norm": 8.1875,
140
+ "learning_rate": 9.491502743208886e-06,
141
+ "loss": 0.9266,
142
+ "step": 380
143
+ },
144
+ {
145
+ "epoch": 0.05352602703064365,
146
+ "grad_norm": 33.0,
147
+ "learning_rate": 9.464739729693564e-06,
148
+ "loss": 0.8922,
149
+ "step": 400
150
+ },
151
+ {
152
+ "epoch": 0.056202328382175835,
153
+ "grad_norm": 20.375,
154
+ "learning_rate": 9.437976716178242e-06,
155
+ "loss": 0.9903,
156
+ "step": 420
157
+ },
158
+ {
159
+ "epoch": 0.05887862973370801,
160
+ "grad_norm": 18.625,
161
+ "learning_rate": 9.41121370266292e-06,
162
+ "loss": 0.8287,
163
+ "step": 440
164
+ },
165
+ {
166
+ "epoch": 0.0615549310852402,
167
+ "grad_norm": 8.75,
168
+ "learning_rate": 9.384450689147598e-06,
169
+ "loss": 0.9283,
170
+ "step": 460
171
+ },
172
+ {
173
+ "epoch": 0.06423123243677238,
174
+ "grad_norm": 21.75,
175
+ "learning_rate": 9.357687675632276e-06,
176
+ "loss": 0.9585,
177
+ "step": 480
178
+ },
179
+ {
180
+ "epoch": 0.06690753378830457,
181
+ "grad_norm": 13.9375,
182
+ "learning_rate": 9.330924662116954e-06,
183
+ "loss": 0.8412,
184
+ "step": 500
185
+ },
186
+ {
187
+ "epoch": 0.06958383513983675,
188
+ "grad_norm": 25.0,
189
+ "learning_rate": 9.304161648601634e-06,
190
+ "loss": 0.9743,
191
+ "step": 520
192
+ },
193
+ {
194
+ "epoch": 0.07226013649136893,
195
+ "grad_norm": 18.625,
196
+ "learning_rate": 9.277398635086312e-06,
197
+ "loss": 0.869,
198
+ "step": 540
199
+ },
200
+ {
201
+ "epoch": 0.0749364378429011,
202
+ "grad_norm": 11.625,
203
+ "learning_rate": 9.25063562157099e-06,
204
+ "loss": 0.7945,
205
+ "step": 560
206
+ },
207
+ {
208
+ "epoch": 0.07761273919443329,
209
+ "grad_norm": 7.1875,
210
+ "learning_rate": 9.223872608055667e-06,
211
+ "loss": 0.8359,
212
+ "step": 580
213
+ },
214
+ {
215
+ "epoch": 0.08028904054596547,
216
+ "grad_norm": 14.3125,
217
+ "learning_rate": 9.197109594540345e-06,
218
+ "loss": 0.7731,
219
+ "step": 600
220
+ },
221
+ {
222
+ "epoch": 0.08296534189749766,
223
+ "grad_norm": 12.9375,
224
+ "learning_rate": 9.170346581025023e-06,
225
+ "loss": 0.8352,
226
+ "step": 620
227
+ },
228
+ {
229
+ "epoch": 0.08564164324902984,
230
+ "grad_norm": 19.75,
231
+ "learning_rate": 9.143583567509703e-06,
232
+ "loss": 0.8792,
233
+ "step": 640
234
+ },
235
+ {
236
+ "epoch": 0.08831794460056203,
237
+ "grad_norm": 8.25,
238
+ "learning_rate": 9.116820553994381e-06,
239
+ "loss": 0.8651,
240
+ "step": 660
241
+ },
242
+ {
243
+ "epoch": 0.09099424595209421,
244
+ "grad_norm": 12.125,
245
+ "learning_rate": 9.090057540479059e-06,
246
+ "loss": 0.812,
247
+ "step": 680
248
+ },
249
+ {
250
+ "epoch": 0.0936705473036264,
251
+ "grad_norm": 15.75,
252
+ "learning_rate": 9.063294526963737e-06,
253
+ "loss": 0.8949,
254
+ "step": 700
255
+ },
256
+ {
257
+ "epoch": 0.09634684865515857,
258
+ "grad_norm": 11.5625,
259
+ "learning_rate": 9.036531513448415e-06,
260
+ "loss": 0.8752,
261
+ "step": 720
262
+ },
263
+ {
264
+ "epoch": 0.09902315000669075,
265
+ "grad_norm": 14.6875,
266
+ "learning_rate": 9.009768499933093e-06,
267
+ "loss": 0.8544,
268
+ "step": 740
269
+ },
270
+ {
271
+ "epoch": 0.10169945135822293,
272
+ "grad_norm": 9.9375,
273
+ "learning_rate": 8.983005486417771e-06,
274
+ "loss": 0.8414,
275
+ "step": 760
276
+ },
277
+ {
278
+ "epoch": 0.10437575270975512,
279
+ "grad_norm": 11.5,
280
+ "learning_rate": 8.95624247290245e-06,
281
+ "loss": 0.8796,
282
+ "step": 780
283
+ },
284
+ {
285
+ "epoch": 0.1070520540612873,
286
+ "grad_norm": 13.0625,
287
+ "learning_rate": 8.929479459387129e-06,
288
+ "loss": 0.853,
289
+ "step": 800
290
+ },
291
+ {
292
+ "epoch": 0.10972835541281949,
293
+ "grad_norm": 12.1875,
294
+ "learning_rate": 8.902716445871807e-06,
295
+ "loss": 0.8864,
296
+ "step": 820
297
+ },
298
+ {
299
+ "epoch": 0.11240465676435167,
300
+ "grad_norm": 60.0,
301
+ "learning_rate": 8.875953432356485e-06,
302
+ "loss": 0.7659,
303
+ "step": 840
304
+ },
305
+ {
306
+ "epoch": 0.11508095811588386,
307
+ "grad_norm": 30.0,
308
+ "learning_rate": 8.849190418841163e-06,
309
+ "loss": 0.9269,
310
+ "step": 860
311
+ },
312
+ {
313
+ "epoch": 0.11775725946741603,
314
+ "grad_norm": 9.125,
315
+ "learning_rate": 8.82242740532584e-06,
316
+ "loss": 0.7939,
317
+ "step": 880
318
+ },
319
+ {
320
+ "epoch": 0.12043356081894821,
321
+ "grad_norm": 9.0,
322
+ "learning_rate": 8.795664391810519e-06,
323
+ "loss": 0.8343,
324
+ "step": 900
325
+ },
326
+ {
327
+ "epoch": 0.1231098621704804,
328
+ "grad_norm": 18.25,
329
+ "learning_rate": 8.768901378295197e-06,
330
+ "loss": 0.7588,
331
+ "step": 920
332
+ },
333
+ {
334
+ "epoch": 0.12578616352201258,
335
+ "grad_norm": 6.34375,
336
+ "learning_rate": 8.742138364779875e-06,
337
+ "loss": 0.8424,
338
+ "step": 940
339
+ },
340
+ {
341
+ "epoch": 0.12846246487354476,
342
+ "grad_norm": 11.875,
343
+ "learning_rate": 8.715375351264553e-06,
344
+ "loss": 0.7666,
345
+ "step": 960
346
+ },
347
+ {
348
+ "epoch": 0.13113876622507695,
349
+ "grad_norm": 10.0,
350
+ "learning_rate": 8.688612337749232e-06,
351
+ "loss": 0.7019,
352
+ "step": 980
353
+ },
354
+ {
355
+ "epoch": 0.13381506757660913,
356
+ "grad_norm": 8.25,
357
+ "learning_rate": 8.66184932423391e-06,
358
+ "loss": 0.7036,
359
+ "step": 1000
360
+ },
361
+ {
362
+ "epoch": 0.13649136892814132,
363
+ "grad_norm": 10.75,
364
+ "learning_rate": 8.635086310718588e-06,
365
+ "loss": 0.7355,
366
+ "step": 1020
367
+ },
368
+ {
369
+ "epoch": 0.1391676702796735,
370
+ "grad_norm": 14.3125,
371
+ "learning_rate": 8.608323297203266e-06,
372
+ "loss": 0.737,
373
+ "step": 1040
374
+ },
375
+ {
376
+ "epoch": 0.14184397163120568,
377
+ "grad_norm": 9.5,
378
+ "learning_rate": 8.581560283687944e-06,
379
+ "loss": 0.7999,
380
+ "step": 1060
381
+ },
382
+ {
383
+ "epoch": 0.14452027298273787,
384
+ "grad_norm": 10.125,
385
+ "learning_rate": 8.554797270172622e-06,
386
+ "loss": 0.7613,
387
+ "step": 1080
388
+ },
389
+ {
390
+ "epoch": 0.14719657433427003,
391
+ "grad_norm": 22.625,
392
+ "learning_rate": 8.5280342566573e-06,
393
+ "loss": 0.8093,
394
+ "step": 1100
395
+ },
396
+ {
397
+ "epoch": 0.1498728756858022,
398
+ "grad_norm": 45.0,
399
+ "learning_rate": 8.501271243141978e-06,
400
+ "loss": 0.8385,
401
+ "step": 1120
402
+ },
403
+ {
404
+ "epoch": 0.1525491770373344,
405
+ "grad_norm": 12.5625,
406
+ "learning_rate": 8.474508229626656e-06,
407
+ "loss": 0.8014,
408
+ "step": 1140
409
+ },
410
+ {
411
+ "epoch": 0.15522547838886658,
412
+ "grad_norm": 12.625,
413
+ "learning_rate": 8.447745216111334e-06,
414
+ "loss": 0.8474,
415
+ "step": 1160
416
+ },
417
+ {
418
+ "epoch": 0.15790177974039876,
419
+ "grad_norm": 11.875,
420
+ "learning_rate": 8.420982202596014e-06,
421
+ "loss": 0.8009,
422
+ "step": 1180
423
+ },
424
+ {
425
+ "epoch": 0.16057808109193095,
426
+ "grad_norm": 20.625,
427
+ "learning_rate": 8.394219189080692e-06,
428
+ "loss": 0.8726,
429
+ "step": 1200
430
+ },
431
+ {
432
+ "epoch": 0.16325438244346313,
433
+ "grad_norm": 11.9375,
434
+ "learning_rate": 8.36745617556537e-06,
435
+ "loss": 0.751,
436
+ "step": 1220
437
+ },
438
+ {
439
+ "epoch": 0.16593068379499532,
440
+ "grad_norm": 8.4375,
441
+ "learning_rate": 8.340693162050048e-06,
442
+ "loss": 0.729,
443
+ "step": 1240
444
+ },
445
+ {
446
+ "epoch": 0.1686069851465275,
447
+ "grad_norm": 14.375,
448
+ "learning_rate": 8.313930148534726e-06,
449
+ "loss": 0.7642,
450
+ "step": 1260
451
+ },
452
+ {
453
+ "epoch": 0.17128328649805968,
454
+ "grad_norm": 9.4375,
455
+ "learning_rate": 8.287167135019404e-06,
456
+ "loss": 0.799,
457
+ "step": 1280
458
+ },
459
+ {
460
+ "epoch": 0.17395958784959187,
461
+ "grad_norm": 17.375,
462
+ "learning_rate": 8.260404121504082e-06,
463
