Hugging Face's logo

Jesteban247
/
medgemma-brats-experiments

Visual Question Answering
Transformers
Safetensors
English
sft
medical-imaging
brats
textbrats
unsloth
Model card Files
xet
 Community
Jesteban247 commited on
Commit
4c842cd
·
verified ·
1 Parent(s): 600f2a5

Upload brats_medgemma_r1_alpha4_20251014_005739

Browse files
Files changed (43) hide show
  1. .gitattributes +3 -0
  2. brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/adapter_config.json +38 -0
  3. brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/adapter_model.safetensors +3 -0
  4. brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/added_tokens.json +3 -0
  5. brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/chat_template.jinja +47 -0
  6. brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/optimizer.pt +3 -0
  7. brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/rng_state.pth +3 -0
  8. brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/scheduler.pt +3 -0
  9. brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/special_tokens_map.json +33 -0
  10. brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/tokenizer.json +3 -0
  11. brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/tokenizer.model +3 -0
  12. brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/tokenizer_config.json +0 -0
  13. brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/trainer_state.json +1770 -0
  14. brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/training_args.bin +3 -0
  15. brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/adapter_config.json +38 -0
  16. brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/adapter_model.safetensors +3 -0
  17. brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/added_tokens.json +3 -0
  18. brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/chat_template.jinja +47 -0
  19. brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/preprocessor_config.json +29 -0
  20. brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/processor_config.json +4 -0
  21. brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/special_tokens_map.json +33 -0
  22. brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/tokenizer.json +3 -0
  23. brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/tokenizer.model +3 -0
  24. brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/tokenizer_config.json +0 -0
  25. brats_medgemma_r1_alpha4_20251014_005739/merged_model/added_tokens.json +3 -0
  26. brats_medgemma_r1_alpha4_20251014_005739/merged_model/chat_template.jinja +47 -0
  27. brats_medgemma_r1_alpha4_20251014_005739/merged_model/config.json +99 -0
  28. brats_medgemma_r1_alpha4_20251014_005739/merged_model/model-00001-of-00002.safetensors +3 -0
  29. brats_medgemma_r1_alpha4_20251014_005739/merged_model/model-00002-of-00002.safetensors +3 -0
  30. brats_medgemma_r1_alpha4_20251014_005739/merged_model/model.safetensors.index.json +891 -0
  31. brats_medgemma_r1_alpha4_20251014_005739/merged_model/preprocessor_config.json +29 -0
  32. brats_medgemma_r1_alpha4_20251014_005739/merged_model/processor_config.json +4 -0
  33. brats_medgemma_r1_alpha4_20251014_005739/merged_model/special_tokens_map.json +33 -0
  34. brats_medgemma_r1_alpha4_20251014_005739/merged_model/tokenizer.json +3 -0
  35. brats_medgemma_r1_alpha4_20251014_005739/merged_model/tokenizer.model +3 -0
  36. brats_medgemma_r1_alpha4_20251014_005739/merged_model/tokenizer_config.json +0 -0
  37. brats_medgemma_r1_alpha4_20251014_005739/metrics/complete_data_distribution_20251014_005739.json +29 -0
  38. brats_medgemma_r1_alpha4_20251014_005739/metrics/test_detailed_20251014_005739.csv +0 -0
  39. brats_medgemma_r1_alpha4_20251014_005739/metrics/test_summary_20251014_005739.csv +4 -0
  40. brats_medgemma_r1_alpha4_20251014_005739/metrics/training_log_20251014_005739.csv +249 -0
  41. brats_medgemma_r1_alpha4_20251014_005739/metrics/training_summary_20251014_005739.csv +16 -0
  42. brats_medgemma_r1_alpha4_20251014_005739/metrics/validation_during_training_20251014_005739.json +0 -0
  43. brats_medgemma_r1_alpha4_20251014_005739/metrics/validation_log_20251014_005739.csv +73 -0
.gitattributes CHANGED
@@ -39,3 +39,6 @@ brats_medgemma_r1_alpha2_20251013_235648/merged_model/tokenizer.json filter=lfs
39
  brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
  brats_medgemma_r1_alpha4_20251014_001744/merged_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
39
  brats_medgemma_r1_alpha4_20251014_001744/checkpoint-124/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  brats_medgemma_r1_alpha4_20251014_001744/lora_adapters/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
  brats_medgemma_r1_alpha4_20251014_001744/merged_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
+ brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
+ brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
+ brats_medgemma_r1_alpha4_20251014_005739/merged_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/adapter_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "Gemma3ForConditionalGeneration",
5
+ "parent_library": "transformers.models.gemma3.modeling_gemma3",
6
+ "unsloth_fixed": true
7
+ },
8
+ "base_model_name_or_path": "unsloth/medgemma-4b-it-unsloth-bnb-4bit",
9
+ "bias": "none",
10
+ "corda_config": null,
11
+ "eva_config": null,
12
+ "exclude_modules": null,
13
+ "fan_in_fan_out": false,
14
+ "inference_mode": true,
15
+ "init_lora_weights": true,
16
+ "layer_replication": null,
17
+ "layers_pattern": null,
18
+ "layers_to_transform": null,
19
+ "loftq_config": {},
20
+ "lora_alpha": 4,
21
+ "lora_bias": false,
22
+ "lora_dropout": 0,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "qalora_group_size": 16,
28
+ "r": 1,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj)))",
32
+ "target_parameters": null,
33
+ "task_type": "CAUSAL_LM",
34
+ "trainable_token_indices": null,
35
+ "use_dora": false,
36
+ "use_qalora": false,
37
+ "use_rslora": false
38
+ }
brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6359aab348cebf78ac407209e2bac026b7e1f8203db96b6bae017784e270dd
3
+ size 9746344
brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/chat_template.jinja ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{ bos_token }}
2
+ {%- if messages[0]['role'] == 'system' -%}
3
+ {%- if messages[0]['content'] is string -%}
4
+ {%- set first_user_prefix = messages[0]['content'] + '
5
+
6
+ ' -%}
7
+ {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
+
10
+ ' -%}
11
+ {%- endif -%}
12
+ {%- set loop_messages = messages[1:] -%}
13
+ {%- else -%}
14
+ {%- set first_user_prefix = "" -%}
15
+ {%- set loop_messages = messages -%}
16
+ {%- endif -%}
17
+ {%- for message in loop_messages -%}
18
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
+ {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
+ {%- endif -%}
21
+ {%- if (message['role'] == 'assistant') -%}
22
+ {%- set role = "model" -%}
23
+ {%- else -%}
24
+ {%- set role = message['role'] -%}
25
+ {%- endif -%}
26
+ {{ '<start_of_turn>' + role + '
27
+ ' + (first_user_prefix if loop.first else "") }}
28
+ {%- if message['content'] is string -%}
29
+ {{ message['content'] | trim }}
30
+ {%- elif message['content'] is iterable -%}
31
+ {%- for item in message['content'] -%}
32
+ {%- if item['type'] == 'image' -%}
33
+ {{ '<start_of_image>' }}
34
+ {%- elif item['type'] == 'text' -%}
35
+ {{ item['text'] | trim }}
36
+ {%- endif -%}
37
+ {%- endfor -%}
38
+ {%- else -%}
39
+ {{ raise_exception("Invalid content type") }}
40
+ {%- endif -%}
41
+ {{ '<end_of_turn>
42
+ ' }}
43
+ {%- endfor -%}
44
+ {%- if add_generation_prompt -%}
45
+ {{'<start_of_turn>model
46
+ '}}
47
+ {%- endif -%}
brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e31e168a3c90d97a2ec5102167dd8998b91b610dbb339332c508ea71cafb841b
3
+ size 19934531
brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad2f538eae82bd3876519f60f6f53bb659d8658f8ba002e349478242b4d74d33
3
+ size 14645
brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfc458a8aed21bb5249e7244720291574e9f88c26ed474990ce80b22219c63ab
3
+ size 1465
brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<end_of_turn>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7666402c0617d170e6b0a985b3130c3fb0795393aa0970600994a5d9aae12351
3
+ size 33384822
brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/trainer_state.json ADDED
@@ -0,0 +1,1770 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.9879518072289155,
6
+ "eval_steps": 500,
7
+ "global_step": 248,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.008032128514056224,
14
+ "grad_norm": 2.018695116043091,
15
+ "learning_rate": 0.0,
16
+ "loss": 3.661,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.01606425702811245,
21
+ "grad_norm": 1.2853336334228516,
22
+ "learning_rate": 2.5e-05,
23
+ "loss": 3.5315,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.024096385542168676,
28
+ "grad_norm": 1.1487480401992798,
29
+ "learning_rate": 5e-05,
30
+ "loss": 3.4594,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.0321285140562249,
35
+ "grad_norm": 1.2604966163635254,
36
+ "learning_rate": 7.500000000000001e-05,
37
+ "loss": 3.556,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.040160642570281124,
42
+ "grad_norm": 1.5687371492385864,
43
+ "learning_rate": 0.0001,
44
+ "loss": 3.6104,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.04819277108433735,
49
+ "grad_norm": 1.5858293771743774,
50
+ "learning_rate": 0.000125,
51
+ "loss": 3.4693,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.05622489959839357,
56
+ "grad_norm": 1.7028231620788574,
57
+ "learning_rate": 0.00015000000000000001,
58
+ "loss": 3.4765,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.0642570281124498,
63
+ "grad_norm": 1.5310205221176147,
64
+ "learning_rate": 0.000175,
65
+ "loss": 3.3037,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.07228915662650602,
70
+ "grad_norm": 1.637330174446106,
71
+ "learning_rate": 0.0002,
72
+ "loss": 3.1884,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.08032128514056225,
77
+ "grad_norm": 1.667618989944458,
78
+ "learning_rate": 0.00019999143275740072,
79
+ "loss": 2.9692,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.08835341365461848,
84
+ "grad_norm": 1.6878788471221924,
85
+ "learning_rate": 0.00019996573249755572,
86
+ "loss": 2.875,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.0963855421686747,
91
+ "grad_norm": 1.7119468450546265,
92
+ "learning_rate": 0.0001999229036240723,
93
+ "loss": 2.8523,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.10441767068273092,
98
+ "grad_norm": 1.833105444908142,
99
+ "learning_rate": 0.0001998629534754574,
100
+ "loss": 2.6203,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.11244979919678715,
105
+ "grad_norm": 1.8832757472991943,
106
+ "learning_rate": 0.00019978589232386035,
107
+ "loss": 2.4552,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.12048192771084337,
112
+ "grad_norm": 2.176262617111206,
113
+ "learning_rate": 0.0001996917333733128,
114
+ "loss": 2.4082,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.1285140562248996,
119
+ "grad_norm": 2.1362876892089844,
120
+ "learning_rate": 0.0001995804927574662,
121
+ "loss": 2.299,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.13654618473895583,
126
+ "grad_norm": 2.2712419033050537,
127
+ "learning_rate": 0.00019945218953682734,
128
+ "loss": 2.1446,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.14457831325301204,
133
+ "grad_norm": 2.2226736545562744,
134
+ "learning_rate": 0.00019930684569549264,
135
+ "loss": 2.1023,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.15261044176706828,
140
+ "grad_norm": 2.280789613723755,
141
+ "learning_rate": 0.00019914448613738106,
142
+ "loss": 1.9587,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.1606425702811245,
147
+ "grad_norm": 2.086296558380127,
148
+ "learning_rate": 0.00019896513868196704,
149
+ "loss": 1.8672,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.1686746987951807,
154
+ "grad_norm": 1.8972057104110718,
155
+ "learning_rate": 0.00019876883405951377,
156
+ "loss": 1.8181,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.17670682730923695,
161
+ "grad_norm": 1.9295737743377686,
162
+ "learning_rate": 0.00019855560590580778,
163
+ "loss": 1.6756,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.18473895582329317,
168
+ "grad_norm": 1.9768654108047485,
169
+ "learning_rate": 0.0001983254907563955,
170
+ "loss": 1.7146,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.1927710843373494,
175
+ "grad_norm": 1.827397346496582,
176
+ "learning_rate": 0.00019807852804032305,
177
+ "loss": 1.6412,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.20080321285140562,
182
+ "grad_norm": 1.851183295249939,
183
+ "learning_rate": 0.00019781476007338058,
184
+ "loss": 1.55,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.20883534136546184,
189
+ "grad_norm": 1.8950697183609009,
190
+ "learning_rate": 0.00019753423205085127,
191
+ "loss": 1.5418,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.21686746987951808,
196
+ "grad_norm": 1.73302161693573,
197
+ "learning_rate": 0.00019723699203976766,
198
+ "loss": 1.4619,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.2248995983935743,
203
+ "grad_norm": 1.8034886121749878,
204
+ "learning_rate": 0.00019692309097067546,
205
+ "loss": 1.3238,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.23293172690763053,
210
+ "grad_norm": 1.6534559726715088,
211
+ "learning_rate": 0.00019659258262890683,
212
+ "loss": 1.3148,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.24096385542168675,
217
+ "grad_norm": 1.7776868343353271,
218
+ "learning_rate": 0.00019624552364536473,
219
+ "loss": 1.4031,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.24899598393574296,
224
+ "grad_norm": 1.5708961486816406,
225
+ "learning_rate": 0.0001958819734868193,
226
+ "loss": 1.1983,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.2570281124497992,
231
+ "grad_norm": 1.7219339609146118,
232
+ "learning_rate": 0.0001955019944457187,
233
+ "loss": 1.3478,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.26506024096385544,
238
+ "grad_norm": 1.5297771692276,
239
+ "learning_rate": 0.00019510565162951537,
240
+ "loss": 1.2241,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.27309236947791166,
245
+ "grad_norm": 1.4228971004486084,
246
+ "learning_rate": 0.0001946930129495106,
247
+ "loss": 1.0815,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.28112449799196787,
252
+ "grad_norm": 1.463700532913208,
253
+ "learning_rate": 0.00019426414910921787,
254
+ "loss": 1.1098,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.2891566265060241,
259
+ "grad_norm": 1.330562949180603,
260
+ "learning_rate": 0.00019381913359224842,
261
+ "loss": 1.1323,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.2971887550200803,
266
+ "grad_norm": 1.2060474157333374,
267
+ "learning_rate": 0.00019335804264972018,
268
+ "loss": 1.0207,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.30522088353413657,
273
+ "grad_norm": 1.3600430488586426,
274
+ "learning_rate": 0.00019288095528719243,
275
+ "loss": 1.0521,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.3132530120481928,
280
+ "grad_norm": 1.299780249595642,
281
+ "learning_rate": 0.0001923879532511287,
282
+ "loss": 0.9586,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.321285140562249,
287
+ "grad_norm": 1.409625768661499,
288
+ "learning_rate": 0.00019187912101488984,
289
+ "loss": 1.0931,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.3293172690763052,
294
+ "grad_norm": 1.282618522644043,
295
+ "learning_rate": 0.0001913545457642601,
296
+ "loss": 0.9383,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.3373493975903614,
301
+ "grad_norm": 1.2694463729858398,
302
+ "learning_rate": 0.00019081431738250814,
303
+ "loss": 0.9767,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.3453815261044177,
308
+ "grad_norm": 1.300519585609436,
309
+ "learning_rate": 0.00019025852843498607,
310
+ "loss": 1.0032,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.3534136546184739,
315
+ "grad_norm": 1.294097900390625,
316
+ "learning_rate": 0.00018968727415326884,
317
+ "loss": 0.9885,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.3614457831325301,
322
+ "grad_norm": 1.391829490661621,
323
+ "learning_rate": 0.0001891006524188368,
324
+ "loss": 0.8711,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.36947791164658633,
329
+ "grad_norm": 1.2822232246398926,
330
+ "learning_rate": 0.0001884987637463042,
331
+ "loss": 0.9265,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.37751004016064255,
336
+ "grad_norm": 1.1994768381118774,
337
+ "learning_rate": 0.00018788171126619653,
338
+ "loss": 0.9051,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.3855421686746988,
343
+ "grad_norm": 1.231257677078247,
344
+ "learning_rate": 0.00018724960070727972,
345
+ "loss": 0.8886,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.39357429718875503,
350
+ "grad_norm": 1.331275463104248,
351
+ "learning_rate": 0.00018660254037844388,
352
+ "loss": 0.9103,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.40160642570281124,
357
+ "grad_norm": 1.316484808921814,
358
+ "learning_rate": 0.0001859406411501453,
359
+ "loss": 0.8927,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.40963855421686746,
364
+ "grad_norm": 1.2710226774215698,
365
+ "learning_rate": 0.00018526401643540922,
366
+ "loss": 0.9498,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.41767068273092367,
371
+ "grad_norm": 1.1253221035003662,
372
+ "learning_rate": 0.00018457278217039736,
373
+ "loss": 0.8568,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.42570281124497994,
378
+ "grad_norm": 1.1712892055511475,
379
+ "learning_rate": 0.00018386705679454242,
380
