Hugging Face's logo

diddmstjr
/
ISEF

TensorBoard
Safetensors
qwen2
Model card Files
xet
 Metrics Community
diddmstjr commited on
Commit
52d664c
·
verified ·
1 Parent(s): 37c2f0b

text_only_model_projector_ft

Browse files
Files changed (44) hide show
  1. .gitattributes +2 -0
  2. added_tokens.json +1 -12
  3. chat_template.jinja +5 -6
  4. checkpoint-4000/added_tokens.json +5 -0
  5. checkpoint-4000/chat_template.jinja +6 -0
  6. checkpoint-4000/config.json +58 -0
  7. checkpoint-4000/generation_config.json +13 -0
  8. checkpoint-4000/merges.txt +0 -0
  9. checkpoint-4000/model.safetensors +3 -0
  10. checkpoint-4000/optimizer.pt +3 -0
  11. checkpoint-4000/rng_state.pth +3 -0
  12. checkpoint-4000/scheduler.pt +3 -0
  13. checkpoint-4000/special_tokens_map.json +20 -0
  14. checkpoint-4000/tokenizer.json +3 -0
  15. checkpoint-4000/tokenizer_config.json +43 -0
  16. checkpoint-4000/trainer_state.json +2834 -0
  17. checkpoint-4000/training_args.bin +3 -0
  18. checkpoint-4000/vocab.json +0 -0
  19. checkpoint-4361/added_tokens.json +5 -0
  20. checkpoint-4361/chat_template.jinja +6 -0
  21. checkpoint-4361/config.json +58 -0
  22. checkpoint-4361/generation_config.json +13 -0
  23. checkpoint-4361/merges.txt +0 -0
  24. checkpoint-4361/model.safetensors +3 -0
  25. checkpoint-4361/optimizer.pt +3 -0
  26. checkpoint-4361/rng_state.pth +3 -0
  27. checkpoint-4361/scheduler.pt +3 -0
  28. checkpoint-4361/special_tokens_map.json +20 -0
  29. checkpoint-4361/tokenizer.json +3 -0
  30. checkpoint-4361/tokenizer_config.json +43 -0
  31. checkpoint-4361/trainer_state.json +3086 -0
  32. checkpoint-4361/training_args.bin +3 -0
  33. checkpoint-4361/vocab.json +0 -0
  34. config.json +36 -102
  35. generation_config.json +4 -3
  36. model.safetensors +2 -2
  37. runs/Jan30_00-44-43_fe3b1825ceb0/events.out.tfevents.1769733888.fe3b1825ceb0 +3 -0
  38. runs/Jan30_01-30-07_fe3b1825ceb0/events.out.tfevents.1769736616.fe3b1825ceb0 +3 -0
  39. runs/Jan30_01-32-52_fe3b1825ceb0/events.out.tfevents.1769736781.fe3b1825ceb0 +3 -0
  40. special_tokens_map.json +1 -12
  41. tokenizer.json +2 -2
  42. tokenizer_config.json +1 -102
  43. trainer_state.json +0 -0
  44. training_args.bin +2 -2
.gitattributes CHANGED
@@ -37,3 +37,5 @@ checkpoint-8000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  checkpoint-8500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
  checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
37
  checkpoint-8500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
  checkpoint-8721/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
+ checkpoint-4361/tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json CHANGED
@@ -1,16 +1,5 @@
1
  {
2
- "<|box_end|>": 151649,
3
- "<|box_start|>": 151648,
4
  "<|endoftext|>": 151643,
5
  "<|im_end|>": 151645,
6
- "<|im_start|>": 151644,
7
- "<|image_pad|>": 151655,
8
- "<|object_ref_end|>": 151647,
9
- "<|object_ref_start|>": 151646,
10
- "<|quad_end|>": 151651,
11
- "<|quad_start|>": 151650,
12
- "<|video_pad|>": 151656,
13
- "<|vision_end|>": 151653,
14
- "<|vision_pad|>": 151654,
15
- "<|vision_start|>": 151652
16
  }
 
1
  {
 
 
2
  "<|endoftext|>": 151643,
3
  "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
 
 
 
 
 
 
 
 
 
5
  }
chat_template.jinja CHANGED
@@ -1,7 +1,6 @@
1
- {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
  You are a helpful assistant.<|im_end|>
3
- {% endif %}<|im_start|>{{ message['role'] }}
4
- {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
- {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
- {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
- {% endif %}
 
1
+ {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
2
  You are a helpful assistant.<|im_end|>
3
+ ' }}{% endif %}{{'<|im_start|>' + message['role'] + '
4
+ ' + message['content'] + '<|im_end|>' + '
5
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
6
+ ' }}{% endif %}
 