+ "loss": 0.7899,
464
+ "step": 1300
465
+ },
466
+ {
467
+ "epoch": 0.17663588920112405,
468
+ "grad_norm": 8.25,
469
+ "learning_rate": 8.23364110798876e-06,
470
+ "loss": 0.8224,
471
+ "step": 1320
472
+ },
473
+ {
474
+ "epoch": 0.17931219055265624,
475
+ "grad_norm": 17.25,
476
+ "learning_rate": 8.206878094473438e-06,
477
+ "loss": 0.7836,
478
+ "step": 1340
479
+ },
480
+ {
481
+ "epoch": 0.18198849190418842,
482
+ "grad_norm": 11.9375,
483
+ "learning_rate": 8.180115080958116e-06,
484
+ "loss": 0.8547,
485
+ "step": 1360
486
+ },
487
+ {
488
+ "epoch": 0.1846647932557206,
489
+ "grad_norm": 11.8125,
490
+ "learning_rate": 8.153352067442795e-06,
491
+ "loss": 0.8314,
492
+ "step": 1380
493
+ },
494
+ {
495
+ "epoch": 0.1873410946072528,
496
+ "grad_norm": 12.25,
497
+ "learning_rate": 8.126589053927473e-06,
498
+ "loss": 0.7372,
499
+ "step": 1400
500
+ },
501
+ {
502
+ "epoch": 0.19001739595878495,
503
+ "grad_norm": 17.625,
504
+ "learning_rate": 8.099826040412151e-06,
505
+ "loss": 0.7241,
506
+ "step": 1420
507
+ },
508
+ {
509
+ "epoch": 0.19269369731031713,
510
+ "grad_norm": 13.25,
511
+ "learning_rate": 8.07306302689683e-06,
512
+ "loss": 0.75,
513
+ "step": 1440
514
+ },
515
+ {
516
+ "epoch": 0.19536999866184931,
517
+ "grad_norm": 9.3125,
518
+ "learning_rate": 8.046300013381507e-06,
519
+ "loss": 0.7802,
520
+ "step": 1460
521
+ },
522
+ {
523
+ "epoch": 0.1980463000133815,
524
+ "grad_norm": 9.1875,
525
+ "learning_rate": 8.019536999866185e-06,
526
+ "loss": 0.8704,
527
+ "step": 1480
528
+ },
529
+ {
530
+ "epoch": 0.20072260136491368,
531
+ "grad_norm": 6.15625,
532
+ "learning_rate": 7.992773986350863e-06,
533
+ "loss": 0.7438,
534
+ "step": 1500
535
+ },
536
+ {
537
+ "epoch": 0.20339890271644587,
538
+ "grad_norm": 9.125,
539
+ "learning_rate": 7.966010972835541e-06,
540
+ "loss": 0.7446,
541
+ "step": 1520
542
+ },
543
+ {
544
+ "epoch": 0.20607520406797805,
545
+ "grad_norm": 21.25,
546
+ "learning_rate": 7.93924795932022e-06,
547
+ "loss": 0.6814,
548
+ "step": 1540
549
+ },
550
+ {
551
+ "epoch": 0.20875150541951024,
552
+ "grad_norm": 6.65625,
553
+ "learning_rate": 7.912484945804897e-06,
554
+ "loss": 0.7361,
555
+ "step": 1560
556
+ },
557
+ {
558
+ "epoch": 0.21142780677104242,
559
+ "grad_norm": 13.125,
560
+ "learning_rate": 7.885721932289577e-06,
561
+ "loss": 0.67,
562
+ "step": 1580
563
+ },
564
+ {
565
+ "epoch": 0.2141041081225746,
566
+ "grad_norm": 15.6875,
567
+ "learning_rate": 7.858958918774255e-06,
568
+ "loss": 0.7145,
569
+ "step": 1600
570
+ },
571
+ {
572
+ "epoch": 0.2167804094741068,
573
+ "grad_norm": 14.1875,
574
+ "learning_rate": 7.832195905258933e-06,
575
+ "loss": 0.818,
576
+ "step": 1620
577
+ },
578
+ {
579
+ "epoch": 0.21945671082563897,
580
+ "grad_norm": 6.53125,
581
+ "learning_rate": 7.805432891743611e-06,
582
+ "loss": 0.7837,
583
+ "step": 1640
584
+ },
585
+ {
586
+ "epoch": 0.22213301217717116,
587
+ "grad_norm": 13.5625,
588
+ "learning_rate": 7.778669878228289e-06,
589
+ "loss": 0.7751,
590
+ "step": 1660
591
+ },
592
+ {
593
+ "epoch": 0.22480931352870334,
594
+ "grad_norm": 15.375,
595
+ "learning_rate": 7.751906864712967e-06,
596
+ "loss": 0.8476,
597
+ "step": 1680
598
+ },
599
+ {
600
+ "epoch": 0.22748561488023553,
601
+ "grad_norm": 7.625,
602
+ "learning_rate": 7.725143851197645e-06,
603
+ "loss": 0.7734,
604
+ "step": 1700
605
+ },
606
+ {
607
+ "epoch": 0.2301619162317677,
608
+ "grad_norm": 14.25,
609
+ "learning_rate": 7.698380837682323e-06,
610
+ "loss": 0.7714,
611
+ "step": 1720
612
+ },
613
+ {
614
+ "epoch": 0.23283821758329987,
615
+ "grad_norm": 18.5,
616
+ "learning_rate": 7.671617824167e-06,
617
+ "loss": 0.7447,
618
+ "step": 1740
619
+ },
620
+ {
621
+ "epoch": 0.23551451893483205,
622
+ "grad_norm": 15.75,
623
+ "learning_rate": 7.644854810651679e-06,
624
+ "loss": 0.7385,
625
+ "step": 1760
626
+ },
627
+ {
628
+ "epoch": 0.23819082028636424,
629
+ "grad_norm": 10.5,
630
+ "learning_rate": 7.618091797136358e-06,
631
+ "loss": 0.7058,
632
+ "step": 1780
633
+ },
634
+ {
635
+ "epoch": 0.24086712163789642,
636
+ "grad_norm": 38.75,
637
+ "learning_rate": 7.591328783621036e-06,
638
+ "loss": 0.737,
639
+ "step": 1800
640
+ },
641
+ {
642
+ "epoch": 0.2435434229894286,
643
+ "grad_norm": 10.5,
644
+ "learning_rate": 7.564565770105714e-06,
645
+ "loss": 0.7831,
646
+ "step": 1820
647
+ },
648
+ {
649
+ "epoch": 0.2462197243409608,
650
+ "grad_norm": 21.0,
651
+ "learning_rate": 7.5378027565903925e-06,
652
+ "loss": 0.8369,
653
+ "step": 1840
654
+ },
655
+ {
656
+ "epoch": 0.24889602569249297,
657
+ "grad_norm": 20.5,
658
+ "learning_rate": 7.5110397430750704e-06,
659
+ "loss": 0.7846,
660
+ "step": 1860
661
+ },
662
+ {
663
+ "epoch": 0.25157232704402516,
664
+ "grad_norm": 6.375,
665
+ "learning_rate": 7.484276729559748e-06,
666
+ "loss": 0.8011,
667
+ "step": 1880
668
+ },
669
+ {
670
+ "epoch": 0.25424862839555734,
671
+ "grad_norm": 9.1875,
672
+ "learning_rate": 7.457513716044428e-06,
673
+ "loss": 0.7536,
674
+ "step": 1900
675
+ },
676
+ {
677
+ "epoch": 0.2569249297470895,
678
+ "grad_norm": 9.0,
679
+ "learning_rate": 7.430750702529106e-06,
680
+ "loss": 0.7622,
681
+ "step": 1920
682
+ },
683
+ {
684
+ "epoch": 0.2596012310986217,
685
+ "grad_norm": 7.875,
686
+ "learning_rate": 7.403987689013784e-06,
687
+ "loss": 0.7059,
688
+ "step": 1940
689
+ },
690
+ {
691
+ "epoch": 0.2622775324501539,
692
+ "grad_norm": 7.46875,
693
+ "learning_rate": 7.377224675498462e-06,
694
+ "loss": 0.7635,
695
+ "step": 1960
696
+ },
697
+ {
698
+ "epoch": 0.2649538338016861,
699
+ "grad_norm": 6.21875,
700
+ "learning_rate": 7.35046166198314e-06,
701
+ "loss": 0.7693,
702
+ "step": 1980
703
+ },
704
+ {
705
+ "epoch": 0.26763013515321826,
706
+ "grad_norm": 9.375,
707
+ "learning_rate": 7.323698648467819e-06,
708
+ "loss": 0.7812,
709
+ "step": 2000
710
+ },
711
+ {
712
+ "epoch": 0.27030643650475045,
713
+ "grad_norm": 13.1875,
714
+ "learning_rate": 7.296935634952497e-06,
715
+ "loss": 0.7372,
716
+ "step": 2020
717
+ },
718
+ {
719
+ "epoch": 0.27298273785628263,
720
+ "grad_norm": 16.75,
721
+ "learning_rate": 7.270172621437175e-06,
722
+ "loss": 0.8489,
723
+ "step": 2040
724
+ },
725
+ {
726
+ "epoch": 0.2756590392078148,
727
+ "grad_norm": 5.40625,
728
+ "learning_rate": 7.243409607921853e-06,
729
+ "loss": 0.6996,
730
+ "step": 2060
731
+ },
732
+ {
733
+ "epoch": 0.278335340559347,
734
+ "grad_norm": 10.875,
735
+ "learning_rate": 7.216646594406531e-06,
736
+ "loss": 0.7596,
737
+ "step": 2080
738
+ },
739
+ {
740
+ "epoch": 0.2810116419108792,
741
+ "grad_norm": 33.5,
742
+ "learning_rate": 7.18988358089121e-06,
743
+ "loss": 0.7819,
744
+ "step": 2100
745
+ },
746
+ {
747
+ "epoch": 0.28368794326241137,
748
+ "grad_norm": 11.4375,
749
+ "learning_rate": 7.163120567375888e-06,
750
+ "loss": 0.8196,
751
+ "step": 2120
752
+ },
753
+ {
754
+ "epoch": 0.28636424461394355,
755
+ "grad_norm": 7.78125,
756
+ "learning_rate": 7.136357553860566e-06,
757
+ "loss": 0.7454,
758
+ "step": 2140
759
+ },
760
+ {
761
+ "epoch": 0.28904054596547574,
762
+ "grad_norm": 14.5625,
763
+ "learning_rate": 7.109594540345244e-06,
764
+ "loss": 0.7306,
765
+ "step": 2160
766
+ },
767
+ {
768
+ "epoch": 0.2917168473170079,
769
+ "grad_norm": 9.5,
770
+ "learning_rate": 7.082831526829922e-06,
771
+ "loss": 0.7076,
772
+ "step": 2180
773
+ },
774
+ {
775
+ "epoch": 0.29439314866854005,
776
+ "grad_norm": 12.875,
777
+ "learning_rate": 7.0560685133146004e-06,
778
+ "loss": 0.7679,
779
+ "step": 2200
780
+ },
781
+ {
782
+ "epoch": 0.29706945002007223,
783
+ "grad_norm": 11.0,
784
+ "learning_rate": 7.029305499799278e-06,
785
+ "loss": 0.6691,
786
+ "step": 2220
787
+ },
788
