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
c7e3197
·
verified ·
1 Parent(s): 4c842cd

Upload brats_medgemma_r4_alpha4_20251014_013202

Browse files
Files changed (43) hide show
  1. .gitattributes +3 -0
  2. brats_medgemma_r4_alpha4_20251014_013202/checkpoint-248/adapter_config.json +38 -0
  3. brats_medgemma_r4_alpha4_20251014_013202/checkpoint-248/adapter_model.safetensors +3 -0
  4. brats_medgemma_r4_alpha4_20251014_013202/checkpoint-248/added_tokens.json +3 -0
  5. brats_medgemma_r4_alpha4_20251014_013202/checkpoint-248/chat_template.jinja +47 -0
  6. brats_medgemma_r4_alpha4_20251014_013202/checkpoint-248/optimizer.pt +3 -0
  7. brats_medgemma_r4_alpha4_20251014_013202/checkpoint-248/rng_state.pth +3 -0
  8. brats_medgemma_r4_alpha4_20251014_013202/checkpoint-248/scheduler.pt +3 -0
  9. brats_medgemma_r4_alpha4_20251014_013202/checkpoint-248/special_tokens_map.json +33 -0
  10. brats_medgemma_r4_alpha4_20251014_013202/checkpoint-248/tokenizer.json +3 -0
  11. brats_medgemma_r4_alpha4_20251014_013202/checkpoint-248/tokenizer.model +3 -0
  12. brats_medgemma_r4_alpha4_20251014_013202/checkpoint-248/tokenizer_config.json +0 -0
  13. brats_medgemma_r4_alpha4_20251014_013202/checkpoint-248/trainer_state.json +1770 -0
  14. brats_medgemma_r4_alpha4_20251014_013202/checkpoint-248/training_args.bin +3 -0
  15. brats_medgemma_r4_alpha4_20251014_013202/lora_adapters/adapter_config.json +38 -0
  16. brats_medgemma_r4_alpha4_20251014_013202/lora_adapters/adapter_model.safetensors +3 -0
  17. brats_medgemma_r4_alpha4_20251014_013202/lora_adapters/added_tokens.json +3 -0
  18. brats_medgemma_r4_alpha4_20251014_013202/lora_adapters/chat_template.jinja +47 -0
  19. brats_medgemma_r4_alpha4_20251014_013202/lora_adapters/preprocessor_config.json +29 -0
  20. brats_medgemma_r4_alpha4_20251014_013202/lora_adapters/processor_config.json +4 -0
  21. brats_medgemma_r4_alpha4_20251014_013202/lora_adapters/special_tokens_map.json +33 -0
  22. brats_medgemma_r4_alpha4_20251014_013202/lora_adapters/tokenizer.json +3 -0
  23. brats_medgemma_r4_alpha4_20251014_013202/lora_adapters/tokenizer.model +3 -0
  24. brats_medgemma_r4_alpha4_20251014_013202/lora_adapters/tokenizer_config.json +0 -0
  25. brats_medgemma_r4_alpha4_20251014_013202/merged_model/added_tokens.json +3 -0
  26. brats_medgemma_r4_alpha4_20251014_013202/merged_model/chat_template.jinja +47 -0
  27. brats_medgemma_r4_alpha4_20251014_013202/merged_model/config.json +99 -0
  28. brats_medgemma_r4_alpha4_20251014_013202/merged_model/model-00001-of-00002.safetensors +3 -0
  29. brats_medgemma_r4_alpha4_20251014_013202/merged_model/model-00002-of-00002.safetensors +3 -0
  30. brats_medgemma_r4_alpha4_20251014_013202/merged_model/model.safetensors.index.json +891 -0
  31. brats_medgemma_r4_alpha4_20251014_013202/merged_model/preprocessor_config.json +29 -0
  32. brats_medgemma_r4_alpha4_20251014_013202/merged_model/processor_config.json +4 -0
  33. brats_medgemma_r4_alpha4_20251014_013202/merged_model/special_tokens_map.json +33 -0
  34. brats_medgemma_r4_alpha4_20251014_013202/merged_model/tokenizer.json +3 -0
  35. brats_medgemma_r4_alpha4_20251014_013202/merged_model/tokenizer.model +3 -0
  36. brats_medgemma_r4_alpha4_20251014_013202/merged_model/tokenizer_config.json +0 -0
  37. brats_medgemma_r4_alpha4_20251014_013202/metrics/complete_data_distribution_20251014_013202.json +29 -0
  38. brats_medgemma_r4_alpha4_20251014_013202/metrics/test_detailed_20251014_013202.csv +0 -0
  39. brats_medgemma_r4_alpha4_20251014_013202/metrics/test_summary_20251014_013202.csv +4 -0
  40. brats_medgemma_r4_alpha4_20251014_013202/metrics/training_log_20251014_013202.csv +249 -0
  41. brats_medgemma_r4_alpha4_20251014_013202/metrics/training_summary_20251014_013202.csv +16 -0
  42. brats_medgemma_r4_alpha4_20251014_013202/metrics/validation_during_training_20251014_013202.json +0 -0
  43. brats_medgemma_r4_alpha4_20251014_013202/metrics/validation_log_20251014_013202.csv +73 -0
.gitattributes CHANGED
@@ -42,3 +42,6 @@ brats_medgemma_r1_alpha4_20251014_001744/merged_model/tokenizer.json filter=lfs
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
 
 
 
 
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
45
+ brats_medgemma_r4_alpha4_20251014_013202/checkpoint-248/tokenizer.json filter=lfs diff=lfs merge=lfs -text
46
+ brats_medgemma_r4_alpha4_20251014_013202/lora_adapters/tokenizer.json filter=lfs diff=lfs merge=lfs -text
47
+ brats_medgemma_r4_alpha4_20251014_013202/merged_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text
brats_medgemma_r4_alpha4_20251014_013202/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": 4,
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_r4_alpha4_20251014_013202/checkpoint-248/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f558f4044e0417e9a105a066162f260579ac07f605804d97c21771ca4bbf31c
3
+ size 38621072
brats_medgemma_r4_alpha4_20251014_013202/checkpoint-248/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
brats_medgemma_r4_alpha4_20251014_013202/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_r4_alpha4_20251014_013202/checkpoint-248/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0ca07b8587e78a53d7f5195bd6abb4f2769af4bfd155898bcde63d77a4e85d6
3
+ size 77681219
brats_medgemma_r4_alpha4_20251014_013202/checkpoint-248/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:556f30e13d2c75c94eb6232c2cf562a696afc27fadd6bb6a7a207b162e3b4eaf
3
+ size 14645
brats_medgemma_r4_alpha4_20251014_013202/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_r4_alpha4_20251014_013202/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_r4_alpha4_20251014_013202/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_r4_alpha4_20251014_013202/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_r4_alpha4_20251014_013202/checkpoint-248/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
brats_medgemma_r4_alpha4_20251014_013202/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": 0.8808280229568481,
15
+ "learning_rate": 0.0,
16
+ "loss": 3.661,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.01606425702811245,
21
+ "grad_norm": 0.611641526222229,
22
+ "learning_rate": 2.5e-05,
23
+ "loss": 3.5315,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.024096385542168676,
28
+ "grad_norm": 0.5583713054656982,
29
+ "learning_rate": 5e-05,
30
+ "loss": 3.4632,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.0321285140562249,
35
+ "grad_norm": 0.7047919034957886,
36
+ "learning_rate": 7.500000000000001e-05,
37
+ "loss": 3.5602,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.040160642570281124,
42
+ "grad_norm": 0.7664794921875,
43
+ "learning_rate": 0.0001,
44
+ "loss": 3.6203,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.04819277108433735,
49
+ "grad_norm": 0.7921016216278076,
50
+ "learning_rate": 0.000125,
51
+ "loss": 3.5015,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.05622489959839357,
56
+ "grad_norm": 0.8905137181282043,
57
+ "learning_rate": 0.00015000000000000001,
58
+ "loss": 3.5307,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.0642570281124498,
63
+ "grad_norm": 0.814842939376831,
64
+ "learning_rate": 0.000175,
65
+ "loss": 3.3573,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.07228915662650602,
70
+ "grad_norm": 0.846863865852356,
71
+ "learning_rate": 0.0002,
72
+ "loss": 3.2466,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.08032128514056225,
77
+ "grad_norm": 0.8540716171264648,
78
+ "learning_rate": 0.00019999143275740072,
79
+ "loss": 3.0212,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.08835341365461848,
84
+ "grad_norm": 0.8685902953147888,
85
+ "learning_rate": 0.00019996573249755572,
86
+ "loss": 2.9135,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.0963855421686747,
91
+ "grad_norm": 0.8775013089179993,
92
+ "learning_rate": 0.0001999229036240723,
93
+ "loss": 2.8853,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.10441767068273092,
98
+ "grad_norm": 0.9171439409255981,
99
+ "learning_rate": 0.0001998629534754574,
100
+ "loss": 2.6506,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.11244979919678715,
105
+ "grad_norm": 0.9009593725204468,
106
+ "learning_rate": 0.00019978589232386035,
107
+ "loss": 2.4754,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.12048192771084337,
112
+ "grad_norm": 1.0508103370666504,
113
+ "learning_rate": 0.0001996917333733128,
114
+ "loss": 2.4226,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.1285140562248996,
119
+ "grad_norm": 1.0355098247528076,
120
+ "learning_rate": 0.0001995804927574662,
121
+ "loss": 2.31,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.13654618473895583,
126
+ "grad_norm": 1.0821917057037354,
127
+ "learning_rate": 0.00019945218953682734,
128
+ "loss": 2.1529,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.14457831325301204,
133
+ "grad_norm": 1.0544633865356445,
134
+ "learning_rate": 0.00019930684569549264,
135
+ "loss": 2.1112,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.15261044176706828,
140
+ "grad_norm": 1.0548778772354126,
141
+ "learning_rate": 0.00019914448613738106,
142
+ "loss": 1.9734,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.1606425702811245,
147
+ "grad_norm": 0.9655290246009827,
148
+ "learning_rate": 0.00019896513868196704,
149
+ "loss": 1.8783,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.1686746987951807,
154
+ "grad_norm": 0.907878041267395,
155
+ "learning_rate": 0.00019876883405951377,
156
+ "loss": 1.8324,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.17670682730923695,
161
+ "grad_norm": 0.9243634939193726,
162
+ "learning_rate": 0.00019855560590580778,
163