checkpoint-4000/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
checkpoint-4000/chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ ' }}{% endif %}{{'<|im_start|>' + message['role'] + '
4
+ ' + message['content'] + '<|im_end|>' + '
5
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
6
+ ' }}{% endif %}
checkpoint-4000/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1536,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 8960,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 32768,
43
+ "max_window_layers": 28,
44
+ "model_type": "qwen2",
45
+ "num_attention_heads": 12,
46
+ "num_hidden_layers": 28,
47
+ "num_key_value_heads": 2,
48
+ "pad_token_id": 151643,
49
+ "rms_norm_eps": 1e-06,
50
+ "rope_scaling": null,
51
+ "rope_theta": 1000000.0,
52
+ "sliding_window": null,
53
+ "tie_word_embeddings": true,
54
+ "transformers_version": "4.57.1",
55
+ "use_cache": false,
56
+ "use_sliding_window": false,
57
+ "vocab_size": 151936
58
+ }
checkpoint-4000/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "repetition_penalty": 1.1,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.57.1"
13
+ }
checkpoint-4000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:142946d863cc5939009c236d63d247ae7abdca10a83bd641fa80334895c665ec
3
+ size 3087467144
checkpoint-4000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:867a3e38e30dacf38b208c978d7e475391d3e42f602da2141f311581d7afdcb9
3
+ size 6175147805
checkpoint-4000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c15d10da233568de54180256b227cfe26dea6eaac6df08048357111de9ef60d
3
+ size 14645
checkpoint-4000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f0f02b8c6993dd3c0a5eb09ceb5ada5120a405f64732e3df0a8c9ec00d94877
3
+ size 1465
checkpoint-4000/special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
checkpoint-4000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
3
+ size 11418266
checkpoint-4000/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "<|im_end|>",
36
+ "errors": "replace",
37
+ "extra_special_tokens": {},
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null
43
+ }
checkpoint-4000/trainer_state.json ADDED
@@ -0,0 +1,2834 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.9172208209126347,
6
+ "eval_steps": 500,
7
+ "global_step": 4000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.002293052052281587,
14
+ "grad_norm": 18.875,
15
+ "learning_rate": 1.9958725063058934e-05,
16
+ "loss": 1.7556,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.004586104104563174,
21
+ "grad_norm": 19.875,
22
+ "learning_rate": 1.99128640220133e-05,
23
+ "loss": 1.1973,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.00687915615684476,
28
+ "grad_norm": 15.6875,
29
+ "learning_rate": 1.986700298096767e-05,
30
+ "loss": 1.2111,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.009172208209126348,
35
+ "grad_norm": 15.5625,
36
+ "learning_rate": 1.9821141939922037e-05,
37
+ "loss": 1.2078,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.011465260261407933,
42
+ "grad_norm": 11.125,
43
+ "learning_rate": 1.9775280898876404e-05,
44
+ "loss": 1.1955,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.01375831231368952,
49
+ "grad_norm": 15.875,
50
+ "learning_rate": 1.9729419857830774e-05,
51
+ "loss": 1.2044,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.016051364365971106,
56
+ "grad_norm": 17.875,
57
+ "learning_rate": 1.968355881678514e-05,
58
+ "loss": 1.1926,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.018344416418252695,
63
+ "grad_norm": 14.5,
64
+ "learning_rate": 1.963769777573951e-05,
65
+ "loss": 1.2002,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.02063746847053428,
70
+ "grad_norm": 11.8125,
71
+ "learning_rate": 1.9591836734693877e-05,
72
+ "loss": 1.1892,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.022930520522815866,
77
+ "grad_norm": 11.5,
78
+ "learning_rate": 1.9545975693648247e-05,
79
+ "loss": 1.19,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.025223572575097455,
84
+ "grad_norm": 16.0,
85
+ "learning_rate": 1.9500114652602614e-05,
86
+ "loss": 1.1949,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.02751662462737904,
91
+ "grad_norm": 16.75,
92
+ "learning_rate": 1.9454253611556984e-05,
93
+ "loss": 1.1921,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.029809676679660627,
98
+ "grad_norm": 14.125,
99
+ "learning_rate": 1.940839257051135e-05,
100
+ "loss": 1.1958,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.03210272873194221,
105
+ "grad_norm": 11.5625,
106
+ "learning_rate": 1.936253152946572e-05,
107
+ "loss": 1.1852,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.034395780784223805,
112
+ "grad_norm": 18.25,
113
+ "learning_rate": 1.9316670488420087e-05,
114
+ "loss": 1.187,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.03668883283650539,
119
+ "grad_norm": 15.9375,
120
+ "learning_rate": 1.9270809447374457e-05,
121
+ "loss": 1.1867,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.038981884888786976,
126
+ "grad_norm": 19.75,
127
+ "learning_rate": 1.9224948406328824e-05,
128
+ "loss": 1.2015,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.04127493694106856,
133
+ "grad_norm": 11.625,
134
+ "learning_rate": 1.9179087365283194e-05,
135
+ "loss": 1.2059,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.04356798899335015,
140
+ "grad_norm": 16.375,
141
+ "learning_rate": 1.913322632423756e-05,
142
+ "loss": 1.1962,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.04586104104563173,
147
+ "grad_norm": 13.0,
148
+ "learning_rate": 1.908736528319193e-05,
149
+ "loss": 1.1955,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.048154093097913325,
154
+ "grad_norm": 11.4375,
155
+ "learning_rate": 1.9041504242146297e-05,
156
+ "loss": 1.1766,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.05044714515019491,
161
+ "grad_norm": 11.5625,
162
+ "learning_rate": 1.8995643201100668e-05,
163
+ "loss": 1.1857,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.052740197202476496,
168
+ "grad_norm": 17.875,
169
+ "learning_rate": 1.8949782160055034e-05,
170
+ "loss": 1.1981,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.05503324925475808,
175
+ "grad_norm": 14.25,
176
+ "learning_rate": 1.8903921119009404e-05,
177
+ "loss": 1.2041,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.05732630130703967,
182
+ "grad_norm": 16.0,
183
+ "learning_rate": 1.885806007796377e-05,
184
+ "loss": 1.1989,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.05961935335932125,
189
+ "grad_norm": 17.25,
190
+ "learning_rate": 1.881219903691814e-05,
191
+ "loss": 1.196,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.061912405411602846,
196
+ "grad_norm": 13.3125,
197
+ "learning_rate": 1.8766337995872508e-05,
198
+ "loss": 1.1797,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.06420545746388442,
203
+ "grad_norm": 13.3125,
204
+ "learning_rate": 1.8720476954826878e-05,
205
+ "loss": 1.1974,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.06649850951616602,
210
+ "grad_norm": 10.375,
211
+ "learning_rate": 1.8674615913781244e-05,
212
+ "loss": 1.1929,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.06879156156844761,
217
+ "grad_norm": 15.125,
218
+ "learning_rate": 1.8628754872735614e-05,
219
+ "loss": 1.1838,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.0710846136207292,
224
+ "grad_norm": 8.75,
225
+ "learning_rate": 1.858289383168998e-05,
226
+ "loss": 1.1515,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.07337766567301078,
231
+ "grad_norm": 10.9375,
232
+ "learning_rate": 1.8537032790644348e-05,
233
+ "loss": 1.2107,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.07567071772529237,
238
+ "grad_norm": 12.5625,
239
+ "learning_rate": 1.8491171749598718e-05,
240
+ "loss": 1.1874,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.07796376977757395,
245
+ "grad_norm": 9.6875,
246
+ "learning_rate": 1.8445310708553084e-05,
247
+ "loss": 1.1988,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.08025682182985554,
252
+ "grad_norm": 10.5625,
253
+ "learning_rate": 1.8399449667507454e-05,
254
+ "loss": 1.1998,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.08254987388213712,
259
+ "grad_norm": 9.1875,
260
+ "learning_rate": 1.835358862646182e-05,
261
+ "loss": 1.1957,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.08484292593441871,
266
+ "grad_norm": 10.1875,
267
+ "learning_rate": 1.830772758541619e-05,
268
+ "loss": 1.204,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.0871359779867003,
273
+ "grad_norm": 17.125,
274
+ "learning_rate": 1.8261866544370558e-05,
275
+ "loss": 1.191,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.08942903003898188,
280
+ "grad_norm": 12.1875,
281
+ "learning_rate": 1.8216005503324928e-05,
282
+ "loss": 1.19,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.09172208209126347,
287
+ "grad_norm": 9.9375,
288
+ "learning_rate": 1.8170144462279294e-05,
289
+ "loss": 1.1729,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.09401513414354506,
294
+ "grad_norm": 12.875,
295
+ "learning_rate": 1.8124283421233664e-05,
296
+ "loss": 1.201,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.09630818619582665,
301
+ "grad_norm": 15.1875,
302
+ "learning_rate": 1.807842238018803e-05,
303
+ "loss": 1.1834,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.09860123824810824,
308
+ "grad_norm": 10.125,
309
+ "learning_rate": 1.80325613391424e-05,
310
+ "loss": 1.1984,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.10089429030038982,
315
+ "grad_norm": 12.875,
316
+ "learning_rate": 1.7986700298096768e-05,
317
+ "loss": 1.1877,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.10318734235267141,
322
+ "grad_norm": 14.8125,
323
+ "learning_rate": 1.7940839257051138e-05,
324
+ "loss": 1.179,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.10548039440495299,
329
+ "grad_norm": 17.75,
330
+ "learning_rate": 1.7894978216005504e-05,
331
+ "loss": 1.1861,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.10777344645723458,
336
+ "grad_norm": 8.375,
337
+ "learning_rate": 1.7849117174959874e-05,
338
+ "loss": 1.1912,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.11006649850951616,
343
+ "grad_norm": 8.9375,
344
+ "learning_rate": 1.780325613391424e-05,
345
+ "loss": 1.1795,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.11235955056179775,
350
+ "grad_norm": 11.5625,
351
+ "learning_rate": 1.775739509286861e-05,
352
+ "loss": 1.1827,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.11465260261407934,
357
+ "grad_norm": 11.625,
358
+ "learning_rate": 1.7711534051822978e-05,
359
+ "loss": 1.1813,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.11694565466636092,
364
+ "grad_norm": 11.6875,
365
+ "learning_rate": 1.7665673010777348e-05,
366
+ "loss": 1.1836,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.1192387067186425,
371
+ "grad_norm": 7.84375,
372
+ "learning_rate": 1.7619811969731714e-05,
373
+ "loss": 1.171,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.1215317587709241,
378
+ "grad_norm": 11.9375,
379
+ "learning_rate": 1.7573950928686084e-05,
380
+ "loss": 1.1835,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.12382481082320569,
385
+ "grad_norm": 14.9375,
386
+ "learning_rate": 1.752808988764045e-05,
387
+ "loss": 1.1887,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.12611786287548726,
392
+ "grad_norm": 13.3125,
393
+ "learning_rate": 1.748222884659482e-05,
394
+ "loss": 1.1737,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.12841091492776885,
399
+ "grad_norm": 13.3125,
400
+ "learning_rate": 1.7436367805549188e-05,
401
+ "loss": 1.1871,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.13070396698005043,
406
+ "grad_norm": 10.5625,
407
+ "learning_rate": 1.7390506764503558e-05,
408
+ "loss": 1.1873,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.13299701903233205,
413
+ "grad_norm": 8.1875,
414
+ "learning_rate": 1.7344645723457925e-05,
415
+ "loss": 1.1946,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.13529007108461363,
420
+ "grad_norm": 13.9375,
421
+ "learning_rate": 1.7298784682412295e-05,
422
+ "loss": 1.1838,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.13758312313689522,
427
+ "grad_norm": 12.8125,
428
+ "learning_rate": 1.725292364136666e-05,
429
+ "loss": 1.1873,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.1398761751891768,
434
+ "grad_norm": 11.3125,
435
+ "learning_rate": 1.7207062600321028e-05,
436
+ "loss": 1.1802,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.1421692272414584,
441
+ "grad_norm": 15.25,
442
+ "learning_rate": 1.7161201559275398e-05,
443
+ "loss": 1.1806,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.14446227929373998,
448
+ "grad_norm": 10.1875,
449
+ "learning_rate": 1.7115340518229765e-05,
450
+ "loss": 1.195,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.14675533134602156,
455
+ "grad_norm": 9.875,
456
+ "learning_rate": 1.7069479477184135e-05,
457
+ "loss": 1.1835,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.14904838339830315,
462
+ "grad_norm": 11.6875,
463
+ "learning_rate": 1.70236184361385e-05,
464
+ "loss": 1.1884,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.15134143545058473,
469
+ "grad_norm": 12.0,
470
+ "learning_rate": 1.697775739509287e-05,
471
+ "loss": 1.1811,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.15363448750286632,
476
+ "grad_norm": 9.875,
477
+ "learning_rate": 1.6931896354047238e-05,
478
+ "loss": 1.195,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.1559275395551479,
483
+ "grad_norm": 11.0,
484
+ "learning_rate": 1.6886035313001608e-05,
485
+ "loss": 1.1827,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.1582205916074295,
490
+ "grad_norm": 11.1875,
491
+ "learning_rate": 1.6840174271955975e-05,
492
+ "loss": 1.1868,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.16051364365971107,
497
+ "grad_norm": 7.84375,
498
+ "learning_rate": 1.6794313230910345e-05,
499
+ "loss": 1.1813,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.16280669571199266,
504
+ "grad_norm": 13.0625,
505
+ "learning_rate": 1.674845218986471e-05,
506
+ "loss": 1.1856,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.16509974776427425,
511
+ "grad_norm": 11.6875,
512
+ "learning_rate": 1.670259114881908e-05,
513
+ "loss": 1.1826,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.16739279981655583,
518
+ "grad_norm": 11.625,
519
+ "learning_rate": 1.6656730107773448e-05,
520
+ "loss": 1.1712,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.16968585186883742,
525
+ "grad_norm": 10.4375,
526
+ "learning_rate": 1.6610869066727818e-05,
527
+ "loss": 1.1701,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.171978903921119,
532
+ "grad_norm": 9.6875,
533
+ "learning_rate": 1.6565008025682185e-05,
534
+ "loss": 1.1905,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.1742719559734006,
539
+ "grad_norm": 12.25,
540
+ "learning_rate": 1.651914698463655e-05,
541
+ "loss": 1.1887,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.17656500802568217,
546
+ "grad_norm": 7.9375,
547
+ "learning_rate": 1.647328594359092e-05,
548
+ "loss": 1.2096,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.17885806007796376,
553
+ "grad_norm": 13.375,
554
+ "learning_rate": 1.6427424902545288e-05,
555
+ "loss": 1.1932,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.18115111213024535,
560
+ "grad_norm": 10.8125,
561
+ "learning_rate": 1.6381563861499658e-05,
562
+ "loss": 1.1798,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.18344416418252693,
567
+ "grad_norm": 12.625,
568
+ "learning_rate": 1.6335702820454025e-05,
569
+ "loss": 1.178,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.18573721623480852,
574
+ "grad_norm": 12.3125,
575
+ "learning_rate": 1.628984177940839e-05,
576
+ "loss": 1.1875,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.18803026828709013,
581
+ "grad_norm": 9.3125,
582
+ "learning_rate": 1.624398073836276e-05,
583
+ "loss": 1.1791,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.19032332033937172,
588
+ "grad_norm": 14.6875,
589
+ "learning_rate": 1.6198119697317128e-05,
590
+ "loss": 1.1764,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.1926163723916533,
595
+ "grad_norm": 10.625,
596
+ "learning_rate": 1.6152258656271498e-05,
597
+ "loss": 1.1783,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.1949094244439349,
602
+ "grad_norm": 12.875,
603
+ "learning_rate": 1.6106397615225865e-05,
604
+ "loss": 1.1882,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.19720247649621647,
609
+ "grad_norm": 14.9375,
610
+ "learning_rate": 1.6060536574180235e-05,
611
+ "loss": 1.1877,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.19949552854849806,
616
+ "grad_norm": 9.75,
617
+ "learning_rate": 1.60146755331346e-05,
618
+ "loss": 1.1942,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.20178858060077964,
623
+ "grad_norm": 12.1875,
624
+ "learning_rate": 1.596881449208897e-05,
625
+ "loss": 1.1855,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.20408163265306123,
630
+ "grad_norm": 14.4375,
631
+ "learning_rate": 1.5922953451043338e-05,
632
+ "loss": 1.1707,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.20637468470534281,
637
+ "grad_norm": 12.5625,
638
+ "learning_rate": 1.5877092409997708e-05,
639
+ "loss": 1.1809,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.2086677367576244,
644
+ "grad_norm": 11.0,
645
+ "learning_rate": 1.5831231368952075e-05,
646
+ "loss": 1.1929,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.21096078880990599,
651
+ "grad_norm": 7.4375,
652
+ "learning_rate": 1.5785370327906445e-05,
653
+ "loss": 1.2096,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.21325384086218757,
658
+ "grad_norm": 7.0,
659
+ "learning_rate": 1.573950928686081e-05,
660
+ "loss": 1.1921,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.21554689291446916,
665
+ "grad_norm": 10.9375,
666
+ "learning_rate": 1.569364824581518e-05,
667
+ "loss": 1.1849,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.21783994496675074,
672
+ "grad_norm": 11.25,
673
+ "learning_rate": 1.5647787204769548e-05,
674
+ "loss": 1.1984,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.22013299701903233,
679
+ "grad_norm": 12.0625,
680
+ "learning_rate": 1.5601926163723918e-05,
681
+ "loss": 1.1942,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.2224260490713139,
686
+ "grad_norm": 10.4375,
687
+ "learning_rate": 1.5556065122678285e-05,
688
+ "loss": 1.1818,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.2247191011235955,
693
+ "grad_norm": 12.8125,
694
+ "learning_rate": 1.5510204081632655e-05,
695
+ "loss": 1.1945,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.22701215317587708,
700
+ "grad_norm": 6.875,
701
+ "learning_rate": 1.546434304058702e-05,
702
+ "loss": 1.1643,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.22930520522815867,
707
+ "grad_norm": 13.25,
708
+ "learning_rate": 1.541848199954139e-05,
709
+ "loss": 1.2059,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.23159825728044026,
714
+ "grad_norm": 10.5,
715
+ "learning_rate": 1.5372620958495758e-05,
716
+ "loss": 1.1918,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.23389130933272184,
721
+ "grad_norm": 6.9375,
722
+ "learning_rate": 1.5326759917450128e-05,
723
+ "loss": 1.1879,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.23618436138500343,
728
+ "grad_norm": 9.25,
729
+ "learning_rate": 1.5280898876404495e-05,
730
+ "loss": 1.1619,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.238477413437285,
735
+ "grad_norm": 8.4375,
736
+ "learning_rate": 1.5235037835358863e-05,
737
+ "loss": 1.1709,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.24077046548956663,
742
+ "grad_norm": 12.625,
743
+ "learning_rate": 1.5189176794313232e-05,
744
+ "loss": 1.1922,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.2430635175418482,
749
+ "grad_norm": 8.0625,
750
+ "learning_rate": 1.51433157532676e-05,
751
+ "loss": 1.1695,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.2453565695941298,
756
+ "grad_norm": 11.3125,
757
+ "learning_rate": 1.5097454712221968e-05,
758
+ "loss": 1.1987,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.24764962164641138,
763
+ "grad_norm": 9.0625,
764
+ "learning_rate": 1.5051593671176337e-05,
765
+ "loss": 1.1807,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.24994267369869297,
770
+ "grad_norm": 12.4375,
771
+ "learning_rate": 1.5005732630130705e-05,
772
+ "loss": 1.1839,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.2522357257509745,
777
+ "grad_norm": 13.0,
778
+ "learning_rate": 1.4959871589085073e-05,
779
+ "loss": 1.1795,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.2545287778032561,
784
+ "grad_norm": 13.125,
785
+ "learning_rate": 1.4914010548039442e-05,
786
+ "loss": 1.1739,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.2568218298555377,
791
+ "grad_norm": 12.3125,
792
+ "learning_rate": 1.486814950699381e-05,
793
+ "loss": 1.1936,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.2591148819078193,
798
+ "grad_norm": 7.03125,
799
+ "learning_rate": 1.4822288465948178e-05,
800
+ "loss": 1.1775,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.26140793396010087,
805
+ "grad_norm": 14.75,
806
+ "learning_rate": 1.4776427424902547e-05,
807
+ "loss": 1.1958,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.26370098601238245,
812
+ "grad_norm": 11.375,
813
+ "learning_rate": 1.4730566383856915e-05,
814
+ "loss": 1.18,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.2659940380646641,
819
+ "grad_norm": 12.3125,
820
+ "learning_rate": 1.4684705342811283e-05,
821
+ "loss": 1.1812,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.2682870901169457,
826
+ "grad_norm": 11.1875,
827
+ "learning_rate": 1.4638844301765652e-05,
828
+ "loss": 1.1657,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.27058014216922727,
833
+ "grad_norm": 11.9375,
834
+ "learning_rate": 1.459298326072002e-05,
835
+ "loss": 1.1862,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.27287319422150885,
840
+ "grad_norm": 9.9375,
841
+ "learning_rate": 1.4547122219674388e-05,
842
+ "loss": 1.1869,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.27516624627379044,
847
+ "grad_norm": 8.9375,
848
+ "learning_rate": 1.4501261178628757e-05,
849
+ "loss": 1.1881,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.277459298326072,
854
+ "grad_norm": 11.625,
855
+ "learning_rate": 1.4455400137583125e-05,
856
+ "loss": 1.1951,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.2797523503783536,
861
+ "grad_norm": 9.375,
862
+ "learning_rate": 1.4409539096537493e-05,
863
+ "loss": 1.1654,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.2820454024306352,
868
+ "grad_norm": 10.6875,
869
+ "learning_rate": 1.436367805549186e-05,
870
+ "loss": 1.1646,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.2843384544829168,
875
+ "grad_norm": 9.125,
876
+ "learning_rate": 1.4317817014446228e-05,
877
+ "loss": 1.1662,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.28663150653519837,
882
+ "grad_norm": 10.8125,
883
+ "learning_rate": 1.4271955973400597e-05,
884
+ "loss": 1.1961,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.28892455858747995,
889
+ "grad_norm": 8.6875,
890
+ "learning_rate": 1.4226094932354965e-05,
891
+ "loss": 1.179,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.29121761063976154,
896
+ "grad_norm": 11.0625,
897
+ "learning_rate": 1.4180233891309333e-05,
898
+ "loss": 1.2015,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.2935106626920431,
903
+ "grad_norm": 8.25,
904
+ "learning_rate": 1.4134372850263702e-05,
905
+ "loss": 1.176,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.2958037147443247,
910
+ "grad_norm": 8.25,
911
+ "learning_rate": 1.408851180921807e-05,
912
+ "loss": 1.1626,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.2980967667966063,
917
+ "grad_norm": 8.8125,
918
+ "learning_rate": 1.4042650768172439e-05,
919
+ "loss": 1.178,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.3003898188488879,
924
+ "grad_norm": 11.25,
925
+ "learning_rate": 1.3996789727126807e-05,
926
+ "loss": 1.1763,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.30268287090116947,
931
+ "grad_norm": 13.0,
932
+ "learning_rate": 1.3950928686081175e-05,
933
+ "loss": 1.1889,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.30497592295345105,
938
+ "grad_norm": 9.8125,
939
+ "learning_rate": 1.3905067645035544e-05,
940
+ "loss": 1.2124,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.30726897500573264,
945
+ "grad_norm": 8.375,
946
+ "learning_rate": 1.3859206603989912e-05,
947
+ "loss": 1.1906,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.3095620270580142,
952
+ "grad_norm": 7.3125,
953
+ "learning_rate": 1.381334556294428e-05,
954
+ "loss": 1.1758,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.3118550791102958,
959
+ "grad_norm": 12.8125,
960
+ "learning_rate": 1.3767484521898649e-05,
961
+ "loss": 1.2033,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.3141481311625774,
966
+ "grad_norm": 9.0625,
967
+ "learning_rate": 1.3721623480853017e-05,
968
+ "loss": 1.1986,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.316441183214859,
973
+ "grad_norm": 11.75,
974
+ "learning_rate": 1.3675762439807385e-05,
975
+ "loss": 1.17,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.31873423526714056,
980
+ "grad_norm": 11.875,
981
+ "learning_rate": 1.3629901398761754e-05,
982
+ "loss": 1.1687,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.32102728731942215,
987
+ "grad_norm": 7.375,
988
+ "learning_rate": 1.3584040357716122e-05,
989
+ "loss": 1.1815,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.32332033937170374,
994
+ "grad_norm": 8.1875,
995
+ "learning_rate": 1.353817931667049e-05,
996
+ "loss": 1.1864,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.3256133914239853,
1001
+ "grad_norm": 14.125,
1002
+ "learning_rate": 1.3492318275624859e-05,
1003
+ "loss": 1.1832,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.3279064434762669,
1008
+ "grad_norm": 7.59375,
1009
+ "learning_rate": 1.3446457234579227e-05,
1010
+ "loss": 1.189,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.3301994955285485,
1015
+ "grad_norm": 10.8125,
1016
+ "learning_rate": 1.3400596193533595e-05,
1017
+ "loss": 1.1734,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.3324925475808301,
1022
+ "grad_norm": 10.6875,
1023
+ "learning_rate": 1.3354735152487964e-05,
1024
+ "loss": 1.1807,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.33478559963311166,
1029
+ "grad_norm": 10.375,
1030
+ "learning_rate": 1.3308874111442332e-05,
1031
+ "loss": 1.1752,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.33707865168539325,
1036
+ "grad_norm": 11.375,
1037
+ "learning_rate": 1.32630130703967e-05,
1038
+ "loss": 1.1578,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.33937170373767483,
1043
+ "grad_norm": 10.0,
1044
+ "learning_rate": 1.3217152029351069e-05,
1045
+ "loss": 1.177,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.3416647557899564,
1050
+ "grad_norm": 12.4375,
1051
+ "learning_rate": 1.3171290988305437e-05,
1052
+ "loss": 1.1644,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.343957807842238,
1057
+ "grad_norm": 9.625,
1058
+ "learning_rate": 1.3125429947259805e-05,
1059
+ "loss": 1.167,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.3462508598945196,
1064
+ "grad_norm": 11.0,
1065
+ "learning_rate": 1.3079568906214172e-05,
1066
+ "loss": 1.1817,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.3485439119468012,
1071
+ "grad_norm": 8.1875,
1072
+ "learning_rate": 1.303370786516854e-05,
1073
+ "loss": 1.1822,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.35083696399908276,
1078
+ "grad_norm": 8.625,
1079
+ "learning_rate": 1.2987846824122909e-05,
1080
+ "loss": 1.1676,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.35313001605136435,
1085
+ "grad_norm": 6.71875,
1086
+ "learning_rate": 1.2941985783077277e-05,
1087
+ "loss": 1.1792,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.35542306810364593,
1092
+ "grad_norm": 9.0625,
1093
+ "learning_rate": 1.2896124742031645e-05,
1094
+ "loss": 1.1726,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.3577161201559275,
1099
+ "grad_norm": 10.1875,
1100
+ "learning_rate": 1.2850263700986014e-05,
1101
+ "loss": 1.1728,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.3600091722082091,
1106
+ "grad_norm": 12.3125,
1107
+ "learning_rate": 1.2804402659940382e-05,
1108
+ "loss": 1.1825,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.3623022242604907,
1113
+ "grad_norm": 7.125,
1114
+ "learning_rate": 1.275854161889475e-05,
1115
+ "loss": 1.159,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.3645952763127723,
1120
+ "grad_norm": 8.8125,
1121
+ "learning_rate": 1.2712680577849119e-05,
1122
+ "loss": 1.1728,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.36688832836505386,
1127
+ "grad_norm": 11.6875,
1128
+ "learning_rate": 1.2666819536803487e-05,
1129
+ "loss": 1.1976,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.36918138041733545,
1134
+ "grad_norm": 9.875,
1135
+ "learning_rate": 1.2620958495757855e-05,
1136
+ "loss": 1.1806,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.37147443246961703,
1141
+ "grad_norm": 9.8125,
1142
+ "learning_rate": 1.2575097454712224e-05,
1143
+ "loss": 1.1829,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.3737674845218987,
1148
+ "grad_norm": 12.625,
1149
+ "learning_rate": 1.2529236413666592e-05,
1150
+ "loss": 1.169,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.37606053657418026,
1155
+ "grad_norm": 7.625,
1156
+ "learning_rate": 1.248337537262096e-05,
1157
+ "loss": 1.1923,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.37835358862646185,
1162
+ "grad_norm": 10.75,
1163
+ "learning_rate": 1.2437514331575329e-05,
1164