+ {
789
+ "epoch": 0.2997457513716044,
790
+ "grad_norm": 13.4375,
791
+ "learning_rate": 7.002542486283956e-06,
792
+ "loss": 0.7002,
793
+ "step": 2240
794
+ },
795
+ {
796
+ "epoch": 0.3024220527231366,
797
+ "grad_norm": 13.25,
798
+ "learning_rate": 6.975779472768634e-06,
799
+ "loss": 0.8657,
800
+ "step": 2260
801
+ },
802
+ {
803
+ "epoch": 0.3050983540746688,
804
+ "grad_norm": 16.25,
805
+ "learning_rate": 6.949016459253312e-06,
806
+ "loss": 0.6808,
807
+ "step": 2280
808
+ },
809
+ {
810
+ "epoch": 0.30777465542620097,
811
+ "grad_norm": 11.75,
812
+ "learning_rate": 6.922253445737991e-06,
813
+ "loss": 0.7294,
814
+ "step": 2300
815
+ },
816
+ {
817
+ "epoch": 0.31045095677773316,
818
+ "grad_norm": 12.5,
819
+ "learning_rate": 6.895490432222669e-06,
820
+ "loss": 0.7018,
821
+ "step": 2320
822
+ },
823
+ {
824
+ "epoch": 0.31312725812926534,
825
+ "grad_norm": 11.6875,
826
+ "learning_rate": 6.868727418707347e-06,
827
+ "loss": 0.6812,
828
+ "step": 2340
829
+ },
830
+ {
831
+ "epoch": 0.3158035594807975,
832
+ "grad_norm": 7.625,
833
+ "learning_rate": 6.841964405192025e-06,
834
+ "loss": 0.7062,
835
+ "step": 2360
836
+ },
837
+ {
838
+ "epoch": 0.3184798608323297,
839
+ "grad_norm": 18.125,
840
+ "learning_rate": 6.815201391676703e-06,
841
+ "loss": 0.7192,
842
+ "step": 2380
843
+ },
844
+ {
845
+ "epoch": 0.3211561621838619,
846
+ "grad_norm": 12.75,
847
+ "learning_rate": 6.788438378161382e-06,
848
+ "loss": 0.6406,
849
+ "step": 2400
850
+ },
851
+ {
852
+ "epoch": 0.3238324635353941,
853
+ "grad_norm": 6.75,
854
+ "learning_rate": 6.76167536464606e-06,
855
+ "loss": 0.7128,
856
+ "step": 2420
857
+ },
858
+ {
859
+ "epoch": 0.32650876488692626,
860
+ "grad_norm": 15.6875,
861
+ "learning_rate": 6.734912351130738e-06,
862
+ "loss": 0.6342,
863
+ "step": 2440
864
+ },
865
+ {
866
+ "epoch": 0.32918506623845845,
867
+ "grad_norm": 14.0,
868
+ "learning_rate": 6.708149337615416e-06,
869
+ "loss": 0.7335,
870
+ "step": 2460
871
+ },
872
+ {
873
+ "epoch": 0.33186136758999063,
874
+ "grad_norm": 13.0,
875
+ "learning_rate": 6.681386324100094e-06,
876
+ "loss": 0.629,
877
+ "step": 2480
878
+ },
879
+ {
880
+ "epoch": 0.3345376689415228,
881
+ "grad_norm": 10.3125,
882
+ "learning_rate": 6.654623310584773e-06,
883
+ "loss": 0.7736,
884
+ "step": 2500
885
+ },
886
+ {
887
+ "epoch": 0.337213970293055,
888
+ "grad_norm": 7.84375,
889
+ "learning_rate": 6.627860297069451e-06,
890
+ "loss": 0.826,
891
+ "step": 2520
892
+ },
893
+ {
894
+ "epoch": 0.3398902716445872,
895
+ "grad_norm": 7.09375,
896
+ "learning_rate": 6.601097283554129e-06,
897
+ "loss": 0.6452,
898
+ "step": 2540
899
+ },
900
+ {
901
+ "epoch": 0.34256657299611937,
902
+ "grad_norm": 6.125,
903
+ "learning_rate": 6.574334270038807e-06,
904
+ "loss": 0.705,
905
+ "step": 2560
906
+ },
907
+ {
908
+ "epoch": 0.34524287434765155,
909
+ "grad_norm": 65.0,
910
+ "learning_rate": 6.547571256523485e-06,
911
+ "loss": 0.6926,
912
+ "step": 2580
913
+ },
914
+ {
915
+ "epoch": 0.34791917569918374,
916
+ "grad_norm": 7.125,
917
+ "learning_rate": 6.5208082430081635e-06,
918
+ "loss": 0.6877,
919
+ "step": 2600
920
+ },
921
+ {
922
+ "epoch": 0.3505954770507159,
923
+ "grad_norm": 12.4375,
924
+ "learning_rate": 6.4940452294928415e-06,
925
+ "loss": 0.8122,
926
+ "step": 2620
927
+ },
928
+ {
929
+ "epoch": 0.3532717784022481,
930
+ "grad_norm": 5.75,
931
+ "learning_rate": 6.4672822159775195e-06,
932
+ "loss": 0.7015,
933
+ "step": 2640
934
+ },
935
+ {
936
+ "epoch": 0.3559480797537803,
937
+ "grad_norm": 9.1875,
938
+ "learning_rate": 6.4405192024621975e-06,
939
+ "loss": 0.7502,
940
+ "step": 2660
941
+ },
942
+ {
943
+ "epoch": 0.3586243811053125,
944
+ "grad_norm": 4.6875,
945
+ "learning_rate": 6.4137561889468755e-06,
946
+ "loss": 0.6114,
947
+ "step": 2680
948
+ },
949
+ {
950
+ "epoch": 0.36130068245684466,
951
+ "grad_norm": 12.0,
952
+ "learning_rate": 6.386993175431554e-06,
953
+ "loss": 0.6149,
954
+ "step": 2700
955
+ },
956
+ {
957
+ "epoch": 0.36397698380837684,
958
+ "grad_norm": 7.78125,
959
+ "learning_rate": 6.360230161916232e-06,
960
+ "loss": 0.6908,
961
+ "step": 2720
962
+ },
963
+ {
964
+ "epoch": 0.366653285159909,
965
+ "grad_norm": 7.65625,
966
+ "learning_rate": 6.33346714840091e-06,
967
+ "loss": 0.7734,
968
+ "step": 2740
969
+ },
970
+ {
971
+ "epoch": 0.3693295865114412,
972
+ "grad_norm": 12.0,
973
+ "learning_rate": 6.306704134885588e-06,
974
+ "loss": 0.7201,
975
+ "step": 2760
976
+ },
977
+ {
978
+ "epoch": 0.3720058878629734,
979
+ "grad_norm": 17.875,
980
+ "learning_rate": 6.279941121370266e-06,
981
+ "loss": 0.7441,
982
+ "step": 2780
983
+ },
984
+ {
985
+ "epoch": 0.3746821892145056,
986
+ "grad_norm": 18.375,
987
+ "learning_rate": 6.253178107854945e-06,
988
+ "loss": 0.6822,
989
+ "step": 2800
990
+ },
991
+ {
992
+ "epoch": 0.37735849056603776,
993
+ "grad_norm": 10.125,
994
+ "learning_rate": 6.226415094339623e-06,
995
+ "loss": 0.758,
996
+ "step": 2820
997
+ },
998
+ {
999
+ "epoch": 0.3800347919175699,
1000
+ "grad_norm": 15.125,
1001
+ "learning_rate": 6.199652080824301e-06,
1002
+ "loss": 0.6623,
1003
+ "step": 2840
1004
+ },
1005
+ {
1006
+ "epoch": 0.3827110932691021,
1007
+ "grad_norm": 8.5,
1008
+ "learning_rate": 6.172889067308979e-06,
1009
+ "loss": 0.6744,
1010
+ "step": 2860
1011
+ },
1012
+ {
1013
+ "epoch": 0.38538739462063426,
1014
+ "grad_norm": 10.8125,
1015
+ "learning_rate": 6.146126053793657e-06,
1016
+ "loss": 0.6643,
1017
+ "step": 2880
1018
+ },
1019
+ {
1020
+ "epoch": 0.38806369597216644,
1021
+ "grad_norm": 11.5625,
1022
+ "learning_rate": 6.119363040278336e-06,
1023
+ "loss": 0.7278,
1024
+ "step": 2900
1025
+ },
1026
+ {
1027
+ "epoch": 0.39073999732369863,
1028
+ "grad_norm": 6.65625,
1029
+ "learning_rate": 6.092600026763014e-06,
1030
+ "loss": 0.6364,
1031
+ "step": 2920
1032
+ },
1033
+ {
1034
+ "epoch": 0.3934162986752308,
1035
+ "grad_norm": 8.75,
1036
+ "learning_rate": 6.065837013247692e-06,
1037
+ "loss": 0.7175,
1038
+ "step": 2940
1039
+ },
1040
+ {
1041
+ "epoch": 0.396092600026763,
1042
+ "grad_norm": 10.25,
1043
+ "learning_rate": 6.03907399973237e-06,
1044
+ "loss": 0.6905,
1045
+ "step": 2960
1046
+ },
1047
+ {
1048
+ "epoch": 0.3987689013782952,
1049
+ "grad_norm": 14.0625,
1050
+ "learning_rate": 6.012310986217048e-06,
1051
+ "loss": 0.599,
1052
+ "step": 2980
1053
+ },
1054
+ {
1055
+ "epoch": 0.40144520272982737,
1056
+ "grad_norm": 9.6875,
1057
+ "learning_rate": 5.985547972701727e-06,
1058
+ "loss": 0.7629,
1059
+ "step": 3000
1060
+ },
1061
+ {
1062
+ "epoch": 0.40412150408135955,
1063
+ "grad_norm": 19.125,
1064
+ "learning_rate": 5.958784959186405e-06,
1065
+ "loss": 0.7624,
1066
+ "step": 3020
1067
+ },
1068
+ {
1069
+ "epoch": 0.40679780543289173,
1070
+ "grad_norm": 9.0625,
1071
+ "learning_rate": 5.932021945671083e-06,
1072
+ "loss": 0.7122,
1073
+ "step": 3040
1074
+ },
1075
+ {
1076
+ "epoch": 0.4094741067844239,
1077
+ "grad_norm": 12.0625,
1078
+ "learning_rate": 5.905258932155761e-06,
1079
+ "loss": 0.711,
1080
+ "step": 3060
1081
+ },
1082
+ {
1083
+ "epoch": 0.4121504081359561,
1084
+ "grad_norm": 8.4375,
1085
+ "learning_rate": 5.878495918640439e-06,
1086
+ "loss": 0.685,
1087
+ "step": 3080
1088
+ },
1089
+ {
1090
+ "epoch": 0.4148267094874883,
1091
+ "grad_norm": 23.5,
1092
+ "learning_rate": 5.851732905125117e-06,
1093
+ "loss": 0.7422,
1094
+ "step": 3100
1095
+ },
1096
+ {
1097
+ "epoch": 0.41750301083902047,
1098
+ "grad_norm": 8.9375,
1099
+ "learning_rate": 5.824969891609795e-06,
1100
+ "loss": 0.7546,
1101
+ "step": 3120
1102
+ },
1103
+ {
1104
+ "epoch": 0.42017931219055266,
1105
+ "grad_norm": 10.375,
1106
+ "learning_rate": 5.798206878094474e-06,