+ "loss": 1.6899,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.18473895582329317,
168
+ "grad_norm": 0.9483376145362854,
169
+ "learning_rate": 0.0001983254907563955,
170
+ "loss": 1.7249,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.1927710843373494,
175
+ "grad_norm": 0.8866730332374573,
176
+ "learning_rate": 0.00019807852804032305,
177
+ "loss": 1.6526,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.20080321285140562,
182
+ "grad_norm": 0.8899125456809998,
183
+ "learning_rate": 0.00019781476007338058,
184
+ "loss": 1.5609,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.20883534136546184,
189
+ "grad_norm": 0.9213573932647705,
190
+ "learning_rate": 0.00019753423205085127,
191
+ "loss": 1.5508,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.21686746987951808,
196
+ "grad_norm": 0.8537583947181702,
197
+ "learning_rate": 0.00019723699203976766,
198
+ "loss": 1.4698,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.2248995983935743,
203
+ "grad_norm": 0.8974253535270691,
204
+ "learning_rate": 0.00019692309097067546,
205
+ "loss": 1.3404,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.23293172690763053,
210
+ "grad_norm": 0.8149802684783936,
211
+ "learning_rate": 0.00019659258262890683,
212
+ "loss": 1.3342,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.24096385542168675,
217
+ "grad_norm": 0.8968461751937866,
218
+ "learning_rate": 0.00019624552364536473,
219
+ "loss": 1.4199,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.24899598393574296,
224
+ "grad_norm": 0.7761573195457458,
225
+ "learning_rate": 0.0001958819734868193,
226
+ "loss": 1.2246,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.2570281124497992,
231
+ "grad_norm": 0.777557909488678,
232
+ "learning_rate": 0.0001955019944457187,
233
+ "loss": 1.3642,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.26506024096385544,
238
+ "grad_norm": 0.7426325082778931,
239
+ "learning_rate": 0.00019510565162951537,
240
+ "loss": 1.2414,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.27309236947791166,
245
+ "grad_norm": 0.7615096569061279,
246
+ "learning_rate": 0.0001946930129495106,
247
+ "loss": 1.0991,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.28112449799196787,
252
+ "grad_norm": 0.7383036017417908,
253
+ "learning_rate": 0.00019426414910921787,
254
+ "loss": 1.1185,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.2891566265060241,
259
+ "grad_norm": 0.6654855012893677,
260
+ "learning_rate": 0.00019381913359224842,
261
+ "loss": 1.1367,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.2971887550200803,
266
+ "grad_norm": 0.610072910785675,
267
+ "learning_rate": 0.00019335804264972018,
268
+ "loss": 1.0286,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.30522088353413657,
273
+ "grad_norm": 0.6931886672973633,
274
+ "learning_rate": 0.00019288095528719243,
275
+ "loss": 1.0577,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.3132530120481928,
280
+ "grad_norm": 0.666835367679596,
281
+ "learning_rate": 0.0001923879532511287,
282
+ "loss": 0.9666,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.321285140562249,
287
+ "grad_norm": 0.6915444135665894,
288
+ "learning_rate": 0.00019187912101488984,
289
+ "loss": 1.0932,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.3293172690763052,
294
+ "grad_norm": 0.6218484044075012,
295
+ "learning_rate": 0.0001913545457642601,
296
+ "loss": 0.9435,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.3373493975903614,
301
+ "grad_norm": 0.6409392356872559,
302
+ "learning_rate": 0.00019081431738250814,
303
+ "loss": 0.9788,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.3453815261044177,
308
+ "grad_norm": 0.6633965373039246,
309
+ "learning_rate": 0.00019025852843498607,
310
+ "loss": 1.0071,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.3534136546184739,
315
+ "grad_norm": 0.688491702079773,
316
+ "learning_rate": 0.00018968727415326884,
317
+ "loss": 0.9942,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.3614457831325301,
322
+ "grad_norm": 0.6982926726341248,
323
+ "learning_rate": 0.0001891006524188368,
324
+ "loss": 0.8807,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.36947791164658633,
329
+ "grad_norm": 0.6224360466003418,
330
+ "learning_rate": 0.0001884987637463042,
331
+ "loss": 0.9344,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.37751004016064255,
336
+ "grad_norm": 0.6020826101303101,
337
+ "learning_rate": 0.00018788171126619653,
338
+ "loss": 0.9162,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.3855421686746988,
343
+ "grad_norm": 0.6043077111244202,
344
+ "learning_rate": 0.00018724960070727972,
345
+ "loss": 0.8927,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.39357429718875503,
350
+ "grad_norm": 0.6711230874061584,
351
+ "learning_rate": 0.00018660254037844388,
352
+ "loss": 0.9246,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.40160642570281124,
357
+ "grad_norm": 0.6075426340103149,
358
+ "learning_rate": 0.0001859406411501453,
359
+ "loss": 0.8925,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.40963855421686746,
364
+ "grad_norm": 0.6121944785118103,
365
+ "learning_rate": 0.00018526401643540922,
366
+ "loss": 0.9545,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.41767068273092367,
371
+ "grad_norm": 0.550818145275116,
372
+ "learning_rate": 0.00018457278217039736,
373
+ "loss": 0.8587,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.42570281124497994,
378
+ "grad_norm": 0.5990152955055237,
379
+ "learning_rate": 0.00018386705679454242,
380
+ "loss": 0.7249,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.43373493975903615,
385
+ "grad_norm": 0.6276233196258545,
386
+ "learning_rate": 0.00018314696123025454,
387
+ "loss": 0.8255,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.44176706827309237,
392
+ "grad_norm": 0.6152111291885376,
393
+ "learning_rate": 0.00018241261886220154,
394
+ "loss": 0.8017,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.4497991967871486,
399
+ "grad_norm": 0.6794621348381042,
400
+ "learning_rate": 0.00018166415551616792,
401
+ "loss": 0.7686,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.4578313253012048,
406
+ "grad_norm": 0.6654403805732727,
407
+ "learning_rate": 0.00018090169943749476,
408
+ "loss": 0.8332,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.46586345381526106,
413
+ "grad_norm": 0.645365297794342,
414
+ "learning_rate": 0.00018012538126910608,
415
+ "loss": 0.7277,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.4738955823293173,
420
+ "grad_norm": 0.7319788932800293,
421
+ "learning_rate": 0.00017933533402912354,
422
+ "loss": 0.8359,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.4819277108433735,
427
+ "grad_norm": 0.6625881195068359,
428
+ "learning_rate": 0.00017853169308807448,
429
+ "loss": 0.9077,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.4899598393574297,
434
+ "grad_norm": 0.74483722448349,
435
+ "learning_rate": 0.0001777145961456971,
436
+ "loss": 0.7432,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.4979919678714859,
441
+ "grad_norm": 0.685007631778717,
442
+ "learning_rate": 0.00017688418320734598,
443
+ "loss": 0.7839,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.5060240963855421,
448
+ "grad_norm": 0.6295930743217468,
449
+ "learning_rate": 0.0001760405965600031,
450
+ "loss": 0.7616,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.5140562248995983,
455
+ "grad_norm": 0.627875030040741,
456
+ "learning_rate": 0.00017518398074789775,
457
+ "loss": 0.7875,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.5220883534136547,
462
+ "grad_norm": 0.5432299971580505,
463
+ "learning_rate": 0.00017431448254773944,
464
+ "loss": 0.7343,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.5301204819277109,
469
+ "grad_norm": 0.5294740796089172,
470
+ "learning_rate": 0.00017343225094356855,
471
+ "loss": 0.8076,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.5381526104417671,
476
+ "grad_norm": 0.5865962505340576,
477
+ "learning_rate": 0.00017253743710122875,
478
+ "loss": 0.7894,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.5461847389558233,
483
+ "grad_norm": 0.6138269305229187,
484
+ "learning_rate": 0.00017163019434246547,
485
+ "loss": 0.7799,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.5542168674698795,
490
+ "grad_norm": 0.9545474648475647,
491
+ "learning_rate": 0.00017071067811865476,
492
+ "loss": 0.7476,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.5622489959839357,
497
+ "grad_norm": 0.6186386942863464,
498
+ "learning_rate": 0.00016977904598416803,
499
+ "loss": 0.7753,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.570281124497992,
504
+ "grad_norm": 0.5626583695411682,
505
+ "learning_rate": 0.0001688354575693754,
506
+ "loss": 0.7136,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.5783132530120482,
511
+ "grad_norm": 0.7152630686759949,
512
+ "learning_rate": 0.0001678800745532942,
513
+ "loss": 0.7447,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.5863453815261044,
518
+ "grad_norm": 0.6004989147186279,
519
+ "learning_rate": 0.00016691306063588583,
520
+ "loss": 0.6872,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.5943775100401606,
525
+ "grad_norm": 0.6217724680900574,
526
+ "learning_rate": 0.00016593458151000688,
527
+ "loss": 0.8433,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.6024096385542169,
532
+ "grad_norm": 0.6377793550491333,
533
+ "learning_rate": 0.00016494480483301836,
534
+ "loss": 0.667,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.6104417670682731,
539
+ "grad_norm": 0.5861509442329407,
540
+ "learning_rate": 0.00016394390019805848,
541