+ "loss": 1.1879,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.38064664067874343,
1169
+ "grad_norm": 8.875,
1170
+ "learning_rate": 1.2391653290529697e-05,
1171
+ "loss": 1.1742,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.382939692731025,
1176
+ "grad_norm": 10.5,
1177
+ "learning_rate": 1.2345792249484066e-05,
1178
+ "loss": 1.1725,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.3852327447833066,
1183
+ "grad_norm": 8.9375,
1184
+ "learning_rate": 1.2299931208438432e-05,
1185
+ "loss": 1.1836,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.3875257968355882,
1190
+ "grad_norm": 8.5,
1191
+ "learning_rate": 1.22540701673928e-05,
1192
+ "loss": 1.1698,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.3898188488878698,
1197
+ "grad_norm": 10.4375,
1198
+ "learning_rate": 1.2208209126347169e-05,
1199
+ "loss": 1.1747,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.39211190094015136,
1204
+ "grad_norm": 11.375,
1205
+ "learning_rate": 1.2162348085301536e-05,
1206
+ "loss": 1.1947,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.39440495299243294,
1211
+ "grad_norm": 9.0625,
1212
+ "learning_rate": 1.2116487044255904e-05,
1213
+ "loss": 1.1847,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.39669800504471453,
1218
+ "grad_norm": 12.0,
1219
+ "learning_rate": 1.2070626003210272e-05,
1220
+ "loss": 1.1897,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.3989910570969961,
1225
+ "grad_norm": 10.6875,
1226
+ "learning_rate": 1.202476496216464e-05,
1227
+ "loss": 1.1668,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.4012841091492777,
1232
+ "grad_norm": 6.8125,
1233
+ "learning_rate": 1.1978903921119009e-05,
1234
+ "loss": 1.1617,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.4035771612015593,
1239
+ "grad_norm": 14.1875,
1240
+ "learning_rate": 1.1933042880073377e-05,
1241
+ "loss": 1.1748,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.4058702132538409,
1246
+ "grad_norm": 11.1875,
1247
+ "learning_rate": 1.1887181839027746e-05,
1248
+ "loss": 1.1836,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.40816326530612246,
1253
+ "grad_norm": 7.90625,
1254
+ "learning_rate": 1.1841320797982114e-05,
1255
+ "loss": 1.1731,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.41045631735840404,
1260
+ "grad_norm": 13.6875,
1261
+ "learning_rate": 1.1795459756936482e-05,
1262
+ "loss": 1.1769,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.41274936941068563,
1267
+ "grad_norm": 10.75,
1268
+ "learning_rate": 1.174959871589085e-05,
1269
+ "loss": 1.181,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.4150424214629672,
1274
+ "grad_norm": 7.28125,
1275
+ "learning_rate": 1.1703737674845219e-05,
1276
+ "loss": 1.1851,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.4173354735152488,
1281
+ "grad_norm": 11.25,
1282
+ "learning_rate": 1.1657876633799587e-05,
1283
+ "loss": 1.1791,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.4196285255675304,
1288
+ "grad_norm": 8.6875,
1289
+ "learning_rate": 1.1612015592753956e-05,
1290
+ "loss": 1.1773,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.42192157761981197,
1295
+ "grad_norm": 11.3125,
1296
+ "learning_rate": 1.1566154551708324e-05,
1297
+ "loss": 1.1644,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.42421462967209356,
1302
+ "grad_norm": 10.0,
1303
+ "learning_rate": 1.1520293510662692e-05,
1304
+ "loss": 1.1703,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.42650768172437514,
1309
+ "grad_norm": 9.4375,
1310
+ "learning_rate": 1.147443246961706e-05,
1311
+ "loss": 1.1696,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.42880073377665673,
1316
+ "grad_norm": 11.625,
1317
+ "learning_rate": 1.1428571428571429e-05,
1318
+ "loss": 1.1809,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.4310937858289383,
1323
+ "grad_norm": 10.0,
1324
+ "learning_rate": 1.1382710387525797e-05,
1325
+ "loss": 1.1865,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.4333868378812199,
1330
+ "grad_norm": 13.0625,
1331
+ "learning_rate": 1.1336849346480166e-05,
1332
+ "loss": 1.1864,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 0.4356798899335015,
1337
+ "grad_norm": 9.1875,
1338
+ "learning_rate": 1.1290988305434534e-05,
1339
+ "loss": 1.1812,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 0.43797294198578307,
1344
+ "grad_norm": 11.1875,
1345
+ "learning_rate": 1.1245127264388902e-05,
1346
+ "loss": 1.1623,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 0.44026599403806466,
1351
+ "grad_norm": 8.9375,
1352
+ "learning_rate": 1.119926622334327e-05,
1353
+ "loss": 1.1655,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 0.44255904609034624,
1358
+ "grad_norm": 9.4375,
1359
+ "learning_rate": 1.1153405182297639e-05,
1360
+ "loss": 1.1528,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 0.4448520981426278,
1365
+ "grad_norm": 12.4375,
1366
+ "learning_rate": 1.1107544141252007e-05,
1367
+ "loss": 1.1836,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 0.4471451501949094,
1372
+ "grad_norm": 10.375,
1373
+ "learning_rate": 1.1061683100206376e-05,
1374
+ "loss": 1.1571,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 0.449438202247191,
1379
+ "grad_norm": 11.8125,
1380
+ "learning_rate": 1.1015822059160744e-05,
1381
+ "loss": 1.1732,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 0.4517312542994726,
1386
+ "grad_norm": 14.3125,
1387
+ "learning_rate": 1.0969961018115112e-05,
1388
+ "loss": 1.1716,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 0.45402430635175417,
1393
+ "grad_norm": 14.1875,
1394
+ "learning_rate": 1.092409997706948e-05,
1395
+ "loss": 1.1583,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 0.45631735840403576,
1400
+ "grad_norm": 10.125,
1401
+ "learning_rate": 1.0878238936023847e-05,
1402
+ "loss": 1.1839,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 0.45861041045631734,
1407
+ "grad_norm": 14.4375,
1408
+ "learning_rate": 1.0832377894978216e-05,
1409
+ "loss": 1.1666,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 0.4609034625085989,
1414
+ "grad_norm": 13.25,
1415
+ "learning_rate": 1.0786516853932584e-05,
1416
+ "loss": 1.1816,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 0.4631965145608805,
1421
+ "grad_norm": 9.75,
1422
+ "learning_rate": 1.0740655812886952e-05,
1423
+ "loss": 1.1702,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 0.4654895666131621,
1428
+ "grad_norm": 9.25,
1429
+ "learning_rate": 1.069479477184132e-05,
1430
+ "loss": 1.1636,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 0.4677826186654437,
1435
+ "grad_norm": 7.9375,
1436
+ "learning_rate": 1.064893373079569e-05,
1437
+ "loss": 1.1645,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 0.47007567071772527,
1442
+ "grad_norm": 12.0625,
1443
+ "learning_rate": 1.0603072689750058e-05,
1444
+ "loss": 1.169,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 0.47236872277000685,
1449
+ "grad_norm": 11.5625,
1450
+ "learning_rate": 1.0557211648704426e-05,
1451
+ "loss": 1.1595,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 0.47466177482228844,
1456
+ "grad_norm": 15.0,
1457
+ "learning_rate": 1.0511350607658794e-05,
1458
+ "loss": 1.16,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 0.47695482687457,
1463
+ "grad_norm": 9.25,
1464
+ "learning_rate": 1.0465489566613163e-05,
1465
+ "loss": 1.1707,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 0.47924787892685167,
1470
+ "grad_norm": 9.75,
1471
+ "learning_rate": 1.0419628525567531e-05,
1472
+ "loss": 1.152,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 0.48154093097913325,
1477
+ "grad_norm": 12.125,
1478
+ "learning_rate": 1.03737674845219e-05,
1479
+ "loss": 1.1793,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 0.48383398303141484,
1484
+ "grad_norm": 12.8125,
1485
+ "learning_rate": 1.0327906443476268e-05,
1486
+ "loss": 1.1921,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 0.4861270350836964,
1491
+ "grad_norm": 13.9375,
1492
+ "learning_rate": 1.0282045402430636e-05,
1493
+ "loss": 1.1683,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 0.488420087135978,
1498
+ "grad_norm": 11.0625,
1499
+ "learning_rate": 1.0236184361385004e-05,
1500
+ "loss": 1.1755,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 0.4907131391882596,
1505
+ "grad_norm": 11.375,
1506
+ "learning_rate": 1.0190323320339373e-05,
1507
+ "loss": 1.1825,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 0.4930061912405412,
1512
+ "grad_norm": 9.8125,
1513
+ "learning_rate": 1.0144462279293741e-05,
1514
+ "loss": 1.1531,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 0.49529924329282277,
1519
+ "grad_norm": 11.375,
1520
+ "learning_rate": 1.009860123824811e-05,
1521
+ "loss": 1.1867,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 0.49759229534510435,
1526
+ "grad_norm": 8.625,
1527
+ "learning_rate": 1.0052740197202478e-05,
1528
+ "loss": 1.1564,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 0.49988534739738594,
1533
+ "grad_norm": 6.46875,
1534
+ "learning_rate": 1.0006879156156846e-05,
1535
+ "loss": 1.1859,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 0.5021783994496675,
1540
+ "grad_norm": 15.25,
1541
+ "learning_rate": 9.961018115111214e-06,
1542
+ "loss": 1.1779,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 0.504471451501949,
1547
+ "grad_norm": 9.5,
1548
+ "learning_rate": 9.915157074065583e-06,
1549
+ "loss": 1.1663,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 0.5067645035542306,
1554
+ "grad_norm": 9.5,
1555
+ "learning_rate": 9.869296033019951e-06,
1556
+ "loss": 1.1526,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 0.5090575556065122,
1561
+ "grad_norm": 7.6875,
1562
+ "learning_rate": 9.82343499197432e-06,
1563
+ "loss": 1.179,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 0.5113506076587938,
1568
+ "grad_norm": 11.125,
1569
+ "learning_rate": 9.777573950928688e-06,
1570
+ "loss": 1.1688,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 0.5136436597110754,
1575
+ "grad_norm": 10.1875,
1576
+ "learning_rate": 9.731712909883056e-06,
1577
+ "loss": 1.159,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 0.515936711763357,
1582
+ "grad_norm": 13.4375,
1583
+ "learning_rate": 9.685851868837424e-06,
1584
+ "loss": 1.153,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 0.5182297638156386,
1589
+ "grad_norm": 12.875,
1590
+ "learning_rate": 9.639990827791793e-06,
1591
+ "loss": 1.1774,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 0.5205228158679202,
1596
+ "grad_norm": 9.9375,
1597
+ "learning_rate": 9.594129786746161e-06,
1598
+ "loss": 1.1825,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 0.5228158679202017,
1603
+ "grad_norm": 6.375,
1604
+ "learning_rate": 9.548268745700528e-06,
1605
+ "loss": 1.1784,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 0.5251089199724833,
1610
+ "grad_norm": 14.375,
1611
+ "learning_rate": 9.502407704654896e-06,
1612
+ "loss": 1.1542,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 0.5274019720247649,
1617
+ "grad_norm": 13.0,
1618
+ "learning_rate": 9.456546663609264e-06,
1619
+ "loss": 1.1705,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 0.5296950240770465,
1624
+ "grad_norm": 15.6875,
1625
+ "learning_rate": 9.410685622563633e-06,
1626
+ "loss": 1.1906,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 0.5319880761293282,
1631
+ "grad_norm": 9.1875,
1632
+ "learning_rate": 9.364824581518001e-06,
1633
+ "loss": 1.1732,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 0.5342811281816098,
1638
+ "grad_norm": 11.4375,
1639
+ "learning_rate": 9.31896354047237e-06,
1640
+ "loss": 1.1994,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 0.5365741802338914,
1645
+ "grad_norm": 9.8125,
1646
+ "learning_rate": 9.273102499426738e-06,
1647
+ "loss": 1.1633,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 0.538867232286173,
1652
+ "grad_norm": 8.9375,
1653
+ "learning_rate": 9.227241458381106e-06,
1654
+ "loss": 1.1683,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 0.5411602843384545,
1659
+ "grad_norm": 12.0,
1660
+ "learning_rate": 9.181380417335474e-06,
1661
+ "loss": 1.1565,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 0.5434533363907361,
1666
+ "grad_norm": 10.0625,
1667
+ "learning_rate": 9.135519376289841e-06,
1668
+ "loss": 1.1726,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 0.5457463884430177,
1673
+ "grad_norm": 13.9375,
1674
+ "learning_rate": 9.08965833524421e-06,
1675
+ "loss": 1.1582,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 0.5480394404952993,
1680
+ "grad_norm": 7.90625,
1681
+ "learning_rate": 9.043797294198578e-06,
1682
+ "loss": 1.1647,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 0.5503324925475809,
1687
+ "grad_norm": 16.0,
1688
+ "learning_rate": 8.997936253152946e-06,
1689
+ "loss": 1.1838,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 0.5526255445998625,
1694
+ "grad_norm": 11.75,
1695
+ "learning_rate": 8.952075212107315e-06,
1696
+ "loss": 1.1699,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 0.554918596652144,
1701
+ "grad_norm": 12.3125,
1702
+ "learning_rate": 8.906214171061683e-06,
1703
+ "loss": 1.1693,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 0.5572116487044256,
1708
+ "grad_norm": 8.625,
1709
+ "learning_rate": 8.860353130016051e-06,
1710
+ "loss": 1.1793,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 0.5595047007567072,
1715
+ "grad_norm": 10.1875,
1716
+ "learning_rate": 8.81449208897042e-06,
1717
+ "loss": 1.1799,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 0.5617977528089888,
1722
+ "grad_norm": 7.625,
1723
+ "learning_rate": 8.768631047924788e-06,
1724
+ "loss": 1.1503,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 0.5640908048612704,
1729
+ "grad_norm": 11.125,
1730
+ "learning_rate": 8.722770006879156e-06,
1731
+ "loss": 1.178,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 0.566383856913552,
1736
+ "grad_norm": 11.375,
1737
+ "learning_rate": 8.676908965833525e-06,
1738
+ "loss": 1.149,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 0.5686769089658336,
1743
+ "grad_norm": 12.1875,
1744
+ "learning_rate": 8.631047924787893e-06,
1745
+ "loss": 1.1781,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 0.5709699610181151,
1750
+ "grad_norm": 11.4375,
1751
+ "learning_rate": 8.585186883742261e-06,
1752
+ "loss": 1.1664,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 0.5732630130703967,
1757
+ "grad_norm": 9.625,
1758
+ "learning_rate": 8.53932584269663e-06,
1759
+ "loss": 1.1448,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 0.5755560651226783,
1764
+ "grad_norm": 11.0625,
1765
+ "learning_rate": 8.493464801650998e-06,
1766
+ "loss": 1.1537,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 0.5778491171749599,
1771
+ "grad_norm": 10.1875,
1772
+ "learning_rate": 8.447603760605366e-06,
1773
+ "loss": 1.1583,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 0.5801421692272415,
1778
+ "grad_norm": 9.25,
1779
+ "learning_rate": 8.401742719559735e-06,
1780
+ "loss": 1.1794,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 0.5824352212795231,
1785
+ "grad_norm": 10.8125,
1786
+ "learning_rate": 8.355881678514103e-06,
1787
+ "loss": 1.1558,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 0.5847282733318047,
1792
+ "grad_norm": 9.9375,
1793
+ "learning_rate": 8.310020637468471e-06,
1794
+ "loss": 1.1693,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 0.5870213253840862,
1799
+ "grad_norm": 13.6875,
1800
+ "learning_rate": 8.26415959642284e-06,
1801
+ "loss": 1.1685,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 0.5893143774363678,
1806
+ "grad_norm": 9.1875,
1807
+ "learning_rate": 8.218298555377208e-06,
1808
+ "loss": 1.1697,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 0.5916074294886494,
1813
+ "grad_norm": 15.0,
1814
+ "learning_rate": 8.172437514331576e-06,
1815
+ "loss": 1.1509,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 0.593900481540931,
1820
+ "grad_norm": 11.75,
1821
+ "learning_rate": 8.126576473285945e-06,
1822
+ "loss": 1.1541,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 0.5961935335932126,
1827
+ "grad_norm": 10.375,
1828
+ "learning_rate": 8.080715432240313e-06,
1829
+ "loss": 1.1517,
1830
+ "step": 2600
1831
+ },
1832
+ {
1833
+ "epoch": 0.5984865856454942,
1834
+ "grad_norm": 13.3125,
1835
+ "learning_rate": 8.034854391194681e-06,
1836
+ "loss": 1.178,
1837
+ "step": 2610
1838
+ },
1839
+ {
1840
+ "epoch": 0.6007796376977758,
1841
+ "grad_norm": 12.6875,
1842
+ "learning_rate": 7.98899335014905e-06,
1843
+ "loss": 1.159,
1844
+ "step": 2620
1845
+ },
1846
+ {
1847
+ "epoch": 0.6030726897500573,
1848
+ "grad_norm": 12.75,
1849
+ "learning_rate": 7.943132309103418e-06,
1850
+ "loss": 1.1604,
1851
+ "step": 2630
1852
+ },
1853
+ {
1854
+ "epoch": 0.6053657418023389,
1855
+ "grad_norm": 7.0625,
1856
+ "learning_rate": 7.897271268057786e-06,
1857
+ "loss": 1.1696,
1858
+ "step": 2640
1859
+ },
1860
+ {
1861
+ "epoch": 0.6076587938546205,
1862
+ "grad_norm": 13.0625,
1863
+ "learning_rate": 7.851410227012155e-06,
1864
+ "loss": 1.1713,
1865
+ "step": 2650
1866
+ },
1867
+ {
1868
+ "epoch": 0.6099518459069021,
1869
+ "grad_norm": 8.8125,
1870
+ "learning_rate": 7.805549185966521e-06,
1871
+ "loss": 1.1678,
1872
+ "step": 2660
1873
+ },
1874
+ {
1875
+ "epoch": 0.6122448979591837,
1876
+ "grad_norm": 12.75,
1877
+ "learning_rate": 7.75968814492089e-06,
1878
+ "loss": 1.168,
1879
+ "step": 2670
1880
+ },
1881
+ {
1882
+ "epoch": 0.6145379500114653,
1883
+ "grad_norm": 7.09375,
1884
+ "learning_rate": 7.713827103875258e-06,
1885
+ "loss": 1.1519,
1886
+ "step": 2680
1887
+ },
1888
+ {
1889
+ "epoch": 0.6168310020637469,
1890
+ "grad_norm": 10.375,
1891
+ "learning_rate": 7.667966062829626e-06,
1892
+ "loss": 1.1651,
1893
+ "step": 2690
1894
+ },
1895
+ {
1896
+ "epoch": 0.6191240541160284,
1897
+ "grad_norm": 11.25,
1898
+ "learning_rate": 7.622105021783996e-06,
1899
+ "loss": 1.1303,
1900
+ "step": 2700
1901
+ },
1902
+ {
1903
+ "epoch": 0.62141710616831,
1904
+ "grad_norm": 13.1875,
1905
+ "learning_rate": 7.576243980738364e-06,
1906
+ "loss": 1.1462,
1907
+ "step": 2710
1908
+ },
1909
+ {
1910
+ "epoch": 0.6237101582205916,
1911
+ "grad_norm": 10.0,
1912
+ "learning_rate": 7.530382939692732e-06,
1913
+ "loss": 1.1786,
1914
+ "step": 2720
1915
+ },
1916
+ {
1917
+ "epoch": 0.6260032102728732,
1918
+ "grad_norm": 11.6875,
1919
+ "learning_rate": 7.4845218986471e-06,
1920
+ "loss": 1.179,
1921
+ "step": 2730
1922
+ },
1923
+ {
1924
+ "epoch": 0.6282962623251548,
1925
+ "grad_norm": 12.3125,
1926
+ "learning_rate": 7.438660857601468e-06,
1927
+ "loss": 1.1708,
1928
+ "step": 2740
1929
+ },
1930
+ {
1931
+ "epoch": 0.6305893143774364,
1932
+ "grad_norm": 11.625,
1933
+ "learning_rate": 7.3927998165558365e-06,
1934
+ "loss": 1.1582,
1935
+ "step": 2750
1936
+ },
1937
+ {
1938
+ "epoch": 0.632882366429718,
1939
+ "grad_norm": 15.3125,
1940
+ "learning_rate": 7.346938775510205e-06,
1941
+ "loss": 1.1622,
1942
+ "step": 2760
1943
+ },
1944
+ {
1945
+ "epoch": 0.6351754184819995,
1946
+ "grad_norm": 13.75,
1947
+ "learning_rate": 7.301077734464573e-06,
1948
+ "loss": 1.1626,
1949
+ "step": 2770
1950
+ },
1951
+ {
1952
+ "epoch": 0.6374684705342811,
1953
+ "grad_norm": 9.0625,
1954
+ "learning_rate": 7.2552166934189415e-06,
1955
+ "loss": 1.1477,
1956
+ "step": 2780
1957
+ },
1958
+ {
1959
+ "epoch": 0.6397615225865627,
1960
+ "grad_norm": 8.75,
1961
+ "learning_rate": 7.20935565237331e-06,
1962
+ "loss": 1.1482,
1963
+ "step": 2790
1964
+ },
1965
+ {
1966
+ "epoch": 0.6420545746388443,
1967
+ "grad_norm": 9.375,
1968
+ "learning_rate": 7.163494611327678e-06,
1969
+ "loss": 1.1293,
1970
+ "step": 2800
1971
+ },
1972
+ {
1973
+ "epoch": 0.6443476266911259,
1974
+ "grad_norm": 10.3125,
1975
+ "learning_rate": 7.1176335702820466e-06,
1976
+ "loss": 1.1391,
1977
+ "step": 2810
1978
+ },
1979
+ {
1980
+ "epoch": 0.6466406787434075,
1981
+ "grad_norm": 12.9375,
1982
+ "learning_rate": 7.071772529236415e-06,
1983
+ "loss": 1.153,
1984
+ "step": 2820
1985
+ },
1986
+ {
1987
+ "epoch": 0.6489337307956891,
1988
+ "grad_norm": 16.875,
1989
+ "learning_rate": 7.025911488190783e-06,
1990
+ "loss": 1.1551,
1991
+ "step": 2830
1992
+ },
1993
+ {
1994
+ "epoch": 0.6512267828479706,
1995
+ "grad_norm": 12.0625,
1996
+ "learning_rate": 6.98005044714515e-06,
1997
+ "loss": 1.1548,
1998
+ "step": 2840
1999
+ },
2000
+ {
2001
+ "epoch": 0.6535198349002522,
2002
+ "grad_norm": 14.0625,
2003
+ "learning_rate": 6.934189406099518e-06,
2004
+ "loss": 1.1771,
2005
+ "step": 2850
2006
+ },
2007
+ {
2008
+ "epoch": 0.6558128869525338,
2009
+ "grad_norm": 14.9375,
2010
+ "learning_rate": 6.888328365053887e-06,
2011
+ "loss": 1.159,
2012
+ "step": 2860
2013
+ },
2014
+ {
2015
+ "epoch": 0.6581059390048154,
2016
+ "grad_norm": 12.0,
2017
+ "learning_rate": 6.842467324008255e-06,
2018
+ "loss": 1.1413,
2019
+ "step": 2870
2020
+ },
2021
+ {
2022
+ "epoch": 0.660398991057097,
2023
+ "grad_norm": 11.3125,
2024
+ "learning_rate": 6.796606282962623e-06,
2025
+ "loss": 1.1717,
2026
+ "step": 2880
2027
+ },
2028
+ {
2029
+ "epoch": 0.6626920431093786,
2030
+ "grad_norm": 11.0625,
2031
+ "learning_rate": 6.750745241916992e-06,
2032
+ "loss": 1.1267,
2033
+ "step": 2890
2034
+ },
2035
+ {
2036
+ "epoch": 0.6649850951616602,
2037
+ "grad_norm": 10.9375,
2038
+ "learning_rate": 6.70488420087136e-06,
2039
+ "loss": 1.121,
2040
+ "step": 2900
2041
+ },
2042
+ {
2043
+ "epoch": 0.6672781472139417,
2044
+ "grad_norm": 8.6875,
2045
+ "learning_rate": 6.659023159825728e-06,
2046
+ "loss": 1.1593,
2047
+ "step": 2910
2048
+ },
2049
+ {
2050
+ "epoch": 0.6695711992662233,
2051
+ "grad_norm": 11.0,
2052
+ "learning_rate": 6.613162118780097e-06,
2053
+ "loss": 1.1764,
2054
+ "step": 2920
2055
+ },
2056
+ {
2057
+ "epoch": 0.6718642513185049,
2058
+ "grad_norm": 8.25,
2059
+ "learning_rate": 6.567301077734465e-06,
2060
+ "loss": 1.1719,
2061
+ "step": 2930
2062
+ },
2063
+ {
2064
+ "epoch": 0.6741573033707865,
2065
+ "grad_norm": 12.4375,
2066
+ "learning_rate": 6.521440036688833e-06,
2067
+ "loss": 1.154,
2068
+ "step": 2940
2069
+ },
2070
+ {
2071
+ "epoch": 0.6764503554230681,
2072
+ "grad_norm": 10.1875,
2073
+ "learning_rate": 6.475578995643202e-06,
2074
+ "loss": 1.1754,
2075
+ "step": 2950
2076
+ },
2077
+ {
2078
+ "epoch": 0.6787434074753497,
2079
+ "grad_norm": 11.75,
2080
+ "learning_rate": 6.42971795459757e-06,
2081
+ "loss": 1.1703,
2082
+ "step": 2960
2083
+ },
2084
+ {
2085
+ "epoch": 0.6810364595276313,
2086
+ "grad_norm": 9.875,
2087
+ "learning_rate": 6.3838569135519375e-06,
2088
+ "loss": 1.1494,
2089
+ "step": 2970
2090
+ },
2091
+ {
2092
+ "epoch": 0.6833295115799128,
2093
+ "grad_norm": 13.0625,
2094
+ "learning_rate": 6.337995872506306e-06,
2095
+ "loss": 1.1638,
2096
+ "step": 2980
2097
+ },
2098
+ {
2099
+ "epoch": 0.6856225636321944,
2100
+ "grad_norm": 10.75,
2101
+ "learning_rate": 6.292134831460674e-06,
2102
+ "loss": 1.1403,
2103
+ "step": 2990
2104
+ },
2105
+ {
2106
+ "epoch": 0.687915615684476,
2107
+ "grad_norm": 10.9375,
2108
+ "learning_rate": 6.2462737904150426e-06,
2109
+ "loss": 1.1696,
2110
+ "step": 3000
2111
+ },
2112
+ {
2113
+ "epoch": 0.6902086677367576,
2114
+ "grad_norm": 9.625,
2115
+ "learning_rate": 6.200412749369411e-06,
2116
+ "loss": 1.1577,
2117
+ "step": 3010
2118
+ },
2119
+ {
2120
+ "epoch": 0.6925017197890392,
2121
+ "grad_norm": 8.4375,
2122
+ "learning_rate": 6.154551708323779e-06,
2123
+ "loss": 1.1644,
2124
+ "step": 3020
2125
+ },
2126
+ {
2127
+ "epoch": 0.6947947718413208,
2128
+ "grad_norm": 9.4375,
2129
+ "learning_rate": 6.108690667278148e-06,
2130
+ "loss": 1.1587,
2131
+ "step": 3030
2132
+ },
2133
+ {
2134
+ "epoch": 0.6970878238936024,
2135
+ "grad_norm": 9.9375,
2136
+ "learning_rate": 6.062829626232516e-06,
2137
+ "loss": 1.1618,
2138
+ "step": 3040
2139
+ },
2140
+ {
2141
+ "epoch": 0.6993808759458839,
2142
+ "grad_norm": 9.5625,
2143
+ "learning_rate": 6.016968585186884e-06,
2144
+ "loss": 1.1613,
2145
+ "step": 3050
2146
+ },
2147
+ {
2148
+ "epoch": 0.7016739279981655,
2149
+ "grad_norm": 12.6875,
2150
+ "learning_rate": 5.971107544141253e-06,
2151
+ "loss": 1.1492,
2152
+ "step": 3060
2153
+ },
2154
+ {
2155
+ "epoch": 0.7039669800504471,
2156
+ "grad_norm": 8.875,
2157
+ "learning_rate": 5.925246503095621e-06,
2158
+ "loss": 1.1495,
2159
+ "step": 3070
2160
+ },
2161
+ {
2162
+ "epoch": 0.7062600321027287,
2163
+ "grad_norm": 12.75,
2164
+ "learning_rate": 5.879385462049989e-06,
2165
+ "loss": 1.149,
2166
+ "step": 3080
2167
+ },
2168
+ {
2169
+ "epoch": 0.7085530841550103,
2170
+ "grad_norm": 9.8125,
2171
+ "learning_rate": 5.833524421004358e-06,
2172
+ "loss": 1.1616,
2173
+ "step": 3090
2174
+ },
2175
+ {
2176
+ "epoch": 0.7108461362072919,
2177
+ "grad_norm": 11.3125,
2178
+ "learning_rate": 5.787663379958726e-06,
2179
+ "loss": 1.1694,
2180
+ "step": 3100
2181
+ },
2182
+ {
2183
+ "epoch": 0.7131391882595735,
2184
+ "grad_norm": 7.90625,
2185
+ "learning_rate": 5.7418023389130935e-06,
2186
+ "loss": 1.1384,
2187
+ "step": 3110
2188
+ },
2189
+ {
2190
+ "epoch": 0.715432240311855,
2191
+ "grad_norm": 10.0,
2192
+ "learning_rate": 5.695941297867462e-06,
2193
+ "loss": 1.156,
2194
+ "step": 3120
2195
+ },
2196
+ {
2197
+ "epoch": 0.7177252923641366,
2198
+ "grad_norm": 14.6875,
2199
+ "learning_rate": 5.65008025682183e-06,
2200
+ "loss": 1.1736,
2201
+ "step": 3130
2202
+ },
2203
+ {
2204
+ "epoch": 0.7200183444164182,
2205
+ "grad_norm": 11.4375,
2206
+ "learning_rate": 5.6042192157761985e-06,
2207
+ "loss": 1.1293,
2208
+ "step": 3140
2209
+ },
2210
+ {
2211
+ "epoch": 0.7223113964686998,
2212
+ "grad_norm": 12.875,
2213
+ "learning_rate": 5.558358174730567e-06,
2214
+ "loss": 1.1067,
2215
+ "step": 3150
2216
+ },
2217
+ {
2218
+ "epoch": 0.7246044485209814,
2219
+ "grad_norm": 11.6875,
2220
+ "learning_rate": 5.512497133684935e-06,
2221
+ "loss": 1.1516,
2222
+ "step": 3160
2223
+ },
2224
+ {
2225
+ "epoch": 0.726897500573263,
2226
+ "grad_norm": 10.5625,
2227
+ "learning_rate": 5.4666360926393036e-06,
2228
+ "loss": 1.1532,
2229
+ "step": 3170
2230
+ },
2231
+ {
2232
+ "epoch": 0.7291905526255446,
2233
+ "grad_norm": 9.6875,
2234
+ "learning_rate": 5.420775051593672e-06,
2235
+ "loss": 1.1647,
2236
+ "step": 3180
2237
+ },
2238
+ {
2239
+ "epoch": 0.7314836046778261,
2240
+ "grad_norm": 12.1875,
2241
+ "learning_rate": 5.37491401054804e-06,
2242
+ "loss": 1.1914,
2243
+ "step": 3190
2244
+ },
2245
+ {
2246
+ "epoch": 0.7337766567301077,
2247
+ "grad_norm": 13.25,
2248
+ "learning_rate": 5.329052969502409e-06,
2249
+ "loss": 1.148,
2250
+ "step": 3200
2251
+ },
2252
+ {
2253
+ "epoch": 0.7360697087823893,
2254
+ "grad_norm": 8.375,
2255
+ "learning_rate": 5.283191928456777e-06,
2256
+ "loss": 1.1612,
2257
+ "step": 3210
2258
+ },
2259
+ {
2260
+ "epoch": 0.7383627608346709,
2261
+ "grad_norm": 8.75,
2262
+ "learning_rate": 5.237330887411145e-06,
2263
+ "loss": 1.1402,
2264
+ "step": 3220
2265
+ },
2266
+ {
2267
+ "epoch": 0.7406558128869525,
2268
+ "grad_norm": 11.5,
2269
+ "learning_rate": 5.191469846365514e-06,
2270
+ "loss": 1.1737,
2271
+ "step": 3230
2272
+ },
2273
+ {
2274
+ "epoch": 0.7429488649392341,
2275
+ "grad_norm": 11.625,
2276
+ "learning_rate": 5.145608805319882e-06,
2277
+ "loss": 1.1854,
2278
+ "step": 3240
2279
+ },
2280
+ {
2281
+ "epoch": 0.7452419169915158,
2282
+ "grad_norm": 11.125,
2283
+ "learning_rate": 5.0997477642742495e-06,
2284
+ "loss": 1.1611,
2285
+ "step": 3250
2286
+ },
2287
+ {
2288
+ "epoch": 0.7475349690437973,
2289
+ "grad_norm": 9.6875,
2290
+ "learning_rate": 5.053886723228618e-06,
2291
+ "loss": 1.1477,
2292
+ "step": 3260
2293
+ },
2294
+ {
2295
+ "epoch": 0.7498280210960789,
2296
+ "grad_norm": 10.75,
2297
+ "learning_rate": 5.008025682182986e-06,
2298
+ "loss": 1.1608,
2299
+ "step": 3270
2300
+ },
2301
+ {
2302
+ "epoch": 0.7521210731483605,
2303
+ "grad_norm": 14.125,
2304
+ "learning_rate": 4.9621646411373545e-06,
2305
+ "loss": 1.1658,
2306
+ "step": 3280
2307
+ },
2308
+ {
2309
+ "epoch": 0.7544141252006421,
2310
+ "grad_norm": 9.5625,
2311
+ "learning_rate": 4.916303600091723e-06,
2312
+ "loss": 1.15,
2313
+ "step": 3290
2314
+ },
2315
+ {
2316
+ "epoch": 0.7567071772529237,
2317
+ "grad_norm": 13.625,
2318
+ "learning_rate": 4.87044255904609e-06,
2319
+ "loss": 1.1616,
2320
+ "step": 3300
2321
+ },
2322
+ {
2323
+ "epoch": 0.7590002293052053,
2324
+ "grad_norm": 12.625,
2325
+ "learning_rate": 4.824581518000459e-06,
2326
+ "loss": 1.1545,
2327
+ "step": 3310
2328
+ },
2329
+ {
2330
+ "epoch": 0.7612932813574869,
2331
+ "grad_norm": 12.75,
2332
+ "learning_rate": 4.778720476954827e-06,
2333
+ "loss": 1.1637,
2334
+ "step": 3320
2335
+ },
2336
+ {
2337
+ "epoch": 0.7635863334097684,
2338
+ "grad_norm": 10.0625,
2339
+ "learning_rate": 4.732859435909195e-06,
2340
+ "loss": 1.1497,
2341
+ "step": 3330
2342
+ },
2343
+ {
2344
+ "epoch": 0.76587938546205,
2345
+ "grad_norm": 11.3125,
2346
+ "learning_rate": 4.686998394863564e-06,
2347
+ "loss": 1.1739,
2348
+ "step": 3340
2349
+ },
2350
+ {
2351
+ "epoch": 0.7681724375143316,
2352
+ "grad_norm": 12.75,
2353
+ "learning_rate": 4.641137353817932e-06,
2354
+ "loss": 1.157,
2355
+ "step": 3350
2356
+ },
2357
+ {
2358
+ "epoch": 0.7704654895666132,
2359
+ "grad_norm": 7.90625,
2360
+ "learning_rate": 4.5952763127723e-06,
2361
+ "loss": 1.1537,
2362
+ "step": 3360
2363
+ },
2364
+ {
2365
+ "epoch": 0.7727585416188948,
2366
+ "grad_norm": 10.625,
2367
+ "learning_rate": 4.549415271726669e-06,
2368
+ "loss": 1.1519,
2369
+ "step": 3370
2370
+ },
2371
+ {
2372
+ "epoch": 0.7750515936711764,
2373
+ "grad_norm": 11.6875,
2374
+ "learning_rate": 4.503554230681037e-06,
2375
+ "loss": 1.1483,
2376
+ "step": 3380
2377
+ },
2378
+ {
2379
+ "epoch": 0.777344645723458,
2380
+ "grad_norm": 11.75,
2381
+ "learning_rate": 4.4576931896354054e-06,
2382
+ "loss": 1.1423,
2383
+ "step": 3390
2384
+ },
2385
+ {
2386
+ "epoch": 0.7796376977757395,
2387
