Upload folder using huggingface_hub

README.md

@@ -3,7 +3,7 @@ base_model:
 - LiquidAI/LFM2-VL-450M
 ---
 
-# model_step_100
+# model_step_300
 
 ## Model Description
 
@@ -11,8 +11,8 @@ This model is a fine-tuned version of **LiquidAI/LFM2-VL-450M** using the brute-
 
 - **Base Model**: LiquidAI/LFM2-VL-450M
 - **Training Status**: 🔄 In Progress
-- **Generated**: 2025-08-14 20:55:09
-- **Training Steps**: 100
+- **Generated**: 2025-08-14 21:03:04
+- **Training Steps**: 300
 
 ## Training Details
 
@@ -29,8 +29,8 @@ This model is a fine-tuned version of **LiquidAI/LFM2-VL-450M** using the brute-
 - **Evaluation Frequency**: Every 100 steps
 
 ### Current Performance
-- **Training Loss**: 4.847933
-- **Evaluation Loss**: 4.821800
+- **Training Loss**: 4.575191
+- **Evaluation Loss**: 4.492388
 
 ## Pre-Training Evaluation
 
@@ -47,22 +47,24 @@ This model is a fine-tuned version of **LiquidAI/LFM2-VL-450M** using the brute-
 |------|----------------|------|------------|----------|----------|--------------------|
 | Pre | pre_training | 5.4191 | 225.67 | 11.4% | 6.9% | +0.0% |
 | 100 | checkpoint | 4.8218 | 124.19 | 10.6% | 6.4% | +11.0% |
+| 200 | checkpoint | 4.6127 | 100.76 | 10.8% | 6.4% | +14.9% |
+| 300 | checkpoint | 4.4924 | 89.33 | 10.6% | 6.4% | +17.1% |
 
 ## Training Progress
 
 ### Recent Training Steps (Loss Only)
 | Step | Training Loss | Timestamp |
 |------|---------------|-----------|
-| 91 | 5.012662 | 2025-08-14T20:51 |
-| 92 | 4.833282 | 2025-08-14T20:52 |
-| 93 | 4.884547 | 2025-08-14T20:52 |
-| 94 | 4.841271 | 2025-08-14T20:52 |
-| 95 | 4.992236 | 2025-08-14T20:52 |
-| 96 | 4.861138 | 2025-08-14T20:52 |
-| 97 | 4.886461 | 2025-08-14T20:52 |
-| 98 | 4.913207 | 2025-08-14T20:52 |
-| 99 | 5.008471 | 2025-08-14T20:52 |
-| 100 | 4.847933 | 2025-08-14T20:52 |
+| 291 | 4.513980 | 2025-08-14T20:59 |
+| 292 | 4.423133 | 2025-08-14T20:59 |
+| 293 | 4.640058 | 2025-08-14T20:59 |
+| 294 | 4.488780 | 2025-08-14T20:59 |
+| 295 | 4.027132 | 2025-08-14T20:59 |
+| 296 | 4.805581 | 2025-08-14T20:59 |
+| 297 | 4.652530 | 2025-08-14T21:00 |
+| 298 | 4.494508 | 2025-08-14T21:00 |
+| 299 | 4.449580 | 2025-08-14T21:00 |
+| 300 | 4.575191 | 2025-08-14T21:00 |
 
 ## Training Visualizations
 
@@ -86,8 +88,8 @@ 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("./model_step_100")
-tokenizer = AutoTokenizer.from_pretrained("./model_step_100")
+model = AutoModelForCausalLM.from_pretrained("./model_step_300")
+tokenizer = AutoTokenizer.from_pretrained("./model_step_300")
 
 # Your inference code here
 ```
@@ -127,4 +129,4 @@ tokenizer = AutoTokenizer.from_pretrained("./model_step_100")
 
 ---
 
-*This model card was automatically generated by brute-force-training on 2025-08-14 20:55:09*
+*This model card was automatically generated by brute-force-training on 2025-08-14 21:03:04*

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73bd67087ca08096ebdeca7389f53fe631c41e9ed1f1a5e286109ea97e089fea
+oid sha256:94846411f2c1171e1ec1a3aff354d161896539bd14085e6bd518449a8c04eaf4
 size 901692416

model_card_metadata.json

@@ -1,8 +1,8 @@
 {
   "base_model": "LiquidAI/LFM2-VL-450M",
   "training_framework": "brute-force-training",
-  "training_date": "2025-08-14T20:55:09.352395",
-  "training_steps": 100,
+  "training_date": "2025-08-14T21:03:04.407697",
+  "training_steps": 300,
   "dataset": "wjbmattingly/medieval-letters-htr-synthetic",
   "training_config": {
     "dataset_name": "wjbmattingly/medieval-letters-htr-synthetic",
@@ -24,8 +24,8 @@
     "user_text": "Transcribe this medieval manuscript line",
     "max_image_size": 200
   },
-  "final_training_loss": 4.847932815551758,
-  "final_evaluation_loss": 4.8217997550964355,
-  "final_char_accuracy": 0.10633391201404206,
-  "final_word_accuracy": 0.06352046181580152
+  "final_training_loss": 4.575191020965576,
+  "final_evaluation_loss": 4.492388168970744,
+  "final_char_accuracy": 0.1061965003999563,
+  "final_word_accuracy": 0.06438001131166525
 }