+ "loss": 0.7983,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.6184738955823293,
546
+ "grad_norm": 0.5659100413322449,
547
+ "learning_rate": 0.00016293203910498376,
548
+ "loss": 0.6761,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.6265060240963856,
553
+ "grad_norm": 0.5006403923034668,
554
+ "learning_rate": 0.00016190939493098344,
555
+ "loss": 0.7,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.6345381526104418,
560
+ "grad_norm": 0.5357438921928406,
561
+ "learning_rate": 0.00016087614290087208,
562
+ "loss": 0.6932,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.642570281124498,
567
+ "grad_norm": 0.48218464851379395,
568
+ "learning_rate": 0.00015983246005706593,
569
+ "loss": 0.717,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.6506024096385542,
574
+ "grad_norm": 0.5074667930603027,
575
+ "learning_rate": 0.00015877852522924732,
576
+ "loss": 0.6943,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.6586345381526104,
581
+ "grad_norm": 0.5325137376785278,
582
+ "learning_rate": 0.0001577145190037234,
583
+ "loss": 0.7092,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.6666666666666666,
588
+ "grad_norm": 0.49130937457084656,
589
+ "learning_rate": 0.00015664062369248328,
590
+ "loss": 0.6736,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.6746987951807228,
595
+ "grad_norm": 0.5002483129501343,
596
+ "learning_rate": 0.00015555702330196023,
597
+ "loss": 0.6549,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.6827309236947792,
602
+ "grad_norm": 0.5355275273323059,
603
+ "learning_rate": 0.00015446390350150273,
604
+ "loss": 0.7113,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.6907630522088354,
609
+ "grad_norm": 0.5229775309562683,
610
+ "learning_rate": 0.00015336145159156115,
611
+ "loss": 0.6934,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.6987951807228916,
616
+ "grad_norm": 0.4623904228210449,
617
+ "learning_rate": 0.0001522498564715949,
618
+ "loss": 0.6716,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.7068273092369478,
623
+ "grad_norm": 0.4906090795993805,
624
+ "learning_rate": 0.0001511293086077052,
625
+ "loss": 0.5762,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.714859437751004,
630
+ "grad_norm": 0.575355052947998,
631
+ "learning_rate": 0.00015000000000000001,
632
+ "loss": 0.7434,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.7228915662650602,
637
+ "grad_norm": 0.48832353949546814,
638
+ "learning_rate": 0.00014886212414969553,
639
+ "loss": 0.6942,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.7309236947791165,
644
+ "grad_norm": 0.5415125489234924,
645
+ "learning_rate": 0.00014771587602596084,
646
+ "loss": 0.7433,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.7389558232931727,
651
+ "grad_norm": 0.48555251955986023,
652
+ "learning_rate": 0.00014656145203251114,
653
+ "loss": 0.66,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.7469879518072289,
658
+ "grad_norm": 0.531299352645874,
659
+ "learning_rate": 0.00014539904997395468,
660
+ "loss": 0.7077,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.7550200803212851,
665
+ "grad_norm": 0.5444431304931641,
666
+ "learning_rate": 0.00014422886902190014,
667
+ "loss": 0.6861,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.7630522088353414,
672
+ "grad_norm": 0.44917309284210205,
673
+ "learning_rate": 0.00014305110968082952,
674
+ "loss": 0.6235,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.7710843373493976,
679
+ "grad_norm": 0.5402846336364746,
680
+ "learning_rate": 0.0001418659737537428,
681
+ "loss": 0.7937,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.7791164658634538,
686
+ "grad_norm": 0.47021472454071045,
687
+ "learning_rate": 0.00014067366430758004,
688
+ "loss": 0.6636,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.7871485943775101,
693
+ "grad_norm": 0.4666689336299896,
694
+ "learning_rate": 0.0001394743856384267,
695
+ "loss": 0.6745,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.7951807228915663,
700
+ "grad_norm": 0.46373042464256287,
701
+ "learning_rate": 0.000138268343236509,
702
+ "loss": 0.6429,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.8032128514056225,
707
+ "grad_norm": 0.49462559819221497,
708
+ "learning_rate": 0.00013705574375098365,
709
+ "loss": 0.7501,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.8112449799196787,
714
+ "grad_norm": 0.4674227237701416,
715
+ "learning_rate": 0.00013583679495453,
716
+ "loss": 0.6762,
717
+ "step": 101
718
+ },
719
+ {
720
+ "epoch": 0.8192771084337349,
721
+ "grad_norm": 0.4376853406429291,
722
+ "learning_rate": 0.0001346117057077493,
723
+ "loss": 0.6444,
724
+ "step": 102
725
+ },
726
+ {
727
+ "epoch": 0.8273092369477911,
728
+ "grad_norm": 0.4977394938468933,
729
+ "learning_rate": 0.0001333806859233771,
730
+ "loss": 0.6958,
731
+ "step": 103
732
+ },
733
+ {
734
+ "epoch": 0.8353413654618473,
735
+ "grad_norm": 0.5216895937919617,
736
+ "learning_rate": 0.00013214394653031616,
737
+ "loss": 0.7656,
738
+ "step": 104
739
+ },
740
+ {
741
+ "epoch": 0.8433734939759037,
742
+ "grad_norm": 0.5547128915786743,
743
+ "learning_rate": 0.00013090169943749476,
744
+ "loss": 0.7072,
745
+ "step": 105
746
+ },
747
+ {
748
+ "epoch": 0.8514056224899599,
749
+ "grad_norm": 0.4783369302749634,
750
+ "learning_rate": 0.00012965415749755709,
751
+ "loss": 0.7329,
752
+ "step": 106
753
+ },
754
+ {
755
+ "epoch": 0.8594377510040161,
756
+ "grad_norm": 0.5335606932640076,
757
+ "learning_rate": 0.00012840153447039228,
758
+ "loss": 0.6697,
759
+ "step": 107
760
+ },
761
+ {
762
+ "epoch": 0.8674698795180723,
763
+ "grad_norm": 0.4853372275829315,
764
+ "learning_rate": 0.00012714404498650743,
765
+ "loss": 0.7241,
766
+ "step": 108
767
+ },
768
+ {
769
+ "epoch": 0.8755020080321285,
770
+ "grad_norm": 0.471878319978714,
771
+ "learning_rate": 0.00012588190451025207,
772
+ "loss": 0.7036,
773
+ "step": 109
774
+ },
775
+ {
776
+ "epoch": 0.8835341365461847,
777
+ "grad_norm": 0.4863775372505188,
778
+ "learning_rate": 0.00012461532930289933,
779
+ "loss": 0.6524,
780
+ "step": 110
781
+ },
782
+ {
783
+ "epoch": 0.891566265060241,
784
+ "grad_norm": 0.478368878364563,
785
+ "learning_rate": 0.00012334453638559057,
786
+ "loss": 0.6123,
787
+ "step": 111
788
+ },
789
+ {
790
+ "epoch": 0.8995983935742972,
791
+ "grad_norm": 0.5125443339347839,
792
+ "learning_rate": 0.00012206974350215015,
793
+ "loss": 0.6827,
794
+ "step": 112
795
+ },
796
+ {
797
+ "epoch": 0.9076305220883534,
798
+ "grad_norm": 0.4801071882247925,
799
+ "learning_rate": 0.00012079116908177593,
800
+ "loss": 0.7105,
801
+ "step": 113
802
+ },
803
+ {
804
+ "epoch": 0.9156626506024096,
805
+ "grad_norm": 0.5098010301589966,
806
+ "learning_rate": 0.00011950903220161285,
807
+ "loss": 0.7019,
808
+ "step": 114
809
+ },
810
+ {
811
+ "epoch": 0.9236947791164659,
812
+ "grad_norm": 0.5258087515830994,
813
+ "learning_rate": 0.00011822355254921478,
814
+ "loss": 0.7268,
815
+ "step": 115
816
+ },
817
+ {
818
+ "epoch": 0.9317269076305221,
819
+ "grad_norm": 0.4453822374343872,
820
+ "learning_rate": 0.00011693495038490245,
821
+ "loss": 0.6535,
822
+ "step": 116
823
+ },
824
+ {
825
+ "epoch": 0.9397590361445783,
826
+ "grad_norm": 0.5008060932159424,
827
+ "learning_rate": 0.0001156434465040231,
828
+ "loss": 0.7287,
829
+ "step": 117
830
+ },
831
+ {
832
+ "epoch": 0.9477911646586346,
833
+ "grad_norm": 0.45167794823646545,
834
+ "learning_rate": 0.00011434926219911793,
835
+ "loss": 0.7004,
836
+ "step": 118
837
+ },
838
+ {
839
+ "epoch": 0.9558232931726908,
840
+ "grad_norm": 0.4586542248725891,
841
+ "learning_rate": 0.00011305261922200519,
842
+ "loss": 0.6845,
843
+ "step": 119
844
+ },
845
+ {
846
+ "epoch": 0.963855421686747,
847
+ "grad_norm": 0.47293469309806824,
848
+ "learning_rate": 0.00011175373974578378,
849
+ "loss": 0.655,
850
+ "step": 120
851
+ },
852
+ {
853
+ "epoch": 0.9718875502008032,
854
+ "grad_norm": 0.5595822930335999,
855
+ "learning_rate": 0.00011045284632676536,
856
+ "loss": 0.7774,
857
+ "step": 121
858
+ },
859
+ {
860
+ "epoch": 0.9799196787148594,
861
+ "grad_norm": 0.5082138776779175,
862
+ "learning_rate": 0.00010915016186634026,
863
+ "loss": 0.6778,
864
+ "step": 122
865
+ },
866
+ {
867
+ "epoch": 0.9879518072289156,
868
+ "grad_norm": 0.46818843483924866,
869
+ "learning_rate": 0.0001078459095727845,
870
+ "loss": 0.8001,
871
+ "step": 123
872
+ },
873
+ {
874
+ "epoch": 0.9959839357429718,
875
+ "grad_norm": 0.4537018835544586,
876
+ "learning_rate": 0.00010654031292301432,
877
+ "loss": 0.6611,
878
+ "step": 124
879
+ },
880
+ {
881
+ "epoch": 1.0,
882
+ "grad_norm": 0.6156761646270752,
883
+ "learning_rate": 0.0001052335956242944,
884
+ "loss": 0.6178,
885
+ "step": 125
886
+ },
887
+ {
888
+ "epoch": 1.0080321285140563,
889
+ "grad_norm": 0.4707377851009369,
890
+ "learning_rate": 0.00010392598157590688,
891
+ "loss": 0.7219,
892
+ "step": 126
893
+ },
894
+ {
895
+ "epoch": 1.0160642570281124,
896
+ "grad_norm": 0.43898022174835205,
897
+ "learning_rate": 0.00010261769483078733,
898
+ "loss": 0.6945,
899
+ "step": 127
900
+ },
901
+ {
902
+ "epoch": 1.0240963855421688,
903
+ "grad_norm": 0.4779644012451172,
904
+ "learning_rate": 0.00010130895955713445,
905
+ "loss": 0.6373,
906
+ "step": 128
907
+ },
908
+ {
909
+ "epoch": 1.0321285140562249,
910
+ "grad_norm": 0.4384426176548004,
911
+ "learning_rate": 0.0001,
912
+ "loss": 0.6464,
913
+ "step": 129
914
+ },
915
+ {
916
+ "epoch": 1.0401606425702812,
917
+ "grad_norm": 0.43972474336624146,
918
+ "learning_rate": 9.869104044286558e-05,
919
+ "loss": 0.6079,
920
+ "step": 130
921
+ },
922
+ {
923
+ "epoch": 1.0481927710843373,
924