+ "grad_norm": 13.9375,
2388
+ "learning_rate": 4.411832148589774e-06,
2389
+ "loss": 1.1684,
2390
+ "step": 3400
2391
+ },
2392
+ {
2393
+ "epoch": 0.7819307498280211,
2394
+ "grad_norm": 15.9375,
2395
+ "learning_rate": 4.365971107544142e-06,
2396
+ "loss": 1.1695,
2397
+ "step": 3410
2398
+ },
2399
+ {
2400
+ "epoch": 0.7842238018803027,
2401
+ "grad_norm": 13.625,
2402
+ "learning_rate": 4.32011006649851e-06,
2403
+ "loss": 1.1625,
2404
+ "step": 3420
2405
+ },
2406
+ {
2407
+ "epoch": 0.7865168539325843,
2408
+ "grad_norm": 13.375,
2409
+ "learning_rate": 4.274249025452878e-06,
2410
+ "loss": 1.1753,
2411
+ "step": 3430
2412
+ },
2413
+ {
2414
+ "epoch": 0.7888099059848659,
2415
+ "grad_norm": 11.25,
2416
+ "learning_rate": 4.228387984407246e-06,
2417
+ "loss": 1.1755,
2418
+ "step": 3440
2419
+ },
2420
+ {
2421
+ "epoch": 0.7911029580371475,
2422
+ "grad_norm": 9.375,
2423
+ "learning_rate": 4.182526943361615e-06,
2424
+ "loss": 1.1578,
2425
+ "step": 3450
2426
+ },
2427
+ {
2428
+ "epoch": 0.7933960100894291,
2429
+ "grad_norm": 9.125,
2430
+ "learning_rate": 4.136665902315983e-06,
2431
+ "loss": 1.1278,
2432
+ "step": 3460
2433
+ },
2434
+ {
2435
+ "epoch": 0.7956890621417106,
2436
+ "grad_norm": 10.625,
2437
+ "learning_rate": 4.090804861270351e-06,
2438
+ "loss": 1.1695,
2439
+ "step": 3470
2440
+ },
2441
+ {
2442
+ "epoch": 0.7979821141939922,
2443
+ "grad_norm": 9.8125,
2444
+ "learning_rate": 4.04494382022472e-06,
2445
+ "loss": 1.1471,
2446
+ "step": 3480
2447
+ },
2448
+ {
2449
+ "epoch": 0.8002751662462738,
2450
+ "grad_norm": 10.5,
2451
+ "learning_rate": 3.999082779179087e-06,
2452
+ "loss": 1.1484,
2453
+ "step": 3490
2454
+ },
2455
+ {
2456
+ "epoch": 0.8025682182985554,
2457
+ "grad_norm": 14.125,
2458
+ "learning_rate": 3.9532217381334555e-06,
2459
+ "loss": 1.173,
2460
+ "step": 3500
2461
+ },
2462
+ {
2463
+ "epoch": 0.804861270350837,
2464
+ "grad_norm": 8.125,
2465
+ "learning_rate": 3.907360697087824e-06,
2466
+ "loss": 1.1756,
2467
+ "step": 3510
2468
+ },
2469
+ {
2470
+ "epoch": 0.8071543224031186,
2471
+ "grad_norm": 9.125,
2472
+ "learning_rate": 3.861499656042192e-06,
2473
+ "loss": 1.1492,
2474
+ "step": 3520
2475
+ },
2476
+ {
2477
+ "epoch": 0.8094473744554002,
2478
+ "grad_norm": 8.3125,
2479
+ "learning_rate": 3.8156386149965606e-06,
2480
+ "loss": 1.1502,
2481
+ "step": 3530
2482
+ },
2483
+ {
2484
+ "epoch": 0.8117404265076817,
2485
+ "grad_norm": 9.625,
2486
+ "learning_rate": 3.769777573950929e-06,
2487
+ "loss": 1.1442,
2488
+ "step": 3540
2489
+ },
2490
+ {
2491
+ "epoch": 0.8140334785599633,
2492
+ "grad_norm": 11.75,
2493
+ "learning_rate": 3.7239165329052972e-06,
2494
+ "loss": 1.1612,
2495
+ "step": 3550
2496
+ },
2497
+ {
2498
+ "epoch": 0.8163265306122449,
2499
+ "grad_norm": 10.5,
2500
+ "learning_rate": 3.6780554918596656e-06,
2501
+ "loss": 1.1628,
2502
+ "step": 3560
2503
+ },
2504
+ {
2505
+ "epoch": 0.8186195826645265,
2506
+ "grad_norm": 10.75,
2507
+ "learning_rate": 3.632194450814034e-06,
2508
+ "loss": 1.1583,
2509
+ "step": 3570
2510
+ },
2511
+ {
2512
+ "epoch": 0.8209126347168081,
2513
+ "grad_norm": 14.5,
2514
+ "learning_rate": 3.5863334097684023e-06,
2515
+ "loss": 1.1596,
2516
+ "step": 3580
2517
+ },
2518
+ {
2519
+ "epoch": 0.8232056867690897,
2520
+ "grad_norm": 10.0,
2521
+ "learning_rate": 3.5404723687227706e-06,
2522
+ "loss": 1.1573,
2523
+ "step": 3590
2524
+ },
2525
+ {
2526
+ "epoch": 0.8254987388213713,
2527
+ "grad_norm": 12.4375,
2528
+ "learning_rate": 3.4946113276771385e-06,
2529
+ "loss": 1.1575,
2530
+ "step": 3600
2531
+ },
2532
+ {
2533
+ "epoch": 0.8277917908736528,
2534
+ "grad_norm": 10.625,
2535
+ "learning_rate": 3.448750286631507e-06,
2536
+ "loss": 1.136,
2537
+ "step": 3610
2538
+ },
2539
+ {
2540
+ "epoch": 0.8300848429259344,
2541
+ "grad_norm": 10.875,
2542
+ "learning_rate": 3.4028892455858752e-06,
2543
+ "loss": 1.1493,
2544
+ "step": 3620
2545
+ },
2546
+ {
2547
+ "epoch": 0.832377894978216,
2548
+ "grad_norm": 17.0,
2549
+ "learning_rate": 3.3570282045402436e-06,
2550
+ "loss": 1.1689,
2551
+ "step": 3630
2552
+ },
2553
+ {
2554
+ "epoch": 0.8346709470304976,
2555
+ "grad_norm": 8.9375,
2556
+ "learning_rate": 3.311167163494612e-06,
2557
+ "loss": 1.1406,
2558
+ "step": 3640
2559
+ },
2560
+ {
2561
+ "epoch": 0.8369639990827792,
2562
+ "grad_norm": 9.625,
2563
+ "learning_rate": 3.2653061224489794e-06,
2564
+ "loss": 1.1438,
2565
+ "step": 3650
2566
+ },
2567
+ {
2568
+ "epoch": 0.8392570511350608,
2569
+ "grad_norm": 12.125,
2570
+ "learning_rate": 3.2194450814033478e-06,
2571
+ "loss": 1.1721,
2572
+ "step": 3660
2573
+ },
2574
+ {
2575
+ "epoch": 0.8415501031873424,
2576
+ "grad_norm": 8.5,
2577
+ "learning_rate": 3.173584040357716e-06,
2578
+ "loss": 1.1498,
2579
+ "step": 3670
2580
+ },
2581
+ {
2582
+ "epoch": 0.8438431552396239,
2583
+ "grad_norm": 11.625,
2584
+ "learning_rate": 3.1277229993120844e-06,
2585
+ "loss": 1.1531,
2586
+ "step": 3680
2587
+ },
2588
+ {
2589
+ "epoch": 0.8461362072919055,
2590
+ "grad_norm": 10.0625,
2591
+ "learning_rate": 3.081861958266453e-06,
2592
+ "loss": 1.1489,
2593
+ "step": 3690
2594
+ },
2595
+ {
2596
+ "epoch": 0.8484292593441871,
2597
+ "grad_norm": 14.375,
2598
+ "learning_rate": 3.036000917220821e-06,
2599
+ "loss": 1.133,
2600
+ "step": 3700
2601
+ },
2602
+ {
2603
+ "epoch": 0.8507223113964687,
2604
+ "grad_norm": 9.3125,
2605
+ "learning_rate": 2.9901398761751895e-06,
2606
+ "loss": 1.1565,
2607
+ "step": 3710
2608
+ },
2609
+ {
2610
+ "epoch": 0.8530153634487503,
2611
+ "grad_norm": 10.0,
2612
+ "learning_rate": 2.9442788351295574e-06,
2613
+ "loss": 1.162,
2614
+ "step": 3720
2615
+ },
2616
+ {
2617
+ "epoch": 0.8553084155010319,
2618
+ "grad_norm": 13.9375,
2619
+ "learning_rate": 2.8984177940839257e-06,
2620
+ "loss": 1.1472,
2621
+ "step": 3730
2622
+ },
2623
+ {
2624
+ "epoch": 0.8576014675533135,
2625
+ "grad_norm": 11.25,
2626
+ "learning_rate": 2.852556753038294e-06,
2627
+ "loss": 1.1293,
2628
+ "step": 3740
2629
+ },
2630
+ {
2631
+ "epoch": 0.859894519605595,
2632
+ "grad_norm": 10.4375,
2633
+ "learning_rate": 2.8066957119926624e-06,
2634
+ "loss": 1.1667,
2635
+ "step": 3750
2636
+ },
2637
+ {
2638
+ "epoch": 0.8621875716578766,
2639
+ "grad_norm": 11.0625,
2640
+ "learning_rate": 2.7608346709470308e-06,
2641
+ "loss": 1.148,
2642
+ "step": 3760
2643
+ },
2644
+ {
2645
+ "epoch": 0.8644806237101582,
2646
+ "grad_norm": 12.6875,
2647
+ "learning_rate": 2.714973629901399e-06,
2648
+ "loss": 1.1476,
2649
+ "step": 3770
2650
+ },
2651
+ {
2652
+ "epoch": 0.8667736757624398,
2653
+ "grad_norm": 15.0,
2654
+ "learning_rate": 2.6691125888557675e-06,
2655
+ "loss": 1.1556,
2656
+ "step": 3780
2657
+ },
2658
+ {
2659
+ "epoch": 0.8690667278147214,
2660
+ "grad_norm": 8.0,
2661
+ "learning_rate": 2.6232515478101354e-06,
2662
+ "loss": 1.1458,
2663
+ "step": 3790
2664
+ },
2665
+ {
2666
+ "epoch": 0.871359779867003,
2667
+ "grad_norm": 13.9375,
2668
+ "learning_rate": 2.5773905067645037e-06,
2669
+ "loss": 1.1335,
2670
+ "step": 3800
2671
+ },
2672
+ {
2673
+ "epoch": 0.8736528319192846,
2674
+ "grad_norm": 11.75,
2675
+ "learning_rate": 2.531529465718872e-06,
2676
+ "loss": 1.1534,
2677
+ "step": 3810
2678
+ },
2679
+ {
2680
+ "epoch": 0.8759458839715661,
2681
+ "grad_norm": 11.9375,
2682
+ "learning_rate": 2.48566842467324e-06,
2683
+ "loss": 1.1266,
2684
+ "step": 3820
2685
+ },
2686
+ {
2687
+ "epoch": 0.8782389360238477,
2688
+ "grad_norm": 9.875,
2689
+ "learning_rate": 2.4398073836276083e-06,
2690
+ "loss": 1.1467,
2691
+ "step": 3830
2692
+ },
2693
+ {
2694
+ "epoch": 0.8805319880761293,
2695
+ "grad_norm": 12.1875,
2696
+ "learning_rate": 2.3939463425819767e-06,
2697
+ "loss": 1.1495,
2698
+ "step": 3840
2699
+ },
2700
+ {
2701
+ "epoch": 0.8828250401284109,
2702
+ "grad_norm": 12.0625,
2703
+ "learning_rate": 2.348085301536345e-06,
2704
+ "loss": 1.1471,
2705
+ "step": 3850
2706
+ },
2707
+ {
2708
+ "epoch": 0.8851180921806925,
2709
+ "grad_norm": 11.5625,
2710
+ "learning_rate": 2.3022242604907134e-06,
2711
+ "loss": 1.143,
2712
+ "step": 3860
2713
+ },
2714
+ {
2715
+ "epoch": 0.8874111442329741,
2716
+ "grad_norm": 13.25,
2717
+ "learning_rate": 2.2563632194450817e-06,
2718
+ "loss": 1.158,
2719
+ "step": 3870
2720
+ },
2721
+ {
2722
+ "epoch": 0.8897041962852557,
2723
+ "grad_norm": 13.4375,
2724
+ "learning_rate": 2.21050217839945e-06,
2725
+ "loss": 1.1639,
2726
+ "step": 3880
2727
+ },
2728
+ {
2729
+ "epoch": 0.8919972483375372,
2730
+ "grad_norm": 16.375,
2731
+ "learning_rate": 2.164641137353818e-06,
2732
+ "loss": 1.1484,
2733
+ "step": 3890
2734
+ },
2735
+ {
2736
+ "epoch": 0.8942903003898188,
2737
+ "grad_norm": 13.0625,
2738
+ "learning_rate": 2.1187800963081863e-06,
2739
+ "loss": 1.1343,
2740
+ "step": 3900
2741
+ },
2742
+ {
2743
+ "epoch": 0.8965833524421004,
2744
+ "grad_norm": 10.0625,
2745
+ "learning_rate": 2.0729190552625547e-06,
2746
+ "loss": 1.1346,
2747
+ "step": 3910
2748
+ },
2749
+ {
2750
+ "epoch": 0.898876404494382,
2751
+ "grad_norm": 13.0625,
2752
+ "learning_rate": 2.027058014216923e-06,
2753
+ "loss": 1.1496,
2754
+ "step": 3920
2755
+ },
2756
+ {
2757
+ "epoch": 0.9011694565466636,
2758
+ "grad_norm": 12.1875,
2759
+ "learning_rate": 1.9811969731712914e-06,
2760
+ "loss": 1.1345,
2761
+ "step": 3930
2762
+ },
2763
+ {
2764
+ "epoch": 0.9034625085989452,
2765
+ "grad_norm": 10.6875,
2766
+ "learning_rate": 1.9353359321256593e-06,
2767
+ "loss": 1.1551,
2768
+ "step": 3940
2769
+ },
2770
+ {
2771
+ "epoch": 0.9057555606512268,
2772
+ "grad_norm": 10.5625,
2773
+ "learning_rate": 1.8894748910800276e-06,
2774
+ "loss": 1.1252,
2775
+ "step": 3950
2776
+ },
2777
+ {
2778
+ "epoch": 0.9080486127035083,
2779
+ "grad_norm": 15.0,
2780
+ "learning_rate": 1.843613850034396e-06,
2781
+ "loss": 1.1214,
2782
+ "step": 3960
2783
+ },
2784
+ {
2785
+ "epoch": 0.9103416647557899,
2786
+ "grad_norm": 11.375,
2787
+ "learning_rate": 1.797752808988764e-06,
2788
+ "loss": 1.1846,
2789
+ "step": 3970
2790
+ },
2791
+ {
2792
+ "epoch": 0.9126347168080715,
2793
+ "grad_norm": 10.125,
2794
+ "learning_rate": 1.7518917679431324e-06,
2795
+ "loss": 1.168,
2796
+ "step": 3980
2797
+ },
2798
+ {
2799
+ "epoch": 0.9149277688603531,
2800
+ "grad_norm": 11.0,
2801
+ "learning_rate": 1.7060307268975008e-06,
2802
+ "loss": 1.1499,
2803
+ "step": 3990
2804
+ },
2805
+ {
2806
+ "epoch": 0.9172208209126347,
2807
+ "grad_norm": 15.0625,
2808
+ "learning_rate": 1.660169685851869e-06,
2809
+ "loss": 1.1486,
2810
+ "step": 4000
2811
+ }
2812
+ ],
2813
+ "logging_steps": 10,
2814
+ "max_steps": 4361,
2815
+ "num_input_tokens_seen": 0,
2816
+ "num_train_epochs": 1,
2817
+ "save_steps": 500,
2818
+ "stateful_callbacks": {
2819
+ "TrainerControl": {
2820
+ "args": {
2821
+ "should_epoch_stop": false,
2822
+ "should_evaluate": false,
2823
+ "should_log": false,
2824
+ "should_save": true,
2825
+ "should_training_stop": false
2826
+ },
2827
+ "attributes": {}
2828
+ }
2829
+ },
2830
+ "total_flos": 7.105650894786232e+17,
2831
+ "train_batch_size": 16,
2832
+ "trial_name": null,
2833
+ "trial_params": null
2834
+ }
checkpoint-4000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:817afec82073fe07bc9956395f9bc90863ff9b9ead8fca93cc3b4cdde0c205cd
3
+ size 6417
checkpoint-4000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4361/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
checkpoint-4361/chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ ' }}{% endif %}{{'<|im_start|>' + message['role'] + '
4
+ ' + message['content'] + '<|im_end|>' + '
5
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
6
+ ' }}{% endif %}
checkpoint-4361/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1536,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 8960,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
+ "max_position_embeddings": 32768,
43
+ "max_window_layers": 28,
44
+ "model_type": "qwen2",
45
+ "num_attention_heads": 12,
46
+ "num_hidden_layers": 28,
47
+ "num_key_value_heads": 2,
48
+ "pad_token_id": 151643,
49
+ "rms_norm_eps": 1e-06,
50
+ "rope_scaling": null,
51
+ "rope_theta": 1000000.0,
52
+ "sliding_window": null,
53
+ "tie_word_embeddings": true,
54
+ "transformers_version": "4.57.1",
55
+ "use_cache": false,
56
+ "use_sliding_window": false,
57
+ "vocab_size": 151936
58
+ }
checkpoint-4361/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "repetition_penalty": 1.1,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.57.1"
13
+ }
checkpoint-4361/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4361/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ce0e62a5a11eed3eec409a6d0995c85bc301de1fbcfc630b86e7badaa54afc9
3
+ size 3087467144
checkpoint-4361/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf282d80d7590e1a96823d6fe8e19eeccab110d42b7f9350ed8b3a8fe77d9c4c
3
+ size 6175147805
checkpoint-4361/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c15d10da233568de54180256b227cfe26dea6eaac6df08048357111de9ef60d
3
+ size 14645
checkpoint-4361/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7efb2c25f030e706dfa8781717a263c439621f5974e67634672fdd7f642112eb
3
+ size 1465
checkpoint-4361/special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
checkpoint-4361/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
3
+ size 11418266
checkpoint-4361/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "<|im_end|>",
36
+ "errors": "replace",
37
+ "extra_special_tokens": {},
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null
43
+ }
checkpoint-4361/trainer_state.json ADDED
@@ -0,0 +1,3086 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 4361,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.002293052052281587,
14
+ "grad_norm": 18.875,
15
+ "learning_rate": 1.9958725063058934e-05,
16
+ "loss": 1.7556,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.004586104104563174,
21
+ "grad_norm": 19.875,
22
+ "learning_rate": 1.99128640220133e-05,
23
+ "loss": 1.1973,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.00687915615684476,
28
+ "grad_norm": 15.6875,
29
+ "learning_rate": 1.986700298096767e-05,
30
+ "loss": 1.2111,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.009172208209126348,
35
+ "grad_norm": 15.5625,
36
+ "learning_rate": 1.9821141939922037e-05,
37
+ "loss": 1.2078,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.011465260261407933,
42
+ "grad_norm": 11.125,
43
+ "learning_rate": 1.9775280898876404e-05,
44
+ "loss": 1.1955,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.01375831231368952,
49
+ "grad_norm": 15.875,
50
+ "learning_rate": 1.9729419857830774e-05,
51
+ "loss": 1.2044,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.016051364365971106,
56
+ "grad_norm": 17.875,
57
+ "learning_rate": 1.968355881678514e-05,
58
+ "loss": 1.1926,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.018344416418252695,
63
+ "grad_norm": 14.5,
64
+ "learning_rate": 1.963769777573951e-05,
65
+ "loss": 1.2002,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.02063746847053428,
70
+ "grad_norm": 11.8125,
71
+ "learning_rate": 1.9591836734693877e-05,
72
+ "loss": 1.1892,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.022930520522815866,
77
+ "grad_norm": 11.5,
78
+ "learning_rate": 1.9545975693648247e-05,
79
+ "loss": 1.19,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.025223572575097455,
84
+ "grad_norm": 16.0,
85
+ "learning_rate": 1.9500114652602614e-05,
86
+ "loss": 1.1949,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.02751662462737904,
91
+ "grad_norm": 16.75,
92
+ "learning_rate": 1.9454253611556984e-05,
93
+ "loss": 1.1921,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.029809676679660627,
98
+ "grad_norm": 14.125,
99
+ "learning_rate": 1.940839257051135e-05,
100
+ "loss": 1.1958,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.03210272873194221,
105
+ "grad_norm": 11.5625,
106
+ "learning_rate": 1.936253152946572e-05,
107
+ "loss": 1.1852,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.034395780784223805,
112
+ "grad_norm": 18.25,
113
+ "learning_rate": 1.9316670488420087e-05,
114
+ "loss": 1.187,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.03668883283650539,
119
+ "grad_norm": 15.9375,
120
+ "learning_rate": 1.9270809447374457e-05,
121
+ "loss": 1.1867,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.038981884888786976,
126
+ "grad_norm": 19.75,
127
+ "learning_rate": 1.9224948406328824e-05,
128
+ "loss": 1.2015,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.04127493694106856,
133
+ "grad_norm": 11.625,
134
+ "learning_rate": 1.9179087365283194e-05,
135
+ "loss": 1.2059,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.04356798899335015,
140
+ "grad_norm": 16.375,
141
+ "learning_rate": 1.913322632423756e-05,
142
+ "loss": 1.1962,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.04586104104563173,
147
+ "grad_norm": 13.0,
148
+ "learning_rate": 1.908736528319193e-05,
149
+ "loss": 1.1955,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.048154093097913325,
154
+ "grad_norm": 11.4375,
155
+ "learning_rate": 1.9041504242146297e-05,
156
+ "loss": 1.1766,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.05044714515019491,
161
+ "grad_norm": 11.5625,
162
+ "learning_rate": 1.8995643201100668e-05,
163
+ "loss": 1.1857,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.052740197202476496,
168
+ "grad_norm": 17.875,
169
+ "learning_rate": 1.8949782160055034e-05,
170
+ "loss": 1.1981,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.05503324925475808,
175
+ "grad_norm": 14.25,
176
+ "learning_rate": 1.8903921119009404e-05,
177
+ "loss": 1.2041,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.05732630130703967,
182
+ "grad_norm": 16.0,
183
+ "learning_rate": 1.885806007796377e-05,
184
+ "loss": 1.1989,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.05961935335932125,
189
+ "grad_norm": 17.25,
190
+ "learning_rate": 1.881219903691814e-05,
191
+ "loss": 1.196,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.061912405411602846,
196
+ "grad_norm": 13.3125,
197
+ "learning_rate": 1.8766337995872508e-05,
198
+ "loss": 1.1797,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.06420545746388442,
203
+ "grad_norm": 13.3125,
204
+ "learning_rate": 1.8720476954826878e-05,
205
+ "loss": 1.1974,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.06649850951616602,
210
+ "grad_norm": 10.375,
211
+ "learning_rate": 1.8674615913781244e-05,
212
+ "loss": 1.1929,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.06879156156844761,
217
+ "grad_norm": 15.125,
218
+ "learning_rate": 1.8628754872735614e-05,
219
+ "loss": 1.1838,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.0710846136207292,
224
+ "grad_norm": 8.75,
225
+ "learning_rate": 1.858289383168998e-05,
226
+ "loss": 1.1515,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.07337766567301078,
231
+ "grad_norm": 10.9375,
232
+ "learning_rate": 1.8537032790644348e-05,
233
+ "loss": 1.2107,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.07567071772529237,
238
+ "grad_norm": 12.5625,
239
+ "learning_rate": 1.8491171749598718e-05,
240
+ "loss": 1.1874,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.07796376977757395,
245
+ "grad_norm": 9.6875,
246
+ "learning_rate": 1.8445310708553084e-05,
247
+ "loss": 1.1988,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.08025682182985554,
252
+ "grad_norm": 10.5625,
253
+ "learning_rate": 1.8399449667507454e-05,
254
+ "loss": 1.1998,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.08254987388213712,
259
+ "grad_norm": 9.1875,
260
+ "learning_rate": 1.835358862646182e-05,
261
+ "loss": 1.1957,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.08484292593441871,
266
+ "grad_norm": 10.1875,
267
+ "learning_rate": 1.830772758541619e-05,
268
+ "loss": 1.204,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.0871359779867003,
273
+ "grad_norm": 17.125,
274
+ "learning_rate": 1.8261866544370558e-05,
275
+ "loss": 1.191,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.08942903003898188,
280
+ "grad_norm": 12.1875,
281
+ "learning_rate": 1.8216005503324928e-05,
282
+ "loss": 1.19,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.09172208209126347,
287
+ "grad_norm": 9.9375,
288
+ "learning_rate": 1.8170144462279294e-05,
289
+ "loss": 1.1729,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.09401513414354506,
294
+ "grad_norm": 12.875,
295
+ "learning_rate": 1.8124283421233664e-05,
296
+ "loss": 1.201,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.09630818619582665,
301
+ "grad_norm": 15.1875,
302
+ "learning_rate": 1.807842238018803e-05,
303
+ "loss": 1.1834,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.09860123824810824,
308
+ "grad_norm": 10.125,
309
+ "learning_rate": 1.80325613391424e-05,
310
+ "loss": 1.1984,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.10089429030038982,
315
+ "grad_norm": 12.875,
316
+ "learning_rate": 1.7986700298096768e-05,
317
+ "loss": 1.1877,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.10318734235267141,
322
+ "grad_norm": 14.8125,
323
+ "learning_rate": 1.7940839257051138e-05,
324
+ "loss": 1.179,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.10548039440495299,
329
+ "grad_norm": 17.75,
330
+ "learning_rate": 1.7894978216005504e-05,
331
+ "loss": 1.1861,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.10777344645723458,
336
+ "grad_norm": 8.375,
337
+ "learning_rate": 1.7849117174959874e-05,
338
+ "loss": 1.1912,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.11006649850951616,
343
+ "grad_norm": 8.9375,
344
+ "learning_rate": 1.780325613391424e-05,
345
+ "loss": 1.1795,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.11235955056179775,
350
+ "grad_norm": 11.5625,
351
+ "learning_rate": 1.775739509286861e-05,
352
+ "loss": 1.1827,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.11465260261407934,
357
+ "grad_norm": 11.625,
358
+ "learning_rate": 1.7711534051822978e-05,
359
+ "loss": 1.1813,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.11694565466636092,
364
+ "grad_norm": 11.6875,
365
+ "learning_rate": 1.7665673010777348e-05,
366
+ "loss": 1.1836,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 0.1192387067186425,
371
+ "grad_norm": 7.84375,
372
+ "learning_rate": 1.7619811969731714e-05,
373
+ "loss": 1.171,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 0.1215317587709241,
378
+ "grad_norm": 11.9375,
379
+ "learning_rate": 1.7573950928686084e-05,
380
+ "loss": 1.1835,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 0.12382481082320569,
385
+ "grad_norm": 14.9375,
386
+ "learning_rate": 1.752808988764045e-05,
387
+ "loss": 1.1887,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 0.12611786287548726,
392
+ "grad_norm": 13.3125,
393
+ "learning_rate": 1.748222884659482e-05,
394
+ "loss": 1.1737,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 0.12841091492776885,
399
+ "grad_norm": 13.3125,
400
+ "learning_rate": 1.7436367805549188e-05,
401
+ "loss": 1.1871,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 0.13070396698005043,
406
+ "grad_norm": 10.5625,
407
+ "learning_rate": 1.7390506764503558e-05,
408
+ "loss": 1.1873,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 0.13299701903233205,
413
+ "grad_norm": 8.1875,
414
+ "learning_rate": 1.7344645723457925e-05,
415
+ "loss": 1.1946,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 0.13529007108461363,
420
+ "grad_norm": 13.9375,
421
+ "learning_rate": 1.7298784682412295e-05,
422
+ "loss": 1.1838,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 0.13758312313689522,
427
+ "grad_norm": 12.8125,
428
+ "learning_rate": 1.725292364136666e-05,
429
+ "loss": 1.1873,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 0.1398761751891768,
434
+ "grad_norm": 11.3125,
435
+ "learning_rate": 1.7207062600321028e-05,
436
+ "loss": 1.1802,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 0.1421692272414584,
441
+ "grad_norm": 15.25,
442
+ "learning_rate": 1.7161201559275398e-05,
443
+ "loss": 1.1806,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 0.14446227929373998,
448
+ "grad_norm": 10.1875,
449
+ "learning_rate": 1.7115340518229765e-05,
450
+ "loss": 1.195,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 0.14675533134602156,
455
+ "grad_norm": 9.875,
456
+ "learning_rate": 1.7069479477184135e-05,
457
+ "loss": 1.1835,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 0.14904838339830315,
462
+ "grad_norm": 11.6875,
463
+ "learning_rate": 1.70236184361385e-05,
464
+ "loss": 1.1884,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 0.15134143545058473,
469
+ "grad_norm": 12.0,
470
+ "learning_rate": 1.697775739509287e-05,
471
+ "loss": 1.1811,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 0.15363448750286632,
476
+ "grad_norm": 9.875,
477
+ "learning_rate": 1.6931896354047238e-05,
478
+ "loss": 1.195,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 0.1559275395551479,
483
+ "grad_norm": 11.0,
484
+ "learning_rate": 1.6886035313001608e-05,
485
+ "loss": 1.1827,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 0.1582205916074295,
490
+ "grad_norm": 11.1875,
491
+ "learning_rate": 1.6840174271955975e-05,
492
+ "loss": 1.1868,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 0.16051364365971107,
497
+ "grad_norm": 7.84375,
498
+ "learning_rate": 1.6794313230910345e-05,
499
+ "loss": 1.1813,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 0.16280669571199266,
504
+ "grad_norm": 13.0625,
505
+ "learning_rate": 1.674845218986471e-05,
506
+ "loss": 1.1856,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 0.16509974776427425,
511
+ "grad_norm": 11.6875,
512
+ "learning_rate": 1.670259114881908e-05,
513
+ "loss": 1.1826,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 0.16739279981655583,
518
+ "grad_norm": 11.625,
519
+ "learning_rate": 1.6656730107773448e-05,
520
+ "loss": 1.1712,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 0.16968585186883742,
525
+ "grad_norm": 10.4375,
526
+ "learning_rate": 1.6610869066727818e-05,
527
+ "loss": 1.1701,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 0.171978903921119,
532
+ "grad_norm": 9.6875,
533
+ "learning_rate": 1.6565008025682185e-05,
534
+ "loss": 1.1905,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 0.1742719559734006,
539
+ "grad_norm": 12.25,
540
+ "learning_rate": 1.651914698463655e-05,
541
+ "loss": 1.1887,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 0.17656500802568217,
546
+ "grad_norm": 7.9375,
547
+ "learning_rate": 1.647328594359092e-05,
548
+ "loss": 1.2096,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 0.17885806007796376,
553
+ "grad_norm": 13.375,
554
+ "learning_rate": 1.6427424902545288e-05,
555
+ "loss": 1.1932,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 0.18115111213024535,
560
+ "grad_norm": 10.8125,
561
+ "learning_rate": 1.6381563861499658e-05,
562
+ "loss": 1.1798,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 0.18344416418252693,
567
+ "grad_norm": 12.625,
568
+ "learning_rate": 1.6335702820454025e-05,
569
+ "loss": 1.178,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 0.18573721623480852,
574
+ "grad_norm": 12.3125,
575
+ "learning_rate": 1.628984177940839e-05,
576
+ "loss": 1.1875,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 0.18803026828709013,
581
+ "grad_norm": 9.3125,
582
+ "learning_rate": 1.624398073836276e-05,
583
+ "loss": 1.1791,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 0.19032332033937172,
588
+ "grad_norm": 14.6875,
589
+ "learning_rate": 1.6198119697317128e-05,
590
+ "loss": 1.1764,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 0.1926163723916533,
595
+ "grad_norm": 10.625,
596
+ "learning_rate": 1.6152258656271498e-05,
597
+ "loss": 1.1783,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 0.1949094244439349,
602
+ "grad_norm": 12.875,
603
+ "learning_rate": 1.6106397615225865e-05,
604
+ "loss": 1.1882,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 0.19720247649621647,
609
+ "grad_norm": 14.9375,
610
+ "learning_rate": 1.6060536574180235e-05,
611
+ "loss": 1.1877,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 0.19949552854849806,
616
+ "grad_norm": 9.75,
617
+ "learning_rate": 1.60146755331346e-05,
618
+ "loss": 1.1942,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 0.20178858060077964,
623
+ "grad_norm": 12.1875,
624
+ "learning_rate": 1.596881449208897e-05,
625
+ "loss": 1.1855,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 0.20408163265306123,
630
+ "grad_norm": 14.4375,
631
+ "learning_rate": 1.5922953451043338e-05,
632
+ "loss": 1.1707,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 0.20637468470534281,
637
+ "grad_norm": 12.5625,
638
+ "learning_rate": 1.5877092409997708e-05,
639
+ "loss": 1.1809,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 0.2086677367576244,
644
+ "grad_norm": 11.0,
645
+ "learning_rate": 1.5831231368952075e-05,
646
+ "loss": 1.1929,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 0.21096078880990599,
651
+ "grad_norm": 7.4375,
652
+ "learning_rate": 1.5785370327906445e-05,
653
+ "loss": 1.2096,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 0.21325384086218757,
658
+ "grad_norm": 7.0,
659
+ "learning_rate": 1.573950928686081e-05,
660
+ "loss": 1.1921,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 0.21554689291446916,
665
+ "grad_norm": 10.9375,
666
+ "learning_rate": 1.569364824581518e-05,
667
+ "loss": 1.1849,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 0.21783994496675074,
672
+ "grad_norm": 11.25,
673
+ "learning_rate": 1.5647787204769548e-05,
674
+ "loss": 1.1984,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 0.22013299701903233,
679
+ "grad_norm": 12.0625,
680
+ "learning_rate": 1.5601926163723918e-05,
681
+ "loss": 1.1942,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 0.2224260490713139,
686
+ "grad_norm": 10.4375,
687
+ "learning_rate": 1.5556065122678285e-05,
688
+ "loss": 1.1818,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 0.2247191011235955,