1107
+ "loss": 0.7204,
1108
+ "step": 3140
1109
+ },
1110
+ {
1111
+ "epoch": 0.42285561354208484,
1112
+ "grad_norm": 7.3125,
1113
+ "learning_rate": 5.771443864579152e-06,
1114
+ "loss": 0.7457,
1115
+ "step": 3160
1116
+ },
1117
+ {
1118
+ "epoch": 0.425531914893617,
1119
+ "grad_norm": 10.9375,
1120
+ "learning_rate": 5.744680851063831e-06,
1121
+ "loss": 0.7411,
1122
+ "step": 3180
1123
+ },
1124
+ {
1125
+ "epoch": 0.4282082162451492,
1126
+ "grad_norm": 12.3125,
1127
+ "learning_rate": 5.717917837548509e-06,
1128
+ "loss": 0.7036,
1129
+ "step": 3200
1130
+ },
1131
+ {
1132
+ "epoch": 0.4308845175966814,
1133
+ "grad_norm": 10.0625,
1134
+ "learning_rate": 5.691154824033187e-06,
1135
+ "loss": 0.7014,
1136
+ "step": 3220
1137
+ },
1138
+ {
1139
+ "epoch": 0.4335608189482136,
1140
+ "grad_norm": 6.875,
1141
+ "learning_rate": 5.664391810517865e-06,
1142
+ "loss": 0.73,
1143
+ "step": 3240
1144
+ },
1145
+ {
1146
+ "epoch": 0.43623712029974576,
1147
+ "grad_norm": 8.375,
1148
+ "learning_rate": 5.637628797002543e-06,
1149
+ "loss": 0.6942,
1150
+ "step": 3260
1151
+ },
1152
+ {
1153
+ "epoch": 0.43891342165127795,
1154
+ "grad_norm": 13.125,
1155
+ "learning_rate": 5.610865783487222e-06,
1156
+ "loss": 0.6773,
1157
+ "step": 3280
1158
+ },
1159
+ {
1160
+ "epoch": 0.44158972300281013,
1161
+ "grad_norm": 10.5,
1162
+ "learning_rate": 5.5841027699719e-06,
1163
+ "loss": 0.6452,
1164
+ "step": 3300
1165
+ },
1166
+ {
1167
+ "epoch": 0.4442660243543423,
1168
+ "grad_norm": 7.59375,
1169
+ "learning_rate": 5.557339756456578e-06,
1170
+ "loss": 0.7561,
1171
+ "step": 3320
1172
+ },
1173
+ {
1174
+ "epoch": 0.4469423257058745,
1175
+ "grad_norm": 10.4375,
1176
+ "learning_rate": 5.530576742941256e-06,
1177
+ "loss": 0.7064,
1178
+ "step": 3340
1179
+ },
1180
+ {
1181
+ "epoch": 0.4496186270574067,
1182
+ "grad_norm": 6.90625,
1183
+ "learning_rate": 5.503813729425934e-06,
1184
+ "loss": 0.6614,
1185
+ "step": 3360
1186
+ },
1187
+ {
1188
+ "epoch": 0.45229492840893887,
1189
+ "grad_norm": 11.125,
1190
+ "learning_rate": 5.477050715910613e-06,
1191
+ "loss": 0.7513,
1192
+ "step": 3380
1193
+ },
1194
+ {
1195
+ "epoch": 0.45497122976047105,
1196
+ "grad_norm": 16.875,
1197
+ "learning_rate": 5.450287702395291e-06,
1198
+ "loss": 0.6785,
1199
+ "step": 3400
1200
+ },
1201
+ {
1202
+ "epoch": 0.45764753111200324,
1203
+ "grad_norm": 12.1875,
1204
+ "learning_rate": 5.4235246888799686e-06,
1205
+ "loss": 0.8056,
1206
+ "step": 3420
1207
+ },
1208
+ {
1209
+ "epoch": 0.4603238324635354,
1210
+ "grad_norm": 19.125,
1211
+ "learning_rate": 5.3967616753646466e-06,
1212
+ "loss": 0.7518,
1213
+ "step": 3440
1214
+ },
1215
+ {
1216
+ "epoch": 0.46300013381506755,
1217
+ "grad_norm": 9.8125,
1218
+ "learning_rate": 5.3699986618493245e-06,
1219
+ "loss": 0.6852,
1220
+ "step": 3460
1221
+ },
1222
+ {
1223
+ "epoch": 0.46567643516659973,
1224
+ "grad_norm": 7.59375,
1225
+ "learning_rate": 5.343235648334003e-06,
1226
+ "loss": 0.7327,
1227
+ "step": 3480
1228
+ },
1229
+ {
1230
+ "epoch": 0.4683527365181319,
1231
+ "grad_norm": 19.0,
1232
+ "learning_rate": 5.316472634818681e-06,
1233
+ "loss": 0.7463,
1234
+ "step": 3500
1235
+ },
1236
+ {
1237
+ "epoch": 0.4710290378696641,
1238
+ "grad_norm": 8.6875,
1239
+ "learning_rate": 5.289709621303359e-06,
1240
+ "loss": 0.6091,
1241
+ "step": 3520
1242
+ },
1243
+ {
1244
+ "epoch": 0.4737053392211963,
1245
+ "grad_norm": 14.0,
1246
+ "learning_rate": 5.262946607788037e-06,
1247
+ "loss": 0.6896,
1248
+ "step": 3540
1249
+ },
1250
+ {
1251
+ "epoch": 0.47638164057272847,
1252
+ "grad_norm": 8.5,
1253
+ "learning_rate": 5.236183594272715e-06,
1254
+ "loss": 0.7641,
1255
+ "step": 3560
1256
+ },
1257
+ {
1258
+ "epoch": 0.47905794192426066,
1259
+ "grad_norm": 12.3125,
1260
+ "learning_rate": 5.209420580757394e-06,
1261
+ "loss": 0.6582,
1262
+ "step": 3580
1263
+ },
1264
+ {
1265
+ "epoch": 0.48173424327579284,
1266
+ "grad_norm": 11.0625,
1267
+ "learning_rate": 5.182657567242072e-06,
1268
+ "loss": 0.7291,
1269
+ "step": 3600
1270
+ },
1271
+ {
1272
+ "epoch": 0.484410544627325,
1273
+ "grad_norm": 12.9375,
1274
+ "learning_rate": 5.15589455372675e-06,
1275
+ "loss": 0.7209,
1276
+ "step": 3620
1277
+ },
1278
+ {
1279
+ "epoch": 0.4870868459788572,
1280
+ "grad_norm": 14.625,
1281
+ "learning_rate": 5.129131540211428e-06,
1282
+ "loss": 0.7259,
1283
+ "step": 3640
1284
+ },
1285
+ {
1286
+ "epoch": 0.4897631473303894,
1287
+ "grad_norm": 9.4375,
1288
+ "learning_rate": 5.102368526696106e-06,
1289
+ "loss": 0.7259,
1290
+ "step": 3660
1291
+ },
1292
+ {
1293
+ "epoch": 0.4924394486819216,
1294
+ "grad_norm": 7.53125,
1295
+ "learning_rate": 5.075605513180785e-06,
1296
+ "loss": 0.6947,
1297
+ "step": 3680
1298
+ },
1299
+ {
1300
+ "epoch": 0.49511575003345376,
1301
+ "grad_norm": 6.59375,
1302
+ "learning_rate": 5.048842499665463e-06,
1303
+ "loss": 0.7026,
1304
+ "step": 3700
1305
+ },
1306
+ {
1307
+ "epoch": 0.49779205138498595,
1308
+ "grad_norm": 22.125,
1309
+ "learning_rate": 5.022079486150141e-06,
1310
+ "loss": 0.7332,
1311
+ "step": 3720
1312
+ },
1313
+ {
1314
+ "epoch": 0.5004683527365181,
1315
+ "grad_norm": 9.625,
1316
+ "learning_rate": 4.995316472634819e-06,
1317
+ "loss": 0.7487,
1318
+ "step": 3740
1319
+ },
1320
+ {
1321
+ "epoch": 0.5031446540880503,
1322
+ "grad_norm": 8.9375,
1323
+ "learning_rate": 4.968553459119497e-06,
1324
+ "loss": 0.6364,
1325
+ "step": 3760
1326
+ },
1327
+ {
1328
+ "epoch": 0.5058209554395825,
1329
+ "grad_norm": 10.125,
1330
+ "learning_rate": 4.941790445604176e-06,
1331
+ "loss": 0.7261,
1332
+ "step": 3780
1333
+ },
1334
+ {
1335
+ "epoch": 0.5084972567911147,
1336
+ "grad_norm": 19.0,
1337
+ "learning_rate": 4.915027432088854e-06,
1338
+ "loss": 0.725,
1339
+ "step": 3800
1340
+ },
1341
+ {
1342
+ "epoch": 0.5111735581426469,
1343
+ "grad_norm": 11.6875,
1344
+ "learning_rate": 4.888264418573532e-06,
1345
+ "loss": 0.6957,
1346
+ "step": 3820
1347
+ },
1348
+ {
1349
+ "epoch": 0.513849859494179,
1350
+ "grad_norm": 9.75,
1351
+ "learning_rate": 4.86150140505821e-06,
1352
+ "loss": 0.6555,
1353
+ "step": 3840
1354
+ },
1355
+ {
1356
+ "epoch": 0.5165261608457112,
1357
+ "grad_norm": 8.875,
1358
+ "learning_rate": 4.834738391542888e-06,
1359
+ "loss": 0.7902,
1360
+ "step": 3860
1361
+ },
1362
+ {
1363
+ "epoch": 0.5192024621972434,
1364
+ "grad_norm": 10.5625,
1365
+ "learning_rate": 4.8079753780275665e-06,
1366
+ "loss": 0.7535,
1367
+ "step": 3880
1368
+ },
1369
+ {
1370
+ "epoch": 0.5218787635487756,
1371
+ "grad_norm": 6.71875,
1372
+ "learning_rate": 4.7812123645122445e-06,
1373
+ "loss": 0.84,
1374
+ "step": 3900
1375
+ },
1376
+ {
1377
+ "epoch": 0.5245550649003078,
1378
+ "grad_norm": 8.3125,
1379
+ "learning_rate": 4.7544493509969225e-06,
1380
+ "loss": 0.6911,
1381
+ "step": 3920
1382
+ },
1383
+ {
1384
+ "epoch": 0.52723136625184,
1385
+ "grad_norm": 9.4375,
1386
+ "learning_rate": 4.7276863374816004e-06,
1387
+ "loss": 0.7435,
1388
+ "step": 3940
1389
+ },
1390
+ {
1391
+ "epoch": 0.5299076676033722,
1392
+ "grad_norm": 12.875,
1393
+ "learning_rate": 4.7009233239662784e-06,
1394
+ "loss": 0.7176,
1395
+ "step": 3960
1396
+ },
1397
+ {
1398
+ "epoch": 0.5325839689549043,
1399
+ "grad_norm": 6.6875,
1400
+ "learning_rate": 4.674160310450957e-06,
1401
+ "loss": 0.6389,
1402
+ "step": 3980
1403
+ },
1404
+ {
1405
+ "epoch": 0.5352602703064365,
1406
+ "grad_norm": 17.0,
1407
+ "learning_rate": 4.647397296935635e-06,
1408
+ "loss": 0.6902,
1409
+ "step": 4000
1410
+ },
1411
+ {
1412
+ "epoch": 0.5379365716579687,
1413
+ "grad_norm": 15.5,
1414
+ "learning_rate": 4.620634283420313e-06,
1415
+ "loss": 0.7835,
1416
+ "step": 4020
1417
+ },
1418