+ "grad_norm": 0.47619956731796265,
925
+ "learning_rate": 9.73823051692127e-05,
926
+ "loss": 0.6543,
927
+ "step": 131
928
+ },
929
+ {
930
+ "epoch": 1.0562248995983936,
931
+ "grad_norm": 0.4707636833190918,
932
+ "learning_rate": 9.607401842409317e-05,
933
+ "loss": 0.6492,
934
+ "step": 132
935
+ },
936
+ {
937
+ "epoch": 1.0642570281124497,
938
+ "grad_norm": 0.48428329825401306,
939
+ "learning_rate": 9.476640437570562e-05,
940
+ "loss": 0.6704,
941
+ "step": 133
942
+ },
943
+ {
944
+ "epoch": 1.072289156626506,
945
+ "grad_norm": 0.533614993095398,
946
+ "learning_rate": 9.345968707698569e-05,
947
+ "loss": 0.7123,
948
+ "step": 134
949
+ },
950
+ {
951
+ "epoch": 1.0803212851405624,
952
+ "grad_norm": 0.49966779351234436,
953
+ "learning_rate": 9.215409042721552e-05,
954
+ "loss": 0.669,
955
+ "step": 135
956
+ },
957
+ {
958
+ "epoch": 1.0883534136546185,
959
+ "grad_norm": 0.4626421630382538,
960
+ "learning_rate": 9.084983813365978e-05,
961
+ "loss": 0.635,
962
+ "step": 136
963
+ },
964
+ {
965
+ "epoch": 1.0963855421686748,
966
+ "grad_norm": 0.49942466616630554,
967
+ "learning_rate": 8.954715367323468e-05,
968
+ "loss": 0.6469,
969
+ "step": 137
970
+ },
971
+ {
972
+ "epoch": 1.104417670682731,
973
+ "grad_norm": 0.48026567697525024,
974
+ "learning_rate": 8.824626025421626e-05,
975
+ "loss": 0.6235,
976
+ "step": 138
977
+ },
978
+ {
979
+ "epoch": 1.1124497991967872,
980
+ "grad_norm": 0.5140242576599121,
981
+ "learning_rate": 8.694738077799488e-05,
982
+ "loss": 0.6634,
983
+ "step": 139
984
+ },
985
+ {
986
+ "epoch": 1.1204819277108433,
987
+ "grad_norm": 0.45677030086517334,
988
+ "learning_rate": 8.565073780088208e-05,
989
+ "loss": 0.6589,
990
+ "step": 140
991
+ },
992
+ {
993
+ "epoch": 1.1285140562248996,
994
+ "grad_norm": 0.4636770486831665,
995
+ "learning_rate": 8.435655349597689e-05,
996
+ "loss": 0.6092,
997
+ "step": 141
998
+ },
999
+ {
1000
+ "epoch": 1.1365461847389557,
1001
+ "grad_norm": 0.5026150345802307,
1002
+ "learning_rate": 8.306504961509754e-05,
1003
+ "loss": 0.6276,
1004
+ "step": 142
1005
+ },
1006
+ {
1007
+ "epoch": 1.144578313253012,
1008
+ "grad_norm": 0.4444529414176941,
1009
+ "learning_rate": 8.177644745078526e-05,
1010
+ "loss": 0.6219,
1011
+ "step": 143
1012
+ },
1013
+ {
1014
+ "epoch": 1.1526104417670684,
1015
+ "grad_norm": 0.5226261615753174,
1016
+ "learning_rate": 8.049096779838719e-05,
1017
+ "loss": 0.5896,
1018
+ "step": 144
1019
+ },
1020
+ {
1021
+ "epoch": 1.1606425702811245,
1022
+ "grad_norm": 0.5188784003257751,
1023
+ "learning_rate": 7.920883091822408e-05,
1024
+ "loss": 0.6283,
1025
+ "step": 145
1026
+ },
1027
+ {
1028
+ "epoch": 1.1686746987951806,
1029
+ "grad_norm": 0.5056262016296387,
1030
+ "learning_rate": 7.79302564978499e-05,
1031
+ "loss": 0.6286,
1032
+ "step": 146
1033
+ },
1034
+ {
1035
+ "epoch": 1.176706827309237,
1036
+ "grad_norm": 0.5214483737945557,
1037
+ "learning_rate": 7.66554636144095e-05,
1038
+ "loss": 0.6618,
1039
+ "step": 147
1040
+ },
1041
+ {
1042
+ "epoch": 1.1847389558232932,
1043
+ "grad_norm": 0.5382218360900879,
1044
+ "learning_rate": 7.53846706971007e-05,
1045
+ "loss": 0.6015,
1046
+ "step": 148
1047
+ },
1048
+ {
1049
+ "epoch": 1.1927710843373494,
1050
+ "grad_norm": 0.4377917945384979,
1051
+ "learning_rate": 7.411809548974792e-05,
1052
+ "loss": 0.5567,
1053
+ "step": 149
1054
+ },
1055
+ {
1056
+ "epoch": 1.2008032128514057,
1057
+ "grad_norm": 0.4758552610874176,
1058
+ "learning_rate": 7.285595501349258e-05,
1059
+ "loss": 0.6583,
1060
+ "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 1.2088353413654618,
1064
+ "grad_norm": 0.5302828550338745,
1065
+ "learning_rate": 7.159846552960774e-05,
1066
+ "loss": 0.7466,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 1.216867469879518,
1071
+ "grad_norm": 0.5071361660957336,
1072
+ "learning_rate": 7.034584250244291e-05,
1073
+ "loss": 0.6113,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 1.2248995983935742,
1078
+ "grad_norm": 0.517138659954071,
1079
+ "learning_rate": 6.909830056250527e-05,
1080
+ "loss": 0.6848,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 1.2329317269076305,
1085
+ "grad_norm": 0.4832388162612915,
1086
+ "learning_rate": 6.785605346968386e-05,
1087
+ "loss": 0.601,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 1.2409638554216866,
1092
+ "grad_norm": 0.4917982220649719,
1093
+ "learning_rate": 6.661931407662292e-05,
1094
+ "loss": 0.6469,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 1.248995983935743,
1099
+ "grad_norm": 0.5130038261413574,
1100
+ "learning_rate": 6.538829429225069e-05,
1101
+ "loss": 0.7213,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 1.2570281124497993,
1106
+ "grad_norm": 0.503336489200592,
1107
+ "learning_rate": 6.416320504546997e-05,
1108
+ "loss": 0.6022,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 1.2650602409638554,
1113
+ "grad_norm": 0.49011409282684326,
1114
+ "learning_rate": 6.294425624901638e-05,
1115
+ "loss": 0.5719,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 1.2730923694779117,
1120
+ "grad_norm": 0.47099483013153076,
1121
+ "learning_rate": 6.173165676349103e-05,
1122
+ "loss": 0.5564,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 1.2811244979919678,
1127
+ "grad_norm": 0.4718809723854065,
1128
+ "learning_rate": 6.052561436157329e-05,
1129
+ "loss": 0.5754,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 1.2891566265060241,
1134
+ "grad_norm": 0.4865042567253113,
1135
+ "learning_rate": 5.9326335692419995e-05,
1136
+ "loss": 0.6416,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 1.2971887550200802,
1141
+ "grad_norm": 0.5055269598960876,
1142
+ "learning_rate": 5.8134026246257225e-05,
1143
+ "loss": 0.5931,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 1.3052208835341366,
1148
+ "grad_norm": 0.5162351131439209,
1149
+ "learning_rate": 5.694889031917047e-05,
1150
+ "loss": 0.6762,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 1.3132530120481927,
1155
+ "grad_norm": 0.5032309293746948,
1156
+ "learning_rate": 5.577113097809989e-05,
1157
+ "loss": 0.564,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 1.321285140562249,
1162
+ "grad_norm": 0.5552712082862854,
1163
+ "learning_rate": 5.4600950026045326e-05,
1164
+ "loss": 0.6599,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 1.3293172690763053,
1169
+ "grad_norm": 0.5489377975463867,
1170
+ "learning_rate": 5.343854796748886e-05,
1171
+ "loss": 0.6645,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 1.3373493975903614,
1176
+ "grad_norm": 0.5030948519706726,
1177
+ "learning_rate": 5.2284123974039154e-05,
1178
+ "loss": 0.5925,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 1.3453815261044177,
1183
+ "grad_norm": 0.4848288893699646,
1184
+ "learning_rate": 5.113787585030454e-05,
1185
+ "loss": 0.6008,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 1.3534136546184738,
1190
+ "grad_norm": 0.535276472568512,
1191
+ "learning_rate": 5.000000000000002e-05,
1192
+ "loss": 0.6506,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 1.3614457831325302,
1197
+ "grad_norm": 0.5142583250999451,
1198
+ "learning_rate": 4.887069139229481e-05,
1199
+ "loss": 0.6494,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 1.3694779116465863,
1204
+ "grad_norm": 0.5223931670188904,
1205
+ "learning_rate": 4.7750143528405126e-05,
1206
+ "loss": 0.6747,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 1.3775100401606426,
1211
+ "grad_norm": 0.4900956153869629,
1212
+ "learning_rate": 4.6638548408438856e-05,
1213
+ "loss": 0.6107,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 1.3855421686746987,
1218
+ "grad_norm": 0.4947897493839264,
1219
+ "learning_rate": 4.5536096498497295e-05,
1220
+ "loss": 0.628,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 1.393574297188755,
1225
+ "grad_norm": 0.5090555548667908,
1226
+ "learning_rate": 4.444297669803981e-05,
1227
+ "loss": 0.6398,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 1.4016064257028114,
1232
+ "grad_norm": 0.4987989068031311,
1233
+ "learning_rate": 4.335937630751674e-05,
1234
+ "loss": 0.6567,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 1.4096385542168675,
1239
+ "grad_norm": 0.47407257556915283,
1240
+ "learning_rate": 4.228548099627665e-05,
1241
+ "loss": 0.6005,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 1.4176706827309236,
1246
+ "grad_norm": 0.4842042028903961,
1247
+ "learning_rate": 4.12214747707527e-05,
1248
+ "loss": 0.5713,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 1.4257028112449799,
1253
+ "grad_norm": 0.5017086267471313,
1254
+ "learning_rate": 4.01675399429341e-05,
1255
+ "loss": 0.5864,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 1.4337349397590362,
1260
+ "grad_norm": 0.5084140300750732,
1261
+ "learning_rate": 3.9123857099127936e-05,
1262
+ "loss": 0.6018,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 1.4417670682730923,
1267
+ "grad_norm": 0.5515051484107971,
1268
+ "learning_rate": 3.8090605069016595e-05,
1269
+ "loss": 0.6425,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 1.4497991967871486,
1274
+ "grad_norm": 0.5663464069366455,
1275
+ "learning_rate": 3.7067960895016275e-05,
1276
+ "loss": 0.7254,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 1.4578313253012047,
1281
+ "grad_norm": 0.5931705832481384,
1282
+ "learning_rate": 3.6056099801941534e-05,
1283
+ "loss": 0.6239,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 1.465863453815261,
1288
+ "grad_norm": 0.5284808874130249,
1289
+ "learning_rate": 3.5055195166981645e-05,
1290
+ "loss": 0.6385,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 1.4738955823293174,
1295
+ "grad_norm": 0.49324554204940796,