693
+ "grad_norm": 12.8125,
694
+ "learning_rate": 1.5510204081632655e-05,
695
+ "loss": 1.1945,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 0.22701215317587708,
700
+ "grad_norm": 6.875,
701
+ "learning_rate": 1.546434304058702e-05,
702
+ "loss": 1.1643,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 0.22930520522815867,
707
+ "grad_norm": 13.25,
708
+ "learning_rate": 1.541848199954139e-05,
709
+ "loss": 1.2059,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 0.23159825728044026,
714
+ "grad_norm": 10.5,
715
+ "learning_rate": 1.5372620958495758e-05,
716
+ "loss": 1.1918,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 0.23389130933272184,
721
+ "grad_norm": 6.9375,
722
+ "learning_rate": 1.5326759917450128e-05,
723
+ "loss": 1.1879,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 0.23618436138500343,
728
+ "grad_norm": 9.25,
729
+ "learning_rate": 1.5280898876404495e-05,
730
+ "loss": 1.1619,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 0.238477413437285,
735
+ "grad_norm": 8.4375,
736
+ "learning_rate": 1.5235037835358863e-05,
737
+ "loss": 1.1709,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 0.24077046548956663,
742
+ "grad_norm": 12.625,
743
+ "learning_rate": 1.5189176794313232e-05,
744
+ "loss": 1.1922,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 0.2430635175418482,
749
+ "grad_norm": 8.0625,
750
+ "learning_rate": 1.51433157532676e-05,
751
+ "loss": 1.1695,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 0.2453565695941298,
756
+ "grad_norm": 11.3125,
757
+ "learning_rate": 1.5097454712221968e-05,
758
+ "loss": 1.1987,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 0.24764962164641138,
763
+ "grad_norm": 9.0625,
764
+ "learning_rate": 1.5051593671176337e-05,
765
+ "loss": 1.1807,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 0.24994267369869297,
770
+ "grad_norm": 12.4375,
771
+ "learning_rate": 1.5005732630130705e-05,
772
+ "loss": 1.1839,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 0.2522357257509745,
777
+ "grad_norm": 13.0,
778
+ "learning_rate": 1.4959871589085073e-05,
779
+ "loss": 1.1795,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 0.2545287778032561,
784
+ "grad_norm": 13.125,
785
+ "learning_rate": 1.4914010548039442e-05,
786
+ "loss": 1.1739,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 0.2568218298555377,
791
+ "grad_norm": 12.3125,
792
+ "learning_rate": 1.486814950699381e-05,
793
+ "loss": 1.1936,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 0.2591148819078193,
798
+ "grad_norm": 7.03125,
799
+ "learning_rate": 1.4822288465948178e-05,
800
+ "loss": 1.1775,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 0.26140793396010087,
805
+ "grad_norm": 14.75,
806
+ "learning_rate": 1.4776427424902547e-05,
807
+ "loss": 1.1958,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 0.26370098601238245,
812
+ "grad_norm": 11.375,
813
+ "learning_rate": 1.4730566383856915e-05,
814
+ "loss": 1.18,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 0.2659940380646641,
819
+ "grad_norm": 12.3125,
820
+ "learning_rate": 1.4684705342811283e-05,
821
+ "loss": 1.1812,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 0.2682870901169457,
826
+ "grad_norm": 11.1875,
827
+ "learning_rate": 1.4638844301765652e-05,
828
+ "loss": 1.1657,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 0.27058014216922727,
833
+ "grad_norm": 11.9375,
834
+ "learning_rate": 1.459298326072002e-05,
835
+ "loss": 1.1862,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 0.27287319422150885,
840
+ "grad_norm": 9.9375,
841
+ "learning_rate": 1.4547122219674388e-05,
842
+ "loss": 1.1869,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 0.27516624627379044,
847
+ "grad_norm": 8.9375,
848
+ "learning_rate": 1.4501261178628757e-05,
849
+ "loss": 1.1881,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 0.277459298326072,
854
+ "grad_norm": 11.625,
855
+ "learning_rate": 1.4455400137583125e-05,
856
+ "loss": 1.1951,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 0.2797523503783536,
861
+ "grad_norm": 9.375,
862
+ "learning_rate": 1.4409539096537493e-05,
863
+ "loss": 1.1654,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 0.2820454024306352,
868
+ "grad_norm": 10.6875,
869
+ "learning_rate": 1.436367805549186e-05,
870
+ "loss": 1.1646,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 0.2843384544829168,
875
+ "grad_norm": 9.125,
876
+ "learning_rate": 1.4317817014446228e-05,
877
+ "loss": 1.1662,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 0.28663150653519837,
882
+ "grad_norm": 10.8125,
883
+ "learning_rate": 1.4271955973400597e-05,
884
+ "loss": 1.1961,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 0.28892455858747995,
889
+ "grad_norm": 8.6875,
890
+ "learning_rate": 1.4226094932354965e-05,
891
+ "loss": 1.179,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 0.29121761063976154,
896
+ "grad_norm": 11.0625,
897
+ "learning_rate": 1.4180233891309333e-05,
898
+ "loss": 1.2015,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 0.2935106626920431,
903
+ "grad_norm": 8.25,
904
+ "learning_rate": 1.4134372850263702e-05,
905
+ "loss": 1.176,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 0.2958037147443247,
910
+ "grad_norm": 8.25,
911
+ "learning_rate": 1.408851180921807e-05,
912
+ "loss": 1.1626,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 0.2980967667966063,
917
+ "grad_norm": 8.8125,
918
+ "learning_rate": 1.4042650768172439e-05,
919
+ "loss": 1.178,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 0.3003898188488879,
924
+ "grad_norm": 11.25,
925
+ "learning_rate": 1.3996789727126807e-05,
926
+ "loss": 1.1763,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 0.30268287090116947,
931
+ "grad_norm": 13.0,
932
+ "learning_rate": 1.3950928686081175e-05,
933
+ "loss": 1.1889,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 0.30497592295345105,
938
+ "grad_norm": 9.8125,
939
+ "learning_rate": 1.3905067645035544e-05,
940
+ "loss": 1.2124,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 0.30726897500573264,
945
+ "grad_norm": 8.375,
946
+ "learning_rate": 1.3859206603989912e-05,
947
+ "loss": 1.1906,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 0.3095620270580142,
952
+ "grad_norm": 7.3125,
953
+ "learning_rate": 1.381334556294428e-05,
954
+ "loss": 1.1758,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 0.3118550791102958,
959
+ "grad_norm": 12.8125,
960
+ "learning_rate": 1.3767484521898649e-05,
961
+ "loss": 1.2033,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 0.3141481311625774,
966
+ "grad_norm": 9.0625,
967
+ "learning_rate": 1.3721623480853017e-05,
968
+ "loss": 1.1986,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 0.316441183214859,
973
+ "grad_norm": 11.75,
974
+ "learning_rate": 1.3675762439807385e-05,
975
+ "loss": 1.17,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 0.31873423526714056,
980
+ "grad_norm": 11.875,
981
+ "learning_rate": 1.3629901398761754e-05,
982
+ "loss": 1.1687,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 0.32102728731942215,
987
+ "grad_norm": 7.375,
988
+ "learning_rate": 1.3584040357716122e-05,
989
+ "loss": 1.1815,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 0.32332033937170374,
994
+ "grad_norm": 8.1875,
995
+ "learning_rate": 1.353817931667049e-05,
996
+ "loss": 1.1864,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 0.3256133914239853,
1001
+ "grad_norm": 14.125,
1002
+ "learning_rate": 1.3492318275624859e-05,
1003
+ "loss": 1.1832,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 0.3279064434762669,
1008
+ "grad_norm": 7.59375,
1009
+ "learning_rate": 1.3446457234579227e-05,
1010
+ "loss": 1.189,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 0.3301994955285485,
1015
+ "grad_norm": 10.8125,
1016
+ "learning_rate": 1.3400596193533595e-05,
1017
+ "loss": 1.1734,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 0.3324925475808301,
1022
+ "grad_norm": 10.6875,
1023
+ "learning_rate": 1.3354735152487964e-05,
1024
+ "loss": 1.1807,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 0.33478559963311166,
1029
+ "grad_norm": 10.375,
1030
+ "learning_rate": 1.3308874111442332e-05,
1031
+ "loss": 1.1752,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 0.33707865168539325,
1036
+ "grad_norm": 11.375,
1037
+ "learning_rate": 1.32630130703967e-05,
1038
+ "loss": 1.1578,
1039
+ "step": 1470
1040
+ },
1041
+ {
1042
+ "epoch": 0.33937170373767483,
1043
+ "grad_norm": 10.0,
1044
+ "learning_rate": 1.3217152029351069e-05,
1045
+ "loss": 1.177,
1046
+ "step": 1480
1047
+ },
1048
+ {
1049
+ "epoch": 0.3416647557899564,
1050
+ "grad_norm": 12.4375,
1051
+ "learning_rate": 1.3171290988305437e-05,
1052
+ "loss": 1.1644,
1053
+ "step": 1490
1054
+ },
1055
+ {
1056
+ "epoch": 0.343957807842238,
1057
+ "grad_norm": 9.625,
1058
+ "learning_rate": 1.3125429947259805e-05,
1059
+ "loss": 1.167,
1060
+ "step": 1500
1061
+ },
1062
+ {
1063
+ "epoch": 0.3462508598945196,
1064
+ "grad_norm": 11.0,
1065
+ "learning_rate": 1.3079568906214172e-05,
1066
+ "loss": 1.1817,
1067
+ "step": 1510
1068
+ },
1069
+ {
1070
+ "epoch": 0.3485439119468012,
1071
+ "grad_norm": 8.1875,
1072
+ "learning_rate": 1.303370786516854e-05,
1073
+ "loss": 1.1822,
1074
+ "step": 1520
1075
+ },
1076
+ {
1077
+ "epoch": 0.35083696399908276,
1078
+ "grad_norm": 8.625,
1079
+ "learning_rate": 1.2987846824122909e-05,
1080
+ "loss": 1.1676,
1081
+ "step": 1530
1082
+ },
1083
+ {
1084
+ "epoch": 0.35313001605136435,
1085
+ "grad_norm": 6.71875,
1086
+ "learning_rate": 1.2941985783077277e-05,
1087
+ "loss": 1.1792,
1088
+ "step": 1540
1089
+ },
1090
+ {
1091
+ "epoch": 0.35542306810364593,
1092
+ "grad_norm": 9.0625,
1093
+ "learning_rate": 1.2896124742031645e-05,
1094
+ "loss": 1.1726,
1095
+ "step": 1550
1096
+ },
1097
+ {
1098
+ "epoch": 0.3577161201559275,
1099
+ "grad_norm": 10.1875,
1100
+ "learning_rate": 1.2850263700986014e-05,
1101
+ "loss": 1.1728,
1102
+ "step": 1560
1103
+ },
1104
+ {
1105
+ "epoch": 0.3600091722082091,
1106
+ "grad_norm": 12.3125,
1107
+ "learning_rate": 1.2804402659940382e-05,
1108
+ "loss": 1.1825,
1109
+ "step": 1570
1110
+ },
1111
+ {
1112
+ "epoch": 0.3623022242604907,
1113
+ "grad_norm": 7.125,
1114
+ "learning_rate": 1.275854161889475e-05,
1115
+ "loss": 1.159,
1116
+ "step": 1580
1117
+ },
1118
+ {
1119
+ "epoch": 0.3645952763127723,
1120
+ "grad_norm": 8.8125,
1121
+ "learning_rate": 1.2712680577849119e-05,
1122
+ "loss": 1.1728,
1123
+ "step": 1590
1124
+ },
1125
+ {
1126
+ "epoch": 0.36688832836505386,
1127
+ "grad_norm": 11.6875,
1128
+ "learning_rate": 1.2666819536803487e-05,
1129
+ "loss": 1.1976,
1130
+ "step": 1600
1131
+ },
1132
+ {
1133
+ "epoch": 0.36918138041733545,
1134
+ "grad_norm": 9.875,
1135
+ "learning_rate": 1.2620958495757855e-05,
1136
+ "loss": 1.1806,
1137
+ "step": 1610
1138
+ },
1139
+ {
1140
+ "epoch": 0.37147443246961703,
1141
+ "grad_norm": 9.8125,
1142
+ "learning_rate": 1.2575097454712224e-05,
1143
+ "loss": 1.1829,
1144
+ "step": 1620
1145
+ },
1146
+ {
1147
+ "epoch": 0.3737674845218987,
1148
+ "grad_norm": 12.625,
1149
+ "learning_rate": 1.2529236413666592e-05,
1150
+ "loss": 1.169,
1151
+ "step": 1630
1152
+ },
1153
+ {
1154
+ "epoch": 0.37606053657418026,
1155
+ "grad_norm": 7.625,
1156
+ "learning_rate": 1.248337537262096e-05,
1157
+ "loss": 1.1923,
1158
+ "step": 1640
1159
+ },
1160
+ {
1161
+ "epoch": 0.37835358862646185,
1162
+ "grad_norm": 10.75,
1163
+ "learning_rate": 1.2437514331575329e-05,
1164
+ "loss": 1.1879,
1165
+ "step": 1650
1166
+ },
1167
+ {
1168
+ "epoch": 0.38064664067874343,
1169
+ "grad_norm": 8.875,
1170
+ "learning_rate": 1.2391653290529697e-05,
1171
+ "loss": 1.1742,
1172
+ "step": 1660
1173
+ },
1174
+ {
1175
+ "epoch": 0.382939692731025,
1176
+ "grad_norm": 10.5,
1177
+ "learning_rate": 1.2345792249484066e-05,
1178
+ "loss": 1.1725,
1179
+ "step": 1670
1180
+ },
1181
+ {
1182
+ "epoch": 0.3852327447833066,
1183
+ "grad_norm": 8.9375,
1184
+ "learning_rate": 1.2299931208438432e-05,
1185
+ "loss": 1.1836,
1186
+ "step": 1680
1187
+ },
1188
+ {
1189
+ "epoch": 0.3875257968355882,
1190
+ "grad_norm": 8.5,
1191
+ "learning_rate": 1.22540701673928e-05,
1192
+ "loss": 1.1698,
1193
+ "step": 1690
1194
+ },
1195
+ {
1196
+ "epoch": 0.3898188488878698,
1197
+ "grad_norm": 10.4375,
1198
+ "learning_rate": 1.2208209126347169e-05,
1199
+ "loss": 1.1747,
1200
+ "step": 1700
1201
+ },
1202
+ {
1203
+ "epoch": 0.39211190094015136,
1204
+ "grad_norm": 11.375,
1205
+ "learning_rate": 1.2162348085301536e-05,
1206
+ "loss": 1.1947,
1207
+ "step": 1710
1208
+ },
1209
+ {
1210
+ "epoch": 0.39440495299243294,
1211
+ "grad_norm": 9.0625,
1212
+ "learning_rate": 1.2116487044255904e-05,
1213
+ "loss": 1.1847,
1214
+ "step": 1720
1215
+ },
1216
+ {
1217
+ "epoch": 0.39669800504471453,
1218
+ "grad_norm": 12.0,
1219
+ "learning_rate": 1.2070626003210272e-05,
1220
+ "loss": 1.1897,
1221
+ "step": 1730
1222
+ },
1223
+ {
1224
+ "epoch": 0.3989910570969961,
1225
+ "grad_norm": 10.6875,
1226
+ "learning_rate": 1.202476496216464e-05,
1227
+ "loss": 1.1668,
1228
+ "step": 1740
1229
+ },
1230
+ {
1231
+ "epoch": 0.4012841091492777,
1232
+ "grad_norm": 6.8125,
1233
+ "learning_rate": 1.1978903921119009e-05,
1234
+ "loss": 1.1617,
1235
+ "step": 1750
1236
+ },
1237
+ {
1238
+ "epoch": 0.4035771612015593,
1239
+ "grad_norm": 14.1875,
1240
+ "learning_rate": 1.1933042880073377e-05,
1241
+ "loss": 1.1748,
1242
+ "step": 1760
1243
+ },
1244
+ {
1245
+ "epoch": 0.4058702132538409,
1246
+ "grad_norm": 11.1875,
1247
+ "learning_rate": 1.1887181839027746e-05,
1248
+ "loss": 1.1836,
1249
+ "step": 1770
1250
+ },
1251
+ {
1252
+ "epoch": 0.40816326530612246,
1253
+ "grad_norm": 7.90625,
1254
+ "learning_rate": 1.1841320797982114e-05,
1255
+ "loss": 1.1731,
1256
+ "step": 1780
1257
+ },
1258
+ {
1259
+ "epoch": 0.41045631735840404,
1260
+ "grad_norm": 13.6875,
1261
+ "learning_rate": 1.1795459756936482e-05,
1262
+ "loss": 1.1769,
1263
+ "step": 1790
1264
+ },
1265
+ {
1266
+ "epoch": 0.41274936941068563,
1267
+ "grad_norm": 10.75,
1268
+ "learning_rate": 1.174959871589085e-05,
1269
+ "loss": 1.181,
1270
+ "step": 1800
1271
+ },
1272
+ {
1273
+ "epoch": 0.4150424214629672,
1274
+ "grad_norm": 7.28125,
1275
+ "learning_rate": 1.1703737674845219e-05,
1276
+ "loss": 1.1851,
1277
+ "step": 1810
1278
+ },
1279
+ {
1280
+ "epoch": 0.4173354735152488,
1281
+ "grad_norm": 11.25,
1282
+ "learning_rate": 1.1657876633799587e-05,
1283
+ "loss": 1.1791,
1284
+ "step": 1820
1285
+ },
1286
+ {
1287
+ "epoch": 0.4196285255675304,
1288
+ "grad_norm": 8.6875,
1289
+ "learning_rate": 1.1612015592753956e-05,
1290
+ "loss": 1.1773,
1291
+ "step": 1830
1292
+ },
1293
+ {
1294
+ "epoch": 0.42192157761981197,
1295
+ "grad_norm": 11.3125,
1296
+ "learning_rate": 1.1566154551708324e-05,
1297
+ "loss": 1.1644,
1298
+ "step": 1840
1299
+ },
1300
+ {
1301
+ "epoch": 0.42421462967209356,
1302
+ "grad_norm": 10.0,
1303
+ "learning_rate": 1.1520293510662692e-05,
1304
+ "loss": 1.1703,
1305
+ "step": 1850
1306
+ },
1307
+ {
1308
+ "epoch": 0.42650768172437514,
1309
+ "grad_norm": 9.4375,
1310
+ "learning_rate": 1.147443246961706e-05,
1311
+ "loss": 1.1696,
1312
+ "step": 1860
1313
+ },
1314
+ {
1315
+ "epoch": 0.42880073377665673,
1316
+ "grad_norm": 11.625,
1317
+ "learning_rate": 1.1428571428571429e-05,
1318
+ "loss": 1.1809,
1319
+ "step": 1870
1320
+ },
1321
+ {
1322
+ "epoch": 0.4310937858289383,
1323
+ "grad_norm": 10.0,
1324
+ "learning_rate": 1.1382710387525797e-05,
1325
+ "loss": 1.1865,
1326
+ "step": 1880
1327
+ },
1328
+ {
1329
+ "epoch": 0.4333868378812199,
1330
+ "grad_norm": 13.0625,
1331
+ "learning_rate": 1.1336849346480166e-05,
1332
+ "loss": 1.1864,
1333
+ "step": 1890
1334
+ },
1335
+ {
1336
+ "epoch": 0.4356798899335015,
1337
+ "grad_norm": 9.1875,
1338
+ "learning_rate": 1.1290988305434534e-05,
1339
+ "loss": 1.1812,
1340
+ "step": 1900
1341
+ },
1342
+ {
1343
+ "epoch": 0.43797294198578307,
1344
+ "grad_norm": 11.1875,
1345
+ "learning_rate": 1.1245127264388902e-05,
1346
+ "loss": 1.1623,
1347
+ "step": 1910
1348
+ },
1349
+ {
1350
+ "epoch": 0.44026599403806466,
1351
+ "grad_norm": 8.9375,
1352
+ "learning_rate": 1.119926622334327e-05,
1353
+ "loss": 1.1655,
1354
+ "step": 1920
1355
+ },
1356
+ {
1357
+ "epoch": 0.44255904609034624,
1358
+ "grad_norm": 9.4375,
1359
+ "learning_rate": 1.1153405182297639e-05,
1360
+ "loss": 1.1528,
1361
+ "step": 1930
1362
+ },
1363
+ {
1364
+ "epoch": 0.4448520981426278,
1365
+ "grad_norm": 12.4375,
1366
+ "learning_rate": 1.1107544141252007e-05,
1367
+ "loss": 1.1836,
1368
+ "step": 1940
1369
+ },
1370
+ {
1371
+ "epoch": 0.4471451501949094,
1372
+ "grad_norm": 10.375,
1373
+ "learning_rate": 1.1061683100206376e-05,
1374
+ "loss": 1.1571,
1375
+ "step": 1950
1376
+ },
1377
+ {
1378
+ "epoch": 0.449438202247191,
1379
+ "grad_norm": 11.8125,
1380
+ "learning_rate": 1.1015822059160744e-05,
1381
+ "loss": 1.1732,
1382
+ "step": 1960
1383
+ },
1384
+ {
1385
+ "epoch": 0.4517312542994726,
1386
+ "grad_norm": 14.3125,
1387
+ "learning_rate": 1.0969961018115112e-05,
1388
+ "loss": 1.1716,
1389
+ "step": 1970
1390
+ },
1391
+ {
1392
+ "epoch": 0.45402430635175417,
1393
+ "grad_norm": 14.1875,
1394
+ "learning_rate": 1.092409997706948e-05,
1395
+ "loss": 1.1583,
1396
+ "step": 1980
1397
+ },
1398
+ {
1399
+ "epoch": 0.45631735840403576,
1400
+ "grad_norm": 10.125,
1401
+ "learning_rate": 1.0878238936023847e-05,
1402
+ "loss": 1.1839,
1403
+ "step": 1990
1404
+ },
1405
+ {
1406
+ "epoch": 0.45861041045631734,
1407
+ "grad_norm": 14.4375,
1408
+ "learning_rate": 1.0832377894978216e-05,
1409
+ "loss": 1.1666,
1410
+ "step": 2000
1411
+ },
1412
+ {
1413
+ "epoch": 0.4609034625085989,
1414
+ "grad_norm": 13.25,
1415
+ "learning_rate": 1.0786516853932584e-05,
1416
+ "loss": 1.1816,
1417
+ "step": 2010
1418
+ },
1419
+ {
1420
+ "epoch": 0.4631965145608805,
1421
+ "grad_norm": 9.75,
1422
+ "learning_rate": 1.0740655812886952e-05,
1423
+ "loss": 1.1702,
1424
+ "step": 2020
1425
+ },
1426
+ {
1427
+ "epoch": 0.4654895666131621,
1428
+ "grad_norm": 9.25,
1429
+ "learning_rate": 1.069479477184132e-05,
1430
+ "loss": 1.1636,
1431
+ "step": 2030
1432
+ },
1433
+ {
1434
+ "epoch": 0.4677826186654437,
1435
+ "grad_norm": 7.9375,
1436
+ "learning_rate": 1.064893373079569e-05,
1437
+ "loss": 1.1645,
1438
+ "step": 2040
1439
+ },
1440
+ {
1441
+ "epoch": 0.47007567071772527,
1442
+ "grad_norm": 12.0625,
1443
+ "learning_rate": 1.0603072689750058e-05,
1444
+ "loss": 1.169,
1445
+ "step": 2050
1446
+ },
1447
+ {
1448
+ "epoch": 0.47236872277000685,
1449
+ "grad_norm": 11.5625,
1450
+ "learning_rate": 1.0557211648704426e-05,
1451
+ "loss": 1.1595,
1452
+ "step": 2060
1453
+ },
1454
+ {
1455
+ "epoch": 0.47466177482228844,
1456
+ "grad_norm": 15.0,
1457
+ "learning_rate": 1.0511350607658794e-05,
1458
+ "loss": 1.16,
1459
+ "step": 2070
1460
+ },
1461
+ {
1462
+ "epoch": 0.47695482687457,
1463
+ "grad_norm": 9.25,
1464
+ "learning_rate": 1.0465489566613163e-05,
1465
+ "loss": 1.1707,
1466
+ "step": 2080
1467
+ },
1468
+ {
1469
+ "epoch": 0.47924787892685167,
1470
+ "grad_norm": 9.75,
1471
+ "learning_rate": 1.0419628525567531e-05,
1472
+ "loss": 1.152,
1473
+ "step": 2090
1474
+ },
1475
+ {
1476
+ "epoch": 0.48154093097913325,
1477
+ "grad_norm": 12.125,
1478
+ "learning_rate": 1.03737674845219e-05,
1479
+ "loss": 1.1793,
1480
+ "step": 2100
1481
+ },
1482
+ {
1483
+ "epoch": 0.48383398303141484,
1484
+ "grad_norm": 12.8125,
1485
+ "learning_rate": 1.0327906443476268e-05,
1486
+ "loss": 1.1921,
1487
+ "step": 2110
1488
+ },
1489
+ {
1490
+ "epoch": 0.4861270350836964,
1491
+ "grad_norm": 13.9375,
1492
+ "learning_rate": 1.0282045402430636e-05,
1493
+ "loss": 1.1683,
1494
+ "step": 2120
1495
+ },
1496
+ {
1497
+ "epoch": 0.488420087135978,
1498
+ "grad_norm": 11.0625,
1499
+ "learning_rate": 1.0236184361385004e-05,
1500
+ "loss": 1.1755,
1501
+ "step": 2130
1502
+ },
1503
+ {
1504
+ "epoch": 0.4907131391882596,
1505
+ "grad_norm": 11.375,
1506
+ "learning_rate": 1.0190323320339373e-05,
1507
+ "loss": 1.1825,
1508
+ "step": 2140
1509
+ },
1510
+ {
1511
+ "epoch": 0.4930061912405412,
1512
+ "grad_norm": 9.8125,
1513
+ "learning_rate": 1.0144462279293741e-05,
1514
+ "loss": 1.1531,
1515
+ "step": 2150
1516
+ },
1517
+ {
1518
+ "epoch": 0.49529924329282277,
1519
+ "grad_norm": 11.375,
1520
+ "learning_rate": 1.009860123824811e-05,
1521
+ "loss": 1.1867,
1522
+ "step": 2160
1523
+ },
1524
+ {
1525
+ "epoch": 0.49759229534510435,
1526
+ "grad_norm": 8.625,
1527
+ "learning_rate": 1.0052740197202478e-05,
1528
+ "loss": 1.1564,
1529
+ "step": 2170
1530
+ },
1531
+ {
1532
+ "epoch": 0.49988534739738594,
1533
+ "grad_norm": 6.46875,
1534
+ "learning_rate": 1.0006879156156846e-05,
1535
+ "loss": 1.1859,
1536
+ "step": 2180
1537
+ },
1538
+ {
1539
+ "epoch": 0.5021783994496675,
1540
+ "grad_norm": 15.25,
1541
+ "learning_rate": 9.961018115111214e-06,
1542
+ "loss": 1.1779,
1543
+ "step": 2190
1544
+ },
1545
+ {
1546
+ "epoch": 0.504471451501949,
1547
+ "grad_norm": 9.5,
1548
+ "learning_rate": 9.915157074065583e-06,
1549
+ "loss": 1.1663,
1550
+ "step": 2200
1551
+ },
1552
+ {
1553
+ "epoch": 0.5067645035542306,
1554
+ "grad_norm": 9.5,
1555
+ "learning_rate": 9.869296033019951e-06,
1556
+ "loss": 1.1526,
1557
+ "step": 2210
1558
+ },
1559
+ {
1560
+ "epoch": 0.5090575556065122,
1561
+ "grad_norm": 7.6875,
1562
+ "learning_rate": 9.82343499197432e-06,
1563
+ "loss": 1.179,
1564
+ "step": 2220
1565
+ },
1566
+ {
1567
+ "epoch": 0.5113506076587938,
1568
+ "grad_norm": 11.125,
1569
+ "learning_rate": 9.777573950928688e-06,
1570
+ "loss": 1.1688,
1571
+ "step": 2230
1572
+ },
1573
+ {
1574
+ "epoch": 0.5136436597110754,
1575
+ "grad_norm": 10.1875,
1576
+ "learning_rate": 9.731712909883056e-06,
1577
+ "loss": 1.159,
1578
+ "step": 2240
1579
+ },
1580
+ {
1581
+ "epoch": 0.515936711763357,
1582
+ "grad_norm": 13.4375,
1583
+ "learning_rate": 9.685851868837424e-06,
1584
+ "loss": 1.153,
1585
+ "step": 2250
1586
+ },
1587
+ {
1588
+ "epoch": 0.5182297638156386,
1589
+ "grad_norm": 12.875,
1590
+ "learning_rate": 9.639990827791793e-06,
1591
+ "loss": 1.1774,
1592
+ "step": 2260
1593
+ },
1594
+ {
1595
+ "epoch": 0.5205228158679202,
1596
+ "grad_norm": 9.9375,
1597
+ "learning_rate": 9.594129786746161e-06,
1598
+ "loss": 1.1825,
1599
+ "step": 2270
1600
+ },
1601
+ {
1602
+ "epoch": 0.5228158679202017,
1603
+ "grad_norm": 6.375,
1604
+ "learning_rate": 9.548268745700528e-06,
1605
+ "loss": 1.1784,
1606
+ "step": 2280
1607
+ },
1608
+ {
1609
+ "epoch": 0.5251089199724833,
1610
+ "grad_norm": 14.375,
1611
+ "learning_rate": 9.502407704654896e-06,
1612
+ "loss": 1.1542,
1613
+ "step": 2290
1614
+ },
1615
+ {
1616
+ "epoch": 0.5274019720247649,
1617
+ "grad_norm": 13.0,
1618
+ "learning_rate": 9.456546663609264e-06,
1619
+ "loss": 1.1705,
1620
+ "step": 2300
1621
+ },
1622
+ {
1623
+ "epoch": 0.5296950240770465,
1624
+ "grad_norm": 15.6875,
1625
+ "learning_rate": 9.410685622563633e-06,
1626
+ "loss": 1.1906,
1627
+ "step": 2310
1628
+ },
1629
+ {
1630
+ "epoch": 0.5319880761293282,
1631
+ "grad_norm": 9.1875,
1632
+ "learning_rate": 9.364824581518001e-06,
1633
+ "loss": 1.1732,
1634
+ "step": 2320
1635
+ },
1636
+ {
1637
+ "epoch": 0.5342811281816098,
1638
+ "grad_norm": 11.4375,
1639
+ "learning_rate": 9.31896354047237e-06,
1640
+ "loss": 1.1994,
1641
+ "step": 2330
1642
+ },
1643
+ {
1644
+ "epoch": 0.5365741802338914,
1645
+ "grad_norm": 9.8125,
1646
+ "learning_rate": 9.273102499426738e-06,
1647
+ "loss": 1.1633,
1648
+ "step": 2340
1649
+ },
1650
+ {
1651
+ "epoch": 0.538867232286173,
1652
+ "grad_norm": 8.9375,
1653
+ "learning_rate": 9.227241458381106e-06,
1654
+ "loss": 1.1683,
1655
+ "step": 2350
1656
+ },
1657
+ {
1658
+ "epoch": 0.5411602843384545,
1659
+ "grad_norm": 12.0,
1660
+ "learning_rate": 9.181380417335474e-06,
1661
+ "loss": 1.1565,
1662
+ "step": 2360
1663
+ },
1664
+ {
1665
+ "epoch": 0.5434533363907361,
1666
+ "grad_norm": 10.0625,
1667
+ "learning_rate": 9.135519376289841e-06,
1668
+ "loss": 1.1726,
1669
+ "step": 2370
1670
+ },
1671
+ {
1672
+ "epoch": 0.5457463884430177,
1673
+ "grad_norm": 13.9375,
1674
+ "learning_rate": 9.08965833524421e-06,
1675
+ "loss": 1.1582,
1676
+ "step": 2380
1677
+ },
1678
+ {
1679
+ "epoch": 0.5480394404952993,
1680
+ "grad_norm": 7.90625,
1681
+ "learning_rate": 9.043797294198578e-06,
1682
+ "loss": 1.1647,
1683
+ "step": 2390
1684
+ },
1685
+ {
1686
+ "epoch": 0.5503324925475809,
1687
+ "grad_norm": 16.0,
1688
+ "learning_rate": 8.997936253152946e-06,
1689
+ "loss": 1.1838,
1690
+ "step": 2400
1691
+ },
1692
+ {
1693
+ "epoch": 0.5526255445998625,
1694
+ "grad_norm": 11.75,
1695
+ "learning_rate": 8.952075212107315e-06,
1696
+ "loss": 1.1699,
1697
+ "step": 2410
1698
+ },
1699
+ {
1700
+ "epoch": 0.554918596652144,
1701
+ "grad_norm": 12.3125,
1702
+ "learning_rate": 8.906214171061683e-06,
1703
+ "loss": 1.1693,
1704
+ "step": 2420
1705
+ },
1706
+ {
1707
+ "epoch": 0.5572116487044256,
1708
+ "grad_norm": 8.625,
1709
+ "learning_rate": 8.860353130016051e-06,
1710
+ "loss": 1.1793,
1711
+ "step": 2430
1712
+ },
1713
+ {
1714
+ "epoch": 0.5595047007567072,
1715
+ "grad_norm": 10.1875,
1716
+ "learning_rate": 8.81449208897042e-06,
1717
+ "loss": 1.1799,
1718
+ "step": 2440
1719
+ },
1720
+ {
1721
+ "epoch": 0.5617977528089888,
1722
+ "grad_norm": 7.625,
1723
+ "learning_rate": 8.768631047924788e-06,
1724
+ "loss": 1.1503,
1725
+ "step": 2450
1726
+ },
1727
+ {
1728
+ "epoch": 0.5640908048612704,
1729
+ "grad_norm": 11.125,
1730
+ "learning_rate": 8.722770006879156e-06,
1731
+ "loss": 1.178,
1732
+ "step": 2460
1733
+ },
1734
+ {
1735
+ "epoch": 0.566383856913552,
1736
+ "grad_norm": 11.375,
1737
+ "learning_rate": 8.676908965833525e-06,
1738
+ "loss": 1.149,
1739
+ "step": 2470
1740
+ },
1741
+ {
1742
+ "epoch": 0.5686769089658336,
1743
+ "grad_norm": 12.1875,
1744
+ "learning_rate": 8.631047924787893e-06,
1745
+ "loss": 1.1781,
1746
+ "step": 2480
1747
+ },
1748
+ {
1749
+ "epoch": 0.5709699610181151,
1750
+ "grad_norm": 11.4375,
1751
+ "learning_rate": 8.585186883742261e-06,
1752
+ "loss": 1.1664,
1753
+ "step": 2490
1754
+ },
1755
+ {
1756
+ "epoch": 0.5732630130703967,
1757
+ "grad_norm": 9.625,
1758
+ "learning_rate": 8.53932584269663e-06,
1759
+ "loss": 1.1448,
1760
+ "step": 2500
1761
+ },
1762
+ {
1763
+ "epoch": 0.5755560651226783,
1764
+ "grad_norm": 11.0625,
1765
+ "learning_rate": 8.493464801650998e-06,
1766
+ "loss": 1.1537,
1767
+ "step": 2510
1768
+ },
1769
+ {
1770
+ "epoch": 0.5778491171749599,
1771
+ "grad_norm": 10.1875,
1772
+ "learning_rate": 8.447603760605366e-06,
1773
+ "loss": 1.1583,
1774
+ "step": 2520
1775
+ },
1776
+ {
1777
+ "epoch": 0.5801421692272415,
1778
+ "grad_norm": 9.25,
1779
+ "learning_rate": 8.401742719559735e-06,
1780
+ "loss": 1.1794,
1781
+ "step": 2530
1782
+ },
1783
+ {
1784
+ "epoch": 0.5824352212795231,
1785
+ "grad_norm": 10.8125,
1786
+ "learning_rate": 8.355881678514103e-06,
1787
+ "loss": 1.1558,
1788
+ "step": 2540
1789
+ },
1790
+ {
1791
+ "epoch": 0.5847282733318047,
1792
+ "grad_norm": 9.9375,
1793
+ "learning_rate": 8.310020637468471e-06,
1794
+ "loss": 1.1693,
1795
+ "step": 2550
1796
+ },
1797
+ {
1798
+ "epoch": 0.5870213253840862,
1799
+ "grad_norm": 13.6875,
1800
+ "learning_rate": 8.26415959642284e-06,
1801
+ "loss": 1.1685,
1802
+ "step": 2560
1803
+ },
1804
+ {
1805
+ "epoch": 0.5893143774363678,
1806
+ "grad_norm": 9.1875,
1807
+ "learning_rate": 8.218298555377208e-06,
1808
+ "loss": 1.1697,
1809
+ "step": 2570
1810
+ },
1811
+ {
1812
+ "epoch": 0.5916074294886494,
1813
+ "grad_norm": 15.0,
1814
+ "learning_rate": 8.172437514331576e-06,
1815
+ "loss": 1.1509,
1816
+ "step": 2580
1817
+ },
1818
+ {
1819
+ "epoch": 0.593900481540931,
1820
+ "grad_norm": 11.75,
1821
+ "learning_rate": 8.126576473285945e-06,
1822
+ "loss": 1.1541,
1823
+ "step": 2590
1824
+ },
1825
+ {
1826
+ "epoch": 0.5961935335932126,
1827
+ "grad_norm": 10.375,
1828
+ "learning_rate": 8.080715432240313e-06,
1829
+ "loss": 1.1517,
1830
+ "step": 2600
1831
+ },
1832
+ {
1833
+ "epoch": 0.5984865856454942,
1834
+ "grad_norm": 13.3125,
1835
+ "learning_rate": 8.034854391194681e-06,
1836
+ "loss": 1.178,
1837
+ "step": 2610
1838
+ },
1839
+ {
1840
+ "epoch": 0.6007796376977758,
1841
+ "grad_norm": 12.6875,
1842
+ "learning_rate": 7.98899335014905e-06,
1843
+ "loss": 1.159,
1844
+ "step": 2620
1845
+ },
1846
+ {
1847
+ "epoch": 0.6030726897500573,
1848
+ "grad_norm": 12.75,
1849
+ "learning_rate": 7.943132309103418e-06,
1850
+ "loss": 1.1604,
1851
+ "step": 2630
1852
+ },
1853
+ {
1854
+ "epoch": 0.6053657418023389,
1855
+ "grad_norm": 7.0625,
1856
+ "learning_rate": 7.897271268057786e-06,
1857
+ "loss": 1.1696,
1858
+ "step": 2640
1859
+ },
1860
+ {
1861
+ "epoch": 0.6076587938546205,
1862
+ "grad_norm": 13.0625,
1863
+ "learning_rate": 7.851410227012155e-06,
1864
+ "loss": 1.1713,
1865
+ "step": 2650
1866
+ },
1867
+ {
1868
+ "epoch": 0.6099518459069021,
1869
+ "grad_norm": 8.8125,
1870
+ "learning_rate": 7.805549185966521e-06,
1871
+ "loss": 1.1678,
1872
+ "step": 2660
1873
+ },
1874
+ {
1875
+ "epoch": 0.6122448979591837,
1876
+ "grad_norm": 12.75,
1877
+ "learning_rate": 7.75968814492089e-06,
1878
+ "loss": 1.168,
1879
+ "step": 2670
1880
+ },
1881
+ {
1882
+ "epoch": 0.6145379500114653,
1883
+ "grad_norm": 7.09375,
1884
+ "learning_rate": 7.713827103875258e-06,
1885
+ "loss": 1.1519,
1886
+ "step": 2680
1887
+ },
1888
+ {
1889
+ "epoch": 0.6168310020637469,
1890
+ "grad_norm": 10.375,
1891
+ "learning_rate": 7.667966062829626e-06,
1892
+ "loss": 1.1651,
1893
+ "step": 2690
1894
+ },
1895
+ {
1896
+ "epoch": 0.6191240541160284,
1897
+ "grad_norm": 11.25,
1898
+ "learning_rate": 7.622105021783996e-06,
1899
+ "loss": 1.1303,
1900
+ "step": 2700
1901
+ },
1902
+ {
1903
+ "epoch": 0.62141710616831,
1904
+ "grad_norm": 13.1875,
1905
+ "learning_rate": 7.576243980738364e-06,
1906
+ "loss": 1.1462,
1907
+ "step": 2710
1908