+ "loss": 0.7183,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.43373493975903615,
385
+ "grad_norm": 1.171975016593933,
386
+ "learning_rate": 0.00018314696123025454,
387
+ "loss": 0.8168,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.44176706827309237,
392
+ "grad_norm": 1.21014404296875,
393
+ "learning_rate": 0.00018241261886220154,
394
+ "loss": 0.7982,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.4497991967871486,
399
+ "grad_norm": 1.293569564819336,
400
+ "learning_rate": 0.00018166415551616792,
401
+ "loss": 0.7626,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.4578313253012048,
406
+ "grad_norm": 1.3370590209960938,
407
+ "learning_rate": 0.00018090169943749476,
408
+ "loss": 0.8259,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.46586345381526106,
413
+ "grad_norm": 1.2913239002227783,
414
+ "learning_rate": 0.00018012538126910608,
415
+ "loss": 0.7207,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.4738955823293173,
420
+ "grad_norm": 1.6398996114730835,
421
+ "learning_rate": 0.00017933533402912354,
422
+ "loss": 0.8388,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.4819277108433735,
427
+ "grad_norm": 1.437935709953308,
428
+ "learning_rate": 0.00017853169308807448,
429
+ "loss": 0.9095,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.4899598393574297,
434
+ "grad_norm": 1.4432635307312012,
435
+ "learning_rate": 0.0001777145961456971,
436
+ "loss": 0.7401,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.4979919678714859,
441
+ "grad_norm": 1.2439310550689697,
442
+ "learning_rate": 0.00017688418320734598,
443
+ "loss": 0.7771,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.5060240963855421,
448
+ "grad_norm": 1.1848706007003784,
449
+ "learning_rate": 0.0001760405965600031,
450
+ "loss": 0.7589,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.5140562248995983,
455
+ "grad_norm": 1.2418718338012695,
456
+ "learning_rate": 0.00017518398074789775,
457
+ "loss": 0.781,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.5220883534136547,
462
+ "grad_norm": 1.0402898788452148,
463
+ "learning_rate": 0.00017431448254773944,
464
+ "loss": 0.7316,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.5301204819277109,
469
+ "grad_norm": 1.018738865852356,
470
+ "learning_rate": 0.00017343225094356855,
471
+ "loss": 0.8006,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.5381526104417671,
476
+ "grad_norm": 1.123284935951233,
477
+ "learning_rate": 0.00017253743710122875,
478
+ "loss": 0.7835,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.5461847389558233,
483
+ "grad_norm": 1.1924985647201538,
484
+ "learning_rate": 0.00017163019434246547,
485
+ "loss": 0.775,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.5542168674698795,
490
+ "grad_norm": 1.794427514076233,
491
+ "learning_rate": 0.00017071067811865476,
492
+ "loss": 0.7513,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.5622489959839357,
497
+ "grad_norm": 1.2267704010009766,
498
+ "learning_rate": 0.00016977904598416803,
499
+ "loss": 0.7753,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.570281124497992,
504
+ "grad_norm": 1.0528597831726074,
505
+ "learning_rate": 0.0001688354575693754,
506
+ "loss": 0.7086,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.5783132530120482,
511
+ "grad_norm": 1.2666501998901367,
512
+ "learning_rate": 0.0001678800745532942,
513
+ "loss": 0.7406,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.5863453815261044,
518
+ "grad_norm": 1.120115041732788,
519
+ "learning_rate": 0.00016691306063588583,
520
+ "loss": 0.6829,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.5943775100401606,
525
+ "grad_norm": 1.2907639741897583,
526
+ "learning_rate": 0.00016593458151000688,
527
+ "loss": 0.8391,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.6024096385542169,
532
+ "grad_norm": 1.1098196506500244,
533
+ "learning_rate": 0.00016494480483301836,
534
+ "loss": 0.6648,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.6104417670682731,
539
+ "grad_norm": 1.2485947608947754,
540
+ "learning_rate": 0.00016394390019805848,
541
+ "loss": 0.7994,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.6184738955823293,
546
+ "grad_norm": 1.0588477849960327,
547
+ "learning_rate": 0.00016293203910498376,
548
+ "loss": 0.6691,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.6265060240963856,
553
+ "grad_norm": 1.0988563299179077,
554
+ "learning_rate": 0.00016190939493098344,
555
+ "loss": 0.697,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.6345381526104418,
560
+ "grad_norm": 1.2326934337615967,
561
+ "learning_rate": 0.00016087614290087208,
562
+ "loss": 0.6998,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.642570281124498,
567
+ "grad_norm": 0.989920973777771,
568
+ "learning_rate": 0.00015983246005706593,
569
+ "loss": 0.7233,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.6506024096385542,
574
+ "grad_norm": 1.0116662979125977,
575
+ "learning_rate": 0.00015877852522924732,
576
+ "loss": 0.6928,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.6586345381526104,
581
+ "grad_norm": 1.0488063097000122,
582
+ "learning_rate": 0.0001577145190037234,
583
+ "loss": 0.7096,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.6666666666666666,
588
+ "grad_norm": 1.0680497884750366,
589
+ "learning_rate": 0.00015664062369248328,
590
+ "loss": 0.6753,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.6746987951807228,
595
+ "grad_norm": 0.9523035883903503,
596
+ "learning_rate": 0.00015555702330196023,
597
+ "loss": 0.6504,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.6827309236947792,
602
+ "grad_norm": 1.1361489295959473,
603
+ "learning_rate": 0.00015446390350150273,
604
+ "loss": 0.7045,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.6907630522088354,
609
+ "grad_norm": 0.9762657880783081,
610
+ "learning_rate": 0.00015336145159156115,
611
+ "loss": 0.6885,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.6987951807228916,
616
+ "grad_norm": 0.9241124987602234,
617
+ "learning_rate": 0.0001522498564715949,
618
+ "loss": 0.6672,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.7068273092369478,
623
+ "grad_norm": 0.9767544269561768,
624
+ "learning_rate": 0.0001511293086077052,
625
+ "loss": 0.5741,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.714859437751004,
630
+ "grad_norm": 1.166563630104065,
631
+ "learning_rate": 0.00015000000000000001,
632
+ "loss": 0.7421,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.7228915662650602,
637
+ "grad_norm": 0.9954823851585388,
638
+ "learning_rate": 0.00014886212414969553,
639
+ "loss": 0.6945,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.7309236947791165,
644
+ "grad_norm": 1.0900086164474487,
645
+ "learning_rate": 0.00014771587602596084,
646
+ "loss": 0.7411,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.7389558232931727,
651
+ "grad_norm": 0.9967132806777954,
652
+ "learning_rate": 0.00014656145203251114,
653
+ "loss": 0.6663,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.7469879518072289,
658
+ "grad_norm": 1.0430046319961548,
659
+ "learning_rate": 0.00014539904997395468,
660
+ "loss": 0.7088,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.7550200803212851,
665
+ "grad_norm": 1.089854121208191,
666
+ "learning_rate": 0.00014422886902190014,
667
+ "loss": 0.6933,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.7630522088353414,
672
+ "grad_norm": 0.8202502727508545,
673
+ "learning_rate": 0.00014305110968082952,
674
+ "loss": 0.6218,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.7710843373493976,
679
+ "grad_norm": 1.0293831825256348,
680
+ "learning_rate": 0.0001418659737537428,
681
+ "loss": 0.7925,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.7791164658634538,
686
+ "grad_norm": 0.9108630418777466,
687
+ "learning_rate": 0.00014067366430758004,
688
+ "loss": 0.6589,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.7871485943775101,
693
+ "grad_norm": 0.9136717915534973,
694
+ "learning_rate": 0.0001394743856384267,
695
+ "loss": 0.6765,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.7951807228915663,
700
+ "grad_norm": 0.9278481602668762,
701
+ "learning_rate": 0.000138268343236509,
702
+ "loss": 0.6468,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.8032128514056225,
707
+ "grad_norm": 0.9486384391784668,
708
+ "learning_rate": 0.00013705574375098365,
709
+ "loss": 0.7486,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.8112449799196787,
714
+ "grad_norm": 0.9050431847572327,
715
+ "learning_rate": 0.00013583679495453,
716
+ "loss": 0.6754,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.8192771084337349,
721
+ "grad_norm": 0.854407548904419,
722
+ "learning_rate": 0.0001346117057077493,
723
+ "loss": 0.6398,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.8273092369477911,
728
+ "grad_norm": 1.0327568054199219,
729
+ "learning_rate": 0.0001333806859233771,
730
+ "loss": 0.6982,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.8353413654618473,
735
+ "grad_norm": 1.2989087104797363,
736
+ "learning_rate": 0.00013214394653031616,
737
+ "loss": 0.7693,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.8433734939759037,
742
+ "grad_norm": 1.0676828622817993,
743
+ "learning_rate": 0.00013090169943749476,
744
+ "loss": 0.7064,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.8514056224899599,
749
+ "grad_norm": 0.9510466456413269,
750
+ "learning_rate": 0.00012965415749755709,
751
+ "loss": 0.7317,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.8594377510040161,
756
+ "grad_norm": 1.0593117475509644,
757
+ "learning_rate": 0.00012840153447039228,
758
+ "loss": 0.668,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.8674698795180723,
763
+ "grad_norm": 0.9986748695373535,
764
+ "learning_rate": 0.00012714404498650743,
765
+ "loss": 0.7272,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.8755020080321285,
770
+ "grad_norm": 0.9522738456726074,
771
+ "learning_rate": 0.00012588190451025207,
772
+ "loss": 0.7019,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.8835341365461847,
777
+ "grad_norm": 0.9643475413322449,
778
+ "learning_rate": 0.00012461532930289933,
779
+ "loss": 0.653,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.891566265060241,
784
+ "grad_norm": 0.9260073900222778,
785
+ "learning_rate": 0.00012334453638559057,
786
+ "loss": 0.6124,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.8995983935742972,
791
+ "grad_norm": 1.0311334133148193,
792
+ "learning_rate": 0.00012206974350215015,
793
+ "loss": 0.6811,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.9076305220883534,
798
+ "grad_norm": 0.9403883814811707,
799
+ "learning_rate": 0.00012079116908177593,
800
+ "loss": 0.7084,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.9156626506024096,
805
+ "grad_norm": 1.0048012733459473,
806
+ "learning_rate": 0.00011950903220161285,
807
+ "loss": 0.7027,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.9236947791164659,
812
+ "grad_norm": 1.0549793243408203,
813
+ "learning_rate": 0.00011822355254921478,
814
+ "loss": 0.7271,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.9317269076305221,
819
+ "grad_norm": 0.887923538684845,
820
+ "learning_rate": 0.00011693495038490245,
821
+ "loss": 0.6574,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.9397590361445783,
826
+ "grad_norm": 0.9580830931663513,
827
+ "learning_rate": 0.0001156434465040231,
828
+ "loss": 0.7258,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.9477911646586346,
833
+ "grad_norm": 0.9398922324180603,
834
+ "learning_rate": 0.00011434926219911793,
835
+ "loss": 0.7006,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.9558232931726908,
840
+ "grad_norm": 0.9026420712471008,
841
+ "learning_rate": 0.00011305261922200519,
842
+ "loss": 0.6843,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.963855421686747,
847
+ "grad_norm": 0.9120410680770874,
848
+ "learning_rate": 0.00011175373974578378,
849
+ "loss": 0.6529,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.9718875502008032,
854
+ "grad_norm": 1.095755934715271,
855
+ "learning_rate": 0.00011045284632676536,
856
+ "loss": 0.7751,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.9799196787148594,
861
+ "grad_norm": 1.0136650800704956,
862
+ "learning_rate": 0.00010915016186634026,
863
+ "loss": 0.679,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.9879518072289156,
868
+ "grad_norm": 0.928086519241333,
869
+ "learning_rate": 0.0001078459095727845,
870
+ "loss": 0.7968,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.9959839357429718,
875
+ "grad_norm": 0.926094651222229,
876
+ "learning_rate": 0.00010654031292301432,
877
+ "loss": 0.6623,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 1.0,
882
+ "grad_norm": 1.2206974029541016,
883
+ "learning_rate": 0.0001052335956242944,
884
+ "loss": 0.615,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 1.0080321285140563,
889
+ "grad_norm": 0.93853759765625,
890
+ "learning_rate": 0.00010392598157590688,
891
+ "loss": 0.7172,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 1.0160642570281124,
896
+ "grad_norm": 0.8901218771934509,
897
+ "learning_rate": 0.00010261769483078733,
898
+ "loss": 0.6951,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 1.0240963855421688,
903
+ "grad_norm": 0.9513447880744934,
904
+ "learning_rate": 0.00010130895955713445,
905
+ "loss": 0.6357,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 1.0321285140562249,
910
+ "grad_norm": 0.8817431330680847,
911
+ "learning_rate": 0.0001,
912
+ "loss": 0.6436,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 1.0401606425702812,
917
+ "grad_norm": 0.869871973991394,
918
+ "learning_rate": 9.869104044286558e-05,
919
+ "loss": 0.6051,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 1.0481927710843373,
924
+ "grad_norm": 0.9639691114425659,
925
+ "learning_rate": 9.73823051692127e-05,
926
+ "loss": 0.6532,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 1.0562248995983936,
931
+ "grad_norm": 0.9207035899162292,
932
+ "learning_rate": 9.607401842409317e-05,
933
+ "loss": 0.6487,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 1.0642570281124497,
938
+ "grad_norm": 0.9587928056716919,
939
+ "learning_rate": 9.476640437570562e-05,
940
+ "loss": 0.6692,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 1.072289156626506,
945
+ "grad_norm": 1.0698909759521484,
946
+ "learning_rate": 9.345968707698569e-05,
947
+ "loss": 0.7164,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 1.0803212851405624,
952
+ "grad_norm": 1.0149202346801758,
953
+ "learning_rate": 9.215409042721552e-05,
954
+ "loss": 0.6689,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 1.0883534136546185,
959
+ "grad_norm": 0.9482234716415405,
960
+ "learning_rate": 9.084983813365978e-05,
961
+ "loss": 0.6387,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 1.0963855421686748,
966
+ "grad_norm": 0.9719244241714478,
967
+ "learning_rate": 8.954715367323468e-05,
968
+ "loss": 0.6457,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 1.104417670682731,
973
+ "grad_norm": 0.9527074098587036,
974
+ "learning_rate": 8.824626025421626e-05,
975
+ "loss": 0.6226,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 1.1124497991967872,
980
+ "grad_norm": 1.0298618078231812,
981
+ "learning_rate": 8.694738077799488e-05,
982
+ "loss": 0.6623,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 1.1204819277108433,
987
+ "grad_norm": 0.927056074142456,
988
+ "learning_rate": 8.565073780088208e-05,
989
+ "loss": 0.6594,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 1.1285140562248996,
994
+ "grad_norm": 0.9237600564956665,
995
+ "learning_rate": 8.435655349597689e-05,
996
+ "loss": 0.6078,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 1.1365461847389557,
1001
+ "grad_norm": 1.0177422761917114,
1002
+ "learning_rate": 8.306504961509754e-05,
1003
+ "loss": 0.6283,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 1.144578313253012,
1008
+ "grad_norm": 0.910376250743866,
1009
+ "learning_rate": 8.177644745078526e-05,
1010
+ "loss": 0.6229,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 1.1526104417670684,
1015
+ "grad_norm": 1.0474944114685059,
1016
+ "learning_rate": 8.049096779838719e-05,
1017
+ "loss": 0.587,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 1.1606425702811245,
1022
+ "grad_norm": 1.0246328115463257,
1023
+ "learning_rate": 7.920883091822408e-05,
1024
+ "loss": 0.6263,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 1.1686746987951806,
1029
+ "grad_norm": 1.027639627456665,
1030
+ "learning_rate": 7.79302564978499e-05,
1031
+ "loss": 0.6249,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 1.176706827309237,
1036
+ "grad_norm": 1.046695590019226,
1037
+ "learning_rate": 7.66554636144095e-05,
1038
+ "loss": 0.6639,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 1.1847389558232932,
1043
+ "grad_norm": 1.0776958465576172,
1044
+ "learning_rate": 7.53846706971007e-05,
1045
+ "loss": 0.6016,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 1.1927710843373494,
1050
+ "grad_norm": 0.900340735912323,
1051
+ "learning_rate": 7.411809548974792e-05,
1052
+ "loss": 0.5556,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 1.2008032128514057,
1057
+ "grad_norm": 0.9593937993049622,
1058
+ "learning_rate": 7.285595501349258e-05,
1059
+ "loss": 0.6574,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 1.2088353413654618,
1064
+ "grad_norm": 1.1022858619689941,
1065
+ "learning_rate": 7.159846552960774e-05,
1066
+ "loss": 0.7477,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 1.216867469879518,
1071
+ "grad_norm": 1.0036520957946777,
1072
+ "learning_rate": 7.034584250244291e-05,
1073
+ "loss": 0.611,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 1.2248995983935742,
1078
+ "grad_norm": 1.02372407913208,
1079
+ "learning_rate": 6.909830056250527e-05,