+ {
1419
+ "epoch": 0.5406128730095009,
1420
+ "grad_norm": 14.0625,
1421
+ "learning_rate": 4.593871269904991e-06,
1422
+ "loss": 0.7667,
1423
+ "step": 4040
1424
+ },
1425
+ {
1426
+ "epoch": 0.5432891743610331,
1427
+ "grad_norm": 15.5625,
1428
+ "learning_rate": 4.567108256389669e-06,
1429
+ "loss": 0.7173,
1430
+ "step": 4060
1431
+ },
1432
+ {
1433
+ "epoch": 0.5459654757125653,
1434
+ "grad_norm": 7.6875,
1435
+ "learning_rate": 4.540345242874348e-06,
1436
+ "loss": 0.6364,
1437
+ "step": 4080
1438
+ },
1439
+ {
1440
+ "epoch": 0.5486417770640974,
1441
+ "grad_norm": 8.0625,
1442
+ "learning_rate": 4.513582229359027e-06,
1443
+ "loss": 0.6644,
1444
+ "step": 4100
1445
+ },
1446
+ {
1447
+ "epoch": 0.5513180784156296,
1448
+ "grad_norm": 8.6875,
1449
+ "learning_rate": 4.486819215843705e-06,
1450
+ "loss": 0.6862,
1451
+ "step": 4120
1452
+ },
1453
+ {
1454
+ "epoch": 0.5539943797671618,
1455
+ "grad_norm": 16.875,
1456
+ "learning_rate": 4.460056202328383e-06,
1457
+ "loss": 0.6885,
1458
+ "step": 4140
1459
+ },
1460
+ {
1461
+ "epoch": 0.556670681118694,
1462
+ "grad_norm": 8.125,
1463
+ "learning_rate": 4.433293188813061e-06,
1464
+ "loss": 0.7585,
1465
+ "step": 4160
1466
+ },
1467
+ {
1468
+ "epoch": 0.5593469824702262,
1469
+ "grad_norm": 13.375,
1470
+ "learning_rate": 4.406530175297739e-06,
1471
+ "loss": 0.7361,
1472
+ "step": 4180
1473
+ },
1474
+ {
1475
+ "epoch": 0.5620232838217584,
1476
+ "grad_norm": 9.875,
1477
+ "learning_rate": 4.379767161782418e-06,
1478
+ "loss": 0.6836,
1479
+ "step": 4200
1480
+ },
1481
+ {
1482
+ "epoch": 0.5646995851732906,
1483
+ "grad_norm": 10.75,
1484
+ "learning_rate": 4.353004148267096e-06,
1485
+ "loss": 0.7238,
1486
+ "step": 4220
1487
+ },
1488
+ {
1489
+ "epoch": 0.5673758865248227,
1490
+ "grad_norm": 10.5625,
1491
+ "learning_rate": 4.326241134751774e-06,
1492
+ "loss": 0.7354,
1493
+ "step": 4240
1494
+ },
1495
+ {
1496
+ "epoch": 0.5700521878763549,
1497
+ "grad_norm": 8.125,
1498
+ "learning_rate": 4.299478121236452e-06,
1499
+ "loss": 0.7141,
1500
+ "step": 4260
1501
+ },
1502
+ {
1503
+ "epoch": 0.5727284892278871,
1504
+ "grad_norm": 9.9375,
1505
+ "learning_rate": 4.27271510772113e-06,
1506
+ "loss": 0.7113,
1507
+ "step": 4280
1508
+ },
1509
+ {
1510
+ "epoch": 0.5754047905794193,
1511
+ "grad_norm": 13.75,
1512
+ "learning_rate": 4.245952094205808e-06,
1513
+ "loss": 0.7338,
1514
+ "step": 4300
1515
+ },
1516
+ {
1517
+ "epoch": 0.5780810919309515,
1518
+ "grad_norm": 14.375,
1519
+ "learning_rate": 4.219189080690486e-06,
1520
+ "loss": 0.7292,
1521
+ "step": 4320
1522
+ },
1523
+ {
1524
+ "epoch": 0.5807573932824837,
1525
+ "grad_norm": 10.3125,
1526
+ "learning_rate": 4.192426067175164e-06,
1527
+ "loss": 0.6675,
1528
+ "step": 4340
1529
+ },
1530
+ {
1531
+ "epoch": 0.5834336946340158,
1532
+ "grad_norm": 27.375,
1533
+ "learning_rate": 4.165663053659842e-06,
1534
+ "loss": 0.6879,
1535
+ "step": 4360
1536
+ },
1537
+ {
1538
+ "epoch": 0.586109995985548,
1539
+ "grad_norm": 11.8125,
1540
+ "learning_rate": 4.13890004014452e-06,
1541
+ "loss": 0.5935,
1542
+ "step": 4380
1543
+ },
1544
+ {
1545
+ "epoch": 0.5887862973370801,
1546
+ "grad_norm": 7.46875,
1547
+ "learning_rate": 4.112137026629199e-06,
1548
+ "loss": 0.7692,
1549
+ "step": 4400
1550
+ },
1551
+ {
1552
+ "epoch": 0.5914625986886123,
1553
+ "grad_norm": 13.875,
1554
+ "learning_rate": 4.085374013113877e-06,
1555
+ "loss": 0.7598,
1556
+ "step": 4420
1557
+ },
1558
+ {
1559
+ "epoch": 0.5941389000401445,
1560
+ "grad_norm": 14.6875,
1561
+ "learning_rate": 4.058610999598555e-06,
1562
+ "loss": 0.63,
1563
+ "step": 4440
1564
+ },
1565
+ {
1566
+ "epoch": 0.5968152013916767,
1567
+ "grad_norm": 17.75,
1568
+ "learning_rate": 4.031847986083233e-06,
1569
+ "loss": 0.7506,
1570
+ "step": 4460
1571
+ },
1572
+ {
1573
+ "epoch": 0.5994915027432088,
1574
+ "grad_norm": 9.625,
1575
+ "learning_rate": 4.005084972567911e-06,
1576
+ "loss": 0.6189,
1577
+ "step": 4480
1578
+ },
1579
+ {
1580
+ "epoch": 0.602167804094741,
1581
+ "grad_norm": 8.875,
1582
+ "learning_rate": 3.97832195905259e-06,
1583
+ "loss": 0.7193,
1584
+ "step": 4500
1585
+ },
1586
+ {
1587
+ "epoch": 0.6048441054462732,
1588
+ "grad_norm": 12.8125,
1589
+ "learning_rate": 3.951558945537268e-06,
1590
+ "loss": 0.7936,
1591
+ "step": 4520
1592
+ },
1593
+ {
1594
+ "epoch": 0.6075204067978054,
1595
+ "grad_norm": 8.3125,
1596
+ "learning_rate": 3.924795932021946e-06,
1597
+ "loss": 0.7412,
1598
+ "step": 4540
1599
+ },
1600
+ {
1601
+ "epoch": 0.6101967081493376,
1602
+ "grad_norm": 13.75,
1603
+ "learning_rate": 3.898032918506624e-06,
1604
+ "loss": 0.6437,
1605
+ "step": 4560
1606
+ },
1607
+ {
1608
+ "epoch": 0.6128730095008698,
1609
+ "grad_norm": 12.1875,
1610
+ "learning_rate": 3.871269904991302e-06,
1611
+ "loss": 0.6643,
1612
+ "step": 4580
1613
+ },
1614
+ {
1615
+ "epoch": 0.6155493108524019,
1616
+ "grad_norm": 14.5,
1617
+ "learning_rate": 3.844506891475981e-06,
1618
+ "loss": 0.6438,
1619
+ "step": 4600
1620
+ },
1621
+ {
1622
+ "epoch": 0.6182256122039341,
1623
+ "grad_norm": 8.6875,
1624
+ "learning_rate": 3.817743877960659e-06,
1625
+ "loss": 0.6731,
1626
+ "step": 4620
1627
+ },
1628
+ {
1629
+ "epoch": 0.6209019135554663,
1630
+ "grad_norm": 23.0,
1631
+ "learning_rate": 3.7909808644453367e-06,
1632
+ "loss": 0.6498,
1633
+ "step": 4640
1634
+ },
1635
+ {
1636
+ "epoch": 0.6235782149069985,
1637
+ "grad_norm": 7.3125,
1638
+ "learning_rate": 3.7642178509300147e-06,
1639
+ "loss": 0.7402,
1640
+ "step": 4660
1641
+ },
1642
+ {
1643
+ "epoch": 0.6262545162585307,
1644
+ "grad_norm": 16.625,
1645
+ "learning_rate": 3.737454837414693e-06,
1646
+ "loss": 0.7464,
1647
+ "step": 4680
1648
+ },
1649
+ {
1650
+ "epoch": 0.6289308176100629,
1651
+ "grad_norm": 8.5625,
1652
+ "learning_rate": 3.710691823899371e-06,
1653
+ "loss": 0.7294,
1654
+ "step": 4700
1655
+ },
1656
+ {
1657
+ "epoch": 0.631607118961595,
1658
+ "grad_norm": 7.1875,
1659
+ "learning_rate": 3.68392881038405e-06,
1660
+ "loss": 0.7184,
1661
+ "step": 4720
1662
+ },
1663
+ {
1664
+ "epoch": 0.6342834203131272,
1665
+ "grad_norm": 8.0625,
1666
+ "learning_rate": 3.657165796868728e-06,
1667
+ "loss": 0.6361,
1668
+ "step": 4740
1669
+ },
1670
+ {
1671
+ "epoch": 0.6369597216646594,
1672
+ "grad_norm": 10.6875,
1673
+ "learning_rate": 3.6304027833534063e-06,
1674
+ "loss": 0.6732,
1675
+ "step": 4760
1676
+ },
1677
+ {
1678
+ "epoch": 0.6396360230161916,
1679
+ "grad_norm": 10.1875,
1680
+ "learning_rate": 3.6036397698380843e-06,
1681
+ "loss": 0.6091,
1682
+ "step": 4780
1683
+ },
1684
+ {
1685
+ "epoch": 0.6423123243677238,
1686
+ "grad_norm": 10.75,
1687
+ "learning_rate": 3.5768767563227623e-06,
1688
+ "loss": 0.6382,
1689
+ "step": 4800
1690
+ },
1691
+ {
1692
+ "epoch": 0.644988625719256,
1693
+ "grad_norm": 10.6875,
1694
+ "learning_rate": 3.5501137428074407e-06,
1695
+ "loss": 0.7222,
1696
+ "step": 4820
1697
+ },
1698
+ {
1699
+ "epoch": 0.6476649270707882,
1700
+ "grad_norm": 16.5,
1701
+ "learning_rate": 3.5233507292921187e-06,
1702
+ "loss": 0.6297,
1703
+ "step": 4840
1704
+ },
1705
+ {
1706
+ "epoch": 0.6503412284223203,
1707
+ "grad_norm": 12.375,
1708
+ "learning_rate": 3.496587715776797e-06,
1709
+ "loss": 0.709,
1710
+ "step": 4860
1711
+ },
1712
+ {
1713
+ "epoch": 0.6530175297738525,
1714
+ "grad_norm": 15.8125,
1715
+ "learning_rate": 3.469824702261475e-06,
1716
+ "loss": 0.6754,
1717
+ "step": 4880
1718
+ },
1719
+ {
1720
+ "epoch": 0.6556938311253847,
1721
+ "grad_norm": 32.5,
1722
+ "learning_rate": 3.443061688746153e-06,
1723
+ "loss": 0.9194,
1724
+ "step": 4900
1725
+ },
1726
+ {
1727
+ "epoch": 0.6583701324769169,
1728
+ "grad_norm": 7.75,
1729