+ },
1909
+ {
1910
+ "epoch": 0.6237101582205916,
1911
+ "grad_norm": 10.0,
1912
+ "learning_rate": 7.530382939692732e-06,
1913
+ "loss": 1.1786,
1914
+ "step": 2720
1915
+ },
1916
+ {
1917
+ "epoch": 0.6260032102728732,
1918
+ "grad_norm": 11.6875,
1919
+ "learning_rate": 7.4845218986471e-06,
1920
+ "loss": 1.179,
1921
+ "step": 2730
1922
+ },
1923
+ {
1924
+ "epoch": 0.6282962623251548,
1925
+ "grad_norm": 12.3125,
1926
+ "learning_rate": 7.438660857601468e-06,
1927
+ "loss": 1.1708,
1928
+ "step": 2740
1929
+ },
1930
+ {
1931
+ "epoch": 0.6305893143774364,
1932
+ "grad_norm": 11.625,
1933
+ "learning_rate": 7.3927998165558365e-06,
1934
+ "loss": 1.1582,
1935
+ "step": 2750
1936
+ },
1937
+ {
1938
+ "epoch": 0.632882366429718,
1939
+ "grad_norm": 15.3125,
1940
+ "learning_rate": 7.346938775510205e-06,
1941
+ "loss": 1.1622,
1942
+ "step": 2760
1943
+ },
1944
+ {
1945
+ "epoch": 0.6351754184819995,
1946
+ "grad_norm": 13.75,
1947
+ "learning_rate": 7.301077734464573e-06,
1948
+ "loss": 1.1626,
1949
+ "step": 2770
1950
+ },
1951
+ {
1952
+ "epoch": 0.6374684705342811,
1953
+ "grad_norm": 9.0625,
1954
+ "learning_rate": 7.2552166934189415e-06,
1955
+ "loss": 1.1477,
1956
+ "step": 2780
1957
+ },
1958
+ {
1959
+ "epoch": 0.6397615225865627,
1960
+ "grad_norm": 8.75,
1961
+ "learning_rate": 7.20935565237331e-06,
1962
+ "loss": 1.1482,
1963
+ "step": 2790
1964
+ },
1965
+ {
1966
+ "epoch": 0.6420545746388443,
1967
+ "grad_norm": 9.375,
1968
+ "learning_rate": 7.163494611327678e-06,
1969
+ "loss": 1.1293,
1970
+ "step": 2800
1971
+ },
1972
+ {
1973
+ "epoch": 0.6443476266911259,
1974
+ "grad_norm": 10.3125,
1975
+ "learning_rate": 7.1176335702820466e-06,
1976
+ "loss": 1.1391,
1977
+ "step": 2810
1978
+ },
1979
+ {
1980
+ "epoch": 0.6466406787434075,
1981
+ "grad_norm": 12.9375,
1982
+ "learning_rate": 7.071772529236415e-06,
1983
+ "loss": 1.153,
1984
+ "step": 2820
1985
+ },
1986
+ {
1987
+ "epoch": 0.6489337307956891,
1988
+ "grad_norm": 16.875,
1989
+ "learning_rate": 7.025911488190783e-06,
1990
+ "loss": 1.1551,
1991
+ "step": 2830
1992
+ },
1993
+ {
1994
+ "epoch": 0.6512267828479706,
1995
+ "grad_norm": 12.0625,
1996
+ "learning_rate": 6.98005044714515e-06,
1997
+ "loss": 1.1548,
1998
+ "step": 2840
1999
+ },
2000
+ {
2001
+ "epoch": 0.6535198349002522,
2002
+ "grad_norm": 14.0625,
2003
+ "learning_rate": 6.934189406099518e-06,
2004
+ "loss": 1.1771,
2005
+ "step": 2850
2006
+ },
2007
+ {
2008
+ "epoch": 0.6558128869525338,
2009
+ "grad_norm": 14.9375,
2010
+ "learning_rate": 6.888328365053887e-06,
2011
+ "loss": 1.159,
2012
+ "step": 2860
2013
+ },
2014
+ {
2015
+ "epoch": 0.6581059390048154,
2016
+ "grad_norm": 12.0,
2017
+ "learning_rate": 6.842467324008255e-06,
2018
+ "loss": 1.1413,
2019
+ "step": 2870
2020
+ },
2021
+ {
2022
+ "epoch": 0.660398991057097,
2023
+ "grad_norm": 11.3125,
2024
+ "learning_rate": 6.796606282962623e-06,
2025
+ "loss": 1.1717,
2026
+ "step": 2880
2027
+ },
2028
+ {
2029
+ "epoch": 0.6626920431093786,
2030
+ "grad_norm": 11.0625,
2031
+ "learning_rate": 6.750745241916992e-06,
2032
+ "loss": 1.1267,
2033
+ "step": 2890
2034
+ },
2035
+ {
2036
+ "epoch": 0.6649850951616602,
2037
+ "grad_norm": 10.9375,
2038
+ "learning_rate": 6.70488420087136e-06,
2039
+ "loss": 1.121,
2040
+ "step": 2900
2041
+ },
2042
+ {
2043
+ "epoch": 0.6672781472139417,
2044
+ "grad_norm": 8.6875,
2045
+ "learning_rate": 6.659023159825728e-06,
2046
+ "loss": 1.1593,
2047
+ "step": 2910
2048
+ },
2049
+ {
2050
+ "epoch": 0.6695711992662233,
2051
+ "grad_norm": 11.0,
2052
+ "learning_rate": 6.613162118780097e-06,
2053
+ "loss": 1.1764,
2054
+ "step": 2920
2055
+ },
2056
+ {
2057
+ "epoch": 0.6718642513185049,
2058
+ "grad_norm": 8.25,
2059
+ "learning_rate": 6.567301077734465e-06,
2060
+ "loss": 1.1719,
2061
+ "step": 2930
2062
+ },
2063
+ {
2064
+ "epoch": 0.6741573033707865,
2065
+ "grad_norm": 12.4375,
2066
+ "learning_rate": 6.521440036688833e-06,
2067
+ "loss": 1.154,
2068
+ "step": 2940
2069
+ },
2070
+ {
2071
+ "epoch": 0.6764503554230681,
2072
+ "grad_norm": 10.1875,
2073
+ "learning_rate": 6.475578995643202e-06,
2074
+ "loss": 1.1754,
2075
+ "step": 2950
2076
+ },
2077
+ {
2078
+ "epoch": 0.6787434074753497,
2079
+ "grad_norm": 11.75,
2080
+ "learning_rate": 6.42971795459757e-06,
2081
+ "loss": 1.1703,
2082
+ "step": 2960
2083
+ },
2084
+ {
2085
+ "epoch": 0.6810364595276313,
2086
+ "grad_norm": 9.875,
2087
+ "learning_rate": 6.3838569135519375e-06,
2088
+ "loss": 1.1494,
2089
+ "step": 2970
2090
+ },
2091
+ {
2092
+ "epoch": 0.6833295115799128,
2093
+ "grad_norm": 13.0625,
2094
+ "learning_rate": 6.337995872506306e-06,
2095
+ "loss": 1.1638,
2096
+ "step": 2980
2097
+ },
2098
+ {
2099
+ "epoch": 0.6856225636321944,
2100
+ "grad_norm": 10.75,
2101
+ "learning_rate": 6.292134831460674e-06,
2102
+ "loss": 1.1403,
2103
+ "step": 2990
2104
+ },
2105
+ {
2106
+ "epoch": 0.687915615684476,
2107
+ "grad_norm": 10.9375,
2108
+ "learning_rate": 6.2462737904150426e-06,
2109
+ "loss": 1.1696,
2110
+ "step": 3000
2111
+ },
2112
+ {
2113
+ "epoch": 0.6902086677367576,
2114
+ "grad_norm": 9.625,
2115
+ "learning_rate": 6.200412749369411e-06,
2116
+ "loss": 1.1577,
2117
+ "step": 3010
2118
+ },
2119
+ {
2120
+ "epoch": 0.6925017197890392,
2121
+ "grad_norm": 8.4375,
2122
+ "learning_rate": 6.154551708323779e-06,
2123
+ "loss": 1.1644,
2124
+ "step": 3020
2125
+ },
2126
+ {
2127
+ "epoch": 0.6947947718413208,
2128
+ "grad_norm": 9.4375,
2129
+ "learning_rate": 6.108690667278148e-06,
2130
+ "loss": 1.1587,
2131
+ "step": 3030
2132
+ },
2133
+ {
2134
+ "epoch": 0.6970878238936024,
2135
+ "grad_norm": 9.9375,
2136
+ "learning_rate": 6.062829626232516e-06,
2137
+ "loss": 1.1618,
2138
+ "step": 3040
2139
+ },
2140
+ {
2141
+ "epoch": 0.6993808759458839,
2142
+ "grad_norm": 9.5625,
2143
+ "learning_rate": 6.016968585186884e-06,
2144
+ "loss": 1.1613,
2145
+ "step": 3050
2146
+ },
2147
+ {
2148
+ "epoch": 0.7016739279981655,
2149
+ "grad_norm": 12.6875,
2150
+ "learning_rate": 5.971107544141253e-06,
2151
+ "loss": 1.1492,
2152
+ "step": 3060
2153
+ },
2154
+ {
2155
+ "epoch": 0.7039669800504471,
2156
+ "grad_norm": 8.875,
2157
+ "learning_rate": 5.925246503095621e-06,
2158
+ "loss": 1.1495,
2159
+ "step": 3070
2160
+ },
2161
+ {
2162
+ "epoch": 0.7062600321027287,
2163
+ "grad_norm": 12.75,
2164
+ "learning_rate": 5.879385462049989e-06,
2165
+ "loss": 1.149,
2166
+ "step": 3080
2167
+ },
2168
+ {
2169
+ "epoch": 0.7085530841550103,
2170
+ "grad_norm": 9.8125,
2171
+ "learning_rate": 5.833524421004358e-06,
2172
+ "loss": 1.1616,
2173
+ "step": 3090
2174
+ },
2175
+ {
2176
+ "epoch": 0.7108461362072919,
2177
+ "grad_norm": 11.3125,
2178
+ "learning_rate": 5.787663379958726e-06,
2179
+ "loss": 1.1694,
2180
+ "step": 3100
2181
+ },
2182
+ {
2183
+ "epoch": 0.7131391882595735,
2184
+ "grad_norm": 7.90625,
2185
+ "learning_rate": 5.7418023389130935e-06,
2186
+ "loss": 1.1384,
2187
+ "step": 3110
2188
+ },
2189
+ {
2190
+ "epoch": 0.715432240311855,
2191
+ "grad_norm": 10.0,
2192
+ "learning_rate": 5.695941297867462e-06,
2193
+ "loss": 1.156,
2194
+ "step": 3120
2195
+ },
2196
+ {
2197
+ "epoch": 0.7177252923641366,
2198
+ "grad_norm": 14.6875,
2199
+ "learning_rate": 5.65008025682183e-06,
2200
+ "loss": 1.1736,
2201
+ "step": 3130
2202
+ },
2203
+ {
2204
+ "epoch": 0.7200183444164182,
2205
+ "grad_norm": 11.4375,
2206
+ "learning_rate": 5.6042192157761985e-06,
2207
+ "loss": 1.1293,
2208
+ "step": 3140
2209
+ },
2210
+ {
2211
+ "epoch": 0.7223113964686998,
2212
+ "grad_norm": 12.875,
2213
+ "learning_rate": 5.558358174730567e-06,
2214
+ "loss": 1.1067,
2215
+ "step": 3150
2216
+ },
2217
+ {
2218
+ "epoch": 0.7246044485209814,
2219
+ "grad_norm": 11.6875,
2220
+ "learning_rate": 5.512497133684935e-06,
2221
+ "loss": 1.1516,
2222
+ "step": 3160
2223
+ },
2224
+ {
2225
+ "epoch": 0.726897500573263,
2226
+ "grad_norm": 10.5625,
2227
+ "learning_rate": 5.4666360926393036e-06,
2228
+ "loss": 1.1532,
2229
+ "step": 3170
2230
+ },
2231
+ {
2232
+ "epoch": 0.7291905526255446,
2233
+ "grad_norm": 9.6875,
2234
+ "learning_rate": 5.420775051593672e-06,
2235
+ "loss": 1.1647,
2236
+ "step": 3180
2237
+ },
2238
+ {
2239
+ "epoch": 0.7314836046778261,
2240
+ "grad_norm": 12.1875,
2241
+ "learning_rate": 5.37491401054804e-06,
2242
+ "loss": 1.1914,
2243
+ "step": 3190
2244
+ },
2245
+ {
2246
+ "epoch": 0.7337766567301077,
2247
+ "grad_norm": 13.25,
2248
+ "learning_rate": 5.329052969502409e-06,
2249
+ "loss": 1.148,
2250
+ "step": 3200
2251
+ },
2252
+ {
2253
+ "epoch": 0.7360697087823893,
2254
+ "grad_norm": 8.375,
2255
+ "learning_rate": 5.283191928456777e-06,
2256
+ "loss": 1.1612,
2257
+ "step": 3210
2258
+ },
2259
+ {
2260
+ "epoch": 0.7383627608346709,
2261
+ "grad_norm": 8.75,
2262
+ "learning_rate": 5.237330887411145e-06,
2263
+ "loss": 1.1402,
2264
+ "step": 3220
2265
+ },
2266
+ {
2267
+ "epoch": 0.7406558128869525,
2268
+ "grad_norm": 11.5,
2269
+ "learning_rate": 5.191469846365514e-06,
2270
+ "loss": 1.1737,
2271
+ "step": 3230
2272
+ },
2273
+ {
2274
+ "epoch": 0.7429488649392341,
2275
+ "grad_norm": 11.625,
2276
+ "learning_rate": 5.145608805319882e-06,
2277
+ "loss": 1.1854,
2278
+ "step": 3240
2279
+ },
2280
+ {
2281
+ "epoch": 0.7452419169915158,
2282
+ "grad_norm": 11.125,
2283
+ "learning_rate": 5.0997477642742495e-06,
2284
+ "loss": 1.1611,
2285
+ "step": 3250
2286
+ },
2287
+ {
2288
+ "epoch": 0.7475349690437973,
2289
+ "grad_norm": 9.6875,
2290
+ "learning_rate": 5.053886723228618e-06,
2291
+ "loss": 1.1477,
2292
+ "step": 3260
2293
+ },
2294
+ {
2295
+ "epoch": 0.7498280210960789,
2296
+ "grad_norm": 10.75,
2297
+ "learning_rate": 5.008025682182986e-06,
2298
+ "loss": 1.1608,
2299
+ "step": 3270
2300
+ },
2301
+ {
2302
+ "epoch": 0.7521210731483605,
2303
+ "grad_norm": 14.125,
2304
+ "learning_rate": 4.9621646411373545e-06,
2305
+ "loss": 1.1658,
2306
+ "step": 3280
2307
+ },
2308
+ {
2309
+ "epoch": 0.7544141252006421,
2310
+ "grad_norm": 9.5625,
2311
+ "learning_rate": 4.916303600091723e-06,
2312
+ "loss": 1.15,
2313
+ "step": 3290
2314
+ },
2315
+ {
2316
+ "epoch": 0.7567071772529237,
2317
+ "grad_norm": 13.625,
2318
+ "learning_rate": 4.87044255904609e-06,
2319
+ "loss": 1.1616,
2320
+ "step": 3300
2321
+ },
2322
+ {
2323
+ "epoch": 0.7590002293052053,
2324
+ "grad_norm": 12.625,
2325
+ "learning_rate": 4.824581518000459e-06,
2326
+ "loss": 1.1545,
2327
+ "step": 3310
2328
+ },
2329
+ {
2330
+ "epoch": 0.7612932813574869,
2331
+ "grad_norm": 12.75,
2332
+ "learning_rate": 4.778720476954827e-06,
2333
+ "loss": 1.1637,
2334
+ "step": 3320
2335
+ },
2336
+ {
2337
+ "epoch": 0.7635863334097684,
2338
+ "grad_norm": 10.0625,
2339
+ "learning_rate": 4.732859435909195e-06,
2340
+ "loss": 1.1497,
2341
+ "step": 3330
2342
+ },
2343
+ {
2344
+ "epoch": 0.76587938546205,
2345
+ "grad_norm": 11.3125,
2346
+ "learning_rate": 4.686998394863564e-06,
2347
+ "loss": 1.1739,
2348
+ "step": 3340
2349
+ },
2350
+ {
2351
+ "epoch": 0.7681724375143316,
2352
+ "grad_norm": 12.75,
2353
+ "learning_rate": 4.641137353817932e-06,
2354
+ "loss": 1.157,
2355
+ "step": 3350
2356
+ },
2357
+ {
2358
+ "epoch": 0.7704654895666132,
2359
+ "grad_norm": 7.90625,
2360
+ "learning_rate": 4.5952763127723e-06,
2361
+ "loss": 1.1537,
2362
+ "step": 3360
2363
+ },
2364
+ {
2365
+ "epoch": 0.7727585416188948,
2366
+ "grad_norm": 10.625,
2367
+ "learning_rate": 4.549415271726669e-06,
2368
+ "loss": 1.1519,
2369
+ "step": 3370
2370
+ },
2371
+ {
2372
+ "epoch": 0.7750515936711764,
2373
+ "grad_norm": 11.6875,
2374
+ "learning_rate": 4.503554230681037e-06,
2375
+ "loss": 1.1483,
2376
+ "step": 3380
2377
+ },
2378
+ {
2379
+ "epoch": 0.777344645723458,
2380
+ "grad_norm": 11.75,
2381
+ "learning_rate": 4.4576931896354054e-06,
2382
+ "loss": 1.1423,
2383
+ "step": 3390
2384
+ },
2385
+ {
2386
+ "epoch": 0.7796376977757395,
2387
+ "grad_norm": 13.9375,
2388
+ "learning_rate": 4.411832148589774e-06,
2389
+ "loss": 1.1684,
2390
+ "step": 3400
2391
+ },
2392
+ {
2393
+ "epoch": 0.7819307498280211,
2394
+ "grad_norm": 15.9375,
2395
+ "learning_rate": 4.365971107544142e-06,
2396
+ "loss": 1.1695,
2397
+ "step": 3410
2398
+ },
2399
+ {
2400
+ "epoch": 0.7842238018803027,
2401
+ "grad_norm": 13.625,
2402
+ "learning_rate": 4.32011006649851e-06,
2403
+ "loss": 1.1625,
2404
+ "step": 3420
2405
+ },
2406
+ {
2407
+ "epoch": 0.7865168539325843,
2408
+ "grad_norm": 13.375,
2409
+ "learning_rate": 4.274249025452878e-06,
2410
+ "loss": 1.1753,
2411
+ "step": 3430
2412
+ },
2413
+ {
2414
+ "epoch": 0.7888099059848659,
2415
+ "grad_norm": 11.25,
2416
+ "learning_rate": 4.228387984407246e-06,
2417
+ "loss": 1.1755,
2418
+ "step": 3440
2419
+ },
2420
+ {
2421
+ "epoch": 0.7911029580371475,
2422
+ "grad_norm": 9.375,
2423
+ "learning_rate": 4.182526943361615e-06,
2424
+ "loss": 1.1578,
2425
+ "step": 3450
2426
+ },
2427
+ {
2428
+ "epoch": 0.7933960100894291,
2429
+ "grad_norm": 9.125,
2430
+ "learning_rate": 4.136665902315983e-06,
2431
+ "loss": 1.1278,
2432
+ "step": 3460
2433
+ },
2434
+ {
2435
+ "epoch": 0.7956890621417106,
2436
+ "grad_norm": 10.625,
2437
+ "learning_rate": 4.090804861270351e-06,
2438
+ "loss": 1.1695,
2439
+ "step": 3470
2440
+ },
2441
+ {
2442
+ "epoch": 0.7979821141939922,
2443
+ "grad_norm": 9.8125,
2444
+ "learning_rate": 4.04494382022472e-06,
2445
+ "loss": 1.1471,
2446
+ "step": 3480
2447
+ },
2448
+ {
2449
+ "epoch": 0.8002751662462738,
2450
+ "grad_norm": 10.5,
2451
+ "learning_rate": 3.999082779179087e-06,
2452
+ "loss": 1.1484,
2453
+ "step": 3490
2454
+ },
2455
+ {
2456
+ "epoch": 0.8025682182985554,
2457
+ "grad_norm": 14.125,
2458
+ "learning_rate": 3.9532217381334555e-06,
2459
+ "loss": 1.173,
2460
+ "step": 3500
2461
+ },
2462
+ {
2463
+ "epoch": 0.804861270350837,
2464
+ "grad_norm": 8.125,
2465
+ "learning_rate": 3.907360697087824e-06,
2466
+ "loss": 1.1756,
2467
+ "step": 3510
2468
+ },
2469
+ {
2470
+ "epoch": 0.8071543224031186,
2471
+ "grad_norm": 9.125,
2472
+ "learning_rate": 3.861499656042192e-06,
2473
+ "loss": 1.1492,
2474
+ "step": 3520
2475
+ },
2476
+ {
2477
+ "epoch": 0.8094473744554002,
2478
+ "grad_norm": 8.3125,
2479
+ "learning_rate": 3.8156386149965606e-06,
2480
+ "loss": 1.1502,
2481
+ "step": 3530
2482
+ },
2483
+ {
2484
+ "epoch": 0.8117404265076817,
2485
+ "grad_norm": 9.625,
2486
+ "learning_rate": 3.769777573950929e-06,
2487
+ "loss": 1.1442,
2488
+ "step": 3540
2489
+ },
2490
+ {
2491
+ "epoch": 0.8140334785599633,
2492
+ "grad_norm": 11.75,
2493
+ "learning_rate": 3.7239165329052972e-06,
2494
+ "loss": 1.1612,
2495
+ "step": 3550
2496
+ },
2497
+ {
2498
+ "epoch": 0.8163265306122449,
2499
+ "grad_norm": 10.5,
2500
+ "learning_rate": 3.6780554918596656e-06,
2501
+ "loss": 1.1628,
2502
+ "step": 3560
2503
+ },
2504
+ {
2505
+ "epoch": 0.8186195826645265,
2506
+ "grad_norm": 10.75,
2507
+ "learning_rate": 3.632194450814034e-06,
2508
+ "loss": 1.1583,
2509
+ "step": 3570
2510
+ },
2511
+ {
2512
+ "epoch": 0.8209126347168081,
2513
+ "grad_norm": 14.5,
2514
+ "learning_rate": 3.5863334097684023e-06,
2515
+ "loss": 1.1596,
2516
+ "step": 3580
2517
+ },
2518
+ {
2519
+ "epoch": 0.8232056867690897,
2520
+ "grad_norm": 10.0,
2521
+ "learning_rate": 3.5404723687227706e-06,
2522
+ "loss": 1.1573,
2523
+ "step": 3590
2524
+ },
2525
+ {
2526
+ "epoch": 0.8254987388213713,
2527
+ "grad_norm": 12.4375,
2528
+ "learning_rate": 3.4946113276771385e-06,
2529
+ "loss": 1.1575,
2530
+ "step": 3600
2531
+ },
2532
+ {
2533
+ "epoch": 0.8277917908736528,
2534
+ "grad_norm": 10.625,
2535
+ "learning_rate": 3.448750286631507e-06,
2536
+ "loss": 1.136,
2537
+ "step": 3610
2538
+ },
2539
+ {
2540
+ "epoch": 0.8300848429259344,
2541
+ "grad_norm": 10.875,
2542
+ "learning_rate": 3.4028892455858752e-06,
2543
+ "loss": 1.1493,
2544
+ "step": 3620
2545
+ },
2546
+ {
2547
+ "epoch": 0.832377894978216,
2548
+ "grad_norm": 17.0,
2549
+ "learning_rate": 3.3570282045402436e-06,
2550
+ "loss": 1.1689,
2551
+ "step": 3630
2552
+ },
2553
+ {
2554
+ "epoch": 0.8346709470304976,
2555
+ "grad_norm": 8.9375,
2556
+ "learning_rate": 3.311167163494612e-06,
2557
+ "loss": 1.1406,
2558
+ "step": 3640
2559
+ },
2560
+ {
2561
+ "epoch": 0.8369639990827792,
2562
+ "grad_norm": 9.625,
2563
+ "learning_rate": 3.2653061224489794e-06,
2564
+ "loss": 1.1438,
2565
+ "step": 3650
2566
+ },
2567
+ {
2568
+ "epoch": 0.8392570511350608,
2569
+ "grad_norm": 12.125,
2570
+ "learning_rate": 3.2194450814033478e-06,
2571
+ "loss": 1.1721,
2572
+ "step": 3660
2573
+ },
2574
+ {
2575
+ "epoch": 0.8415501031873424,
2576
+ "grad_norm": 8.5,
2577
+ "learning_rate": 3.173584040357716e-06,
2578
+ "loss": 1.1498,
2579
+ "step": 3670
2580
+ },
2581
+ {
2582
+ "epoch": 0.8438431552396239,
2583
+ "grad_norm": 11.625,
2584
+ "learning_rate": 3.1277229993120844e-06,
2585
+ "loss": 1.1531,
2586
+ "step": 3680
2587
+ },
2588
+ {
2589
+ "epoch": 0.8461362072919055,
2590
+ "grad_norm": 10.0625,
2591
+ "learning_rate": 3.081861958266453e-06,
2592
+ "loss": 1.1489,
2593
+ "step": 3690
2594
+ },
2595
+ {
2596
+ "epoch": 0.8484292593441871,
2597
+ "grad_norm": 14.375,
2598
+ "learning_rate": 3.036000917220821e-06,
2599
+ "loss": 1.133,
2600
+ "step": 3700
2601
+ },
2602
+ {
2603
+ "epoch": 0.8507223113964687,
2604
+ "grad_norm": 9.3125,
2605
+ "learning_rate": 2.9901398761751895e-06,
2606
+ "loss": 1.1565,
2607
+ "step": 3710
2608
+ },
2609
+ {
2610
+ "epoch": 0.8530153634487503,
2611
+ "grad_norm": 10.0,
2612
+ "learning_rate": 2.9442788351295574e-06,
2613
+ "loss": 1.162,
2614
+ "step": 3720
2615
+ },
2616
+ {
2617
+ "epoch": 0.8553084155010319,
2618
+ "grad_norm": 13.9375,
2619
+ "learning_rate": 2.8984177940839257e-06,
2620
+ "loss": 1.1472,
2621
+ "step": 3730
2622
+ },
2623
+ {
2624
+ "epoch": 0.8576014675533135,
2625
+ "grad_norm": 11.25,
2626
+ "learning_rate": 2.852556753038294e-06,
2627
+ "loss": 1.1293,
2628
+ "step": 3740
2629
+ },
2630
+ {
2631
+ "epoch": 0.859894519605595,
2632
+ "grad_norm": 10.4375,
2633
+ "learning_rate": 2.8066957119926624e-06,
2634
+ "loss": 1.1667,
2635
+ "step": 3750
2636
+ },
2637
+ {
2638
+ "epoch": 0.8621875716578766,
2639
+ "grad_norm": 11.0625,
2640
+ "learning_rate": 2.7608346709470308e-06,
2641
+ "loss": 1.148,
2642
+ "step": 3760
2643
+ },
2644
+ {
2645
+ "epoch": 0.8644806237101582,
2646
+ "grad_norm": 12.6875,
2647
+ "learning_rate": 2.714973629901399e-06,
2648
+ "loss": 1.1476,
2649
+ "step": 3770
2650
+ },
2651
+ {
2652
+ "epoch": 0.8667736757624398,
2653
+ "grad_norm": 15.0,
2654
+ "learning_rate": 2.6691125888557675e-06,
2655
+ "loss": 1.1556,
2656
+ "step": 3780
2657
+ },
2658
+ {
2659
+ "epoch": 0.8690667278147214,
2660
+ "grad_norm": 8.0,
2661
+ "learning_rate": 2.6232515478101354e-06,
2662
+ "loss": 1.1458,
2663
+ "step": 3790
2664
+ },
2665
+ {
2666
+ "epoch": 0.871359779867003,
2667
+ "grad_norm": 13.9375,
2668
+ "learning_rate": 2.5773905067645037e-06,
2669
+ "loss": 1.1335,
2670
+ "step": 3800
2671
+ },
2672
+ {
2673
+ "epoch": 0.8736528319192846,
2674
+ "grad_norm": 11.75,
2675
+ "learning_rate": 2.531529465718872e-06,
2676
+ "loss": 1.1534,
2677
+ "step": 3810
2678
+ },
2679
+ {
2680
+ "epoch": 0.8759458839715661,
2681
+ "grad_norm": 11.9375,
2682
+ "learning_rate": 2.48566842467324e-06,
2683
+ "loss": 1.1266,
2684
+ "step": 3820
2685
+ },
2686
+ {
2687
+ "epoch": 0.8782389360238477,
2688
+ "grad_norm": 9.875,
2689
+ "learning_rate": 2.4398073836276083e-06,
2690
+ "loss": 1.1467,
2691
+ "step": 3830
2692
+ },
2693
+ {
2694
+ "epoch": 0.8805319880761293,
2695
+ "grad_norm": 12.1875,
2696
+ "learning_rate": 2.3939463425819767e-06,
2697
+ "loss": 1.1495,
2698
+ "step": 3840
2699
+ },
2700
+ {
2701
+ "epoch": 0.8828250401284109,
2702
+ "grad_norm": 12.0625,
2703
+ "learning_rate": 2.348085301536345e-06,
2704
+ "loss": 1.1471,
2705
+ "step": 3850
2706
+ },
2707
+ {
2708
+ "epoch": 0.8851180921806925,
2709
+ "grad_norm": 11.5625,
2710
+ "learning_rate": 2.3022242604907134e-06,
2711
+ "loss": 1.143,
2712
+ "step": 3860
2713
+ },
2714
+ {
2715
+ "epoch": 0.8874111442329741,
2716
+ "grad_norm": 13.25,
2717
+ "learning_rate": 2.2563632194450817e-06,
2718
+ "loss": 1.158,
2719
+ "step": 3870
2720
+ },
2721
+ {
2722
+ "epoch": 0.8897041962852557,
2723
+ "grad_norm": 13.4375,
2724
+ "learning_rate": 2.21050217839945e-06,
2725
+ "loss": 1.1639,
2726
+ "step": 3880
2727
+ },
2728
+ {
2729
+ "epoch": 0.8919972483375372,
2730
+ "grad_norm": 16.375,
2731
+ "learning_rate": 2.164641137353818e-06,
2732
+ "loss": 1.1484,
2733
+ "step": 3890
2734
+ },
2735
+ {
2736
+ "epoch": 0.8942903003898188,
2737
+ "grad_norm": 13.0625,
2738
+ "learning_rate": 2.1187800963081863e-06,
2739
+ "loss": 1.1343,
2740
+ "step": 3900
2741
+ },
2742
+ {
2743
+ "epoch": 0.8965833524421004,
2744
+ "grad_norm": 10.0625,
2745
+ "learning_rate": 2.0729190552625547e-06,
2746
+ "loss": 1.1346,
2747
+ "step": 3910
2748
+ },
2749
+ {
2750
+ "epoch": 0.898876404494382,
2751
+ "grad_norm": 13.0625,
2752
+ "learning_rate": 2.027058014216923e-06,
2753
+ "loss": 1.1496,
2754
+ "step": 3920
2755
+ },
2756
+ {
2757
+ "epoch": 0.9011694565466636,
2758
+ "grad_norm": 12.1875,
2759
+ "learning_rate": 1.9811969731712914e-06,
2760
+ "loss": 1.1345,
2761
+ "step": 3930
2762
+ },
2763
+ {
2764
+ "epoch": 0.9034625085989452,
2765
+ "grad_norm": 10.6875,
2766
+ "learning_rate": 1.9353359321256593e-06,
2767
+ "loss": 1.1551,
2768
+ "step": 3940
2769
+ },
2770
+ {
2771
+ "epoch": 0.9057555606512268,
2772
+ "grad_norm": 10.5625,
2773
+ "learning_rate": 1.8894748910800276e-06,
2774
+ "loss": 1.1252,
2775
+ "step": 3950
2776
+ },
2777
+ {
2778
+ "epoch": 0.9080486127035083,
2779
+ "grad_norm": 15.0,
2780
+ "learning_rate": 1.843613850034396e-06,
2781
+ "loss": 1.1214,
2782
+ "step": 3960
2783
+ },
2784
+ {
2785
+ "epoch": 0.9103416647557899,
2786
+ "grad_norm": 11.375,
2787
+ "learning_rate": 1.797752808988764e-06,
2788
+ "loss": 1.1846,
2789
+ "step": 3970
2790
+ },
2791
+ {
2792
+ "epoch": 0.9126347168080715,
2793
+ "grad_norm": 10.125,
2794
+ "learning_rate": 1.7518917679431324e-06,
2795
+ "loss": 1.168,
2796
+ "step": 3980
2797
+ },
2798
+ {
2799
+ "epoch": 0.9149277688603531,
2800
+ "grad_norm": 11.0,
2801
+ "learning_rate": 1.7060307268975008e-06,
2802
+ "loss": 1.1499,
2803
+ "step": 3990
2804
+ },
2805
+ {
2806
+ "epoch": 0.9172208209126347,
2807
+ "grad_norm": 15.0625,
2808
+ "learning_rate": 1.660169685851869e-06,
2809
+ "loss": 1.1486,
2810
+ "step": 4000
2811
+ },
2812
+ {
2813
+ "epoch": 0.9195138729649163,
2814
+ "grad_norm": 14.875,
2815
+ "learning_rate": 1.6143086448062373e-06,
2816
+ "loss": 1.1458,
2817
+ "step": 4010
2818
+ },
2819
+ {
2820
+ "epoch": 0.9218069250171979,
2821
+ "grad_norm": 10.25,
2822
+ "learning_rate": 1.5684476037606056e-06,
2823
+ "loss": 1.1349,
2824
+ "step": 4020
2825
+ },
2826
+ {
2827
+ "epoch": 0.9240999770694794,
2828
+ "grad_norm": 12.75,
2829
+ "learning_rate": 1.522586562714974e-06,
2830
+ "loss": 1.1826,
2831
+ "step": 4030
2832
+ },
2833
+ {
2834
+ "epoch": 0.926393029121761,
2835
+ "grad_norm": 10.0625,
2836
+ "learning_rate": 1.476725521669342e-06,
2837
+ "loss": 1.1549,
2838
+ "step": 4040
2839
+ },
2840
+ {
2841
+ "epoch": 0.9286860811740426,
2842
+ "grad_norm": 14.0,
2843
+ "learning_rate": 1.4308644806237102e-06,
2844
+ "loss": 1.1659,
2845
+ "step": 4050
2846
+ },
2847
+ {
2848
+ "epoch": 0.9309791332263242,
2849
+ "grad_norm": 13.6875,
2850
+ "learning_rate": 1.3850034395780783e-06,
2851
+ "loss": 1.1705,
2852
+ "step": 4060
2853
+ },
2854
+ {
2855
+ "epoch": 0.9332721852786058,
2856
+ "grad_norm": 9.0,
2857
+ "learning_rate": 1.3391423985324467e-06,
2858
+ "loss": 1.1297,
2859
+ "step": 4070
2860
+ },
2861
+ {
2862
+ "epoch": 0.9355652373308874,
2863
+ "grad_norm": 11.4375,
2864
+ "learning_rate": 1.293281357486815e-06,
2865
+ "loss": 1.1488,
2866
+ "step": 4080
2867
+ },
2868
+ {
2869
+ "epoch": 0.937858289383169,
2870
+ "grad_norm": 9.6875,
2871
+ "learning_rate": 1.2474203164411834e-06,
2872
+ "loss": 1.1374,
2873
+ "step": 4090
2874
+ },
2875
+ {
2876
+ "epoch": 0.9401513414354505,
2877
+ "grad_norm": 10.9375,
2878
+ "learning_rate": 1.2015592753955515e-06,
2879
+ "loss": 1.1393,
2880
+ "step": 4100
2881
+ },
2882
+ {
2883
+ "epoch": 0.9424443934877321,
2884
+ "grad_norm": 14.5,
2885
+ "learning_rate": 1.1556982343499199e-06,
2886
+ "loss": 1.1513,
2887
+ "step": 4110
2888
+ },
2889
+ {
2890
+ "epoch": 0.9447374455400137,
2891
+ "grad_norm": 8.9375,
2892
+ "learning_rate": 1.1098371933042882e-06,
2893
+ "loss": 1.139,
2894
+ "step": 4120
2895
+ },
2896
+ {
2897
+ "epoch": 0.9470304975922953,
2898
+ "grad_norm": 11.5625,
2899
+ "learning_rate": 1.0639761522586563e-06,
2900
+ "loss": 1.1548,
2901
+ "step": 4130
2902
+ },
2903
+ {
2904
+ "epoch": 0.9493235496445769,
2905
+ "grad_norm": 11.3125,
2906
+ "learning_rate": 1.0181151112130245e-06,
2907
+ "loss": 1.1737,
2908
+ "step": 4140
2909
+ },
2910
+ {
2911
+ "epoch": 0.9516166016968585,
2912
+ "grad_norm": 13.6875,
2913
+ "learning_rate": 9.722540701673928e-07,
2914
+ "loss": 1.1784,
2915
+ "step": 4150
2916
+ },
2917
+ {
2918
+ "epoch": 0.95390965374914,
2919
+ "grad_norm": 11.75,
2920
+ "learning_rate": 9.263930291217611e-07,
2921
+ "loss": 1.1478,
2922
+ "step": 4160
2923
+ },
2924
+ {
2925
+ "epoch": 0.9562027058014216,
2926
+ "grad_norm": 15.6875,
2927
+ "learning_rate": 8.805319880761294e-07,
2928
+ "loss": 1.1353,
2929
+ "step": 4170
2930
+ },
2931
+ {
2932
+ "epoch": 0.9584957578537033,
2933
+ "grad_norm": 12.625,
2934
+ "learning_rate": 8.346709470304977e-07,
2935
+ "loss": 1.145,
2936
+ "step": 4180
2937
+ },
2938
+ {
2939
+ "epoch": 0.9607888099059849,
2940
+ "grad_norm": 10.0625,
2941
+ "learning_rate": 7.88809905984866e-07,
2942
+ "loss": 1.1473,
2943
+ "step": 4190
2944
+ },
2945
+ {
2946
+ "epoch": 0.9630818619582665,
2947
+ "grad_norm": 13.375,
2948
+ "learning_rate": 7.429488649392341e-07,
2949
+ "loss": 1.1293,
2950
+ "step": 4200
2951
+ },
2952
+ {
2953
+ "epoch": 0.9653749140105481,
2954
+ "grad_norm": 10.0625,
2955
+ "learning_rate": 6.970878238936024e-07,
2956
+ "loss": 1.1409,
2957
+ "step": 4210
2958
+ },
2959
+ {
2960
+ "epoch": 0.9676679660628297,
2961
+ "grad_norm": 9.625,
2962
+ "learning_rate": 6.512267828479707e-07,
2963
+ "loss": 1.1391,
2964
+ "step": 4220
2965
+ },
2966
+ {
2967
+ "epoch": 0.9699610181151113,
2968
+ "grad_norm": 9.3125,
2969
+ "learning_rate": 6.05365741802339e-07,
2970
+ "loss": 1.1364,
2971
+ "step": 4230
2972
+ },
2973
+ {
2974
+ "epoch": 0.9722540701673928,
2975
+ "grad_norm": 11.25,
2976
+ "learning_rate": 5.595047007567072e-07,
2977
+ "loss": 1.1412,
2978
+ "step": 4240
2979
+ },
2980
+ {
2981
+ "epoch": 0.9745471222196744,
2982
+ "grad_norm": 12.4375,
2983
+ "learning_rate": 5.136436597110755e-07,
2984
+ "loss": 1.146,
2985
+ "step": 4250
2986
+ },
2987
+ {
2988
+ "epoch": 0.976840174271956,
2989
+ "grad_norm": 10.875,
2990
+ "learning_rate": 4.6778261866544374e-07,
2991
+ "loss": 1.1279,
2992
+ "step": 4260
2993
+ },
2994
+ {
2995
+ "epoch": 0.9791332263242376,
2996
+ "grad_norm": 16.375,
2997
+ "learning_rate": 4.21921577619812e-07,
2998
+ "loss": 1.1603,
2999
+ "step": 4270
3000
+ },
3001
+ {
3002
+ "epoch": 0.9814262783765192,
3003
+ "grad_norm": 11.0625,
3004
+ "learning_rate": 3.7606053657418027e-07,
3005
+ "loss": 1.1666,
3006
+ "step": 4280
3007
+ },
3008
+ {
3009
+ "epoch": 0.9837193304288008,
3010
+ "grad_norm": 9.375,
3011
+ "learning_rate": 3.3019949552854856e-07,
3012
+ "loss": 1.1609,
3013
+ "step": 4290
3014
+ },
3015
+ {
3016
+ "epoch": 0.9860123824810824,
3017
+ "grad_norm": 14.5625,
3018
+ "learning_rate": 2.843384544829168e-07,
3019
+ "loss": 1.1507,
3020
+ "step": 4300
3021
+ },
3022
+ {
3023
+ "epoch": 0.988305434533364,
3024
+ "grad_norm": 10.1875,
3025
+ "learning_rate": 2.3847741343728504e-07,
3026
+ "loss": 1.1535,
3027
+ "step": 4310
3028
+ },
3029
+ {
3030
+ "epoch": 0.9905984865856455,
3031
+ "grad_norm": 12.3125,
3032
+ "learning_rate": 1.926163723916533e-07,
3033
+ "loss": 1.1835,
3034
+ "step": 4320
3035
+ },
3036
+ {
3037
+ "epoch": 0.9928915386379271,
3038
+ "grad_norm": 9.75,
3039
+ "learning_rate": 1.4675533134602156e-07,
3040
+ "loss": 1.1578,
3041
+ "step": 4330
3042
+ },
3043
+ {
3044
+ "epoch": 0.9951845906902087,
3045
+ "grad_norm": 11.3125,
3046
+ "learning_rate": 1.0089429030038983e-07,
3047
+ "loss": 1.1447,
3048
+ "step": 4340
3049
+ },
3050
+ {
3051
+ "epoch": 0.9974776427424903,
3052
+ "grad_norm": 11.875,
3053
+ "learning_rate": 5.5033249254758087e-08,
3054
+ "loss": 1.1568,
3055
+ "step": 4350
3056
+ },
3057
+ {
3058
+ "epoch": 0.9997706947947719,
3059
+ "grad_norm": 11.375,
3060
+ "learning_rate": 9.172208209126348e-09,
3061
+ "loss": 1.15,
3062
+ "step": 4360
3063
+ }
3064
+ ],
3065
+ "logging_steps": 10,
3066
+ "max_steps": 4361,
3067
+ "num_input_tokens_seen": 0,
3068
+ "num_train_epochs": 1,
3069
+ "save_steps": 500,
3070
+ "stateful_callbacks": {
3071
+ "TrainerControl": {
3072
+ "args": {
3073
+ "should_epoch_stop": false,
3074
+ "should_evaluate": false,
3075
+ "should_log": false,
3076
+ "should_save": true,
3077
+ "should_training_stop": true
3078
+ },
3079
+ "attributes": {}
3080
+ }
3081
+ },
3082
+ "total_flos": 7.745762607278223e+17,
3083
+ "train_batch_size": 16,
3084
+ "trial_name": null,
3085
+ "trial_params": null
3086
+ }
checkpoint-4361/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:817afec82073fe07bc9956395f9bc90863ff9b9ead8fca93cc3b4cdde0c205cd
3
+ size 6417
checkpoint-4361/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json CHANGED
@@ -1,124 +1,58 @@
1
  {
2
  "architectures": [
3
- "Qwen2VLForConditionalGeneration"
4
  ],
5
  "attention_dropout": 0.0,
6
- "bos_token_id": 151643,
7
  "dtype": "bfloat16",
8
  "eos_token_id": 151645,
9
  "hidden_act": "silu",
10
  "hidden_size": 1536,
11
- "image_token_id": 151655,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 8960,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  "max_position_embeddings": 32768,
15
  "max_window_layers": 28,
16
- "model_type": "qwen2_vl",
17
  "num_attention_heads": 12,
18
  "num_hidden_layers": 28,
19
  "num_key_value_heads": 2,
 