1080
+ "loss": 0.6819,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 1.2329317269076305,
1085
+ "grad_norm": 0.9779181480407715,
1086
+ "learning_rate": 6.785605346968386e-05,
1087
+ "loss": 0.599,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 1.2409638554216866,
1092
+ "grad_norm": 0.9718801975250244,
1093
+ "learning_rate": 6.661931407662292e-05,
1094
+ "loss": 0.6447,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 1.248995983935743,
1099
+ "grad_norm": 1.0557126998901367,
1100
+ "learning_rate": 6.538829429225069e-05,
1101
+ "loss": 0.7225,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 1.2570281124497993,
1106
+ "grad_norm": 1.0305792093276978,
1107
+ "learning_rate": 6.416320504546997e-05,
1108
+ "loss": 0.6028,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 1.2650602409638554,
1113
+ "grad_norm": 0.9871490597724915,
1114
+ "learning_rate": 6.294425624901638e-05,
1115
+ "loss": 0.5735,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 1.2730923694779117,
1120
+ "grad_norm": 0.9500276446342468,
1121
+ "learning_rate": 6.173165676349103e-05,
1122
+ "loss": 0.5559,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 1.2811244979919678,
1127
+ "grad_norm": 0.9343807697296143,
1128
+ "learning_rate": 6.052561436157329e-05,
1129
+ "loss": 0.5738,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 1.2891566265060241,
1134
+ "grad_norm": 0.9733037948608398,
1135
+ "learning_rate": 5.9326335692419995e-05,
1136
+ "loss": 0.6435,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 1.2971887550200802,
1141
+ "grad_norm": 1.02507746219635,
1142
+ "learning_rate": 5.8134026246257225e-05,
1143
+ "loss": 0.591,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 1.3052208835341366,
1148
+ "grad_norm": 1.0366383790969849,
1149
+ "learning_rate": 5.694889031917047e-05,
1150
+ "loss": 0.6713,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 1.3132530120481927,
1155
+ "grad_norm": 1.018324613571167,
1156
+ "learning_rate": 5.577113097809989e-05,
1157
+ "loss": 0.5624,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 1.321285140562249,
1162
+ "grad_norm": 1.0992127656936646,
1163
+ "learning_rate": 5.4600950026045326e-05,
1164
+ "loss": 0.6605,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 1.3293172690763053,
1169
+ "grad_norm": 1.0975652933120728,
1170
+ "learning_rate": 5.343854796748886e-05,
1171
+ "loss": 0.6625,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 1.3373493975903614,
1176
+ "grad_norm": 0.9974353909492493,
1177
+ "learning_rate": 5.2284123974039154e-05,
1178
+ "loss": 0.588,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 1.3453815261044177,
1183
+ "grad_norm": 0.9780750870704651,
1184
+ "learning_rate": 5.113787585030454e-05,
1185
+ "loss": 0.5993,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 1.3534136546184738,
1190
+ "grad_norm": 1.0631235837936401,
1191
+ "learning_rate": 5.000000000000002e-05,
1192
+ "loss": 0.6468,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 1.3614457831325302,
1197
+ "grad_norm": 1.0321671962738037,
1198
+ "learning_rate": 4.887069139229481e-05,
1199
+ "loss": 0.6445,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 1.3694779116465863,
1204
+ "grad_norm": 1.0585201978683472,
1205
+ "learning_rate": 4.7750143528405126e-05,
1206
+ "loss": 0.6748,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 1.3775100401606426,
1211
+ "grad_norm": 0.9845882654190063,
1212
+ "learning_rate": 4.6638548408438856e-05,
1213
+ "loss": 0.6114,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 1.3855421686746987,
1218
+ "grad_norm": 0.9892096519470215,
1219
+ "learning_rate": 4.5536096498497295e-05,
1220
+ "loss": 0.6282,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 1.393574297188755,
1225
+ "grad_norm": 1.0388250350952148,
1226
+ "learning_rate": 4.444297669803981e-05,
1227
+ "loss": 0.6422,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 1.4016064257028114,
1232
+ "grad_norm": 1.000816822052002,
1233
+ "learning_rate": 4.335937630751674e-05,
1234
+ "loss": 0.6536,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 1.4096385542168675,
1239
+ "grad_norm": 1.0262826681137085,
1240
+ "learning_rate": 4.228548099627665e-05,
1241
+ "loss": 0.5983,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 1.4176706827309236,
1246
+ "grad_norm": 0.9772481918334961,
1247
+ "learning_rate": 4.12214747707527e-05,
1248
+ "loss": 0.5689,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 1.4257028112449799,
1253
+ "grad_norm": 1.025686502456665,
1254
+ "learning_rate": 4.01675399429341e-05,
1255
+ "loss": 0.5811,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 1.4337349397590362,
1260
+ "grad_norm": 1.0345141887664795,
1261
+ "learning_rate": 3.9123857099127936e-05,
1262
+ "loss": 0.6013,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 1.4417670682730923,
1267
+ "grad_norm": 1.111274242401123,
1268
+ "learning_rate": 3.8090605069016595e-05,
1269
+ "loss": 0.6435,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 1.4497991967871486,
1274
+ "grad_norm": 1.151214361190796,
1275
+ "learning_rate": 3.7067960895016275e-05,
1276
+ "loss": 0.7286,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 1.4578313253012047,
1281
+ "grad_norm": 1.1735557317733765,
1282
+ "learning_rate": 3.6056099801941534e-05,
1283
+ "loss": 0.6192,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 1.465863453815261,
1288
+ "grad_norm": 1.049812912940979,
1289
+ "learning_rate": 3.5055195166981645e-05,
1290
+ "loss": 0.6364,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 1.4738955823293174,
1295
+ "grad_norm": 1.0111303329467773,
1296
+ "learning_rate": 3.406541848999312e-05,
1297
+ "loss": 0.6445,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 1.4819277108433735,
1302
+ "grad_norm": 0.9973188042640686,
1303
+ "learning_rate": 3.308693936411421e-05,
1304
+ "loss": 0.6267,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 1.4899598393574296,
1309
+ "grad_norm": 1.01885187625885,
1310
+ "learning_rate": 3.211992544670582e-05,
1311
+ "loss": 0.7316,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 1.497991967871486,
1316
+ "grad_norm": 1.1159658432006836,
1317
+ "learning_rate": 3.116454243062459e-05,
1318
+ "loss": 0.7153,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 1.5060240963855422,
1323
+ "grad_norm": 1.1160449981689453,
1324
+ "learning_rate": 3.0220954015832003e-05,
1325
+ "loss": 0.6544,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 1.5140562248995983,
1330
+ "grad_norm": 1.0619198083877563,
1331
+ "learning_rate": 2.9289321881345254e-05,
1332
+ "loss": 0.565,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 1.5220883534136547,
1337
+ "grad_norm": 1.0562235116958618,
1338
+ "learning_rate": 2.8369805657534575e-05,
1339
+ "loss": 0.6388,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 1.5301204819277108,
1344
+ "grad_norm": 1.0207993984222412,
1345
+ "learning_rate": 2.746256289877126e-05,
1346
+ "loss": 0.6225,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 1.538152610441767,
1351
+ "grad_norm": 1.0186342000961304,
1352
+ "learning_rate": 2.6567749056431467e-05,
1353
+ "loss": 0.6349,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 1.5461847389558234,
1358
+ "grad_norm": 1.1594632863998413,
1359
+ "learning_rate": 2.5685517452260567e-05,
1360
+ "loss": 0.5717,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 1.5542168674698795,
1365
+ "grad_norm": 1.030584454536438,
1366
+ "learning_rate": 2.4816019252102273e-05,
1367
+ "loss": 0.6339,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 1.5622489959839356,
1372
+ "grad_norm": 1.1938083171844482,
1373
+ "learning_rate": 2.3959403439996907e-05,
1374
+ "loss": 0.6509,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 1.570281124497992,
1379
+ "grad_norm": 0.935763955116272,
1380
+ "learning_rate": 2.3115816792654056e-05,
1381
+ "loss": 0.6088,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 1.5783132530120483,
1386
+ "grad_norm": 1.009050965309143,
1387
+ "learning_rate": 2.2285403854302912e-05,
1388
+ "loss": 0.5793,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 1.5863453815261044,
1393
+ "grad_norm": 1.0741722583770752,
1394
+ "learning_rate": 2.146830691192553e-05,
1395
+ "loss": 0.6567,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 1.5943775100401605,
1400
+ "grad_norm": 0.9663232564926147,
1401
+ "learning_rate": 2.0664665970876496e-05,
1402
+ "loss": 0.6097,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 1.6024096385542168,
1407
+ "grad_norm": 0.9675998091697693,
1408
+ "learning_rate": 1.9874618730893946e-05,
1409
+ "loss": 0.6194,
1410
+ "step": 200
1411
+ },
1412
+ {
1413
+ "epoch": 1.6104417670682731,
1414
+ "grad_norm": 1.0715385675430298,
1415
+ "learning_rate": 1.9098300562505266e-05,
1416
+ "loss": 0.7099,
1417
+ "step": 201
1418
+ },
1419
+ {
1420
+ "epoch": 1.6184738955823295,
1421
+ "grad_norm": 0.9676709175109863,
1422
+ "learning_rate": 1.833584448383211e-05,
1423
+ "loss": 0.6384,
1424
+ "step": 202
1425
+ },
1426
+ {
1427
+ "epoch": 1.6265060240963856,
1428
+ "grad_norm": 1.0132137537002563,
1429
+ "learning_rate": 1.7587381137798432e-05,
1430
+ "loss": 0.5714,
1431
+ "step": 203
1432
+ },
1433
+ {
1434
+ "epoch": 1.6345381526104417,
1435
+ "grad_norm": 1.016739845275879,
1436
+ "learning_rate": 1.6853038769745467e-05,
1437
+ "loss": 0.5884,
1438
+ "step": 204
1439
+ },
1440
+ {
1441
+ "epoch": 1.642570281124498,
1442
+ "grad_norm": 1.0687060356140137,
1443
+ "learning_rate": 1.6132943205457606e-05,
1444
+ "loss": 0.6543,
1445
+ "step": 205
1446
+ },
1447
+ {
1448
+ "epoch": 1.6506024096385543,
1449
+ "grad_norm": 1.0614928007125854,
1450
+ "learning_rate": 1.542721782960268e-05,
1451
+ "loss": 0.6319,
1452
+ "step": 206
1453
+ },
1454
+ {
1455
+ "epoch": 1.6586345381526104,
1456
+ "grad_norm": 1.0821624994277954,
1457
+ "learning_rate": 1.4735983564590783e-05,
1458
+ "loss": 0.592,
1459
+ "step": 207
1460
+ },
1461
+ {
1462
+ "epoch": 1.6666666666666665,
1463
+ "grad_norm": 1.0043268203735352,
1464
+ "learning_rate": 1.405935884985473e-05,
1465
+ "loss": 0.5886,
1466
+ "step": 208
1467
+ },
1468
+ {
1469
+ "epoch": 1.6746987951807228,
1470
+ "grad_norm": 1.1566835641860962,
1471
+ "learning_rate": 1.339745962155613e-05,
1472
+ "loss": 0.7061,
1473
+ "step": 209
1474
+ },
1475
+ {
1476
+ "epoch": 1.6827309236947792,
1477
+ "grad_norm": 1.04037344455719,
1478
+ "learning_rate": 1.2750399292720283e-05,
1479
+ "loss": 0.6133,
1480
+ "step": 210
1481
+ },
1482
+ {
1483
+ "epoch": 1.6907630522088355,
1484
+ "grad_norm": 1.0147126913070679,
1485
+ "learning_rate": 1.2118288733803473e-05,
1486
+ "loss": 0.6338,
1487
+ "step": 211
1488
+ },
1489
+ {
1490
+ "epoch": 1.6987951807228916,
1491
+ "grad_norm": 1.0179274082183838,
1492
+ "learning_rate": 1.1501236253695823e-05,
1493
+ "loss": 0.6642,
1494
+ "step": 212
1495
+ },
1496
+ {
1497
+ "epoch": 1.7068273092369477,
1498
+ "grad_norm": 1.1099425554275513,
1499
+ "learning_rate": 1.0899347581163221e-05,
1500
+ "loss": 0.6223,
1501
+ "step": 213
1502
+ },
1503
+ {
1504
+ "epoch": 1.714859437751004,
1505
+ "grad_norm": 0.9550982713699341,
1506
+ "learning_rate": 1.0312725846731175e-05,
1507
+ "loss": 0.6445,
1508
+ "step": 214
1509
+ },
1510
+ {
1511
+ "epoch": 1.7228915662650603,
1512
+ "grad_norm": 1.0273432731628418,
1513
+ "learning_rate": 9.74147156501396e-06,
1514
+ "loss": 0.5875,
1515
+ "step": 215
1516
+ },
1517
+ {
1518
+ "epoch": 1.7309236947791165,
1519
+ "grad_norm": 1.0903980731964111,
1520
+ "learning_rate": 9.185682617491863e-06,
1521
+ "loss": 0.6402,
1522
+ "step": 216
1523
+ },
1524
+ {
1525
+ "epoch": 1.7389558232931726,
1526
+ "grad_norm": 1.0869786739349365,
1527
+ "learning_rate": 8.645454235739903e-06,
1528
+ "loss": 0.69,
1529
+ "step": 217
1530
+ },
1531
+ {
1532
+ "epoch": 1.7469879518072289,
1533
+ "grad_norm": 1.012239933013916,
1534
+ "learning_rate": 8.12087898511018e-06,
1535
+ "loss": 0.5995,
1536
+ "step": 218
1537
+ },
1538
+ {
1539
+ "epoch": 1.7550200803212852,
1540
+ "grad_norm": 1.0018348693847656,
1541
+ "learning_rate": 7.612046748871327e-06,
1542
+ "loss": 0.639,
1543
+ "step": 219
1544
+ },
1545
+ {
1546
+ "epoch": 1.7630522088353415,
1547
+ "grad_norm": 1.0906120538711548,
1548
+ "learning_rate": 7.119044712807577e-06,
1549
+ "loss": 0.6471,
1550
+ "step": 220
1551
+ },
1552
+ {
1553
+ "epoch": 1.7710843373493976,
1554
+ "grad_norm": 1.064482569694519,
1555
+ "learning_rate": 6.6419573502798374e-06,
1556
+ "loss": 0.6236,
1557
+ "step": 221
1558
+ },
1559
+ {
1560
+ "epoch": 1.7791164658634537,
1561
+ "grad_norm": 1.0269008874893188,
1562
+ "learning_rate": 6.180866407751595e-06,
1563
+ "loss": 0.541,
1564
+ "step": 222
1565
+ },
1566
+ {
1567
+ "epoch": 1.78714859437751,
1568
+ "grad_norm": 1.0960509777069092,
1569
+ "learning_rate": 5.735850890782157e-06,
1570
+ "loss": 0.6389,
1571
+ "step": 223
1572
+ },
1573
+ {
1574
+ "epoch": 1.7951807228915664,
1575
+ "grad_norm": 1.213438630104065,
1576
+ "learning_rate": 5.306987050489442e-06,
1577
+ "loss": 0.629,
1578
+ "step": 224
1579
+ },
1580
+ {
1581
+ "epoch": 1.8032128514056225,
1582
+ "grad_norm": 0.9688934683799744,
1583
+ "learning_rate": 4.8943483704846475e-06,
1584
+ "loss": 0.5533,
1585
+ "step": 225
1586
+ },
1587
+ {
1588
+ "epoch": 1.8112449799196786,
1589
+ "grad_norm": 1.0122694969177246,
1590
+ "learning_rate": 4.498005554281337e-06,
1591
+ "loss": 0.6185,
1592
+ "step": 226
1593
+ },
1594
+ {
1595
+ "epoch": 1.819277108433735,
1596
+ "grad_norm": 1.0139045715332031,
1597
+ "learning_rate": 4.118026513180695e-06,
1598
+ "loss": 0.6863,
1599
+ "step": 227
1600
+ },
1601
+ {
1602
+ "epoch": 1.8273092369477912,
1603
+ "grad_norm": 1.0382832288742065,
1604
+ "learning_rate": 3.7544763546352834e-06,
1605
+ "loss": 0.6393,
1606
+ "step": 228
1607
+ },
1608
+ {
1609
+ "epoch": 1.8353413654618473,
1610
+ "grad_norm": 1.0690598487854004,
1611
+ "learning_rate": 3.40741737109318e-06,
1612
+ "loss": 0.6561,
1613
+ "step": 229
1614
+ },
1615
+ {
1616
+ "epoch": 1.8433734939759037,
1617
+ "grad_norm": 1.1074793338775635,
1618
+ "learning_rate": 3.0769090293245705e-06,
1619
+ "loss": 0.6343,
1620
+ "step": 230
1621
+ },
1622
+ {
1623
+ "epoch": 1.8514056224899598,
1624
+ "grad_norm": 1.0213125944137573,
1625
+ "learning_rate": 2.7630079602323442e-06,
1626
+ "loss": 0.5771,
1627
+ "step": 231
1628
+ },
1629
+ {
1630
+ "epoch": 1.859437751004016,
1631
+ "grad_norm": 1.0134626626968384,
1632
+ "learning_rate": 2.465767949148734e-06,
1633
+ "loss": 0.588,
1634
+ "step": 232
1635
+ },
1636
+ {
1637
+ "epoch": 1.8674698795180724,
1638
+ "grad_norm": 1.0337550640106201,
1639
+ "learning_rate": 2.1852399266194314e-06,
1640
+ "loss": 0.6011,
1641
+ "step": 233
1642
+ },
1643
+ {
1644
+ "epoch": 1.8755020080321285,
1645
+ "grad_norm": 0.97963547706604,
1646
+ "learning_rate": 1.921471959676957e-06,
1647
+ "loss": 0.5825,
1648
+ "step": 234
1649
+ },
1650
+ {
1651
+ "epoch": 1.8835341365461846,
1652
+ "grad_norm": 1.3414318561553955,
1653
+ "learning_rate": 1.6745092436045494e-06,
1654
+ "loss": 0.6096,
1655
+ "step": 235
1656
+ },
1657
+ {
1658
+ "epoch": 1.891566265060241,
1659
+ "grad_norm": 1.0074564218521118,
1660
+ "learning_rate": 1.444394094192225e-06,
1661
+ "loss": 0.5894,
1662
+ "step": 236
1663
+ },
1664
+ {
1665
+ "epoch": 1.8995983935742973,
1666
+ "grad_norm": 0.9695460200309753,
1667
+ "learning_rate": 1.231165940486234e-06,
1668
+ "loss": 0.547,
1669
+ "step": 237
1670
+ },
1671
+ {
1672
+ "epoch": 1.9076305220883534,
1673
+ "grad_norm": 1.030746340751648,
1674
+ "learning_rate": 1.0348613180329757e-06,
1675
+ "loss": 0.5488,
1676
+ "step": 238
1677
+ },
1678
+ {
1679
+ "epoch": 1.9156626506024095,
1680
+ "grad_norm": 1.073717713356018,
1681
+ "learning_rate": 8.555138626189618e-07,
1682
+ "loss": 0.6462,
1683
+ "step": 239
1684
+ },
1685
+ {
1686
+ "epoch": 1.9236947791164658,
1687
+ "grad_norm": 0.9700558185577393,
1688
+ "learning_rate": 6.931543045073708e-07,
1689
+ "loss": 0.5866,
1690
+ "step": 240
1691
+ },
1692
+ {
1693
+ "epoch": 1.9317269076305221,
1694
+ "grad_norm": 1.024263620376587,
1695
+ "learning_rate": 5.478104631726711e-07,
1696
+ "loss": 0.6498,
1697
+ "step": 241
1698
+ },
1699
+ {
1700
+ "epoch": 1.9397590361445785,
1701
+ "grad_norm": 0.984827995300293,
1702
+ "learning_rate": 4.1950724253383423e-07,
1703
+ "loss": 0.6554,
1704
+ "step": 242
1705
+ },
1706
+ {
1707
+ "epoch": 1.9477911646586346,
1708
+ "grad_norm": 1.0877512693405151,
1709
+ "learning_rate": 3.0826662668720364e-07,
1710
+ "loss": 0.6898,
1711
+ "step": 243
1712
+ },
1713
+ {
1714
+ "epoch": 1.9558232931726907,
1715
+ "grad_norm": 1.0173510313034058,
1716
+ "learning_rate": 2.141076761396521e-07,
1717
+ "loss": 0.6608,
1718
+ "step": 244
1719
+ },
1720
+ {
1721
+ "epoch": 1.963855421686747,
1722
+ "grad_norm": 1.0585603713989258,
1723
+ "learning_rate": 1.3704652454261668e-07,
1724
+ "loss": 0.686,
1725
+ "step": 245
1726
+ },
1727
+ {
1728
+ "epoch": 1.9718875502008033,
1729
+ "grad_norm": 1.075766921043396,
1730
+ "learning_rate": 7.709637592770991e-08,
1731
+ "loss": 0.6371,
1732
+ "step": 246
1733
+ },
1734
+ {
1735
+ "epoch": 1.9799196787148594,
1736
+ "grad_norm": 1.1289372444152832,
1737
+ "learning_rate": 3.4267502444274015e-08,
1738
+ "loss": 0.5713,
1739
+ "step": 247
1740
+ },
1741
+ {
1742
+ "epoch": 1.9879518072289155,
1743
+ "grad_norm": 1.0978978872299194,
1744
+ "learning_rate": 8.567242599299973e-09,
1745
+ "loss": 0.5833,
1746
+ "step": 248
1747
+ }
1748
+ ],
1749
+ "logging_steps": 1,
1750
+ "max_steps": 248,
1751
+ "num_input_tokens_seen": 0,
1752
+ "num_train_epochs": 2,
1753
+ "save_steps": 248,
1754
+ "stateful_callbacks": {
1755
+ "TrainerControl": {
1756
+ "args": {
1757
+ "should_epoch_stop": false,
1758
+ "should_evaluate": false,
1759
+ "should_log": false,
1760
+ "should_save": true,
1761
+ "should_training_stop": true