+ "learning_rate": 3.4162986752308315e-06,
1730
+ "loss": 0.6851,
1731
+ "step": 4920
1732
+ },
1733
+ {
1734
+ "epoch": 0.6610464338284491,
1735
+ "grad_norm": 24.5,
1736
+ "learning_rate": 3.3895356617155095e-06,
1737
+ "loss": 0.728,
1738
+ "step": 4940
1739
+ },
1740
+ {
1741
+ "epoch": 0.6637227351799813,
1742
+ "grad_norm": 13.3125,
1743
+ "learning_rate": 3.362772648200188e-06,
1744
+ "loss": 0.6899,
1745
+ "step": 4960
1746
+ },
1747
+ {
1748
+ "epoch": 0.6663990365315134,
1749
+ "grad_norm": 12.4375,
1750
+ "learning_rate": 3.336009634684866e-06,
1751
+ "loss": 0.714,
1752
+ "step": 4980
1753
+ },
1754
+ {
1755
+ "epoch": 0.6690753378830456,
1756
+ "grad_norm": 11.0625,
1757
+ "learning_rate": 3.309246621169544e-06,
1758
+ "loss": 0.721,
1759
+ "step": 5000
1760
+ },
1761
+ {
1762
+ "epoch": 0.6717516392345778,
1763
+ "grad_norm": 9.3125,
1764
+ "learning_rate": 3.2824836076542223e-06,
1765
+ "loss": 0.7363,
1766
+ "step": 5020
1767
+ },
1768
+ {
1769
+ "epoch": 0.67442794058611,
1770
+ "grad_norm": 3.921875,
1771
+ "learning_rate": 3.2557205941389002e-06,
1772
+ "loss": 0.6483,
1773
+ "step": 5040
1774
+ },
1775
+ {
1776
+ "epoch": 0.6771042419376422,
1777
+ "grad_norm": 6.8125,
1778
+ "learning_rate": 3.2289575806235787e-06,
1779
+ "loss": 0.7267,
1780
+ "step": 5060
1781
+ },
1782
+ {
1783
+ "epoch": 0.6797805432891744,
1784
+ "grad_norm": 8.4375,
1785
+ "learning_rate": 3.2021945671082566e-06,
1786
+ "loss": 0.73,
1787
+ "step": 5080
1788
+ },
1789
+ {
1790
+ "epoch": 0.6824568446407066,
1791
+ "grad_norm": 11.125,
1792
+ "learning_rate": 3.1754315535929346e-06,
1793
+ "loss": 0.7075,
1794
+ "step": 5100
1795
+ },
1796
+ {
1797
+ "epoch": 0.6851331459922387,
1798
+ "grad_norm": 15.0,
1799
+ "learning_rate": 3.148668540077613e-06,
1800
+ "loss": 0.7503,
1801
+ "step": 5120
1802
+ },
1803
+ {
1804
+ "epoch": 0.6878094473437709,
1805
+ "grad_norm": 5.46875,
1806
+ "learning_rate": 3.121905526562291e-06,
1807
+ "loss": 0.6256,
1808
+ "step": 5140
1809
+ },
1810
+ {
1811
+ "epoch": 0.6904857486953031,
1812
+ "grad_norm": 8.875,
1813
+ "learning_rate": 3.0951425130469694e-06,
1814
+ "loss": 0.7156,
1815
+ "step": 5160
1816
+ },
1817
+ {
1818
+ "epoch": 0.6931620500468353,
1819
+ "grad_norm": 9.9375,
1820
+ "learning_rate": 3.0683794995316474e-06,
1821
+ "loss": 0.6339,
1822
+ "step": 5180
1823
+ },
1824
+ {
1825
+ "epoch": 0.6958383513983675,
1826
+ "grad_norm": 6.09375,
1827
+ "learning_rate": 3.0416164860163254e-06,
1828
+ "loss": 0.7028,
1829
+ "step": 5200
1830
+ },
1831
+ {
1832
+ "epoch": 0.6985146527498997,
1833
+ "grad_norm": 7.65625,
1834
+ "learning_rate": 3.014853472501004e-06,
1835
+ "loss": 0.7132,
1836
+ "step": 5220
1837
+ },
1838
+ {
1839
+ "epoch": 0.7011909541014318,
1840
+ "grad_norm": 6.0625,
1841
+ "learning_rate": 2.988090458985682e-06,
1842
+ "loss": 0.6992,
1843
+ "step": 5240
1844
+ },
1845
+ {
1846
+ "epoch": 0.703867255452964,
1847
+ "grad_norm": 7.5625,
1848
+ "learning_rate": 2.96132744547036e-06,
1849
+ "loss": 0.7433,
1850
+ "step": 5260
1851
+ },
1852
+ {
1853
+ "epoch": 0.7065435568044962,
1854
+ "grad_norm": 11.8125,
1855
+ "learning_rate": 2.934564431955038e-06,
1856
+ "loss": 0.6577,
1857
+ "step": 5280
1858
+ },
1859
+ {
1860
+ "epoch": 0.7092198581560284,
1861
+ "grad_norm": 37.0,
1862
+ "learning_rate": 2.907801418439716e-06,
1863
+ "loss": 0.7209,
1864
+ "step": 5300
1865
+ },
1866
+ {
1867
+ "epoch": 0.7118961595075606,
1868
+ "grad_norm": 17.75,
1869
+ "learning_rate": 2.8810384049243946e-06,
1870
+ "loss": 0.6553,
1871
+ "step": 5320
1872
+ },
1873
+ {
1874
+ "epoch": 0.7145724608590928,
1875
+ "grad_norm": 9.8125,
1876
+ "learning_rate": 2.854275391409073e-06,
1877
+ "loss": 0.8166,
1878
+ "step": 5340
1879
+ },
1880
+ {
1881
+ "epoch": 0.717248762210625,
1882
+ "grad_norm": 7.0625,
1883
+ "learning_rate": 2.8275123778937514e-06,
1884
+ "loss": 0.6525,
1885
+ "step": 5360
1886
+ },
1887
+ {
1888
+ "epoch": 0.7199250635621571,
1889
+ "grad_norm": 8.1875,
1890
+ "learning_rate": 2.8007493643784294e-06,
1891
+ "loss": 0.6576,
1892
+ "step": 5380
1893
+ },
1894
+ {
1895
+ "epoch": 0.7226013649136893,
1896
+ "grad_norm": 9.0,
1897
+ "learning_rate": 2.773986350863108e-06,
1898
+ "loss": 0.6565,
1899
+ "step": 5400
1900
+ },
1901
+ {
1902
+ "epoch": 0.7252776662652215,
1903
+ "grad_norm": 12.875,
1904
+ "learning_rate": 2.7472233373477858e-06,
1905
+ "loss": 0.6848,
1906
+ "step": 5420
1907
+ },
1908
+ {
1909
+ "epoch": 0.7279539676167537,
1910
+ "grad_norm": 9.9375,
1911
+ "learning_rate": 2.7204603238324638e-06,
1912
+ "loss": 0.6987,
1913
+ "step": 5440
1914
+ },
1915
+ {
1916
+ "epoch": 0.7306302689682859,
1917
+ "grad_norm": 16.375,
1918
+ "learning_rate": 2.693697310317142e-06,
1919
+ "loss": 0.8492,
1920
+ "step": 5460
1921
+ },
1922
+ {
1923
+ "epoch": 0.733306570319818,
1924
+ "grad_norm": 14.5625,
1925
+ "learning_rate": 2.66693429680182e-06,
1926
+ "loss": 0.6154,
1927
+ "step": 5480
1928
+ },
1929
+ {
1930
+ "epoch": 0.7359828716713502,
1931
+ "grad_norm": 10.3125,
1932
+ "learning_rate": 2.6401712832864986e-06,
1933
+ "loss": 0.6097,
1934
+ "step": 5500
1935
+ },
1936
+ {
1937
+ "epoch": 0.7386591730228824,
1938
+ "grad_norm": 17.5,
1939
+ "learning_rate": 2.6134082697711766e-06,
1940
+ "loss": 0.7904,
1941
+ "step": 5520
1942
+ },
1943
+ {
1944
+ "epoch": 0.7413354743744146,
1945
+ "grad_norm": 10.625,
1946
+ "learning_rate": 2.5866452562558545e-06,
1947
+ "loss": 0.6887,
1948
+ "step": 5540
1949
+ },
1950
+ {
1951
+ "epoch": 0.7440117757259468,
1952
+ "grad_norm": 9.8125,
1953
+ "learning_rate": 2.559882242740533e-06,
1954
+ "loss": 0.6463,
1955
+ "step": 5560
1956
+ },
1957
+ {
1958
+ "epoch": 0.746688077077479,
1959
+ "grad_norm": 12.0625,
1960
+ "learning_rate": 2.533119229225211e-06,
1961
+ "loss": 0.7327,
1962
+ "step": 5580
1963
+ },
1964
+ {
1965
+ "epoch": 0.7493643784290112,
1966
+ "grad_norm": 7.4375,
1967
+ "learning_rate": 2.5063562157098894e-06,
1968
+ "loss": 0.637,
1969
+ "step": 5600
1970
+ },
1971
+ {
1972
+ "epoch": 0.7520406797805433,
1973
+ "grad_norm": 7.78125,
1974
+ "learning_rate": 2.4795932021945673e-06,
1975
+ "loss": 0.7037,
1976
+ "step": 5620
1977
+ },
1978
+ {
1979
+ "epoch": 0.7547169811320755,
1980
+ "grad_norm": 12.625,
1981
+ "learning_rate": 2.4528301886792453e-06,
1982
+ "loss": 0.7834,
1983
+ "step": 5640
1984
+ },
1985
+ {
1986
+ "epoch": 0.7573932824836076,
1987
+ "grad_norm": 7.75,
1988
+ "learning_rate": 2.4260671751639237e-06,
1989
+ "loss": 0.5978,
1990
+ "step": 5660
1991
+ },
1992
+ {
1993
+ "epoch": 0.7600695838351398,
1994
+ "grad_norm": 11.25,
1995
+ "learning_rate": 2.3993041616486017e-06,
1996
+ "loss": 0.6954,
1997
+ "step": 5680
1998
+ },
1999
+ {
2000
+ "epoch": 0.762745885186672,
2001
+ "grad_norm": 22.75,
2002
+ "learning_rate": 2.37254114813328e-06,
2003
+ "loss": 0.6904,
2004
+ "step": 5700
2005
+ },
2006
+ {
2007
+ "epoch": 0.7654221865382042,
2008
+ "grad_norm": 9.8125,
2009
+ "learning_rate": 2.345778134617958e-06,
2010
+ "loss": 0.6372,
2011
+ "step": 5720
2012
+ },
2013
+ {
2014
+ "epoch": 0.7680984878897363,
2015
+ "grad_norm": 9.3125,
2016
+ "learning_rate": 2.319015121102636e-06,
2017
+ "loss": 0.5761,
2018
+ "step": 5740
2019
+ },
2020
+ {
2021
+ "epoch": 0.7707747892412685,
2022
+ "grad_norm": 7.1875,
2023
+ "learning_rate": 2.2922521075873145e-06,
2024
+ "loss": 0.7424,
2025
+ "step": 5760
2026
+ },
2027
+ {
2028
+ "epoch": 0.7734510905928007,
2029
+ "grad_norm": 7.3125,
2030
+ "learning_rate": 2.2654890940719925e-06,
2031
+ "loss": 0.6615,
2032
+ "step": 5780
2033
+ },
2034
+ {
2035
+ "epoch": 0.7761273919443329,
2036
+ "grad_norm": 6.5625,
2037
+ "learning_rate": 2.238726080556671e-06,
2038
+ "loss": 0.7074,