20
  "rms_norm_eps": 1e-06,
21
- "rope_scaling": {
22
- "mrope_section": [
23
- 16,
24
- 24,
25
- 24
26
- ],
27
- "rope_type": "default",
28
- "type": "default"
29
- },
30
  "rope_theta": 1000000.0,
31
- "sliding_window": 32768,
32
- "text_config": {
33
- "_name_or_path": "/workspace/ISEF/pretrained/ISEF",
34
- "architectures": [
35
- "Qwen2VLForConditionalGeneration"
36
- ],
37
- "attention_dropout": 0.0,
38
- "dtype": "bfloat16",
39
- "eos_token_id": 151645,
40
- "hidden_act": "silu",
41
- "hidden_size": 1536,
42
- "initializer_range": 0.02,
43
- "intermediate_size": 8960,
44
- "layer_types": [
45
- "full_attention",
46
- "full_attention",
47
- "full_attention",
48
- "full_attention",
49
- "full_attention",
50
- "full_attention",
51
- "full_attention",
52
- "full_attention",
53
- "full_attention",
54
- "full_attention",
55
- "full_attention",
56
- "full_attention",
57
- "full_attention",
58
- "full_attention",
59
- "full_attention",
60
- "full_attention",
61
- "full_attention",
62
- "full_attention",
63
- "full_attention",
64
- "full_attention",
65
- "full_attention",
66
- "full_attention",
67
- "full_attention",
68
- "full_attention",
69
- "full_attention",
70
- "full_attention",
71
- "full_attention",
72
- "full_attention"
73
- ],
74
- "max_position_embeddings": 32768,
75
- "max_window_layers": 28,
76
- "model_type": "qwen2_vl_text",
77
- "num_attention_heads": 12,
78
- "num_hidden_layers": 28,
79
- "num_key_value_heads": 2,
80
- "pad_token_id": 151643,
81
- "rms_norm_eps": 1e-06,
82
- "rope_scaling": {
83
- "mrope_section": [
84
- 16,
85
- 24,
86
- 24
87
- ],
88
- "rope_type": "default",
89
- "type": "default"
90
- },
91
- "rope_theta": 1000000.0,
92
- "sliding_window": null,
93
- "tie_word_embeddings": true,
94
- "use_cache": true,
95
- "use_sliding_window": false,
96
- "vision_token_id": 151654,
97
- "vocab_size": 151936
98
- },
99
  "transformers_version": "4.57.1",
100
  "use_cache": true,
101
  "use_sliding_window": false,
102
- "video_token_id": 151656,
103
- "vision_config": {
104
- "depth": 32,
105
- "dtype": "bfloat16",
106
- "embed_dim": 1280,
107
- "hidden_act": "quick_gelu",
108
- "hidden_size": 1536,
109
- "in_channels": 3,
110
- "in_chans": 3,
111
- "initializer_range": 0.02,
112
- "mlp_ratio": 4,
113
- "model_type": "qwen2_vl",
114
- "num_heads": 16,
115
- "patch_size": 14,
116
- "spatial_merge_size": 2,
117
- "spatial_patch_size": 14,
118
- "temporal_patch_size": 2
119
- },
120
- "vision_end_token_id": 151653,
121
- "vision_start_token_id": 151652,
122
- "vision_token_id": 151654,
123
  "vocab_size": 151936
124
  }
 