1762
+ },
1763
+ "attributes": {}
1764
+ }
1765
+ },
1766
+ "total_flos": 2.072735819939405e+16,
1767
+ "train_batch_size": 2,
1768
+ "trial_name": null,
1769
+ "trial_params": null
1770
+ }
brats_medgemma_r1_alpha4_20251014_005739/checkpoint-248/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dad0304949e4ae8ce7b2c24553f8575ab3ddb57525d2657a77709a0ec8003637
3
+ size 6353
brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/adapter_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "Gemma3ForConditionalGeneration",
5
+ "parent_library": "transformers.models.gemma3.modeling_gemma3",
6
+ "unsloth_fixed": true
7
+ },
8
+ "base_model_name_or_path": "unsloth/medgemma-4b-it-unsloth-bnb-4bit",
9
+ "bias": "none",
10
+ "corda_config": null,
11
+ "eva_config": null,
12
+ "exclude_modules": null,
13
+ "fan_in_fan_out": false,
14
+ "inference_mode": true,
15
+ "init_lora_weights": true,
16
+ "layer_replication": null,
17
+ "layers_pattern": null,
18
+ "layers_to_transform": null,
19
+ "loftq_config": {},
20
+ "lora_alpha": 4,
21
+ "lora_bias": false,
22
+ "lora_dropout": 0,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "qalora_group_size": 16,
28
+ "r": 1,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:k_proj|v_proj|q_proj|out_proj|fc1|fc2|o_proj|gate_proj|up_proj|down_proj)))",
32
+ "target_parameters": null,
33
+ "task_type": "CAUSAL_LM",
34
+ "trainable_token_indices": null,
35
+ "use_dora": false,
36
+ "use_qalora": false,
37
+ "use_rslora": false
38
+ }
brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6359aab348cebf78ac407209e2bac026b7e1f8203db96b6bae017784e270dd
3
+ size 9746344
brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/chat_template.jinja ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{ bos_token }}
2
+ {%- if messages[0]['role'] == 'system' -%}
3
+ {%- if messages[0]['content'] is string -%}
4
+ {%- set first_user_prefix = messages[0]['content'] + '
5
+
6
+ ' -%}
7
+ {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
+
10
+ ' -%}
11
+ {%- endif -%}
12
+ {%- set loop_messages = messages[1:] -%}
13
+ {%- else -%}
14
+ {%- set first_user_prefix = "" -%}
15
+ {%- set loop_messages = messages -%}
16
+ {%- endif -%}
17
+ {%- for message in loop_messages -%}
18
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
+ {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
+ {%- endif -%}
21
+ {%- if (message['role'] == 'assistant') -%}
22
+ {%- set role = "model" -%}
23
+ {%- else -%}
24
+ {%- set role = message['role'] -%}
25
+ {%- endif -%}
26
+ {{ '<start_of_turn>' + role + '
27
+ ' + (first_user_prefix if loop.first else "") }}
28
+ {%- if message['content'] is string -%}
29
+ {{ message['content'] | trim }}
30
+ {%- elif message['content'] is iterable -%}
31
+ {%- for item in message['content'] -%}
32
+ {%- if item['type'] == 'image' -%}
33
+ {{ '<start_of_image>' }}
34
+ {%- elif item['type'] == 'text' -%}
35
+ {{ item['text'] | trim }}
36
+ {%- endif -%}
37
+ {%- endfor -%}
38
+ {%- else -%}
39
+ {{ raise_exception("Invalid content type") }}
40
+ {%- endif -%}
41
+ {{ '<end_of_turn>
42
+ ' }}
43
+ {%- endfor -%}
44
+ {%- if add_generation_prompt -%}
45
+ {{ '<start_of_turn>model
46
+ ' }}
47
+ {%- endif -%}
brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_pan_and_scan": null,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Gemma3ImageProcessor",
13
+ "image_seq_length": 256,
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "pan_and_scan_max_num_crops": null,
20
+ "pan_and_scan_min_crop_size": null,
21
+ "pan_and_scan_min_ratio_to_activate": null,
22
+ "processor_class": "Gemma3Processor",
23
+ "resample": 2,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 896,
27
+ "width": 896
28
+ }
29
+ }
brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_length": 256,
3
+ "processor_class": "Gemma3Processor"
4
+ }
brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<end_of_turn>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
brats_medgemma_r1_alpha4_20251014_005739/lora_adapters/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
brats_medgemma_r1_alpha4_20251014_005739/merged_model/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
brats_medgemma_r1_alpha4_20251014_005739/merged_model/chat_template.jinja ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{ bos_token }}
2
+ {%- if messages[0]['role'] == 'system' -%}
3
+ {%- if messages[0]['content'] is string -%}
4
+ {%- set first_user_prefix = messages[0]['content'] + '
5
+
6
+ ' -%}
7
+ {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
+
10
+ ' -%}
11
+ {%- endif -%}
12
+ {%- set loop_messages = messages[1:] -%}
13
+ {%- else -%}
14
+ {%- set first_user_prefix = "" -%}
15
+ {%- set loop_messages = messages -%}
16
+ {%- endif -%}
17
+ {%- for message in loop_messages -%}
18
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
+ {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
+ {%- endif -%}
21
+ {%- if (message['role'] == 'assistant') -%}
22
+ {%- set role = "model" -%}
23
+ {%- else -%}
24
+ {%- set role = message['role'] -%}
25
+ {%- endif -%}
26
+ {{ '<start_of_turn>' + role + '
27
+ ' + (first_user_prefix if loop.first else "") }}
28
+ {%- if message['content'] is string -%}
29
+ {{ message['content'] | trim }}
30
+ {%- elif message['content'] is iterable -%}
31
+ {%- for item in message['content'] -%}
32
+ {%- if item['type'] == 'image' -%}
33
+ {{ '<start_of_image>' }}
34
+ {%- elif item['type'] == 'text' -%}
35
+ {{ item['text'] | trim }}
36
+ {%- endif -%}
37
+ {%- endfor -%}
38
+ {%- else -%}
39
+ {{ raise_exception("Invalid content type") }}
40
+ {%- endif -%}
41
+ {{ '<end_of_turn>
42
+ ' }}
43
+ {%- endfor -%}
44
+ {%- if add_generation_prompt -%}
45
+ {{ '<start_of_turn>model
46
+ ' }}
47
+ {%- endif -%}
brats_medgemma_r1_alpha4_20251014_005739/merged_model/config.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "bos_token_id": 2,
7
+ "torch_dtype": "bfloat16",
8
+ "eoi_token_index": 256000,
9
+ "eos_token_id": 106,
10
+ "image_token_index": 262144,
11
+ "initializer_range": 0.02,
12
+ "mm_tokens_per_image": 256,
13
+ "model_type": "gemma3",
14
+ "pad_token_id": 0,
15
+ "text_config": {
16
+ "_sliding_window_pattern": 6,
17
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "attn_logit_softcapping": null,
20
+ "cache_implementation": "hybrid",
21
+ "torch_dtype": "bfloat16",
22
+ "final_logit_softcapping": null,
23
+ "head_dim": 256,
24
+ "hidden_activation": "gelu_pytorch_tanh",
25
+ "hidden_size": 2560,
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 10240,
28
+ "layer_types": [
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "full_attention",
35
+ "sliding_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "full_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "full_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "full_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "full_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "sliding_attention",
62
+ "sliding_attention"
63
+ ],
64
+ "max_position_embeddings": 131072,
65
+ "model_type": "gemma3_text",
66
+ "num_attention_heads": 8,
67
+ "num_hidden_layers": 34,
68
+ "num_key_value_heads": 4,
69
+ "query_pre_attn_scalar": 256,
70
+ "rms_norm_eps": 1e-06,
71
+ "rope_local_base_freq": 10000,
72
+ "rope_scaling": {
73
+ "factor": 8.0,
74
+ "rope_type": "linear"
75
+ },
76
+ "rope_theta": 1000000,
77
+ "sliding_window": 1024,
78
+ "use_cache": true,
79
+ "vocab_size": 262208
80
+ },
81
+ "transformers_version": "4.56.2",
82
+ "unsloth_fixed": true,
83
+ "unsloth_version": "2025.10.1",
84
+ "vision_config": {
85
+ "attention_dropout": 0.0,
86
+ "torch_dtype": "bfloat16",
87
+ "hidden_act": "gelu_pytorch_tanh",
88
+ "hidden_size": 1152,
89
+ "image_size": 896,
90
+ "intermediate_size": 4304,
91
+ "layer_norm_eps": 1e-06,
92
+ "model_type": "siglip_vision_model",
93
+ "num_attention_heads": 16,
94
+ "num_channels": 3,
95
+ "num_hidden_layers": 27,
96
+ "patch_size": 14,
97
+ "vision_use_head": false
98
+ }
99
+ }
brats_medgemma_r1_alpha4_20251014_005739/merged_model/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e4178b12f47d245dfc766653f4a20c910c56f373f84c663e32f5a1771b95356
3
+ size 4961251752
brats_medgemma_r1_alpha4_20251014_005739/merged_model/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b43e89c540446f7d72a15a4ea5f14d83024a30ee1d0f86723c432691a35a2b02
3
+ size 3639026128
brats_medgemma_r1_alpha4_20251014_005739/merged_model/model.safetensors.index.json ADDED
@@ -0,0 +1,891 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4971331952,
4
+ "total_size": 8600158944
5
+ },
6
+ "weight_map": {
7
+ "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "language_model.model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "language_model.model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
15
+ "language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
16
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
17
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
18
+ "language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
19
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
20
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
21
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
23
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
24
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
25
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "language_model.model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "language_model.model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
28
+ "language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
29
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
30
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
31
+ "language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
32
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
33
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
34
+ "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
36
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
37
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
38
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "language_model.model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "language_model.model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
42
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
43
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
44
+ "language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
45
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
46
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
47
+ "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
49
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
50
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
51
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
52
+ "language_model.model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "language_model.model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
55
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
56
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
57
+ "language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
58
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
59
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
60
+ "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
61
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
62
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
63
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
64
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
65
+ "language_model.model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
66
+ "language_model.model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "language_model.model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
68
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
69
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
70
+ "language_model.model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
71
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
72
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
73
+ "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
74
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
75
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
76
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
77
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
78
+ "language_model.model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
79
+ "language_model.model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "language_model.model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
81
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
82
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
83
+ "language_model.model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
84
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
85
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
86
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
87
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
88
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
89
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
90
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
91
+ "language_model.model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
92
+ "language_model.model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
93
+ "language_model.model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
94
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "language_model.model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
97
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
98
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
99
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
100
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
101
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
102
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
103
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
104
+ "language_model.model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
105
+ "language_model.model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
106
+ "language_model.model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
107
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
108
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
109
+ "language_model.model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
110
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
111
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
112
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
113
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
114
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
115
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
116
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
117
+ "language_model.model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
118
+ "language_model.model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
119
+ "language_model.model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
120
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
121
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
122
+ "language_model.model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
123
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
124
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
125
+ "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
126
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
127
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
128
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
129
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
130
+ "language_model.model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
131
+ "language_model.model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
132
+ "language_model.model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
133
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
134
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
135
+ "language_model.model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
136
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
137
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
138
+ "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
139
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
140
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
141
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
142
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
143
+ "language_model.model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
144
+ "language_model.model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
145
+ "language_model.model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
146
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
147
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
148
+ "language_model.model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
149
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
150
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
151
+ "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
154
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
155
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "language_model.model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
157
+ "language_model.model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
158
+ "language_model.model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
159
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
160
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
161
+ "language_model.model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
162
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
163
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
164