2039
+ "step": 5800
2040
+ },
2041
+ {
2042
+ "epoch": 0.7788036932958651,
2043
+ "grad_norm": 14.0,
2044
+ "learning_rate": 2.2119630670413493e-06,
2045
+ "loss": 0.7508,
2046
+ "step": 5820
2047
+ },
2048
+ {
2049
+ "epoch": 0.7814799946473973,
2050
+ "grad_norm": 24.0,
2051
+ "learning_rate": 2.1852000535260273e-06,
2052
+ "loss": 0.619,
2053
+ "step": 5840
2054
+ },
2055
+ {
2056
+ "epoch": 0.7841562959989294,
2057
+ "grad_norm": 6.21875,
2058
+ "learning_rate": 2.1584370400107053e-06,
2059
+ "loss": 0.7471,
2060
+ "step": 5860
2061
+ },
2062
+ {
2063
+ "epoch": 0.7868325973504616,
2064
+ "grad_norm": 8.9375,
2065
+ "learning_rate": 2.1316740264953837e-06,
2066
+ "loss": 0.6773,
2067
+ "step": 5880
2068
+ },
2069
+ {
2070
+ "epoch": 0.7895088987019938,
2071
+ "grad_norm": 13.375,
2072
+ "learning_rate": 2.1049110129800617e-06,
2073
+ "loss": 0.6566,
2074
+ "step": 5900
2075
+ },
2076
+ {
2077
+ "epoch": 0.792185200053526,
2078
+ "grad_norm": 9.9375,
2079
+ "learning_rate": 2.07814799946474e-06,
2080
+ "loss": 0.8063,
2081
+ "step": 5920
2082
+ },
2083
+ {
2084
+ "epoch": 0.7948615014050582,
2085
+ "grad_norm": 10.625,
2086
+ "learning_rate": 2.051384985949418e-06,
2087
+ "loss": 0.7928,
2088
+ "step": 5940
2089
+ },
2090
+ {
2091
+ "epoch": 0.7975378027565904,
2092
+ "grad_norm": 6.15625,
2093
+ "learning_rate": 2.024621972434096e-06,
2094
+ "loss": 0.714,
2095
+ "step": 5960
2096
+ },
2097
+ {
2098
+ "epoch": 0.8002141041081225,
2099
+ "grad_norm": 4.8125,
2100
+ "learning_rate": 1.9978589589187745e-06,
2101
+ "loss": 0.7086,
2102
+ "step": 5980
2103
+ },
2104
+ {
2105
+ "epoch": 0.8028904054596547,
2106
+ "grad_norm": 8.5,
2107
+ "learning_rate": 1.9710959454034525e-06,
2108
+ "loss": 0.665,
2109
+ "step": 6000
2110
+ },
2111
+ {
2112
+ "epoch": 0.8055667068111869,
2113
+ "grad_norm": 5.21875,
2114
+ "learning_rate": 1.944332931888131e-06,
2115
+ "loss": 0.6577,
2116
+ "step": 6020
2117
+ },
2118
+ {
2119
+ "epoch": 0.8082430081627191,
2120
+ "grad_norm": 10.0625,
2121
+ "learning_rate": 1.917569918372809e-06,
2122
+ "loss": 0.6418,
2123
+ "step": 6040
2124
+ },
2125
+ {
2126
+ "epoch": 0.8109193095142513,
2127
+ "grad_norm": 9.75,
2128
+ "learning_rate": 1.890806904857487e-06,
2129
+ "loss": 0.7353,
2130
+ "step": 6060
2131
+ },
2132
+ {
2133
+ "epoch": 0.8135956108657835,
2134
+ "grad_norm": 9.0625,
2135
+ "learning_rate": 1.8640438913421652e-06,
2136
+ "loss": 0.7601,
2137
+ "step": 6080
2138
+ },
2139
+ {
2140
+ "epoch": 0.8162719122173157,
2141
+ "grad_norm": 13.6875,
2142
+ "learning_rate": 1.8372808778268432e-06,
2143
+ "loss": 0.7325,
2144
+ "step": 6100
2145
+ },
2146
+ {
2147
+ "epoch": 0.8189482135688478,
2148
+ "grad_norm": 13.9375,
2149
+ "learning_rate": 1.8105178643115214e-06,
2150
+ "loss": 0.6905,
2151
+ "step": 6120
2152
+ },
2153
+ {
2154
+ "epoch": 0.82162451492038,
2155
+ "grad_norm": 16.0,
2156
+ "learning_rate": 1.7837548507961998e-06,
2157
+ "loss": 0.6566,
2158
+ "step": 6140
2159
+ },
2160
+ {
2161
+ "epoch": 0.8243008162719122,
2162
+ "grad_norm": 7.59375,
2163
+ "learning_rate": 1.756991837280878e-06,
2164
+ "loss": 0.6967,
2165
+ "step": 6160
2166
+ },
2167
+ {
2168
+ "epoch": 0.8269771176234444,
2169
+ "grad_norm": 18.75,
2170
+ "learning_rate": 1.7302288237655562e-06,
2171
+ "loss": 0.8126,
2172
+ "step": 6180
2173
+ },
2174
+ {
2175
+ "epoch": 0.8296534189749766,
2176
+ "grad_norm": 10.5625,
2177
+ "learning_rate": 1.7034658102502344e-06,
2178
+ "loss": 0.7035,
2179
+ "step": 6200
2180
+ },
2181
+ {
2182
+ "epoch": 0.8323297203265088,
2183
+ "grad_norm": 7.25,
2184
+ "learning_rate": 1.6767027967349126e-06,
2185
+ "loss": 0.7178,
2186
+ "step": 6220
2187
+ },
2188
+ {
2189
+ "epoch": 0.8350060216780409,
2190
+ "grad_norm": 5.0625,
2191
+ "learning_rate": 1.6499397832195906e-06,
2192
+ "loss": 0.7009,
2193
+ "step": 6240
2194
+ },
2195
+ {
2196
+ "epoch": 0.8376823230295731,
2197
+ "grad_norm": 7.28125,
2198
+ "learning_rate": 1.6231767697042688e-06,
2199
+ "loss": 0.65,
2200
+ "step": 6260
2201
+ },
2202
+ {
2203
+ "epoch": 0.8403586243811053,
2204
+ "grad_norm": 8.8125,
2205
+ "learning_rate": 1.596413756188947e-06,
2206
+ "loss": 0.6868,
2207
+ "step": 6280
2208
+ },
2209
+ {
2210
+ "epoch": 0.8430349257326375,
2211
+ "grad_norm": 12.4375,
2212
+ "learning_rate": 1.5696507426736252e-06,
2213
+ "loss": 0.7927,
2214
+ "step": 6300
2215
+ },
2216
+ {
2217
+ "epoch": 0.8457112270841697,
2218
+ "grad_norm": 9.3125,
2219
+ "learning_rate": 1.5428877291583034e-06,
2220
+ "loss": 0.7587,
2221
+ "step": 6320
2222
+ },
2223
+ {
2224
+ "epoch": 0.8483875284357019,
2225
+ "grad_norm": 7.3125,
2226
+ "learning_rate": 1.5161247156429814e-06,
2227
+ "loss": 0.7038,
2228
+ "step": 6340
2229
+ },
2230
+ {
2231
+ "epoch": 0.851063829787234,
2232
+ "grad_norm": 10.9375,
2233
+ "learning_rate": 1.4893617021276596e-06,
2234
+ "loss": 0.8245,
2235
+ "step": 6360
2236
+ },
2237
+ {
2238
+ "epoch": 0.8537401311387662,
2239
+ "grad_norm": 8.375,
2240
+ "learning_rate": 1.4625986886123378e-06,
2241
+ "loss": 0.6673,
2242
+ "step": 6380
2243
+ },
2244
+ {
2245
+ "epoch": 0.8564164324902984,
2246
+ "grad_norm": 7.09375,
2247
+ "learning_rate": 1.435835675097016e-06,
2248
+ "loss": 0.7309,
2249
+ "step": 6400
2250
+ },
2251
+ {
2252
+ "epoch": 0.8590927338418306,
2253
+ "grad_norm": 8.125,
2254
+ "learning_rate": 1.4090726615816942e-06,
2255
+ "loss": 0.725,
2256
+ "step": 6420
2257
+ },
2258
+ {
2259
+ "epoch": 0.8617690351933628,
2260
+ "grad_norm": 8.25,
2261
+ "learning_rate": 1.3823096480663726e-06,
2262
+ "loss": 0.6646,
2263
+ "step": 6440
2264
+ },
2265
+ {
2266
+ "epoch": 0.864445336544895,
2267
+ "grad_norm": 6.4375,
2268
+ "learning_rate": 1.3555466345510506e-06,
2269
+ "loss": 0.7158,
2270
+ "step": 6460
2271
+ },
2272
+ {
2273
+ "epoch": 0.8671216378964272,
2274
+ "grad_norm": 5.71875,
2275
+ "learning_rate": 1.3287836210357288e-06,
2276
+ "loss": 0.6649,
2277
+ "step": 6480
2278
+ },
2279
+ {
2280
+ "epoch": 0.8697979392479593,
2281
+ "grad_norm": 16.875,
2282
+ "learning_rate": 1.302020607520407e-06,
2283
+ "loss": 0.7767,
2284
+ "step": 6500
2285
+ },
2286
+ {
2287
+ "epoch": 0.8724742405994915,
2288
+ "grad_norm": 12.875,
2289
+ "learning_rate": 1.2752575940050852e-06,
2290
+ "loss": 0.6689,
2291
+ "step": 6520
2292
+ },
2293
+ {
2294
+ "epoch": 0.8751505419510237,
2295
+ "grad_norm": 9.5625,
2296
+ "learning_rate": 1.2484945804897634e-06,
2297
+ "loss": 0.6509,
2298
+ "step": 6540
2299
+ },
2300
+ {
2301
+ "epoch": 0.8778268433025559,
2302
+ "grad_norm": 8.625,
2303
+ "learning_rate": 1.2217315669744414e-06,
2304
+ "loss": 0.6574,
2305
+ "step": 6560
2306
+ },
2307
+ {
2308
+ "epoch": 0.8805031446540881,
2309
+ "grad_norm": 12.375,
2310
+ "learning_rate": 1.1949685534591195e-06,
2311
+ "loss": 0.7337,
2312
+ "step": 6580
2313
+ },
2314
+ {
2315
+ "epoch": 0.8831794460056203,
2316
+ "grad_norm": 9.375,
2317
+ "learning_rate": 1.1682055399437977e-06,
2318
+ "loss": 0.6465,
2319
+ "step": 6600
2320
+ },
2321
+ {
2322
+ "epoch": 0.8858557473571524,
2323
+ "grad_norm": 8.8125,
2324
+ "learning_rate": 1.141442526428476e-06,
2325
+ "loss": 0.7548,
2326
+ "step": 6620
2327
+ },
2328
+ {
2329
+ "epoch": 0.8885320487086846,
2330
+ "grad_norm": 11.125,
2331
+ "learning_rate": 1.1146795129131541e-06,
2332
+ "loss": 0.7219,
2333
+ "step": 6640
2334
+ },
2335
+ {
2336
+ "epoch": 0.8912083500602168,
2337
+ "grad_norm": 6.625,
2338
+ "learning_rate": 1.0879164993978321e-06,
2339
+ "loss": 0.8184,
2340
+ "step": 6660
2341
+ },
2342
+ {
2343
+ "epoch": 0.893884651411749,
2344
+ "grad_norm": 6.84375,
2345
+ "learning_rate": 1.0611534858825105e-06,
2346
+ "loss": 0.6956,
2347
+ "step": 6680
2348
+ },
2349
+ {
2350