1296
+ "learning_rate": 3.406541848999312e-05,
1297
+ "loss": 0.646,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 1.4819277108433735,
1302
+ "grad_norm": 0.48566392064094543,
1303
+ "learning_rate": 3.308693936411421e-05,
1304
+ "loss": 0.6252,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 1.4899598393574296,
1309
+ "grad_norm": 0.4936532974243164,
1310
+ "learning_rate": 3.211992544670582e-05,
1311
+ "loss": 0.7321,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 1.497991967871486,
1316
+ "grad_norm": 0.5535200238227844,
1317
+ "learning_rate": 3.116454243062459e-05,
1318
+ "loss": 0.7168,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 1.5060240963855422,
1323
+ "grad_norm": 0.5473021864891052,
1324
+ "learning_rate": 3.0220954015832003e-05,
1325
+ "loss": 0.6546,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 1.5140562248995983,
1330
+ "grad_norm": 0.5319312214851379,
1331
+ "learning_rate": 2.9289321881345254e-05,
1332
+ "loss": 0.5711,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 1.5220883534136547,
1337
+ "grad_norm": 0.5224682092666626,
1338
+ "learning_rate": 2.8369805657534575e-05,
1339
+ "loss": 0.6385,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 1.5301204819277108,
1344
+ "grad_norm": 0.5093374848365784,
1345
+ "learning_rate": 2.746256289877126e-05,
1346
+ "loss": 0.623,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 1.538152610441767,
1351
+ "grad_norm": 0.4990738034248352,
1352
+ "learning_rate": 2.6567749056431467e-05,
1353
+ "loss": 0.635,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 1.5461847389558234,
1358
+ "grad_norm": 0.5833855867385864,
1359
+ "learning_rate": 2.5685517452260567e-05,
1360
+ "loss": 0.5746,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 1.5542168674698795,
1365
+ "grad_norm": 0.5148371458053589,
1366
+ "learning_rate": 2.4816019252102273e-05,
1367
+ "loss": 0.6367,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 1.5622489959839356,
1372
+ "grad_norm": 0.5850048065185547,
1373
+ "learning_rate": 2.3959403439996907e-05,
1374
+ "loss": 0.6538,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 1.570281124497992,
1379
+ "grad_norm": 0.46460628509521484,
1380
+ "learning_rate": 2.3115816792654056e-05,
1381
+ "loss": 0.6088,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 1.5783132530120483,
1386
+ "grad_norm": 0.4936422109603882,
1387
+ "learning_rate": 2.2285403854302912e-05,
1388
+ "loss": 0.5808,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 1.5863453815261044,
1393
+ "grad_norm": 0.5358330607414246,
1394
+ "learning_rate": 2.146830691192553e-05,
1395
+ "loss": 0.6558,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 1.5943775100401605,
1400
+ "grad_norm": 0.47787192463874817,
1401
+ "learning_rate": 2.0664665970876496e-05,
1402
+ "loss": 0.61,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 1.6024096385542168,
1407
+ "grad_norm": 0.49321621656417847,
1408
+ "learning_rate": 1.9874618730893946e-05,
1409
+ "loss": 0.6198,
1410
+ "step": 200
1411
+ },
1412
+ {
1413
+ "epoch": 1.6104417670682731,
1414
+ "grad_norm": 0.5312886238098145,
1415
+ "learning_rate": 1.9098300562505266e-05,
1416
+ "loss": 0.7118,
1417
+ "step": 201
1418
+ },
1419
+ {
1420
+ "epoch": 1.6184738955823295,
1421
+ "grad_norm": 0.475717157125473,
1422
+ "learning_rate": 1.833584448383211e-05,
1423
+ "loss": 0.6367,
1424
+ "step": 202
1425
+ },
1426
+ {
1427
+ "epoch": 1.6265060240963856,
1428
+ "grad_norm": 0.501308262348175,
1429
+ "learning_rate": 1.7587381137798432e-05,
1430
+ "loss": 0.5711,
1431
+ "step": 203
1432
+ },
1433
+ {
1434
+ "epoch": 1.6345381526104417,
1435
+ "grad_norm": 0.4929254353046417,
1436
+ "learning_rate": 1.6853038769745467e-05,
1437
+ "loss": 0.5877,
1438
+ "step": 204
1439
+ },
1440
+ {
1441
+ "epoch": 1.642570281124498,
1442
+ "grad_norm": 0.5243952870368958,
1443
+ "learning_rate": 1.6132943205457606e-05,
1444
+ "loss": 0.6521,
1445
+ "step": 205
1446
+ },
1447
+ {
1448
+ "epoch": 1.6506024096385543,
1449
+ "grad_norm": 0.5256708264350891,
1450
+ "learning_rate": 1.542721782960268e-05,
1451
+ "loss": 0.631,
1452
+ "step": 206
1453
+ },
1454
+ {
1455
+ "epoch": 1.6586345381526104,
1456
+ "grad_norm": 0.5346550941467285,
1457
+ "learning_rate": 1.4735983564590783e-05,
1458
+ "loss": 0.5908,
1459
+ "step": 207
1460
+ },
1461
+ {
1462
+ "epoch": 1.6666666666666665,
1463
+ "grad_norm": 0.4967620372772217,
1464
+ "learning_rate": 1.405935884985473e-05,
1465
+ "loss": 0.5922,
1466
+ "step": 208
1467
+ },
1468
+ {
1469
+ "epoch": 1.6746987951807228,
1470
+ "grad_norm": 0.5798769593238831,
1471
+ "learning_rate": 1.339745962155613e-05,
1472
+ "loss": 0.7033,
1473
+ "step": 209
1474
+ },
1475
+ {
1476
+ "epoch": 1.6827309236947792,
1477
+ "grad_norm": 0.5225862860679626,
1478
+ "learning_rate": 1.2750399292720283e-05,
1479
+ "loss": 0.6109,
1480
+ "step": 210
1481
+ },
1482
+ {
1483
+ "epoch": 1.6907630522088355,
1484
+ "grad_norm": 0.5068684220314026,
1485
+ "learning_rate": 1.2118288733803473e-05,
1486
+ "loss": 0.6323,
1487
+ "step": 211
1488
+ },
1489
+ {
1490
+ "epoch": 1.6987951807228916,
1491
+ "grad_norm": 0.49447447061538696,
1492
+ "learning_rate": 1.1501236253695823e-05,
1493
+ "loss": 0.6625,
1494
+ "step": 212
1495
+ },
1496
+ {
1497
+ "epoch": 1.7068273092369477,
1498
+ "grad_norm": 0.5502182245254517,
1499
+ "learning_rate": 1.0899347581163221e-05,
1500
+ "loss": 0.6218,
1501
+ "step": 213
1502
+ },
1503
+ {
1504
+ "epoch": 1.714859437751004,
1505
+ "grad_norm": 0.48162364959716797,
1506
+ "learning_rate": 1.0312725846731175e-05,
1507
+ "loss": 0.6451,
1508
+ "step": 214
1509
+ },
1510
+ {
1511
+ "epoch": 1.7228915662650603,
1512
+ "grad_norm": 0.5141961574554443,
1513
+ "learning_rate": 9.74147156501396e-06,
1514
+ "loss": 0.5873,
1515
+ "step": 215
1516
+ },
1517
+ {
1518
+ "epoch": 1.7309236947791165,
1519
+ "grad_norm": 0.5545074939727783,
1520
+ "learning_rate": 9.185682617491863e-06,
1521
+ "loss": 0.6375,
1522
+ "step": 216
1523
+ },
1524
+ {
1525
+ "epoch": 1.7389558232931726,
1526
+ "grad_norm": 0.5388469099998474,
1527
+ "learning_rate": 8.645454235739903e-06,
1528
+ "loss": 0.6884,
1529
+ "step": 217
1530
+ },
1531
+ {
1532
+ "epoch": 1.7469879518072289,
1533
+ "grad_norm": 0.5042293667793274,
1534
+ "learning_rate": 8.12087898511018e-06,
1535
+ "loss": 0.6026,
1536
+ "step": 218
1537
+ },
1538
+ {
1539
+ "epoch": 1.7550200803212852,
1540
+ "grad_norm": 0.4900529980659485,
1541
+ "learning_rate": 7.612046748871327e-06,
1542
+ "loss": 0.6428,
1543
+ "step": 219
1544
+ },
1545
+ {
1546
+ "epoch": 1.7630522088353415,
1547
+ "grad_norm": 0.5415508151054382,
1548
+ "learning_rate": 7.119044712807577e-06,
1549
+ "loss": 0.6487,
1550
+ "step": 220
1551
+ },
1552
+ {
1553
+ "epoch": 1.7710843373493976,
1554
+ "grad_norm": 0.5361891984939575,
1555
+ "learning_rate": 6.6419573502798374e-06,
1556
+ "loss": 0.6283,
1557
+ "step": 221
1558
+ },
1559
+ {
1560
+ "epoch": 1.7791164658634537,
1561
+ "grad_norm": 0.5072835087776184,
1562
+ "learning_rate": 6.180866407751595e-06,
1563
+ "loss": 0.5435,
1564
+ "step": 222
1565
+ },
1566
+ {
1567
+ "epoch": 1.78714859437751,
1568
+ "grad_norm": 0.5388532280921936,
1569
+ "learning_rate": 5.735850890782157e-06,
1570
+ "loss": 0.6392,
1571
+ "step": 223
1572
+ },
1573
+ {
1574
+ "epoch": 1.7951807228915664,
1575
+ "grad_norm": 0.5281851887702942,
1576
+ "learning_rate": 5.306987050489442e-06,
1577
+ "loss": 0.6308,
1578
+ "step": 224
1579
+ },
1580
+ {
1581
+ "epoch": 1.8032128514056225,
1582
+ "grad_norm": 0.4928033947944641,
1583
+ "learning_rate": 4.8943483704846475e-06,
1584
+ "loss": 0.5549,
1585
+ "step": 225
1586
+ },
1587
+ {
1588
+ "epoch": 1.8112449799196786,
1589
+ "grad_norm": 0.5024735331535339,
1590
+ "learning_rate": 4.498005554281337e-06,
1591
+ "loss": 0.6204,
1592
+ "step": 226
1593
+ },
1594
+ {
1595
+ "epoch": 1.819277108433735,
1596
+ "grad_norm": 0.5138055682182312,
1597
+ "learning_rate": 4.118026513180695e-06,
1598
+ "loss": 0.6869,
1599
+ "step": 227
1600
+ },
1601
+ {
1602
+ "epoch": 1.8273092369477912,
1603
+ "grad_norm": 0.5072734355926514,
1604
+ "learning_rate": 3.7544763546352834e-06,
1605
+ "loss": 0.6442,
1606
+ "step": 228
1607
+ },
1608
+ {
1609
+ "epoch": 1.8353413654618473,
1610
+ "grad_norm": 0.5381031036376953,
1611
+ "learning_rate": 3.40741737109318e-06,
1612
+ "loss": 0.6542,
1613
+ "step": 229
1614
+ },
1615
+ {
1616
+ "epoch": 1.8433734939759037,
1617
+ "grad_norm": 0.5466237664222717,
1618
+ "learning_rate": 3.0769090293245705e-06,
1619
+ "loss": 0.6344,
1620
+ "step": 230
1621
+ },
1622
+ {
1623
+ "epoch": 1.8514056224899598,
1624
+ "grad_norm": 0.5064017176628113,
1625
+ "learning_rate": 2.7630079602323442e-06,
1626
+ "loss": 0.576,
1627
+ "step": 231
1628
+ },
1629
+ {
1630
+ "epoch": 1.859437751004016,
1631
+ "grad_norm": 0.5045104622840881,
1632
+ "learning_rate": 2.465767949148734e-06,
1633
+ "loss": 0.5898,
1634
+ "step": 232
1635
+ },
1636
+ {
1637
+ "epoch": 1.8674698795180724,
1638
+ "grad_norm": 0.5149812698364258,
1639
+ "learning_rate": 2.1852399266194314e-06,
1640
+ "loss": 0.6054,
1641
+ "step": 233
1642
+ },
1643
+ {
1644
+ "epoch": 1.8755020080321285,
1645
+ "grad_norm": 0.49734801054000854,
1646
+ "learning_rate": 1.921471959676957e-06,
1647
+ "loss": 0.5815,
1648
+ "step": 234
1649
+ },
1650
+ {
1651
+ "epoch": 1.8835341365461846,
1652
+ "grad_norm": 0.6586103439331055,
1653
+ "learning_rate": 1.6745092436045494e-06,
1654
+ "loss": 0.6128,
1655
+ "step": 235
1656
+ },
1657
+ {
1658
+ "epoch": 1.891566265060241,
1659
+ "grad_norm": 0.5035130381584167,
1660
+ "learning_rate": 1.444394094192225e-06,
1661
+ "loss": 0.5911,
1662
+ "step": 236
1663
+ },
1664