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
165
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
166
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
167
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
168
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
169
+ "language_model.model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
170
+ "language_model.model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
171
+ "language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
172
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
173
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
174
+ "language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
175
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
176
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
177
+ "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
178
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
179
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
180
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
181
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
182
+ "language_model.model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
183
+ "language_model.model.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
184
+ "language_model.model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
185
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
186
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
187
+ "language_model.model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
188
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
189
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
190
+ "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
191
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
192
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
193
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
194
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
195
+ "language_model.model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
196
+ "language_model.model.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
197
+ "language_model.model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
198
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
199
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
200
+ "language_model.model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
201
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
202
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
203
+ "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
204
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
205
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
206
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
207
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
208
+ "language_model.model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
209
+ "language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
210
+ "language_model.model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
211
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
212
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
213
+ "language_model.model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
214
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
215
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
216
+ "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
217
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
218
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
219
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
220
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
221
+ "language_model.model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
222
+ "language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
223
+ "language_model.model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
224
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
225
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
226
+ "language_model.model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
227
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
228
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
229
+ "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
230
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
231
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
232
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
233
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
234
+ "language_model.model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
235
+ "language_model.model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
236
+ "language_model.model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
237
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
238
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
239
+ "language_model.model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
240
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
241
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
242
+ "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
243
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
244
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
245
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
246
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
247
+ "language_model.model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
248
+ "language_model.model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
249
+ "language_model.model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
250
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
251
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
252
+ "language_model.model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
253
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
254
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
255
+ "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
256
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
257
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
258
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
259
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
260
+ "language_model.model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
261
+ "language_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
262
+ "language_model.model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
263
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
264
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
265
+ "language_model.model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
266
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
267
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
268
+ "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
269
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
270
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
271
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
272
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
273
+ "language_model.model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
274
+ "language_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
275
+ "language_model.model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
276
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
277
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
278
+ "language_model.model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
279
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
280
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
281
+ "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
282
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
283
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
284
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
285
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
286
+ "language_model.model.layers.28.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
287
+ "language_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
288
+ "language_model.model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
289
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
290
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
291
+ "language_model.model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
292
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
293
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
294
+ "language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
295
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
296
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
297
+ "language_model.model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
298
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
299
+ "language_model.model.layers.29.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
300
+ "language_model.model.layers.29.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
301
+ "language_model.model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
302
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
303
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
304
+ "language_model.model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
305
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
306
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
307
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
308
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
309
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
310
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
311
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
312
+ "language_model.model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
313
+ "language_model.model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
314
+ "language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
315
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
316
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
317
+ "language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
318
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
319
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
320
+ "language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
321
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
322
+ "language_model.model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
323
+ "language_model.model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
324
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
325
+ "language_model.model.layers.30.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
326
+ "language_model.model.layers.30.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
327
+ "language_model.model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
328
+ "language_model.model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
329
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
330
+ "language_model.model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
331
+ "language_model.model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
332
+ "language_model.model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
333
+ "language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
334
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
335
+ "language_model.model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
336
+ "language_model.model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
337
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
338
+ "language_model.model.layers.31.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
339
+ "language_model.model.layers.31.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
340
+ "language_model.model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
341
+ "language_model.model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
342
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
343
+ "language_model.model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
344
+ "language_model.model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
345
+ "language_model.model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
346
+ "language_model.model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
347
+ "language_model.model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
348
+ "language_model.model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
349
+ "language_model.model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
350
+ "language_model.model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
351
+ "language_model.model.layers.32.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
352
+ "language_model.model.layers.32.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
353
+ "language_model.model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
354
+ "language_model.model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
355
+ "language_model.model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
356
+ "language_model.model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
357
+ "language_model.model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
358
+ "language_model.model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
359
+ "language_model.model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
360
+ "language_model.model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
361
+ "language_model.model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
362
+ "language_model.model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
363
+ "language_model.model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
364
+ "language_model.model.layers.33.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
365
+ "language_model.model.layers.33.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
366
+ "language_model.model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
367
+ "language_model.model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
368
+ "language_model.model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
369
+ "language_model.model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
370
+ "language_model.model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
371
+ "language_model.model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
372
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
373
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
374
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
375
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
376
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
377
+ "language_model.model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
378
+ "language_model.model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
379
+ "language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
380
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
381
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
382
+ "language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
383
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
384
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
385
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
386
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
387
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
388
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
389
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
390
+ "language_model.model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
391
+ "language_model.model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
392
+ "language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
393
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
394
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
395
+ "language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
396
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
397
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
398
+ "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
399
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
400
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
401
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
402
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
403
+ "language_model.model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
404
+ "language_model.model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
405
+ "language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
406
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
407
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
408
+ "language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
409
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
410
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
411
+ "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
412
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
413
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
414
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
415
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
416
+ "language_model.model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
417
+ "language_model.model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
418
+ "language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
419
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
420
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
421
+ "language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
422
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
423
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
424
+ "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
425
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
426
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
427
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
428
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
429
