Upload folder using huggingface_hub

README.md

@@ -3,16 +3,16 @@ base_model:
 - LiquidAI/LFM2-VL-450M
 ---
 
-# final
+# model_step_7000
 
 ## Model Description
 
 This model is a fine-tuned version of **LiquidAI/LFM2-VL-450M** using the brute-force-training package.
 
 - **Base Model**: LiquidAI/LFM2-VL-450M
-- **Training Status**: ✅ Complete
-- **Generated**: 2025-08-18 19:51:23
-- **Training Steps**: 10,000
+- **Training Status**: 🔄 In Progress
+- **Generated**: 2025-08-18 20:39:32
+- **Training Steps**: 7,000
 
 ## Training Details
 
@@ -24,19 +24,19 @@ This model is a fine-tuned version of **LiquidAI/LFM2-VL-450M** using the brute-
 ### Training Configuration
 - **Max Steps**: 10,000
 - **Batch Size**: 2
-- **Learning Rate**: 5e-06
-- **Gradient Accumulation**: 2 steps
-- **Evaluation Frequency**: Every 1,000 steps
+- **Learning Rate**: 1e-05
+- **Gradient Accumulation**: 1 steps
+- **Evaluation Frequency**: Every 500 steps
 
 ### Current Performance
-- **Training Loss**: 0.918973
-- **Evaluation Loss**: 3.461486
+- **Training Loss**: 0.619257
+- **Evaluation Loss**: 0.722366
 
 ## Pre-Training Evaluation
 
 **Initial Model Performance (before training):**
-- **Loss**: 6.255835
-- **Perplexity**: 521.04
+- **Loss**: 1.297430
+- **Perplexity**: 3.66
 - **Character Accuracy**: 27.7%
 - **Word Accuracy**: 11.6%
 
@@ -45,33 +45,37 @@ This model is a fine-tuned version of **LiquidAI/LFM2-VL-450M** using the brute-
 ### All Checkpoint Evaluations
 | Step | Checkpoint Type | Loss | Perplexity | Char Acc | Word Acc | Improvement vs Pre |
 |------|----------------|------|------------|----------|----------|--------------------|
-| Pre | pre_training | 6.2558 | 521.04 | 27.7% | 11.6% | +0.0% |
-| 1,000 | checkpoint | 4.4533 | 85.91 | 33.8% | 16.1% | +28.8% |
-| 2,000 | checkpoint | 4.1024 | 60.49 | 32.5% | 15.1% | +34.4% |
-| 3,000 | checkpoint | 3.9043 | 49.62 | 33.2% | 16.9% | +37.6% |
-| 4,000 | checkpoint | 3.7561 | 42.78 | 30.9% | 14.2% | +40.0% |
-| 5,000 | checkpoint | 3.6675 | 39.15 | 33.5% | 17.0% | +41.4% |
-| 6,000 | checkpoint | 3.6180 | 37.26 | 31.8% | 15.1% | +42.2% |
-| 7,000 | checkpoint | 3.5651 | 35.34 | 32.2% | 15.6% | +43.0% |
-| 8,000 | checkpoint | 3.5113 | 33.49 | 30.6% | 14.2% | +43.9% |
-| 9,000 | checkpoint | 3.4908 | 32.81 | 33.4% | 16.9% | +44.2% |
-| 10,000 | final | 3.4615 | 31.86 | 32.5% | 16.5% | +44.7% |
+| Pre | pre_training | 1.2974 | 3.66 | 27.7% | 11.6% | +0.0% |
+| 500 | checkpoint | 0.9454 | 2.57 | 39.4% | 19.9% | +27.1% |
+| 1,000 | checkpoint | 0.8644 | 2.37 | 38.7% | 19.1% | +33.4% |
+| 1,500 | checkpoint | 0.8402 | 2.32 | 38.4% | 18.9% | +35.2% |
+| 2,000 | checkpoint | 0.8139 | 2.26 | 37.9% | 19.8% | +37.3% |
+| 2,500 | checkpoint | 0.7890 | 2.20 | 38.5% | 18.9% | +39.2% |
+| 3,000 | checkpoint | 0.7793 | 2.18 | 39.3% | 19.5% | +39.9% |
+| 3,500 | checkpoint | 0.7639 | 2.15 | 42.7% | 21.4% | +41.1% |
+| 4,000 | checkpoint | 0.7483 | 2.11 | 41.2% | 20.4% | +42.3% |
+| 4,500 | checkpoint | 0.7466 | 2.11 | 37.3% | 18.8% | +42.5% |
+| 5,000 | checkpoint | 0.7358 | 2.09 | 40.4% | 20.5% | +43.3% |
+| 5,500 | checkpoint | 0.7321 | 2.08 | 38.1% | 18.9% | +43.6% |
+| 6,000 | checkpoint | 0.7276 | 2.07 | 38.8% | 17.6% | +43.9% |
+| 6,500 | checkpoint | 0.7190 | 2.05 | 41.5% | 18.9% | +44.6% |
+| 7,000 | checkpoint | 0.7224 | 2.06 | 41.6% | 18.7% | +44.3% |
 