+ {
1665
+ "epoch": 1.8995983935742973,
1666
+ "grad_norm": 0.48038026690483093,
1667
+ "learning_rate": 1.231165940486234e-06,
1668
+ "loss": 0.5497,
1669
+ "step": 237
1670
+ },
1671
+ {
1672
+ "epoch": 1.9076305220883534,
1673
+ "grad_norm": 0.5178364515304565,
1674
+ "learning_rate": 1.0348613180329757e-06,
1675
+ "loss": 0.5481,
1676
+ "step": 238
1677
+ },
1678
+ {
1679
+ "epoch": 1.9156626506024095,
1680
+ "grad_norm": 0.5295966863632202,
1681
+ "learning_rate": 8.555138626189618e-07,
1682
+ "loss": 0.6499,
1683
+ "step": 239
1684
+ },
1685
+ {
1686
+ "epoch": 1.9236947791164658,
1687
+ "grad_norm": 0.4835861325263977,
1688
+ "learning_rate": 6.931543045073708e-07,
1689
+ "loss": 0.5878,
1690
+ "step": 240
1691
+ },
1692
+ {
1693
+ "epoch": 1.9317269076305221,
1694
+ "grad_norm": 0.5067093372344971,
1695
+ "learning_rate": 5.478104631726711e-07,
1696
+ "loss": 0.6487,
1697
+ "step": 241
1698
+ },
1699
+ {
1700
+ "epoch": 1.9397590361445785,
1701
+ "grad_norm": 0.48038163781166077,
1702
+ "learning_rate": 4.1950724253383423e-07,
1703
+ "loss": 0.6515,
1704
+ "step": 242
1705
+ },
1706
+ {
1707
+ "epoch": 1.9477911646586346,
1708
+ "grad_norm": 0.5362065434455872,
1709
+ "learning_rate": 3.0826662668720364e-07,
1710
+ "loss": 0.6896,
1711
+ "step": 243
1712
+ },
1713
+ {
1714
+ "epoch": 1.9558232931726907,
1715
+ "grad_norm": 0.5073680877685547,
1716
+ "learning_rate": 2.141076761396521e-07,
1717
+ "loss": 0.6568,
1718
+ "step": 244
1719
+ },
1720
+ {
1721
+ "epoch": 1.963855421686747,
1722
+ "grad_norm": 0.5293211936950684,
1723
+ "learning_rate": 1.3704652454261668e-07,
1724
+ "loss": 0.6856,
1725
+ "step": 245
1726
+ },
1727
+ {
1728
+ "epoch": 1.9718875502008033,
1729
+ "grad_norm": 0.531893253326416,
1730
+ "learning_rate": 7.709637592770991e-08,
1731
+ "loss": 0.6341,
1732
+ "step": 246
1733
+ },
1734
+ {
1735
+ "epoch": 1.9799196787148594,
1736
+ "grad_norm": 0.5639507174491882,
1737
+ "learning_rate": 3.4267502444274015e-08,
1738
+ "loss": 0.575,
1739
+ "step": 247
1740
+ },
1741
+ {
1742
+ "epoch": 1.9879518072289155,
1743
+ "grad_norm": 0.5526799559593201,
1744
+ "learning_rate": 8.567242599299973e-09,
1745
+ "loss": 0.5863,
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": 2.076861462767539e+16,
1767
+ "train_batch_size": 2,
1768
+ "trial_name": null,
1769
+ "trial_params": null
1770
+ }
brats_medgemma_r4_alpha4_20251014_013202/checkpoint-248/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aef673004b927be1e530633d7230c2c181df96cd9d85522d8c0c8590ffd08d49
3
+ size 6353
brats_medgemma_r4_alpha4_20251014_013202/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": 4,
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_r4_alpha4_20251014_013202/lora_adapters/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f558f4044e0417e9a105a066162f260579ac07f605804d97c21771ca4bbf31c
3
+ size 38621072
brats_medgemma_r4_alpha4_20251014_013202/lora_adapters/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
brats_medgemma_r4_alpha4_20251014_013202/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_r4_alpha4_20251014_013202/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_r4_alpha4_20251014_013202/lora_adapters/processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_length": 256,
3
+ "processor_class": "Gemma3Processor"
4
+ }
brats_medgemma_r4_alpha4_20251014_013202/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_r4_alpha4_20251014_013202/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_r4_alpha4_20251014_013202/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_r4_alpha4_20251014_013202/lora_adapters/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
brats_medgemma_r4_alpha4_20251014_013202/merged_model/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
brats_medgemma_r4_alpha4_20251014_013202/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_r4_alpha4_20251014_013202/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_r4_alpha4_20251014_013202/merged_model/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc1c678703b55a58e986628e039b29877adc300cdb09899abb8e206006da8f14
3
+ size 4961251752
brats_medgemma_r4_alpha4_20251014_013202/merged_model/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b5947f34a56c5c9ab5f951899614dea1ffd683f1f0a97833cbae4406523a8e1
3
+ size 3639026128
brats_medgemma_r4_alpha4_20251014_013202/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_r4_alpha4_20251014_013202/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_r4_alpha4_20251014_013202/merged_model/processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_length": 256,
3
+ "processor_class": "Gemma3Processor"
4
+ }
brats_medgemma_r4_alpha4_20251014_013202/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_r4_alpha4_20251014_013202/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_r4_alpha4_20251014_013202/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_r4_alpha4_20251014_013202/merged_model/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
brats_medgemma_r4_alpha4_20251014_013202/metrics/complete_data_distribution_20251014_013202.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "experiment_metadata": {
3
+ "timestamp": "20251014_013202",
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_r4_alpha4_20251014_013202/metrics/test_detailed_20251014_013202.csv ADDED
The diff for this file is too large to render. See raw diff
 
brats_medgemma_r4_alpha4_20251014_013202/metrics/test_summary_20251014_013202.csv ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ Metric,Score
2
+ ROUGE1,0.611715
3
+ ROUGE2,0.328585
4
+ ROUGEL,0.445056
brats_medgemma_r4_alpha4_20251014_013202/metrics/training_log_20251014_013202.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+00,0.8808,4.48,2025-10-14 01:34:04
3
+ 2,0.0161,3.531500,2.50e-05,0.6116,7.30,2025-10-14 01:34:07
4
+ 3,0.0241,3.463200,5.00e-05,0.5584,10.35,2025-10-14 01:34:10
5
+ 4,0.0321,3.560200,7.50e-05,0.7048,13.12,2025-10-14 01:34:13
6
+ 5,0.0402,3.620300,1.00e-04,0.7665,15.95,2025-10-14 01:34:16
7
+ 6,0.0482,3.501500,1.25e-04,0.7921,18.98,2025-10-14 01:34:19
8
+ 7,0.0562,3.530700,1.50e-04,0.8905,21.67,2025-10-14 01:34:21
9
+ 8,0.0643,3.357300,1.75e-04,0.8148,24.51,2025-10-14 01:34:24
10
+ 9,0.0723,3.246600,2.00e-04,0.8469,27.45,2025-10-14 01:34:27
11
+ 10,0.0803,3.021200,2.00e-04,0.8541,57.26,2025-10-14 01:34:57
12
+ 11,0.0884,2.913500,2.00e-04,0.8686,59.98,2025-10-14 01:35:00
13
+ 12,0.0964,2.885300,2.00e-04,0.8775,63.04,2025-10-14 01:35:03
14
+ 13,0.1044,2.650600,2.00e-04,0.9171,65.80,2025-10-14 01:35:05
15
+ 14,0.1124,2.475400,2.00e-04,0.9010,68.52,2025-10-14 01:35:08
16
+ 15,0.1205,2.422600,2.00e-04,1.0508,71.46,2025-10-14 01:35:11
17
+ 16,0.1285,2.310000,2.00e-04,1.0355,74.25,2025-10-14 01:35:14
18
+ 17,0.1365,2.152900,1.99e-04,1.0822,76.90,2025-10-14 01:35:17
19
+ 18,0.1446,2.111200,1.99e-04,1.0545,79.84,2025-10-14 01:35:19
20
+ 19,0.1526,1.973400,1.99e-04,1.0549,82.61,2025-10-14 01:35:22
21
+ 20,0.1606,1.878300,1.99e-04,0.9655,104.30,2025-10-14 01:35:44
22
+ 21,0.1687,1.832400,1.99e-04,0.9079,107.34,2025-10-14 01:35:47
23
+ 22,0.1767,1.689900,1.99e-04,0.9244,110.10,2025-10-14 01:35:50
24
+ 23,0.1847,1.724900,1.98e-04,0.9483,112.78,2025-10-14 01:35:52
25
+ 24,0.1928,1.652600,1.98e-04,0.8867,115.81,2025-10-14 01:35:55
26
+ 25,0.2008,1.560900,1.98e-04,0.8899,118.55,2025-10-14 01:35:58
27
+ 26,0.2088,1.550800,1.98e-04,0.9214,121.27,2025-10-14 01:36:01
28
+ 27,0.2169,1.469800,1.97e-04,0.8538,124.22,2025-10-14 01:36:04
29
+ 28,0.2249,1.340400,1.97e-04,0.8974,126.98,2025-10-14 01:36:07
30
+ 29,0.2329,1.334200,1.97e-04,0.8150,129.70,2025-10-14 01:36:09
31
+ 30,0.2410,1.419900,1.96e-04,0.8968,158.94,2025-10-14 01:36:39
32
+ 31,0.2490,1.224600,1.96e-04,0.7762,161.64,2025-10-14 01:36:41
33
+ 32,0.2570,1.364200,1.96e-04,0.7776,164.31,2025-10-14 01:36:44
34
+ 33,0.2651,1.241400,1.95e-04,0.7426,167.25,2025-10-14 01:36:47
35
+ 34,0.2731,1.099100,1.95e-04,0.7615,169.96,2025-10-14 01:36:50
36
+ 35,0.2811,1.118500,1.94e-04,0.7383,172.64,2025-10-14 01:36:52
37
+ 36,0.2892,1.136700,1.94e-04,0.6655,175.59,2025-10-14 01:36:55
38
+ 37,0.2972,1.028600,1.93e-04,0.6101,178.35,2025-10-14 01:36:58
39
+ 38,0.3052,1.057700,1.93e-04,0.6932,181.14,2025-10-14 01:37:01
40
+ 39,0.3133,0.966600,1.92e-04,0.6668,184.10,2025-10-14 01:37:04
41
+ 40,0.3213,1.093200,1.92e-04,0.6915,208.72,2025-10-14 01:37:28
42
+ 41,0.3293,0.943500,1.91e-04,0.6218,211.40,2025-10-14 01:37:31
43
+ 42,0.3373,0.978800,1.91e-04,0.6409,214.43,2025-10-14 01:37:34
44
+ 43,0.3454,1.007100,1.90e-04,0.6634,217.21,2025-10-14 01:37:37
45
+ 44,0.3534,0.994200,1.90e-04,0.6885,219.94,2025-10-14 01:37:40
46
+ 45,0.3614,0.880700,1.89e-04,0.6983,222.83,2025-10-14 01:37:42
47
+ 46,0.3695,0.934400,1.88e-04,0.6224,225.55,2025-10-14 01:37:45
48
+ 47,0.3775,0.916200,1.88e-04,0.6021,228.28,2025-10-14 01:37:48
49
+ 48,0.3855,0.892700,1.87e-04,0.6043,231.25,2025-10-14 01:37:51
50
+ 49,0.3936,0.924600,1.87e-04,0.6711,233.93,2025-10-14 01:37:54
51
+ 50,0.4016,0.892500,1.86e-04,0.6075,260.20,2025-10-14 01:38:20
52
+ 51,0.4096,0.954500,1.85e-04,0.6122,263.14,2025-10-14 01:38:23
53
+ 52,0.4177,0.858700,1.85e-04,0.5508,265.91,2025-10-14 01:38:26
54
+ 53,0.4257,0.724900,1.84e-04,0.5990,268.64,2025-10-14 01:38:28
55
+ 54,0.4337,0.825500,1.83e-04,0.6276,271.53,2025-10-14 01:38:31
56
+ 55,0.4418,0.801700,1.82e-04,0.6152,274.26,2025-10-14 01:38:34
57
+ 56,0.4498,0.768600,1.82e-04,0.6795,276.98,2025-10-14 01:38:37
58
+ 57,0.4578,0.833200,1.81e-04,0.6654,279.92,2025-10-14 01:38:40
59
+ 58,0.4659,0.727700,1.80e-04,0.6454,282.62,2025-10-14 01:38:42
60
+ 59,0.4739,0.835900,1.79e-04,0.7320,285.38,2025-10-14 01:38:45
61
+ 60,0.4819,0.907700,1.79e-04,0.6626,312.42,2025-10-14 01:39:12