+ "language_model.model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
430
+ "language_model.model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
431
+ "language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
432
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
433
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
434
+ "language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
435
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
436
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
437
+ "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
438
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
439
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
440
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
441
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
442
+ "language_model.model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
443
+ "language_model.model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
444
+ "language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
445
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
446
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
447
+ "language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
448
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
449
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
450
+ "language_model.model.norm.weight": "model-00002-of-00002.safetensors",
451
+ "multi_modal_projector.mm_input_projection_weight": "model-00001-of-00002.safetensors",
452
+ "multi_modal_projector.mm_soft_emb_norm.weight": "model-00001-of-00002.safetensors",
453
+ "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
454
+ "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
455
+ "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
456
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
457
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
458
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
459
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
460
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
461
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
462
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
463
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
464
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
465
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
466
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
467
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
468
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
469
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
470
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
471
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
472
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
473
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
474
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
475
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
476
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
477
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
478
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
479
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
480
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
481
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
482
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
483
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
484
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
485
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
486
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
487
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
488
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
489
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
490
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
491
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
492
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
493
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
494
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
495
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
496
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
497
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
498
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
499
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
500
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
501
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
502
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
503
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
504
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
505
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
506
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
507
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
508
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
509
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
510
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
511
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
512
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
513
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
514
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
515
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
516
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
517
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
518
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
519
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
520
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
521
+ "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
522
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
523
+ "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
524
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
525
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
526
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
527
+ "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
528
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
529
+ "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
530
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
531
+ "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
532
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
533
+ "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
534
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
535
+ "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
536
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
537
+ "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
538
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
539
+ "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
540
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
541
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
542
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
543
+ "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
544
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
545
+ "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
546
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
547
+ "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
548
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
549
+ "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
550
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
551
+ "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
552
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
553
+ "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
554
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
555
+ "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
556
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
557
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
558
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
559
+ "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
560
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
561
+ "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
562
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
563
+ "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
564
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
565
+ "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
566
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
567
+ "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
568
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
569
+ "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
570
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
571
+ "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
572
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
573
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
574
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
575
+ "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
576
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
577
+ "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
578
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
579
+ "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
580
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
581
+ "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
582
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
583
+ "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
584
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
585
+ "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
586
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
587
+ "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
588
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
589
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
590
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
591
+ "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
592
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
593
+ "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
594
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
595
+ "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
596
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
597
+ "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
598
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
599
+ "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
600
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
601
+ "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
602
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
603
+ "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
604
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
605
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
606
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
607
+ "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
608
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
609
+ "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
610
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
611
+ "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
612
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
613
+ "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
614
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
615
+ "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
616
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
617
+ "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
618
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
619
+ "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
620
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
621
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
622
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
623
+ "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
624
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
625
+ "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
626
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
627
+ "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
628
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
629
+ "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
630
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
631
+ "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
632
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
633
+ "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
634
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
635
+ "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
636
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
637
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
638
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
639
+ "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
640
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
641
+ "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
642
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
643
+ "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
644
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
645
+ "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
646
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
647
+ "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
648
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
649
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
650
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
651
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
652
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
653
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
654
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
655
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
656
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
657
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
658
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
659
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
660
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
661
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
662
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
663
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
664
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
665
+ "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
666
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
667
+ "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
668
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
669
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
670
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
671
+ "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
672
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
673
+ "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
674
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
675
+ "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
676
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
677
+ "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
678
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
679
+ "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
680
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
681
+ "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
682
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
683
+ "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
684
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
685
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
686
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
687
+ "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
688
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
689
+ "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
690
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
691
+ "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
692
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
693
+ "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
694
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
695
+ "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
696
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
697
+ "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
698
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
699
+ "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
700
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
701
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
702
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
703
+ "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
704
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
705
+ "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
706
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
707
+ "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
708
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
709
+ "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
710
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
711
+ "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
712
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
713
+ "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
714
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
715
+ "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
716
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
717
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
718
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
719
+ "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
720
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
721
+ "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
722
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
723
+ "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
724
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
725
+ "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
726
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
727
+ "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
728
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