1
  {
2
  "architectures": [
3
+ "Qwen2ForCausalLM"
4
  ],
5
  "attention_dropout": 0.0,
 
6
  "dtype": "bfloat16",
7
  "eos_token_id": 151645,
8
  "hidden_act": "silu",
9
  "hidden_size": 1536,
 
10
  "initializer_range": 0.02,
11
  "intermediate_size": 8960,
12
+ "layer_types": [
13
+ "full_attention",
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention"
41
+ ],
42
  "max_position_embeddings": 32768,
43
  "max_window_layers": 28,
44
+ "model_type": "qwen2",
45
  "num_attention_heads": 12,
46
  "num_hidden_layers": 28,
47
  "num_key_value_heads": 2,
48
+ "pad_token_id": 151643,
49
  "rms_norm_eps": 1e-06,
50
+ "rope_scaling": null,
 
 
 
 
 
 
 
 
51
  "rope_theta": 1000000.0,
52
+ "sliding_window": null,
53
+ "tie_word_embeddings": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54
  "transformers_version": "4.57.1",
55
  "use_cache": true,
56
  "use_sliding_window": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
  "vocab_size": 151936
58
  }
generation_config.json CHANGED
@@ -5,8 +5,9 @@
5
  151643
6
  ],
7
  "pad_token_id": 151643,
8
- "temperature": 0.01,
9
- "top_k": 1,
10
- "top_p": 0.001,
 
11
  "transformers_version": "4.57.1"
12
  }
 
5
  151643
6
  ],
7
  "pad_token_id": 151643,
8
+ "repetition_penalty": 1.1,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
  "transformers_version": "4.57.1"
13
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ce598f818635804aa7c052da86c0e395ebd74c5bebf915c940196b45491296b
3
- size 4884798456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e3618f4f91c295baa46d7219c92b45cef077fe01929ef16408d381aff9db13
3
+ size 3554214752
runs/Jan30_00-44-43_fe3b1825ceb0/events.out.tfevents.1769733888.fe3b1825ceb0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4b1ec0ce0a83f262948faa8753e67df0c61d01306857c9c34eabdcf0088e402
3
+ size 98581
runs/Jan30_01-30-07_fe3b1825ceb0/events.out.tfevents.1769736616.fe3b1825ceb0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba160d47c4bc479a59395e4fd94bf67533359d2e9e3df3ef95b01d4fb0346e19
3
+ size 6633
runs/Jan30_01-32-52_fe3b1825ceb0/events.out.tfevents.1769736781.fe3b1825ceb0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4f19c7446a31c2a847244d33c74be0c939c6fbeb80cc05de4da5817e12ef1f3
3
+ size 6633
special_tokens_map.json CHANGED
@@ -1,18 +1,7 @@
1
  {
2
  "additional_special_tokens": [
3
  "<|im_start|>",
4
- "<|im_end|>",
5
- "<|object_ref_start|>",
6
- "<|object_ref_end|>",
7
- "<|box_start|>",
8
- "<|box_end|>",
9
- "<|quad_start|>",
10
- "<|quad_end|>",
11
- "<|vision_start|>",
12
- "<|vision_end|>",
13
- "<|vision_pad|>",
14
- "<|image_pad|>",
15
- "<|video_pad|>"
16
  ],
17
  "eos_token": {
18
  "content": "<|im_end|>",
 
1
  {
2
  "additional_special_tokens": [
3
  "<|im_start|>",
4
+ "<|im_end|>"
 
 
 
 
 
 
 
 
 
 
 
5
  ],
6
  "eos_token": {
7
  "content": "<|im_end|>",
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
3
- size 11420371
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
3
+ size 11418266
tokenizer_config.json CHANGED
@@ -24,110 +24,11 @@
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
- },
28
- "151646": {
29
- "content": "<|object_ref_start|>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "151647": {
37
- "content": "<|object_ref_end|>",
38
- "lstrip": false,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "151648": {
45
- "content": "<|box_start|>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": true
51
- },
52
- "151649": {
53
- "content": "<|box_end|>",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": true
59
- },
60
- "151650": {
61
- "content": "<|quad_start|>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": true
67
- },
68
- "151651": {
69
- "content": "<|quad_end|>",
70
- "lstrip": false,
71
- "normalized": false,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": true
75
- },
76
- "151652": {
77
- "content": "<|vision_start|>",
78
- "lstrip": false,
79
- "normalized": false,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": true
83
- },
84
- "151653": {
85
- "content": "<|vision_end|>",
86
- "lstrip": false,
87
- "normalized": false,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": true
91
- },
92
- "151654": {
93
- "content": "<|vision_pad|>",
94
- "lstrip": false,
95
- "normalized": false,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": true
99
- },
100
- "151655": {
101
- "content": "<|image_pad|>",
102
- "lstrip": false,
103
- "normalized": false,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": true
107
- },
108
- "151656": {
109
- "content": "<|video_pad|>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": true
115
  }
116
  },
117
  "additional_special_tokens": [
118
  "<|im_start|>",
119
- "<|im_end|>",
120
- "<|object_ref_start|>",
121
- "<|object_ref_end|>",
122
- "<|box_start|>",
123
- "<|box_end|>",
124
- "<|quad_start|>",
125
- "<|quad_end|>",
126
- "<|vision_start|>",
127
- "<|vision_end|>",
128
- "<|vision_pad|>",
129
- "<|image_pad|>",
130
- "<|video_pad|>"
131
  ],
132
  "bos_token": null,
133
  "clean_up_tokenization_spaces": false,
@@ -136,8 +37,6 @@
136
  "extra_special_tokens": {},
137
  "model_max_length": 32768,
138
  "pad_token": "<|endoftext|>",
139
- "padding_side": "left",
140
- "processor_class": "Qwen2VLProcessor",
141
  "split_special_tokens": false,
142
  "tokenizer_class": "Qwen2Tokenizer",
143
  "unk_token": null
 
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  }
28
  },
29
  "additional_special_tokens": [
30
  "<|im_start|>",
31
+ "<|im_end|>"
 
 
 
 
 
 
 
 
 
 
 
32
  ],
33
  "bos_token": null,
34
  "clean_up_tokenization_spaces": false,
 
37
  "extra_special_tokens": {},
38
  "model_max_length": 32768,
39
  "pad_token": "<|endoftext|>",
 
 
40
  "split_special_tokens": false,
41
  "tokenizer_class": "Qwen2Tokenizer",
42
  "unk_token": null
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3ef80a3ffbe6e9f3bac13d27eb101a3b41e10fa91362399bd924060b19d769e
3
- size 6481
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43e7c687e8fa12eeb75e6349d5c91a13232ed7b04af854cc57461dedd16b7220
3
+ size 6417