BitMar 100M tokens (no memory) - Epoch 6 - 598,093,703 tokens processed

README.md

@@ -20,9 +20,9 @@ This model was trained on exactly 100 million tokens as part of the BabyLM chall
 
 ## Training Details
 - Total tokens: 100,000,000
-- Epochs completed: 5
-- Tokens processed: 498,411,339
-- Cross-modal similarity: 0.2932
+- Epochs completed: 6
+- Tokens processed: 598,093,703
+- Cross-modal similarity: 0.3192
 - Episodic memory: Disabled
 
 ## Model Architecture
@@ -40,6 +40,6 @@ tokenizer = AutoTokenizer.from_pretrained("estebancarlin/bitmar-no-memory")
 
 
 ## Training Status
-- **Status**: In Progress (Epoch 5)
-- **Tokens Processed**: 498,411,339
-- **Best Cross-modal Similarity**: 0.2932
+- **Status**: In Progress (Epoch 6)
+- **Tokens Processed**: 598,093,703
+- **Best Cross-modal Similarity**: 0.3192

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fba73a8d54dc75de3f26bb560486ede9461642db6607316f62a1f9f927f11b55
+oid sha256:50a04ec2a46b421c2a94c06fb50eaf4828d2f5cfbd7989b27e817dc41a1a42a8
 size 85226595

training_metadata.json

@@ -1,9 +1,9 @@
 {
-  "epoch": 4,
-  "global_step": 82905,
-  "tokens_processed": 498411339,
+  "epoch": 5,
+  "global_step": 99486,
+  "tokens_processed": 598093703,
   "target_tokens": 100000000,
-  "best_similarity": 0.2931603789329529,
+  "best_similarity": 0.3191567361354828,
   "training_config": {
     "model": {
       "vocab_size": 50257,