729
+ "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
730
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
731
+ "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
732
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
733
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
734
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
735
+ "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
736
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
737
+ "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
738
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
739
+ "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
740
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
741
+ "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
742
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
743
+ "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
744
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
745
+ "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
746
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
747
+ "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
748
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
749
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
750
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
751
+ "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
752
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
753
+ "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
754
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
755
+ "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
756
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
757
+ "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
758
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
759
+ "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
760
+ "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
761
+ "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
762
+ "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
763
+ "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
764
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
765
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
766
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
767
+ "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
768
+ "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
769
+ "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
770
+ "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
771
+ "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
772
+ "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
773
+ "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
774
+ "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
775
+ "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
776
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
777
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
778
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
779
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
780
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
781
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
782
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
783
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
784
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
785
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
786
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
787
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
788
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
789
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
790
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
791
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
792
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
793
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
794
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
795
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
796
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
797
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
798
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
799
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
800
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
801
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
802
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
803
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
804
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
805
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
806
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
807
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
808
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
809
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
810
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
811
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
812
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
813
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
814
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
815
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
816
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
817
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
818
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
819
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
820
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
821
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
822
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
823
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
824
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
825
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
826
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
827
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
828
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
829
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
830
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
831
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
832
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
833
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
834
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
835
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
836
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
837
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
838
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
839
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
840
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
841
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
842
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
843
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
844
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
845
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
846
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
847
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
848
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
849
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
850
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
851
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
852
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
853
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
854
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
855
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
856
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
857
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
858
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
859
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
860
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
861
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
862
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
863
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
864
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
865
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
866
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
867
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
868
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
869
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
870
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
871
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
872
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
873
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
874
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
875
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
876
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
877
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
878
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
879
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
880
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
881
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
882
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
883
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
884
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
885
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
886
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
887
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
888
+ "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
889
+ "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
890
+ }
891
+ }
brats_medgemma_r1_alpha4_20251014_005739/merged_model/preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_pan_and_scan": null,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "Gemma3ImageProcessor",
13
+ "image_seq_length": 256,
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "pan_and_scan_max_num_crops": null,
20
+ "pan_and_scan_min_crop_size": null,
21
+ "pan_and_scan_min_ratio_to_activate": null,
22
+ "processor_class": "Gemma3Processor",
23
+ "resample": 2,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "height": 896,
27
+ "width": 896
28
+ }
29
+ }
brats_medgemma_r1_alpha4_20251014_005739/merged_model/processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_length": 256,
3
+ "processor_class": "Gemma3Processor"
4
+ }
brats_medgemma_r1_alpha4_20251014_005739/merged_model/special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<end_of_turn>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
brats_medgemma_r1_alpha4_20251014_005739/merged_model/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
brats_medgemma_r1_alpha4_20251014_005739/merged_model/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
brats_medgemma_r1_alpha4_20251014_005739/merged_model/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
brats_medgemma_r1_alpha4_20251014_005739/metrics/complete_data_distribution_20251014_005739.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "experiment_metadata": {
3
+ "timestamp": "20251014_005739",
4
+ "random_seed": 3407,
5
+ "source_dataset": "Jupitern52/TextBraTS"
6
+ },
7
+ "data_summary": {
8
+ "original_textbrats_samples": 369,
9
+ "available_patients": 369,
10
+ "patients_used": 369,
11
+ "total_created_samples": 1107,
12
+ "train_samples": 996,
13
+ "test_samples": 111
14
+ },
15
+ "train_split": {
16
+ "image_type_distribution": {
17
+ "single_slice": 336,
18
+ "three_slices": 326,
19
+ "five_slices": 334
20
+ }
21
+ },
22
+ "test_split": {
23
+ "image_type_distribution": {
24
+ "three_slices": 43,
25
+ "five_slices": 35,
26
+ "single_slice": 33
27
+ }
28
+ }
29
+ }
brats_medgemma_r1_alpha4_20251014_005739/metrics/test_detailed_20251014_005739.csv ADDED
The diff for this file is too large to render. See raw diff
 
brats_medgemma_r1_alpha4_20251014_005739/metrics/test_summary_20251014_005739.csv ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ Metric,Score
2
+ ROUGE1,0.619414
3
+ ROUGE2,0.336955
4
+ ROUGEL,0.453630
brats_medgemma_r1_alpha4_20251014_005739/metrics/training_log_20251014_005739.csv ADDED
@@ -0,0 +1,249 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ step,epoch,loss,learning_rate,grad_norm,elapsed_time_s,timestamp
2
+ 1,0.0080,3.661000,0.00e+00,2.0187,4.48,2025-10-14 00:59:43
3
+ 2,0.0161,3.531500,2.50e-05,1.2853,7.27,2025-10-14 00:59:46
4
+ 3,0.0241,3.459400,5.00e-05,1.1487,10.24,2025-10-14 00:59:49
5
+ 4,0.0321,3.556000,7.50e-05,1.2605,12.96,2025-10-14 00:59:51
6
+ 5,0.0402,3.610400,1.00e-04,1.5687,15.74,2025-10-14 00:59:54
7
+ 6,0.0482,3.469300,1.25e-04,1.5858,18.75,2025-10-14 00:59:57
8
+ 7,0.0562,3.476500,1.50e-04,1.7028,21.42,2025-10-14 01:00:00
9
+ 8,0.0643,3.303700,1.75e-04,1.5310,24.24,2025-10-14 01:00:03
10
+ 9,0.0723,3.188400,2.00e-04,1.6373,27.19,2025-10-14 01:00:05
11
+ 10,0.0803,2.969200,2.00e-04,1.6676,57.95,2025-10-14 01:00:36
12
+ 11,0.0884,2.875000,2.00e-04,1.6879,60.65,2025-10-14 01:00:39
13
+ 12,0.0964,2.852300,2.00e-04,1.7119,63.63,2025-10-14 01:00:42
14
+ 13,0.1044,2.620300,2.00e-04,1.8331,66.36,2025-10-14 01:00:45
15
+ 14,0.1124,2.455200,2.00e-04,1.8833,69.07,2025-10-14 01:00:47
16
+ 15,0.1205,2.408200,2.00e-04,2.1763,71.99,2025-10-14 01:00:50
17
+ 16,0.1285,2.299000,2.00e-04,2.1363,74.74,2025-10-14 01:00:53
18
+ 17,0.1365,2.144600,1.99e-04,2.2712,77.36,2025-10-14 01:00:56
19
+ 18,0.1446,2.102300,1.99e-04,2.2227,80.29,2025-10-14 01:00:59
20
+ 19,0.1526,1.958700,1.99e-04,2.2808,83.02,2025-10-14 01:01:01
21
+ 20,0.1606,1.867200,1.99e-04,2.0863,108.41,2025-10-14 01:01:27
22
+ 21,0.1687,1.818100,1.99e-04,1.8972,111.41,2025-10-14 01:01:30
23
+ 22,0.1767,1.675600,1.99e-04,1.9296,114.17,2025-10-14 01:01:32
24
+ 23,0.1847,1.714600,1.98e-04,1.9769,116.88,2025-10-14 01:01:35
25
+ 24,0.1928,1.641200,1.98e-04,1.8274,119.87,2025-10-14 01:01:38
26
+ 25,0.2008,1.550000,1.98e-04,1.8512,122.59,2025-10-14 01:01:41
27
+ 26,0.2088,1.541800,1.98e-04,1.8951,125.27,2025-10-14 01:01:44
28
+ 27,0.2169,1.461900,1.97e-04,1.7330,128.26,2025-10-14 01:01:47
29
+ 28,0.2249,1.323800,1.97e-04,1.8035,130.98,2025-10-14 01:01:49
30
+ 29,0.2329,1.314800,1.97e-04,1.6535,133.71,2025-10-14 01:01:52
31
+ 30,0.2410,1.403100,1.96e-04,1.7777,160.63,2025-10-14 01:02:19
32
+ 31,0.2490,1.198300,1.96e-04,1.5709,163.32,2025-10-14 01:02:22
33
+ 32,0.2570,1.347800,1.96e-04,1.7219,165.97,2025-10-14 01:02:24
34
+ 33,0.2651,1.224100,1.95e-04,1.5298,168.87,2025-10-14 01:02:27
35
+ 34,0.2731,1.081500,1.95e-04,1.4229,171.55,2025-10-14 01:02:30
36
+ 35,0.2811,1.109800,1.94e-04,1.4637,174.19,2025-10-14 01:02:32
37
+ 36,0.2892,1.132300,1.94e-04,1.3306,177.13,2025-10-14 01:02:35
38
+ 37,0.2972,1.020700,1.93e-04,1.2060,179.84,2025-10-14 01:02:38
39
+ 38,0.3052,1.052100,1.93e-04,1.3600,182.59,2025-10-14 01:02:41
40
+ 39,0.3133,0.958600,1.92e-04,1.2998,185.28,2025-10-14 01:02:44
41
+ 40,0.3213,1.093100,1.92e-04,1.4096,214.58,2025-10-14 01:03:13
42
+ 41,0.3293,0.938300,1.91e-04,1.2826,217.24,2025-10-14 01:03:16
43
+ 42,0.3373,0.976700,1.91e-04,1.2694,220.26,2025-10-14 01:03:19
44
+ 43,0.3454,1.003200,1.90e-04,1.3005,223.00,2025-10-14 01:03:21
45
+ 44,0.3534,0.988500,1.90e-04,1.2941,225.74,2025-10-14 01:03:24
46
+ 45,0.3614,0.871100,1.89e-04,1.3918,228.60,2025-10-14 01:03:27
47
+ 46,0.3695,0.926500,1.88e-04,1.2822,231.26,2025-10-14 01:03:30
48
+ 47,0.3775,0.905100,1.88e-04,1.1995,233.96,2025-10-14 01:03:32
49
+ 48,0.3855,0.888600,1.87e-04,1.2313,236.89,2025-10-14 01:03:35
50
+ 49,0.3936,0.910300,1.87e-04,1.3313,239.55,2025-10-14 01:03:38
51
+ 50,0.4016,0.892700,1.86e-04,1.3165,267.78,2025-10-14 01:04:06
52
+ 51,0.4096,0.949800,1.85e-04,1.2710,270.76,2025-10-14 01:04:09
53
+ 52,0.4177,0.856800,1.85e-04,1.1253,273.47,2025-10-14 01:04:12
54
+ 53,0.4257,0.718300,1.84e-04,1.1713,276.18,2025-10-14 01:04:14
55
+ 54,0.4337,0.816800,1.83e-04,1.1720,279.04,2025-10-14 01:04:17
56
+ 55,0.4418,0.798200,1.82e-04,1.2101,281.75,2025-10-14 01:04:20
57
+ 56,0.4498,0.762600,1.82e-04,1.2936,284.44,2025-10-14 01:04:23
58
+ 57,0.4578,0.825900,1.81e-04,1.3371,287.30,2025-10-14 01:04:26
59
+ 58,0.4659,0.720700,1.80e-04,1.2913,289.98,2025-10-14 01:04:28
60
+ 59,0.4739,0.838800,1.79e-04,1.6399,292.71,2025-10-14 01:04:31
61
+ 60,0.4819,0.909500,1.79e-04,1.4379,322.58,2025-10-14 01:05:01
62
+ 61,0.4900,0.740100,1.78e-04,1.4433,325.24,2025-10-14 01:05:04
63
+ 62,0.4980,0.777100,1.77e-04,1.2439,327.94,2025-10-14 01:05:06
64
+ 63,0.5060,0.758900,1.76e-04,1.1849,330.84,2025-10-14 01:05:09
65
+ 64,0.5141,0.781000,1.75e-04,1.2419,333.53,2025-10-14 01:05:12
66
+ 65,0.5221,0.731600,1.74e-04,1.0403,336.26,2025-10-14 01:05:15
67
+ 66,0.5301,0.800600,1.73e-04,1.0187,339.12,2025-10-14 01:05:17
68
+ 67,0.5382,0.783500,1.73e-04,1.1233,341.79,2025-10-14 01:05:20
69
+ 68,0.5462,0.775000,1.72e-04,1.1925,344.53,2025-10-14 01:05:23
70
+ 69,0.5542,0.751300,1.71e-04,1.7944,347.49,2025-10-14 01:05:26
71
+ 70,0.5622,0.775300,1.70e-04,1.2268,377.53,2025-10-14 01:05:56
72
+ 71,0.5703,0.708600,1.69e-04,1.0529,380.24,2025-10-14 01:05:59
73
+ 72,0.5783,0.740600,1.68e-04,1.2667,383.15,2025-10-14 01:06:01
74
+ 73,0.5863,0.682900,1.67e-04,1.1201,385.86,2025-10-14 01:06:04
75
+ 74,0.5944,0.839100,1.66e-04,1.2908,388.56,2025-10-14 01:06:07
76
+ 75,0.6024,0.664800,1.65e-04,1.1098,391.48,2025-10-14 01:06:10
77
+ 76,0.6104,0.799400,1.64e-04,1.2486,394.11,2025-10-14 01:06:12
78
+ 77,0.6185,0.669100,1.63e-04,1.0588,396.80,2025-10-14 01:06:15
79
+ 78,0.6265,0.697000,1.62e-04,1.0989,399.50,2025-10-14 01:06:18
80
+ 79,0.6345,0.699800,1.61e-04,1.2327,402.42,2025-10-14 01:06:21
81
+ 80,0.6426,0.723300,1.60e-04,0.9899,430.34,2025-10-14 01:06:49
82
+ 81,0.6506,0.692800,1.59e-04,1.0117,433.01,2025-10-14 01:06:51
83
+ 82,0.6586,0.709600,1.58e-04,1.0488,436.01,2025-10-14 01:06:54
84
+ 83,0.6667,0.675300,1.57e-04,1.0680,438.72,2025-10-14 01:06:57
85
+ 84,0.6747,0.650400,1.56e-04,0.9523,441.37,2025-10-14 01:07:00
86
+ 85,0.6827,0.704500,1.54e-04,1.1361,444.25,2025-10-14 01:07:03
87
+ 86,0.6908,0.688500,1.53e-04,0.9763,446.96,2025-10-14 01:07:05
88