62
+ 61,0.4900,0.743200,1.78e-04,0.7448,315.11,2025-10-14 01:39:15
63
+ 62,0.4980,0.783900,1.77e-04,0.6850,317.83,2025-10-14 01:39:17
64
+ 63,0.5060,0.761600,1.76e-04,0.6296,320.79,2025-10-14 01:39:20
65
+ 64,0.5141,0.787500,1.75e-04,0.6279,323.52,2025-10-14 01:39:23
66
+ 65,0.5221,0.734300,1.74e-04,0.5432,326.28,2025-10-14 01:39:26
67
+ 66,0.5301,0.807600,1.73e-04,0.5295,329.17,2025-10-14 01:39:29
68
+ 67,0.5382,0.789400,1.73e-04,0.5866,331.88,2025-10-14 01:39:31
69
+ 68,0.5462,0.779900,1.72e-04,0.6138,334.64,2025-10-14 01:39:34
70
+ 69,0.5542,0.747600,1.71e-04,0.9545,337.54,2025-10-14 01:39:37
71
+ 70,0.5622,0.775300,1.70e-04,0.6186,366.20,2025-10-14 01:40:06
72
+ 71,0.5703,0.713600,1.69e-04,0.5627,368.96,2025-10-14 01:40:09
73
+ 72,0.5783,0.744700,1.68e-04,0.7153,371.92,2025-10-14 01:40:12
74
+ 73,0.5863,0.687200,1.67e-04,0.6005,374.66,2025-10-14 01:40:14
75
+ 74,0.5944,0.843300,1.66e-04,0.6218,377.38,2025-10-14 01:40:17
76
+ 75,0.6024,0.667000,1.65e-04,0.6378,380.11,2025-10-14 01:40:20
77
+ 76,0.6104,0.798300,1.64e-04,0.5862,382.97,2025-10-14 01:40:23
78
+ 77,0.6185,0.676100,1.63e-04,0.5659,385.67,2025-10-14 01:40:25
79
+ 78,0.6265,0.700000,1.62e-04,0.5006,388.41,2025-10-14 01:40:28
80
+ 79,0.6345,0.693200,1.61e-04,0.5357,391.36,2025-10-14 01:40:31
81
+ 80,0.6426,0.717000,1.60e-04,0.4822,420.40,2025-10-14 01:41:00
82
+ 81,0.6506,0.694300,1.59e-04,0.5075,423.12,2025-10-14 01:41:03
83
+ 82,0.6586,0.709200,1.58e-04,0.5325,426.10,2025-10-14 01:41:06
84
+ 83,0.6667,0.673600,1.57e-04,0.4913,428.85,2025-10-14 01:41:08
85
+ 84,0.6747,0.654900,1.56e-04,0.5002,431.53,2025-10-14 01:41:11
86
+ 85,0.6827,0.711300,1.54e-04,0.5355,434.45,2025-10-14 01:41:14
87
+ 86,0.6908,0.693400,1.53e-04,0.5230,437.20,2025-10-14 01:41:17
88
+ 87,0.6988,0.671600,1.52e-04,0.4624,439.87,2025-10-14 01:41:19
89
+ 88,0.7068,0.576200,1.51e-04,0.4906,442.84,2025-10-14 01:41:22
90
+ 89,0.7149,0.743400,1.50e-04,0.5754,445.63,2025-10-14 01:41:25
91
+ 90,0.7229,0.694200,1.49e-04,0.4883,473.69,2025-10-14 01:41:53
92
+ 91,0.7309,0.743300,1.48e-04,0.5415,476.44,2025-10-14 01:41:56
93
+ 92,0.7390,0.660000,1.47e-04,0.4856,479.19,2025-10-14 01:41:59
94
+ 93,0.7470,0.707700,1.45e-04,0.5313,482.13,2025-10-14 01:42:02
95
+ 94,0.7550,0.686100,1.44e-04,0.5444,484.86,2025-10-14 01:42:04
96
+ 95,0.7631,0.623500,1.43e-04,0.4492,487.57,2025-10-14 01:42:07
97
+ 96,0.7711,0.793700,1.42e-04,0.5403,490.50,2025-10-14 01:42:10
98
+ 97,0.7791,0.663600,1.41e-04,0.4702,493.25,2025-10-14 01:42:13
99
+ 98,0.7871,0.674500,1.39e-04,0.4667,495.96,2025-10-14 01:42:16
100
+ 99,0.7952,0.642900,1.38e-04,0.4637,498.90,2025-10-14 01:42:18
101
+ 100,0.8032,0.750100,1.37e-04,0.4946,526.52,2025-10-14 01:42:46
102
+ 101,0.8112,0.676200,1.36e-04,0.4674,529.21,2025-10-14 01:42:49
103
+ 102,0.8193,0.644400,1.35e-04,0.4377,532.18,2025-10-14 01:42:52
104
+ 103,0.8273,0.695800,1.33e-04,0.4977,534.93,2025-10-14 01:42:55
105
+ 104,0.8353,0.765600,1.32e-04,0.5217,537.64,2025-10-14 01:42:57
106
+ 105,0.8434,0.707200,1.31e-04,0.5547,540.65,2025-10-14 01:43:00
107
+ 106,0.8514,0.732900,1.30e-04,0.4783,543.33,2025-10-14 01:43:03
108
+ 107,0.8594,0.669700,1.28e-04,0.5336,546.09,2025-10-14 01:43:06
109
+ 108,0.8675,0.724100,1.27e-04,0.4853,548.95,2025-10-14 01:43:09
110
+ 109,0.8755,0.703600,1.26e-04,0.4719,551.60,2025-10-14 01:43:11
111
+ 110,0.8835,0.652400,1.25e-04,0.4864,578.57,2025-10-14 01:43:38
112
+ 111,0.8916,0.612300,1.23e-04,0.4784,581.48,2025-10-14 01:43:41
113
+ 112,0.8996,0.682700,1.22e-04,0.5125,584.20,2025-10-14 01:43:44
114
+ 113,0.9076,0.710500,1.21e-04,0.4801,586.91,2025-10-14 01:43:47
115
+ 114,0.9157,0.701900,1.20e-04,0.5098,589.82,2025-10-14 01:43:49
116
+ 115,0.9237,0.726800,1.18e-04,0.5258,592.54,2025-10-14 01:43:52
117
+ 116,0.9317,0.653500,1.17e-04,0.4454,595.23,2025-10-14 01:43:55
118
+ 117,0.9398,0.728700,1.16e-04,0.5008,598.27,2025-10-14 01:43:58
119
+ 118,0.9478,0.700400,1.14e-04,0.4517,600.96,2025-10-14 01:44:01
120
+ 119,0.9558,0.684500,1.13e-04,0.4587,603.70,2025-10-14 01:44:03
121
+ 120,0.9639,0.655000,1.12e-04,0.4729,630.59,2025-10-14 01:44:30
122
+ 121,0.9719,0.777400,1.10e-04,0.5596,633.32,2025-10-14 01:44:33
123
+ 122,0.9799,0.677800,1.09e-04,0.5082,636.07,2025-10-14 01:44:36
124
+ 123,0.9880,0.800100,1.08e-04,0.4682,639.04,2025-10-14 01:44:39
125
+ 124,0.9960,0.661100,1.07e-04,0.4537,641.74,2025-10-14 01:44:41
126
+ 125,1.0000,0.617800,1.05e-04,0.6157,643.03,2025-10-14 01:44:43
127
+ 126,1.0080,0.721900,1.04e-04,0.4707,645.86,2025-10-14 01:44:45
128
+ 127,1.0161,0.694500,1.03e-04,0.4390,648.81,2025-10-14 01:44:48
129
+ 128,1.0241,0.637300,1.01e-04,0.4780,651.48,2025-10-14 01:44:51
130
+ 129,1.0321,0.646400,1.00e-04,0.4384,654.19,2025-10-14 01:44:54
131
+ 130,1.0402,0.607900,9.87e-05,0.4397,682.46,2025-10-14 01:45:22
132
+ 131,1.0482,0.654300,9.74e-05,0.4762,685.13,2025-10-14 01:45:25
133
+ 132,1.0562,0.649200,9.61e-05,0.4708,688.19,2025-10-14 01:45:28
134
+ 133,1.0643,0.670400,9.48e-05,0.4843,690.88,2025-10-14 01:45:30
135
+ 134,1.0723,0.712300,9.35e-05,0.5336,693.49,2025-10-14 01:45:33
136
+ 135,1.0803,0.669000,9.22e-05,0.4997,696.18,2025-10-14 01:45:36
137
+ 136,1.0884,0.635000,9.08e-05,0.4626,699.00,2025-10-14 01:45:39
138
+ 137,1.0964,0.646900,8.95e-05,0.4994,701.71,2025-10-14 01:45:41
139
+ 138,1.1044,0.623500,8.82e-05,0.4803,704.47,2025-10-14 01:45:44
140
+ 139,1.1124,0.663400,8.69e-05,0.5140,707.40,2025-10-14 01:45:47
141
+ 140,1.1205,0.658900,8.57e-05,0.4568,732.42,2025-10-14 01:46:12
142
+ 141,1.1285,0.609200,8.44e-05,0.4637,735.14,2025-10-14 01:46:15
143
+ 142,1.1365,0.627600,8.31e-05,0.5026,738.04,2025-10-14 01:46:18
144
+ 143,1.1446,0.621900,8.18e-05,0.4445,740.69,2025-10-14 01:46:20
145
+ 144,1.1526,0.589600,8.05e-05,0.5226,743.40,2025-10-14 01:46:23
146
+ 145,1.1606,0.628300,7.92e-05,0.5189,746.20,2025-10-14 01:46:26
147
+ 146,1.1687,0.628600,7.79e-05,0.5056,748.85,2025-10-14 01:46:28
148
+ 147,1.1767,0.661800,7.67e-05,0.5214,751.60,2025-10-14 01:46:31
149
+ 148,1.1847,0.601500,7.54e-05,0.5382,754.50,2025-10-14 01:46:34
150
+ 149,1.1928,0.556700,7.41e-05,0.4378,757.19,2025-10-14 01:46:37
151
+ 150,1.2008,0.658300,7.29e-05,0.4759,785.67,2025-10-14 01:47:05
152
+ 151,1.2088,0.746600,7.16e-05,0.5303,788.39,2025-10-14 01:47:08
153
+ 152,1.2169,0.611300,7.03e-05,0.5071,791.13,2025-10-14 01:47:11
154
+ 153,1.2249,0.684800,6.91e-05,0.5171,794.00,2025-10-14 01:47:14
155
+ 154,1.2329,0.601000,6.79e-05,0.4832,796.67,2025-10-14 01:47:16
156
+ 155,1.2410,0.646900,6.66e-05,0.4918,799.29,2025-10-14 01:47:19
157
+ 156,1.2490,0.721300,6.54e-05,0.5130,802.24,2025-10-14 01:47:22
158
+ 157,1.2570,0.602200,6.42e-05,0.5033,804.91,2025-10-14 01:47:25
159
+ 158,1.2651,0.571900,6.29e-05,0.4901,807.52,2025-10-14 01:47:27
160
+ 159,1.2731,0.556400,6.17e-05,0.4710,810.22,2025-10-14 01:47:30
161
+ 160,1.2811,0.575400,6.05e-05,0.4719,837.42,2025-10-14 01:47:57
162
+ 161,1.2892,0.641600,5.93e-05,0.4865,840.09,2025-10-14 01:48:00
163
+ 162,1.2972,0.593100,5.81e-05,0.5055,843.13,2025-10-14 01:48:03
164
+ 163,1.3052,0.676200,5.69e-05,0.5162,845.80,2025-10-14 01:48:05
165
+ 164,1.3133,0.564000,5.58e-05,0.5032,848.47,2025-10-14 01:48:08
166
+ 165,1.3213,0.659900,5.46e-05,0.5553,851.34,2025-10-14 01:48:11
167
+ 166,1.3293,0.664500,5.34e-05,0.5489,854.04,2025-10-14 01:48:14
168
+ 167,1.3373,0.592500,5.23e-05,0.5031,856.73,2025-10-14 01:48:16
169
+ 168,1.3454,0.600800,5.11e-05,0.4848,859.72,2025-10-14 01:48:19
170
+ 169,1.3534,0.650600,5.00e-05,0.5353,862.45,2025-10-14 01:48:22
171
+ 170,1.3614,0.649400,4.89e-05,0.5143,888.62,2025-10-14 01:48:48
172
+ 171,1.3695,0.674700,4.78e-05,0.5224,891.43,2025-10-14 01:48:51
173
+ 172,1.3775,0.610700,4.66e-05,0.4901,894.11,2025-10-14 01:48:54
174
+ 173,1.3855,0.628000,4.55e-05,0.4948,896.83,2025-10-14 01:48:56
175
+ 174,1.3936,0.639800,4.44e-05,0.5091,899.83,2025-10-14 01:48:59
176
+ 175,1.4016,0.656700,4.34e-05,0.4988,902.57,2025-10-14 01:49:02
177
+ 176,1.4096,0.600500,4.23e-05,0.4741,905.21,2025-10-14 01:49:05
178
+ 177,1.4177,0.571300,4.12e-05,0.4842,908.12,2025-10-14 01:49:08
179
+ 178,1.4257,0.586400,4.02e-05,0.5017,910.83,2025-10-14 01:49:10
180
+ 179,1.4337,0.601800,3.91e-05,0.5084,913.49,2025-10-14 01:49:13
181
+ 180,1.4418,0.642500,3.81e-05,0.5515,941.91,2025-10-14 01:49:42
182
+ 181,1.4498,0.725400,3.71e-05,0.5663,944.56,2025-10-14 01:49:44
183
+ 182,1.4578,0.623900,3.61e-05,0.5932,947.25,2025-10-14 01:49:47
184
+ 183,1.4659,0.638500,3.51e-05,0.5285,950.22,2025-10-14 01:49:50
185
+ 184,1.4739,0.646000,3.41e-05,0.4932,952.89,2025-10-14 01:49:52
186
+ 185,1.4819,0.625200,3.31e-05,0.4857,955.58,2025-10-14 01:49:55
187
+ 186,1.4900,0.732100,3.21e-05,0.4937,958.48,2025-10-14 01:49:58
188
+ 187,1.4980,0.716800,3.12e-05,0.5535,961.14,2025-10-14 01:50:01
189
+ 188,1.5060,0.654600,3.02e-05,0.5473,963.85,2025-10-14 01:50:03
190
+ 189,1.5141,0.571100,2.93e-05,0.5319,966.57,2025-10-14 01:50:06
191
+ 190,1.5221,0.638500,2.84e-05,0.5225,996.03,2025-10-14 01:50:36
192
+ 191,1.5301,0.623000,2.75e-05,0.5093,998.72,2025-10-14 01:50:38
193
+ 192,1.5382,0.635000,2.66e-05,0.4991,1001.70,2025-10-14 01:50:41
194
+ 193,1.5462,0.574600,2.57e-05,0.5834,1004.39,2025-10-14 01:50:44
195
+ 194,1.5542,0.636700,2.48e-05,0.5148,1007.12,2025-10-14 01:50:47
196
+ 195,1.5622,0.653800,2.40e-05,0.5850,1010.05,2025-10-14 01:50:50
197
+ 196,1.5703,0.608800,2.31e-05,0.4646,1012.76,2025-10-14 01:50:52
198
+ 197,1.5783,0.580800,2.23e-05,0.4936,1015.48,2025-10-14 01:50:55
199
+ 198,1.5863,0.655800,2.15e-05,0.5358,1018.30,2025-10-14 01:50:58
200
+ 199,1.5944,0.610000,2.07e-05,0.4779,1021.01,2025-10-14 01:51:01
201
+ 200,1.6024,0.619800,1.99e-05,0.4932,1048.35,2025-10-14 01:51:28
202
+ 201,1.6104,0.711800,1.91e-05,0.5313,1051.26,2025-10-14 01:51:31