+ "epoch": 0.8965609527632812,
2351
+ "grad_norm": 7.03125,
2352
+ "learning_rate": 1.0343904723671887e-06,
2353
+ "loss": 0.6756,
2354
+ "step": 6700
2355
+ },
2356
+ {
2357
+ "epoch": 0.8992372541148134,
2358
+ "grad_norm": 8.1875,
2359
+ "learning_rate": 1.007627458851867e-06,
2360
+ "loss": 0.6936,
2361
+ "step": 6720
2362
+ },
2363
+ {
2364
+ "epoch": 0.9019135554663456,
2365
+ "grad_norm": 10.0,
2366
+ "learning_rate": 9.80864445336545e-07,
2367
+ "loss": 0.6416,
2368
+ "step": 6740
2369
+ },
2370
+ {
2371
+ "epoch": 0.9045898568178777,
2372
+ "grad_norm": 8.1875,
2373
+ "learning_rate": 9.541014318212231e-07,
2374
+ "loss": 0.7569,
2375
+ "step": 6760
2376
+ },
2377
+ {
2378
+ "epoch": 0.9072661581694099,
2379
+ "grad_norm": 47.0,
2380
+ "learning_rate": 9.273384183059013e-07,
2381
+ "loss": 0.7972,
2382
+ "step": 6780
2383
+ },
2384
+ {
2385
+ "epoch": 0.9099424595209421,
2386
+ "grad_norm": 7.625,
2387
+ "learning_rate": 9.005754047905794e-07,
2388
+ "loss": 0.6925,
2389
+ "step": 6800
2390
+ },
2391
+ {
2392
+ "epoch": 0.9126187608724743,
2393
+ "grad_norm": 23.875,
2394
+ "learning_rate": 8.738123912752576e-07,
2395
+ "loss": 0.67,
2396
+ "step": 6820
2397
+ },
2398
+ {
2399
+ "epoch": 0.9152950622240065,
2400
+ "grad_norm": 7.6875,
2401
+ "learning_rate": 8.470493777599359e-07,
2402
+ "loss": 0.7114,
2403
+ "step": 6840
2404
+ },
2405
+ {
2406
+ "epoch": 0.9179713635755387,
2407
+ "grad_norm": 8.1875,
2408
+ "learning_rate": 8.202863642446141e-07,
2409
+ "loss": 0.6751,
2410
+ "step": 6860
2411
+ },
2412
+ {
2413
+ "epoch": 0.9206476649270708,
2414
+ "grad_norm": 11.0625,
2415
+ "learning_rate": 7.935233507292922e-07,
2416
+ "loss": 0.6867,
2417
+ "step": 6880
2418
+ },
2419
+ {
2420
+ "epoch": 0.923323966278603,
2421
+ "grad_norm": 15.375,
2422
+ "learning_rate": 7.667603372139704e-07,
2423
+ "loss": 0.7322,
2424
+ "step": 6900
2425
+ },
2426
+ {
2427
+ "epoch": 0.9260002676301351,
2428
+ "grad_norm": 6.15625,
2429
+ "learning_rate": 7.399973236986485e-07,
2430
+ "loss": 0.7396,
2431
+ "step": 6920
2432
+ },
2433
+ {
2434
+ "epoch": 0.9286765689816673,
2435
+ "grad_norm": 18.0,
2436
+ "learning_rate": 7.132343101833267e-07,
2437
+ "loss": 0.7134,
2438
+ "step": 6940
2439
+ },
2440
+ {
2441
+ "epoch": 0.9313528703331995,
2442
+ "grad_norm": 12.125,
2443
+ "learning_rate": 6.864712966680049e-07,
2444
+ "loss": 0.682,
2445
+ "step": 6960
2446
+ },
2447
+ {
2448
+ "epoch": 0.9340291716847317,
2449
+ "grad_norm": 8.5625,
2450
+ "learning_rate": 6.59708283152683e-07,
2451
+ "loss": 0.8207,
2452
+ "step": 6980
2453
+ },
2454
+ {
2455
+ "epoch": 0.9367054730362638,
2456
+ "grad_norm": 5.3125,
2457
+ "learning_rate": 6.329452696373613e-07,
2458
+ "loss": 0.6548,
2459
+ "step": 7000
2460
+ },
2461
+ {
2462
+ "epoch": 0.939381774387796,
2463
+ "grad_norm": 13.0,
2464
+ "learning_rate": 6.061822561220394e-07,
2465
+ "loss": 0.6879,
2466
+ "step": 7020
2467
+ },
2468
+ {
2469
+ "epoch": 0.9420580757393282,
2470
+ "grad_norm": 7.625,
2471
+ "learning_rate": 5.794192426067176e-07,
2472
+ "loss": 0.7555,
2473
+ "step": 7040
2474
+ },
2475
+ {
2476
+ "epoch": 0.9447343770908604,
2477
+ "grad_norm": 6.4375,
2478
+ "learning_rate": 5.526562290913958e-07,
2479
+ "loss": 0.6822,
2480
+ "step": 7060
2481
+ },
2482
+ {
2483
+ "epoch": 0.9474106784423926,
2484
+ "grad_norm": 6.375,
2485
+ "learning_rate": 5.258932155760739e-07,
2486
+ "loss": 0.7273,
2487
+ "step": 7080
2488
+ },
2489
+ {
2490
+ "epoch": 0.9500869797939248,
2491
+ "grad_norm": 9.1875,
2492
+ "learning_rate": 4.99130202060752e-07,
2493
+ "loss": 0.6715,
2494
+ "step": 7100
2495
+ },
2496
+ {
2497
+ "epoch": 0.9527632811454569,
2498
+ "grad_norm": 5.75,
2499
+ "learning_rate": 4.723671885454303e-07,
2500
+ "loss": 0.8109,
2501
+ "step": 7120
2502
+ },
2503
+ {
2504
+ "epoch": 0.9554395824969891,
2505
+ "grad_norm": 13.75,
2506
+ "learning_rate": 4.4560417503010845e-07,
2507
+ "loss": 0.6167,
2508
+ "step": 7140
2509
+ },
2510
+ {
2511
+ "epoch": 0.9581158838485213,
2512
+ "grad_norm": 7.59375,
2513
+ "learning_rate": 4.188411615147866e-07,
2514
+ "loss": 0.6606,
2515
+ "step": 7160
2516
+ },
2517
+ {
2518
+ "epoch": 0.9607921852000535,
2519
+ "grad_norm": 9.1875,
2520
+ "learning_rate": 3.9207814799946473e-07,
2521
+ "loss": 0.7073,
2522
+ "step": 7180
2523
+ },
2524
+ {
2525
+ "epoch": 0.9634684865515857,
2526
+ "grad_norm": 9.75,
2527
+ "learning_rate": 3.65315134484143e-07,
2528
+ "loss": 0.682,
2529
+ "step": 7200
2530
+ },
2531
+ {
2532
+ "epoch": 0.9661447879031179,
2533
+ "grad_norm": 11.8125,
2534
+ "learning_rate": 3.3855212096882113e-07,
2535
+ "loss": 0.7581,
2536
+ "step": 7220
2537
+ },
2538
+ {
2539
+ "epoch": 0.96882108925465,
2540
+ "grad_norm": 8.875,
2541
+ "learning_rate": 3.117891074534993e-07,
2542
+ "loss": 0.6873,
2543
+ "step": 7240
2544
+ },
2545
+ {
2546
+ "epoch": 0.9714973906061822,
2547
+ "grad_norm": 27.375,
2548
+ "learning_rate": 2.8502609393817747e-07,
2549
+ "loss": 0.647,
2550
+ "step": 7260
2551
+ },
2552
+ {
2553
+ "epoch": 0.9741736919577144,
2554
+ "grad_norm": 12.1875,
2555
+ "learning_rate": 2.582630804228556e-07,
2556
+ "loss": 0.6391,
2557
+ "step": 7280
2558
+ },
2559
+ {
2560
+ "epoch": 0.9768499933092466,
2561
+ "grad_norm": 14.1875,
2562
+ "learning_rate": 2.3150006690753381e-07,
2563
+ "loss": 0.8126,
2564
+ "step": 7300
2565
+ },
2566
+ {
2567
+ "epoch": 0.9795262946607788,
2568
+ "grad_norm": 6.4375,
2569
+ "learning_rate": 2.0473705339221198e-07,
2570
+ "loss": 0.7084,
2571
+ "step": 7320
2572
+ },
2573
+ {
2574
+ "epoch": 0.982202596012311,
2575
+ "grad_norm": 25.0,
2576
+ "learning_rate": 1.7797403987689016e-07,
2577
+ "loss": 0.6649,
2578
+ "step": 7340
2579
+ },
2580
+ {
2581
+ "epoch": 0.9848788973638432,
2582
+ "grad_norm": 11.6875,
2583
+ "learning_rate": 1.5121102636156833e-07,
2584
+ "loss": 0.7436,
2585
+ "step": 7360
2586
+ },
2587
+ {
2588
+ "epoch": 0.9875551987153753,
2589
+ "grad_norm": 12.8125,
2590
+ "learning_rate": 1.244480128462465e-07,
2591
+ "loss": 0.6809,
2592
+ "step": 7380
2593
+ },
2594
+ {
2595
+ "epoch": 0.9902315000669075,
2596
+ "grad_norm": 7.125,
2597
+ "learning_rate": 9.768499933092467e-08,
2598
+ "loss": 0.6806,
2599
+ "step": 7400
2600
+ },
2601
+ {
2602
+ "epoch": 0.9929078014184397,
2603
+ "grad_norm": 15.625,
2604
+ "learning_rate": 7.092198581560284e-08,
2605
+ "loss": 0.7224,
2606
+ "step": 7420
2607
+ },
2608
+ {
2609
+ "epoch": 0.9955841027699719,
2610
+ "grad_norm": 7.46875,
2611
+ "learning_rate": 4.415897230028101e-08,
2612
+ "loss": 0.7614,
2613
+ "step": 7440
2614
+ },
2615
+ {
2616
+ "epoch": 0.9982604041215041,
2617
+ "grad_norm": 8.5,
2618
+ "learning_rate": 1.739595878495919e-08,
2619
+ "loss": 0.6988,
2620
+ "step": 7460
2621
+ },
2622
+ {
2623
+ "epoch": 1.0,
2624
+ "step": 7473,
2625
+ "total_flos": 1.1170284894683136e+16,
2626
+ "train_loss": 0.7570252240493756,
2627
+ "train_runtime": 920.0938,
2628
+ "train_samples_per_second": 8.122,
2629
+ "train_steps_per_second": 8.122
2630
+ }
2631
+ ],
2632
+ "logging_steps": 20,
2633
+ "max_steps": 7473,
2634
+ "num_input_tokens_seen": 0,
2635
+ "num_train_epochs": 1,
2636
+ "save_steps": 5000,
2637
+ "stateful_callbacks": {
2638
+ "TrainerControl": {
2639
+ "args": {
2640
+ "should_epoch_stop": false,
2641
+ "should_evaluate": false,
2642
+ "should_log": false,
2643
+ "should_save": true,
2644
+ "should_training_stop": true
2645
+ },
2646
+ "attributes": {}
2647
+ }
2648
+ },
2649
+ "total_flos": 1.1170284894683136e+16,
2650
+ "train_batch_size": 1,
2651
+ "trial_name": null,
2652
+ "trial_params": null
2653
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5192ed7d4caa2f74e975a410893b27550adcd92c93eb22def9cf35fa3c6a5484
3
+ size 6008