+ 87,0.6988,0.667200,1.52e-04,0.9241,449.62,2025-10-14 01:07:08
89
+ 88,0.7068,0.574100,1.51e-04,0.9768,452.54,2025-10-14 01:07:11
90
+ 89,0.7149,0.742100,1.50e-04,1.1666,455.29,2025-10-14 01:07:14
91
+ 90,0.7229,0.694500,1.49e-04,0.9955,483.93,2025-10-14 01:07:42
92
+ 91,0.7309,0.741100,1.48e-04,1.0900,486.88,2025-10-14 01:07:45
93
+ 92,0.7390,0.666300,1.47e-04,0.9967,489.61,2025-10-14 01:07:48
94
+ 93,0.7470,0.708800,1.45e-04,1.0430,492.31,2025-10-14 01:07:51
95
+ 94,0.7550,0.693300,1.44e-04,1.0899,495.24,2025-10-14 01:07:54
96
+ 95,0.7631,0.621800,1.43e-04,0.8203,497.93,2025-10-14 01:07:56
97
+ 96,0.7711,0.792500,1.42e-04,1.0294,500.63,2025-10-14 01:07:59
98
+ 97,0.7791,0.658900,1.41e-04,0.9109,503.64,2025-10-14 01:08:02
99
+ 98,0.7871,0.676500,1.39e-04,0.9137,506.32,2025-10-14 01:08:05
100
+ 99,0.7952,0.646800,1.38e-04,0.9278,509.04,2025-10-14 01:08:07
101
+ 100,0.8032,0.748600,1.37e-04,0.9486,533.79,2025-10-14 01:08:32
102
+ 101,0.8112,0.675400,1.36e-04,0.9050,536.45,2025-10-14 01:08:35
103
+ 102,0.8193,0.639800,1.35e-04,0.8544,539.12,2025-10-14 01:08:37
104
+ 103,0.8273,0.698200,1.33e-04,1.0328,542.03,2025-10-14 01:08:40
105
+ 104,0.8353,0.769300,1.32e-04,1.2989,544.71,2025-10-14 01:08:43
106
+ 105,0.8434,0.706400,1.31e-04,1.0677,547.46,2025-10-14 01:08:46
107
+ 106,0.8514,0.731700,1.30e-04,0.9510,550.32,2025-10-14 01:08:49
108
+ 107,0.8594,0.668000,1.28e-04,1.0593,553.04,2025-10-14 01:08:51
109
+ 108,0.8675,0.727200,1.27e-04,0.9987,555.67,2025-10-14 01:08:54
110
+ 109,0.8755,0.701900,1.26e-04,0.9523,558.53,2025-10-14 01:08:57
111
+ 110,0.8835,0.653000,1.25e-04,0.9643,587.71,2025-10-14 01:09:26
112
+ 111,0.8916,0.612400,1.23e-04,0.9260,590.40,2025-10-14 01:09:29
113
+ 112,0.8996,0.681100,1.22e-04,1.0311,593.38,2025-10-14 01:09:32
114
+ 113,0.9076,0.708400,1.21e-04,0.9404,596.07,2025-10-14 01:09:34
115
+ 114,0.9157,0.702700,1.20e-04,1.0048,598.75,2025-10-14 01:09:37
116
+ 115,0.9237,0.727100,1.18e-04,1.0550,601.64,2025-10-14 01:09:40
117
+ 116,0.9317,0.657400,1.17e-04,0.8879,604.28,2025-10-14 01:09:43
118
+ 117,0.9398,0.725800,1.16e-04,0.9581,607.01,2025-10-14 01:09:45
119
+ 118,0.9478,0.700600,1.14e-04,0.9399,609.86,2025-10-14 01:09:48
120
+ 119,0.9558,0.684300,1.13e-04,0.9026,612.52,2025-10-14 01:09:51
121
+ 120,0.9639,0.652900,1.12e-04,0.9120,641.26,2025-10-14 01:10:20
122
+ 121,0.9719,0.775100,1.10e-04,1.0958,644.21,2025-10-14 01:10:23
123
+ 122,0.9799,0.679000,1.09e-04,1.0137,646.93,2025-10-14 01:10:25
124
+ 123,0.9880,0.796800,1.08e-04,0.9281,649.63,2025-10-14 01:10:28
125
+ 124,0.9960,0.662300,1.07e-04,0.9261,652.53,2025-10-14 01:10:31
126
+ 125,1.0000,0.615000,1.05e-04,1.2207,653.81,2025-10-14 01:10:32
127
+ 126,1.0080,0.717200,1.04e-04,0.9385,656.60,2025-10-14 01:10:35
128
+ 127,1.0161,0.695100,1.03e-04,0.8901,659.33,2025-10-14 01:10:38
129
+ 128,1.0241,0.635700,1.01e-04,0.9513,662.18,2025-10-14 01:10:40
130
+ 129,1.0321,0.643600,1.00e-04,0.8817,664.86,2025-10-14 01:10:43
131
+ 130,1.0402,0.605100,9.87e-05,0.8699,695.26,2025-10-14 01:11:14
132
+ 131,1.0482,0.653200,9.74e-05,0.9640,697.90,2025-10-14 01:11:16
133
+ 132,1.0562,0.648700,9.61e-05,0.9207,700.65,2025-10-14 01:11:19
134
+ 133,1.0643,0.669200,9.48e-05,0.9588,703.33,2025-10-14 01:11:22
135
+ 134,1.0723,0.716400,9.35e-05,1.0699,706.10,2025-10-14 01:11:24
136
+ 135,1.0803,0.668900,9.22e-05,1.0149,708.79,2025-10-14 01:11:27
137
+ 136,1.0884,0.638700,9.08e-05,0.9482,711.41,2025-10-14 01:11:30
138
+ 137,1.0964,0.645700,8.95e-05,0.9719,714.33,2025-10-14 01:11:33
139
+ 138,1.1044,0.622600,8.82e-05,0.9527,717.09,2025-10-14 01:11:35
140
+ 139,1.1124,0.662300,8.69e-05,1.0299,719.79,2025-10-14 01:11:38
141
+ 140,1.1205,0.659400,8.57e-05,0.9271,747.12,2025-10-14 01:12:05
142
+ 141,1.1285,0.607800,8.44e-05,0.9238,749.83,2025-10-14 01:12:08
143
+ 142,1.1365,0.628300,8.31e-05,1.0177,752.49,2025-10-14 01:12:11
144
+ 143,1.1446,0.622900,8.18e-05,0.9104,755.43,2025-10-14 01:12:14
145
+ 144,1.1526,0.587000,8.05e-05,1.0475,758.11,2025-10-14 01:12:16
146
+ 145,1.1606,0.626300,7.92e-05,1.0246,760.71,2025-10-14 01:12:19
147
+ 146,1.1687,0.624900,7.79e-05,1.0276,763.57,2025-10-14 01:12:22
148
+ 147,1.1767,0.663900,7.67e-05,1.0467,766.30,2025-10-14 01:12:25
149
+ 148,1.1847,0.601600,7.54e-05,1.0777,768.95,2025-10-14 01:12:27
150
+ 149,1.1928,0.555600,7.41e-05,0.9003,771.84,2025-10-14 01:12:30
151
+ 150,1.2008,0.657400,7.29e-05,0.9594,798.88,2025-10-14 01:12:57
152
+ 151,1.2088,0.747700,7.16e-05,1.1023,801.57,2025-10-14 01:13:00
153
+ 152,1.2169,0.611000,7.03e-05,1.0037,804.54,2025-10-14 01:13:03
154
+ 153,1.2249,0.681900,6.91e-05,1.0237,807.21,2025-10-14 01:13:06
155
+ 154,1.2329,0.599000,6.79e-05,0.9779,809.85,2025-10-14 01:13:08
156
+ 155,1.2410,0.644700,6.66e-05,0.9719,812.70,2025-10-14 01:13:11
157
+ 156,1.2490,0.722500,6.54e-05,1.0557,815.43,2025-10-14 01:13:14
158
+ 157,1.2570,0.602800,6.42e-05,1.0306,818.12,2025-10-14 01:13:16
159
+ 158,1.2651,0.573500,6.29e-05,0.9871,820.95,2025-10-14 01:13:19
160
+ 159,1.2731,0.555900,6.17e-05,0.9500,823.66,2025-10-14 01:13:22
161
+ 160,1.2811,0.573800,6.05e-05,0.9344,851.66,2025-10-14 01:13:50
162
+ 161,1.2892,0.643500,5.93e-05,0.9733,854.60,2025-10-14 01:13:53
163
+ 162,1.2972,0.591000,5.81e-05,1.0251,857.34,2025-10-14 01:13:56
164
+ 163,1.3052,0.671300,5.69e-05,1.0366,859.99,2025-10-14 01:13:58
165
+ 164,1.3133,0.562400,5.58e-05,1.0183,862.89,2025-10-14 01:14:01
166
+ 165,1.3213,0.660500,5.46e-05,1.0992,865.58,2025-10-14 01:14:04
167
+ 166,1.3293,0.662500,5.34e-05,1.0976,868.28,2025-10-14 01:14:07
168
+ 167,1.3373,0.588000,5.23e-05,0.9974,871.16,2025-10-14 01:14:09
169
+ 168,1.3454,0.599300,5.11e-05,0.9781,873.90,2025-10-14 01:14:12
170
+ 169,1.3534,0.646800,5.00e-05,1.0631,876.61,2025-10-14 01:14:15
171
+ 170,1.3614,0.644500,4.89e-05,1.0322,907.05,2025-10-14 01:14:45
172
+ 171,1.3695,0.674800,4.78e-05,1.0585,909.66,2025-10-14 01:14:48
173
+ 172,1.3775,0.611400,4.66e-05,0.9846,912.31,2025-10-14 01:14:51
174
+ 173,1.3855,0.628200,4.55e-05,0.9892,915.34,2025-10-14 01:14:54
175
+ 174,1.3936,0.642200,4.44e-05,1.0388,918.08,2025-10-14 01:14:56
176
+ 175,1.4016,0.653600,4.34e-05,1.0008,920.80,2025-10-14 01:14:59
177
+ 176,1.4096,0.598300,4.23e-05,1.0263,923.63,2025-10-14 01:15:02
178
+ 177,1.4177,0.568900,4.12e-05,0.9772,926.33,2025-10-14 01:15:05
179
+ 178,1.4257,0.581100,4.02e-05,1.0257,929.03,2025-10-14 01:15:07
180
+ 179,1.4337,0.601300,3.91e-05,1.0345,931.91,2025-10-14 01:15:10
181
+ 180,1.4418,0.643500,3.81e-05,1.1113,960.16,2025-10-14 01:15:38
182
+ 181,1.4498,0.728600,3.71e-05,1.1512,962.78,2025-10-14 01:15:41
183
+ 182,1.4578,0.619200,3.61e-05,1.1736,965.68,2025-10-14 01:15:44
184
+ 183,1.4659,0.636400,3.51e-05,1.0498,968.40,2025-10-14 01:15:47
185
+ 184,1.4739,0.644500,3.41e-05,1.0111,971.07,2025-10-14 01:15:49
186
+ 185,1.4819,0.626700,3.31e-05,0.9973,973.96,2025-10-14 01:15:52
187
+ 186,1.4900,0.731600,3.21e-05,1.0189,976.65,2025-10-14 01:15:55
188
+ 187,1.4980,0.715300,3.12e-05,1.1160,979.28,2025-10-14 01:15:58
189
+ 188,1.5060,0.654400,3.02e-05,1.1160,982.22,2025-10-14 01:16:01
190
+ 189,1.5141,0.565000,2.93e-05,1.0619,984.92,2025-10-14 01:16:03
191
+ 190,1.5221,0.638800,2.84e-05,1.0562,1011.49,2025-10-14 01:16:30
192
+ 191,1.5301,0.622500,2.75e-05,1.0208,1014.44,2025-10-14 01:16:33
193
+ 192,1.5382,0.634900,2.66e-05,1.0186,1017.15,2025-10-14 01:16:35
194
+ 193,1.5462,0.571700,2.57e-05,1.1595,1019.81,2025-10-14 01:16:38
195
+ 194,1.5542,0.633900,2.48e-05,1.0306,1022.75,2025-10-14 01:16:41
196
+ 195,1.5622,0.650900,2.40e-05,1.1938,1025.45,2025-10-14 01:16:44
197
+ 196,1.5703,0.608800,2.31e-05,0.9358,1028.14,2025-10-14 01:16:46
198
+ 197,1.5783,0.579300,2.23e-05,1.0091,1031.06,2025-10-14 01:16:49
199
+ 198,1.5863,0.656700,2.15e-05,1.0742,1033.67,2025-10-14 01:16:52
200
+ 199,1.5944,0.609700,2.07e-05,0.9663,1036.37,2025-10-14 01:16:55
201
+ 200,1.6024,0.619400,1.99e-05,0.9676,1065.74,2025-10-14 01:17:24
202
+ 201,1.6104,0.709900,1.91e-05,1.0715,1068.45,2025-10-14 01:17:27
203
+ 202,1.6185,0.638400,1.83e-05,0.9677,1071.16,2025-10-14 01:17:29
204
+ 203,1.6265,0.571400,1.76e-05,1.0132,1074.18,2025-10-14 01:17:32
205
+ 204,1.6345,0.588400,1.69e-05,1.0167,1076.86,2025-10-14 01:17:35
206
+ 205,1.6426,0.654300,1.61e-05,1.0687,1079.56,2025-10-14 01:17:38
207
+ 206,1.6506,0.631900,1.54e-05,1.0615,1082.48,2025-10-14 01:17:41
208
+ 207,1.6586,0.592000,1.47e-05,1.0822,1085.17,2025-10-14 01:17:43
209
+ 208,1.6667,0.588600,1.41e-05,1.0043,1087.87,2025-10-14 01:17:46
210
+ 209,1.6747,0.706100,1.34e-05,1.1567,1090.69,2025-10-14 01:17:49
211
+ 210,1.6827,0.613300,1.28e-05,1.0404,1121.03,2025-10-14 01:18:19
212
+ 211,1.6908,0.633800,1.21e-05,1.0147,1123.65,2025-10-14 01:18:22
213
+ 212,1.6988,0.664200,1.15e-05,1.0179,1126.61,2025-10-14 01:18:25
214
+ 213,1.7068,0.622300,1.09e-05,1.1099,1129.31,2025-10-14 01:18:28
215
+ 214,1.7149,0.644500,1.03e-05,0.9551,1131.96,2025-10-14 01:18:30
216
+ 215,1.7229,0.587500,9.74e-06,1.0273,1134.79,2025-10-14 01:18:33
217
+ 216,1.7309,0.640200,9.19e-06,1.0904,1137.41,2025-10-14 01:18:36
218
+ 217,1.7390,0.690000,8.65e-06,1.0870,1140.07,2025-10-14 01:18:38
219
+ 218,1.7470,0.599500,8.12e-06,1.0122,1142.99,2025-10-14 01:18:41
220
+ 219,1.7550,0.639000,7.61e-06,1.0018,1145.72,2025-10-14 01:18:44
221
+ 220,1.7631,0.647100,7.12e-06,1.0906,1174.86,2025-10-14 01:19:13
222
+ 221,1.7711,0.623600,6.64e-06,1.0645,1177.80,2025-10-14 01:19:16
223
+ 222,1.7791,0.541000,6.18e-06,1.0269,1180.53,2025-10-14 01:19:19
224
+ 223,1.7871,0.638900,5.74e-06,1.0961,1183.25,2025-10-14 01:19:22
225
+ 224,1.7952,0.629000,5.31e-06,1.2134,1186.08,2025-10-14 01:19:24
226
+ 225,1.8032,0.553300,4.89e-06,0.9689,1188.76,2025-10-14 01:19:27
227
+ 226,1.8112,0.618500,4.50e-06,1.0123,1191.45,2025-10-14 01:19:30
228
+ 227,1.8193,0.686300,4.12e-06,1.0139,1194.36,2025-10-14 01:19:33
229
+ 228,1.8273,0.639300,3.75e-06,1.0383,1197.02,2025-10-14 01:19:35
230
+ 229,1.8353,0.656100,3.41e-06,1.0691,1199.74,2025-10-14 01:19:38
231
+ 230,1.8434,0.634300,3.08e-06,1.1075,1230.41,2025-10-14 01:20:09
232
+ 231,1.8514,0.577100,2.76e-06,1.0213,1233.11,2025-10-14 01:20:11
233
+ 232,1.8594,0.588000,2.47e-06,1.0135,1235.84,2025-10-14 01:20:14
234
+ 233,1.8675,0.601100,2.19e-06,1.0338,1238.80,2025-10-14 01:20:17
235
+ 234,1.8755,0.582500,1.92e-06,0.9796,1241.51,2025-10-14 01:20:20
236
+ 235,1.8835,0.609600,1.67e-06,1.3414,1244.22,2025-10-14 01:20:23
237
+ 236,1.8916,0.589400,1.44e-06,1.0075,1247.20,2025-10-14 01:20:25
238
+ 237,1.8996,0.547000,1.23e-06,0.9695,1249.89,2025-10-14 01:20:28
239
+ 238,1.9076,0.548800,1.03e-06,1.0307,1252.60,2025-10-14 01:20:31
240
+ 239,1.9157,0.646200,8.56e-07,1.0737,1255.53,2025-10-14 01:20:34
241
+ 240,1.9237,0.586600,6.93e-07,0.9701,1284.48,2025-10-14 01:21:03
242
+ 241,1.9317,0.649800,5.48e-07,1.0243,1287.15,2025-10-14 01:21:05
243
+ 242,1.9398,0.655400,4.20e-07,0.9848,1290.10,2025-10-14 01:21:08
244
+ 243,1.9478,0.689800,3.08e-07,1.0878,1292.81,2025-10-14 01:21:11
245
+ 244,1.9558,0.660800,2.14e-07,1.0174,1295.56,2025-10-14 01:21:14
246
+ 245,1.9639,0.686000,1.37e-07,1.0586,1298.53,2025-10-14 01:21:17
247
+ 246,1.9719,0.637100,7.71e-08,1.0758,1301.14,2025-10-14 01:21:19
248
+ 247,1.9799,0.571300,3.43e-08,1.1289,1303.86,2025-10-14 01:21:22
249
+ 248,1.9880,0.583300,8.57e-09,1.0979,1306.72,2025-10-14 01:21:25
brats_medgemma_r1_alpha4_20251014_005739/metrics/training_summary_20251014_005739.csv ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Metric,Value
2
+ Timestamp,20251014_005739
3
+ Training Time (s),1307.72
4
+ Training Time (min),21.80
5
+ Final Loss,0.9091048788639807
6
+ Epochs,2
7
+ Steps,Full epochs
8
+ Train Samples,996
9
+ Test Samples,111
10
+ Train Split,0.9
11
+ Learning Rate,0.0002
12
+ LoRA Rank,1
13
+ LoRA Alpha,4
14
+ Batch Size,2
15
+ Gradient Accumulation,4
16
+ Validation Every N Steps,10
brats_medgemma_r1_alpha4_20251014_005739/metrics/validation_during_training_20251014_005739.json ADDED
The diff for this file is too large to render. See raw diff
 
brats_medgemma_r1_alpha4_20251014_005739/metrics/validation_log_20251014_005739.csv ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ step,epoch,sample_id,patient_id,image_type,rouge1,rouge2,rougeL,avg_rouge
2
+ 10,0.0803,7,BraTS20_Training_005,three_slices,0.3249,0.0718,0.2030,0.1999
3
+ 10,0.0803,53,BraTS20_Training_048,five_slices,0.4078,0.1078,0.2427,0.2528
4
+ 10,0.0803,16,BraTS20_Training_199,three_slices,0.3905,0.1346,0.2190,0.2480
5
+ 20,0.1606,42,BraTS20_Training_165,three_slices,0.4106,0.0805,0.2517,0.2476
6
+ 20,0.1606,27,BraTS20_Training_128,three_slices,0.4904,0.1942,0.2692,0.3179
7
+ 20,0.1606,51,BraTS20_Training_146,single_slice,0.5789,0.2124,0.2982,0.3632
8
+ 30,0.2410,39,BraTS20_Training_107,single_slice,0.4466,0.2157,0.3398,0.3340
9
+ 30,0.2410,75,BraTS20_Training_347,five_slices,0.5918,0.2371,0.3367,0.3886
10
+ 30,0.2410,108,BraTS20_Training_279,three_slices,0.4343,0.1837,0.3232,0.3137
11
+ 40,0.3213,45,BraTS20_Training_364,single_slice,0.5419,0.2488,0.3744,0.3883
12
+ 40,0.3213,31,BraTS20_Training_080,single_slice,0.6099,0.2805,0.3498,0.4134
13
+ 40,0.3213,99,BraTS20_Training_329,five_slices,0.5315,0.2000,0.3423,0.3580
14
+ 50,0.4016,108,BraTS20_Training_279,three_slices,0.5366,0.2365,0.3512,0.3748
15
+ 50,0.4016,60,BraTS20_Training_366,single_slice,0.5882,0.2574,0.4216,0.4224
16
+ 50,0.4016,90,BraTS20_Training_248,five_slices,0.6040,0.3500,0.5050,0.4863
17
+ 60,0.4819,65,BraTS20_Training_368,five_slices,0.5914,0.2500,0.4194,0.4203
18
+ 60,0.4819,52,BraTS20_Training_239,five_slices,0.5600,0.2121,0.3600,0.3774
19
+ 60,0.4819,86,BraTS20_Training_121,single_slice,0.6355,0.3679,0.4486,0.4840
20
+ 70,0.5622,33,BraTS20_Training_214,five_slices,0.5872,0.2500,0.3945,0.4106
21
+ 70,0.5622,109,BraTS20_Training_178,three_slices,0.5766,0.3182,0.4234,0.4394
22
+ 70,0.5622,34,BraTS20_Training_116,three_slices,0.5882,0.2831,0.3891,0.4202
23
+ 80,0.6426,28,BraTS20_Training_271,three_slices,0.6849,0.4424,0.5114,0.5462
24
+ 80,0.6426,13,BraTS20_Training_132,three_slices,0.6316,0.3540,0.4912,0.4923
25
+ 80,0.6426,38,BraTS20_Training_040,single_slice,0.5778,0.3258,0.4667,0.4568
26
+ 90,0.7229,108,BraTS20_Training_279,three_slices,0.5837,0.3092,0.4115,0.4348
27
+ 90,0.7229,24,BraTS20_Training_139,five_slices,0.6439,0.3645,0.5171,0.5085
28
+ 90,0.7229,40,BraTS20_Training_192,three_slices,0.6111,0.3084,0.4722,0.4639
29
+ 100,0.8032,73,BraTS20_Training_111,single_slice,0.6941,0.3929,0.5412,0.5427
30
+ 100,0.8032,95,BraTS20_Training_039,single_slice,0.6154,0.3972,0.4755,0.4960
31
+ 100,0.8032,14,BraTS20_Training_259,five_slices,0.6288,0.3524,0.4629,0.4814
32
+ 110,0.8835,15,BraTS20_Training_343,five_slices,0.6140,0.3756,0.4651,0.4849
33
+ 110,0.8835,75,BraTS20_Training_347,five_slices,0.6311,0.4020,0.4854,0.5062
34
+ 110,0.8835,82,BraTS20_Training_301,five_slices,0.7225,0.4089,0.5198,0.5504
35
+ 120,0.9639,28,BraTS20_Training_271,three_slices,0.6184,0.3610,0.5024,0.4939
36
+ 120,0.9639,42,BraTS20_Training_165,three_slices,0.6256,0.3636,0.4739,0.4877
37
+ 120,0.9639,3,BraTS20_Training_355,single_slice,0.6304,0.3736,0.4457,0.4832
38
+ 130,1.0402,14,BraTS20_Training_259,five_slices,0.6293,0.3304,0.5000,0.4866
39
+ 130,1.0402,35,BraTS20_Training_178,single_slice,0.6878,0.3744,0.4796,0.5140
40
+ 130,1.0402,106,BraTS20_Training_004,three_slices,0.6486,0.3169,0.4649,0.4768
41
+ 140,1.1205,71,BraTS20_Training_367,five_slices,0.6881,0.3981,0.5138,0.5333
42
+ 140,1.1205,5,BraTS20_Training_344,single_slice,0.6214,0.2647,0.4369,0.4410
43
+ 140,1.1205,3,BraTS20_Training_355,single_slice,0.6333,0.3708,0.4556,0.4866
44
+ 150,1.2008,94,BraTS20_Training_091,three_slices,0.6533,0.3959,0.5025,0.5172
45
+ 150,1.2008,20,BraTS20_Training_130,three_slices,0.6739,0.3846,0.5000,0.5195
46
+ 150,1.2008,102,BraTS20_Training_274,three_slices,0.5950,0.3250,0.4132,0.4444
47
+ 160,1.2811,107,BraTS20_Training_145,five_slices,0.6579,0.3540,0.4649,0.4923
48
+ 160,1.2811,72,BraTS20_Training_203,three_slices,0.5477,0.3180,0.4564,0.4407
49
+ 160,1.2811,30,BraTS20_Training_300,five_slices,0.6378,0.3060,0.4432,0.4624
50
+ 170,1.3614,62,BraTS20_Training_122,five_slices,0.6250,0.3474,0.4479,0.4734
51
+ 170,1.3614,70,BraTS20_Training_244,three_slices,0.6389,0.3364,0.4537,0.4763
52
+ 170,1.3614,109,BraTS20_Training_178,three_slices,0.7378,0.4215,0.5156,0.5583
53
+ 180,1.4418,37,BraTS20_Training_296,five_slices,0.6737,0.4255,0.5368,0.5454
54
+ 180,1.4418,68,BraTS20_Training_215,three_slices,0.5217,0.2895,0.4087,0.4066
55
+ 180,1.4418,17,BraTS20_Training_211,five_slices,0.6667,0.3895,0.5208,0.5257
56
+ 190,1.5221,27,BraTS20_Training_128,three_slices,0.6768,0.4286,0.5354,0.5469
57
+ 190,1.5221,63,BraTS20_Training_236,single_slice,0.6780,0.3657,0.5311,0.5249
58
+ 190,1.5221,75,BraTS20_Training_347,five_slices,0.6569,0.3960,0.4804,0.5111
59
+ 200,1.6024,93,BraTS20_Training_321,five_slices,0.5953,0.2911,0.4279,0.4381
60
+ 200,1.6024,74,BraTS20_Training_180,single_slice,0.6599,0.3795,0.4365,0.4920
61
+ 200,1.6024,72,BraTS20_Training_203,three_slices,0.5923,0.3101,0.4462,0.4495
62
+ 210,1.6827,59,BraTS20_Training_260,single_slice,0.5571,0.2857,0.3744,0.4057
63
+ 210,1.6827,85,BraTS20_Training_369,five_slices,0.6190,0.3269,0.4762,0.4741
64
+ 210,1.6827,1,BraTS20_Training_060,three_slices,0.5846,0.3420,0.4615,0.4627
65
+ 220,1.7631,49,BraTS20_Training_110,three_slices,0.5275,0.2778,0.4066,0.4039
66
+ 220,1.7631,60,BraTS20_Training_366,single_slice,0.6373,0.3663,0.5294,0.5110
67
+ 220,1.7631,32,BraTS20_Training_101,five_slices,0.7480,0.4344,0.5203,0.5676
68
+ 230,1.8434,83,BraTS20_Training_320,three_slices,0.6250,0.3689,0.4808,0.4916
69
+ 230,1.8434,94,BraTS20_Training_091,three_slices,0.6607,0.3784,0.5179,0.5190
70
+ 230,1.8434,43,BraTS20_Training_114,five_slices,0.5870,0.2967,0.4891,0.4576
71
+ 240,1.9237,10,BraTS20_Training_327,three_slices,0.5756,0.3153,0.4195,0.4368
72
+ 240,1.9237,31,BraTS20_Training_080,single_slice,0.6009,0.3033,0.4319,0.4454
73
+ 240,1.9237,53,BraTS20_Training_048,five_slices,0.6346,0.3883,0.4615,0.4948