203
+ 202,1.6185,0.636700,1.83e-05,0.4757,1054.00,2025-10-14 01:51:34
204
+ 203,1.6265,0.571100,1.76e-05,0.5013,1056.70,2025-10-14 01:51:36
205
+ 204,1.6345,0.587700,1.69e-05,0.4929,1059.60,2025-10-14 01:51:39
206
+ 205,1.6426,0.652100,1.61e-05,0.5244,1062.32,2025-10-14 01:51:42
207
+ 206,1.6506,0.631000,1.54e-05,0.5257,1065.03,2025-10-14 01:51:45
208
+ 207,1.6586,0.590800,1.47e-05,0.5347,1067.98,2025-10-14 01:51:48
209
+ 208,1.6667,0.592200,1.41e-05,0.4968,1070.68,2025-10-14 01:51:50
210
+ 209,1.6747,0.703300,1.34e-05,0.5799,1073.31,2025-10-14 01:51:53
211
+ 210,1.6827,0.610900,1.28e-05,0.5226,1101.49,2025-10-14 01:52:21
212
+ 211,1.6908,0.632300,1.21e-05,0.5069,1104.14,2025-10-14 01:52:24
213
+ 212,1.6988,0.662500,1.15e-05,0.4945,1106.86,2025-10-14 01:52:26
214
+ 213,1.7068,0.621800,1.09e-05,0.5502,1109.76,2025-10-14 01:52:29
215
+ 214,1.7149,0.645100,1.03e-05,0.4816,1112.42,2025-10-14 01:52:32
216
+ 215,1.7229,0.587300,9.74e-06,0.5142,1115.04,2025-10-14 01:52:35
217
+ 216,1.7309,0.637500,9.19e-06,0.5545,1117.90,2025-10-14 01:52:37
218
+ 217,1.7390,0.688400,8.65e-06,0.5388,1120.58,2025-10-14 01:52:40
219
+ 218,1.7470,0.602600,8.12e-06,0.5042,1123.24,2025-10-14 01:52:43
220
+ 219,1.7550,0.642800,7.61e-06,0.4901,1126.21,2025-10-14 01:52:46
221
+ 220,1.7631,0.648700,7.12e-06,0.5416,1154.90,2025-10-14 01:53:14
222
+ 221,1.7711,0.628300,6.64e-06,0.5362,1157.61,2025-10-14 01:53:17
223
+ 222,1.7791,0.543500,6.18e-06,0.5073,1160.62,2025-10-14 01:53:20
224
+ 223,1.7871,0.639200,5.74e-06,0.5389,1163.36,2025-10-14 01:53:23
225
+ 224,1.7952,0.630800,5.31e-06,0.5282,1165.98,2025-10-14 01:53:26
226
+ 225,1.8032,0.554900,4.89e-06,0.4928,1168.87,2025-10-14 01:53:28
227
+ 226,1.8112,0.620400,4.50e-06,0.5025,1171.58,2025-10-14 01:53:31
228
+ 227,1.8193,0.686900,4.12e-06,0.5138,1174.29,2025-10-14 01:53:34
229
+ 228,1.8273,0.644200,3.75e-06,0.5073,1177.18,2025-10-14 01:53:37
230
+ 229,1.8353,0.654200,3.41e-06,0.5381,1179.90,2025-10-14 01:53:39
231
+ 230,1.8434,0.634400,3.08e-06,0.5466,1208.24,2025-10-14 01:54:08
232
+ 231,1.8514,0.576000,2.76e-06,0.5064,1211.13,2025-10-14 01:54:11
233
+ 232,1.8594,0.589800,2.47e-06,0.5045,1213.85,2025-10-14 01:54:13
234
+ 233,1.8675,0.605400,2.19e-06,0.5150,1216.54,2025-10-14 01:54:16
235
+ 234,1.8755,0.581500,1.92e-06,0.4973,1219.43,2025-10-14 01:54:19
236
+ 235,1.8835,0.612800,1.67e-06,0.6586,1222.12,2025-10-14 01:54:22
237
+ 236,1.8916,0.591100,1.44e-06,0.5035,1224.87,2025-10-14 01:54:24
238
+ 237,1.8996,0.549700,1.23e-06,0.4804,1227.80,2025-10-14 01:54:27
239
+ 238,1.9076,0.548100,1.03e-06,0.5178,1230.51,2025-10-14 01:54:30
240
+ 239,1.9157,0.649900,8.56e-07,0.5296,1233.20,2025-10-14 01:54:33
241
+ 240,1.9237,0.587800,6.93e-07,0.4836,1258.82,2025-10-14 01:54:58
242
+ 241,1.9317,0.648700,5.48e-07,0.5067,1261.49,2025-10-14 01:55:01
243
+ 242,1.9398,0.651500,4.20e-07,0.4804,1264.20,2025-10-14 01:55:04
244
+ 243,1.9478,0.689600,3.08e-07,0.5362,1267.19,2025-10-14 01:55:07
245
+ 244,1.9558,0.656800,2.14e-07,0.5074,1269.94,2025-10-14 01:55:10
246
+ 245,1.9639,0.685600,1.37e-07,0.5293,1272.66,2025-10-14 01:55:12
247
+ 246,1.9719,0.634100,7.71e-08,0.5319,1275.52,2025-10-14 01:55:15
248
+ 247,1.9799,0.575000,3.43e-08,0.5640,1278.22,2025-10-14 01:55:18
249
+ 248,1.9880,0.586300,8.57e-09,0.5527,1280.85,2025-10-14 01:55:20
brats_medgemma_r4_alpha4_20251014_013202/metrics/training_summary_20251014_013202.csv ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Metric,Value
2
+ Timestamp,20251014_013202
3
+ Training Time (s),1281.65
4
+ Training Time (min),21.36
5
+ Final Loss,0.9130522214597271
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,4
13
+ LoRA Alpha,4
14
+ Batch Size,2
15
+ Gradient Accumulation,4
16
+ Validation Every N Steps,10
brats_medgemma_r4_alpha4_20251014_013202/metrics/validation_during_training_20251014_013202.json ADDED
The diff for this file is too large to render. See raw diff
 
brats_medgemma_r4_alpha4_20251014_013202/metrics/validation_log_20251014_013202.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,0.3655,0.1026,0.2234,0.2305
4
+ 10,0.0803,16,BraTS20_Training_199,three_slices,0.3024,0.0493,0.1659,0.1725
5
+ 20,0.1606,42,BraTS20_Training_165,three_slices,0.5185,0.1869,0.2963,0.3339
6
+ 20,0.1606,27,BraTS20_Training_128,three_slices,0.3441,0.0652,0.1720,0.1938
7
+ 20,0.1606,51,BraTS20_Training_146,single_slice,0.1067,0.0000,0.0933,0.0667
8
+ 30,0.2410,39,BraTS20_Training_107,single_slice,0.4304,0.0936,0.2447,0.2562
9
+ 30,0.2410,75,BraTS20_Training_347,five_slices,0.5333,0.1731,0.2857,0.3307
10
+ 30,0.2410,108,BraTS20_Training_279,three_slices,0.4478,0.1608,0.3184,0.3090
11
+ 40,0.3213,45,BraTS20_Training_364,single_slice,0.6524,0.3676,0.4171,0.4790
12
+ 40,0.3213,31,BraTS20_Training_080,single_slice,0.5347,0.2900,0.4059,0.4102
13
+ 40,0.3213,99,BraTS20_Training_329,five_slices,0.5320,0.2587,0.3547,0.3818
14
+ 50,0.4016,108,BraTS20_Training_279,three_slices,0.5030,0.2424,0.3832,0.3762
15
+ 50,0.4016,60,BraTS20_Training_366,single_slice,0.5600,0.2511,0.3289,0.3800
16
+ 50,0.4016,90,BraTS20_Training_248,five_slices,0.6573,0.3412,0.4507,0.4831
17
+ 60,0.4819,65,BraTS20_Training_368,five_slices,0.7006,0.4258,0.5605,0.5623
18
+ 60,0.4819,52,BraTS20_Training_239,five_slices,0.5078,0.2408,0.3938,0.3808
19
+ 60,0.4819,86,BraTS20_Training_121,single_slice,0.6079,0.3289,0.4053,0.4474
20
+ 70,0.5622,33,BraTS20_Training_214,five_slices,0.5926,0.2897,0.4537,0.4453
21
+ 70,0.5622,109,BraTS20_Training_178,three_slices,0.6027,0.3134,0.4201,0.4454
22
+ 70,0.5622,34,BraTS20_Training_116,three_slices,0.5872,0.3148,0.4771,0.4597
23
+ 80,0.6426,28,BraTS20_Training_271,three_slices,0.5315,0.2727,0.4324,0.4122
24
+ 80,0.6426,13,BraTS20_Training_132,three_slices,0.6725,0.4493,0.5240,0.5486
25
+ 80,0.6426,38,BraTS20_Training_040,single_slice,0.6078,0.3168,0.4412,0.4553
26
+ 90,0.7229,108,BraTS20_Training_279,three_slices,0.5865,0.3010,0.4423,0.4433
27
+ 90,0.7229,24,BraTS20_Training_139,five_slices,0.6083,0.3628,0.4516,0.4742
28
+ 90,0.7229,40,BraTS20_Training_192,three_slices,0.5437,0.2745,0.3883,0.4022
29
+ 100,0.8032,73,BraTS20_Training_111,single_slice,0.5745,0.3011,0.4149,0.4301
30
+ 100,0.8032,95,BraTS20_Training_039,single_slice,0.5747,0.3605,0.4483,0.4612
31
+ 100,0.8032,14,BraTS20_Training_259,five_slices,0.6579,0.3451,0.4825,0.4952
32
+ 110,0.8835,15,BraTS20_Training_343,five_slices,0.6489,0.3677,0.4622,0.4929
33
+ 110,0.8835,75,BraTS20_Training_347,five_slices,0.6804,0.4271,0.5258,0.5444
34
+ 110,0.8835,82,BraTS20_Training_301,five_slices,0.6854,0.4739,0.5258,0.5617
35
+ 120,0.9639,28,BraTS20_Training_271,three_slices,0.5905,0.3462,0.4762,0.4709
36
+ 120,0.9639,42,BraTS20_Training_165,three_slices,0.6571,0.3558,0.5143,0.5091
37
+ 120,0.9639,3,BraTS20_Training_355,single_slice,0.6296,0.3625,0.4938,0.4953
38
+ 130,1.0402,14,BraTS20_Training_259,five_slices,0.6638,0.3524,0.4716,0.4959
39
+ 130,1.0402,35,BraTS20_Training_178,single_slice,0.6535,0.3500,0.4059,0.4698
40
+ 130,1.0402,106,BraTS20_Training_004,three_slices,0.6211,0.3298,0.4842,0.4784
41
+ 140,1.1205,71,BraTS20_Training_367,five_slices,0.6058,0.3107,0.4038,0.4401
42
+ 140,1.1205,5,BraTS20_Training_344,single_slice,0.6354,0.3895,0.4792,0.5014
43
+ 140,1.1205,3,BraTS20_Training_355,single_slice,0.6105,0.2979,0.4105,0.4396
44
+ 150,1.2008,94,BraTS20_Training_091,three_slices,0.6944,0.3925,0.5000,0.5290
45
+ 150,1.2008,20,BraTS20_Training_130,three_slices,0.6533,0.4162,0.5327,0.5341
46
+ 150,1.2008,102,BraTS20_Training_274,three_slices,0.6235,0.3837,0.4858,0.4977
47
+ 160,1.2811,107,BraTS20_Training_145,five_slices,0.6697,0.3796,0.4954,0.5149
48
+ 160,1.2811,72,BraTS20_Training_203,three_slices,0.6070,0.3451,0.4514,0.4678
49
+ 160,1.2811,30,BraTS20_Training_300,five_slices,0.6054,0.3497,0.4649,0.4733
50
+ 170,1.3614,62,BraTS20_Training_122,five_slices,0.5952,0.3855,0.5119,0.4976
51
+ 170,1.3614,70,BraTS20_Training_244,three_slices,0.6364,0.3367,0.4444,0.4725
52
+ 170,1.3614,109,BraTS20_Training_178,three_slices,0.6518,0.4054,0.4732,0.5101
53
+ 180,1.4418,37,BraTS20_Training_296,five_slices,0.6837,0.4124,0.5306,0.5422
54
+ 180,1.4418,68,BraTS20_Training_215,three_slices,0.6119,0.3134,0.4201,0.4484
55
+ 180,1.4418,17,BraTS20_Training_211,five_slices,0.6415,0.3524,0.5189,0.5043
56
+ 190,1.5221,27,BraTS20_Training_128,three_slices,0.6038,0.3714,0.4434,0.4729
57
+ 190,1.5221,63,BraTS20_Training_236,single_slice,0.6140,0.3099,0.4279,0.4506
58
+ 190,1.5221,75,BraTS20_Training_347,five_slices,0.6029,0.3575,0.4211,0.4605
59
+ 200,1.6024,93,BraTS20_Training_321,five_slices,0.6091,0.2844,0.4455,0.4463
60
+ 200,1.6024,74,BraTS20_Training_180,single_slice,0.6238,0.2900,0.4059,0.4399
61
+ 200,1.6024,72,BraTS20_Training_203,three_slices,0.5806,0.2927,0.4355,0.4363
62
+ 210,1.6827,59,BraTS20_Training_260,single_slice,0.5659,0.3251,0.4195,0.4368
63
+ 210,1.6827,85,BraTS20_Training_369,five_slices,0.6733,0.3700,0.4554,0.4996
64
+ 210,1.6827,1,BraTS20_Training_060,three_slices,0.5761,0.3297,0.4674,0.4577
65
+ 220,1.7631,49,BraTS20_Training_110,three_slices,0.5517,0.3256,0.4483,0.4419
66
+ 220,1.7631,60,BraTS20_Training_366,single_slice,0.6575,0.3318,0.4932,0.4942
67
+ 220,1.7631,32,BraTS20_Training_101,five_slices,0.6855,0.3821,0.4919,0.5198
68
+ 230,1.8434,83,BraTS20_Training_320,three_slices,0.6316,0.3865,0.4689,0.4957
69
+ 230,1.8434,94,BraTS20_Training_091,three_slices,0.7048,0.4231,0.4762,0.5347
70
+ 230,1.8434,43,BraTS20_Training_114,five_slices,0.5591,0.3370,0.4731,0.4564
71
+ 240,1.9237,10,BraTS20_Training_327,three_slices,0.6702,0.3548,0.4681,0.4977
72
+ 240,1.9237,31,BraTS20_Training_080,single_slice,0.6073,0.3492,0.4817,0.4794
73
+ 240,1.9237,53,BraTS20_Training_048,five_slices,0.6792,0.4095,0.5189,0.5359