 ## Training Progress
 
 ### Recent Training Steps (Loss Only)
 | Step | Training Loss | Timestamp |
 |------|---------------|-----------|
-| 9,991 | 0.764521 | 2025-08-18T19:50 |
-| 9,992 | 0.948460 | 2025-08-18T19:50 |
-| 9,993 | 0.758166 | 2025-08-18T19:50 |
-| 9,994 | 0.898506 | 2025-08-18T19:50 |
-| 9,995 | 0.784889 | 2025-08-18T19:50 |
-| 9,996 | 0.786168 | 2025-08-18T19:50 |
-| 9,997 | 0.674831 | 2025-08-18T19:50 |
-| 9,998 | 0.950868 | 2025-08-18T19:50 |
-| 9,999 | 0.960045 | 2025-08-18T19:50 |
-| 10,000 | 0.918973 | 2025-08-18T19:50 |
+| 6,991 | 0.846698 | 2025-08-18T20:39 |
+| 6,992 | 0.538150 | 2025-08-18T20:39 |
+| 6,993 | 0.721188 | 2025-08-18T20:39 |
+| 6,994 | 0.819544 | 2025-08-18T20:39 |
+| 6,995 | 0.925656 | 2025-08-18T20:39 |
+| 6,996 | 0.724563 | 2025-08-18T20:39 |
+| 6,997 | 0.738329 | 2025-08-18T20:39 |
+| 6,998 | 0.658910 | 2025-08-18T20:39 |
+| 6,999 | 0.439738 | 2025-08-18T20:39 |
+| 7,000 | 0.619257 | 2025-08-18T20:39 |
 
 ## Training Visualizations
 
@@ -95,8 +99,8 @@ This model is a fine-tuned version of **LiquidAI/LFM2-VL-450M** using the brute-
 from transformers import AutoModelForCausalLM, AutoTokenizer
 # For vision-language models, use appropriate imports
 
-model = AutoModelForCausalLM.from_pretrained("./final")
-tokenizer = AutoTokenizer.from_pretrained("./final")
+model = AutoModelForCausalLM.from_pretrained("./model_step_7000")
+tokenizer = AutoTokenizer.from_pretrained("./model_step_7000")
 
 # Your inference code here
 ```
@@ -108,9 +112,9 @@ tokenizer = AutoTokenizer.from_pretrained("./final")
   "dataset_name": "CATMuS/medieval",
   "model_name": "LiquidAI/LFM2-VL-450M",
   "max_steps": 10000,
-  "eval_steps": 1000,
-  "num_accumulation_steps": 2,
-  "learning_rate": 5e-06,
+  "eval_steps": 500,
+  "num_accumulation_steps": 1,
+  "learning_rate": 1e-05,
   "train_batch_size": 2,
   "val_batch_size": 2,
   "train_select_start": 0,
@@ -136,4 +140,4 @@ tokenizer = AutoTokenizer.from_pretrained("./final")
 
 ---
 
-*This model card was automatically generated by brute-force-training on 2025-08-18 19:51:23*
+*This model card was automatically generated by brute-force-training on 2025-08-18 20:39:32*

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d1c7bf9a67a65d0305165d7d04b3a5275ece0b8040925556407941f0b971da8
+oid sha256:4d05714a3806120122abbeed7fd3c4930fe07972e5ed14a4ce6bf7554cf1b5ca
 size 901692416

model_card_metadata.json

@@ -1,16 +1,16 @@
 {
   "base_model": "LiquidAI/LFM2-VL-450M",
   "training_framework": "brute-force-training",
-  "training_date": "2025-08-18T19:51:23.156386",
-  "training_steps": 10000,
+  "training_date": "2025-08-18T20:39:32.801669",
+  "training_steps": 7000,
   "dataset": "CATMuS/medieval",
   "training_config": {
     "dataset_name": "CATMuS/medieval",
     "model_name": "LiquidAI/LFM2-VL-450M",
     "max_steps": 10000,
-    "eval_steps": 1000,
-    "num_accumulation_steps": 2,
-    "learning_rate": 5e-06,
+    "eval_steps": 500,
+    "num_accumulation_steps": 1,
+    "learning_rate": 1e-05,
     "train_batch_size": 2,
     "val_batch_size": 2,
     "train_select_start": 0,
@@ -24,8 +24,8 @@
     "user_text": "Transcribe this medieval manuscript line.",
     "max_image_size": 200
   },
-  "final_training_loss": 0.9189727306365967,
-  "final_evaluation_loss": 3.461486041545868,
-  "final_char_accuracy": 0.3254617025073297,
-  "final_word_accuracy": 0.16456672762721147
+  "final_training_loss": 0.6192573308944702,
+  "final_evaluation_loss": 0.7223658800125122,
+  "final_char_accuracy": 0.41553718527220956,
+  "final_word_accuracy": 0.18711077811077811
 }