BitMar 100M tokens (no memory) - Epoch 8 - 797,458,002 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: 7
-- Tokens processed: 697,775,898
-- Cross-modal similarity: 0.3340
+- Epochs completed: 8
+- Tokens processed: 797,458,002
+- Cross-modal similarity: 0.3342
 - Episodic memory: Disabled
 
 ## Model Architecture
@@ -40,6 +40,6 @@ tokenizer = AutoTokenizer.from_pretrained("estebancarlin/bitmar-no-memory")
 
 
 ## Training Status
-- **Status**: In Progress (Epoch 7)
-- **Tokens Processed**: 697,775,898
-- **Best Cross-modal Similarity**: 0.3340
+- **Status**: In Progress (Epoch 8)
+- **Tokens Processed**: 797,458,002
+- **Best Cross-modal Similarity**: 0.3342

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7c0255243f07e53cb5ae469ff79780ff268d73271e3456d411686e5933b0c40
+oid sha256:85d8b2614e03b5b9cf65e84a6e7cc5d4b0ad52e581f076a0c041c1f250fc3300
 size 85226595

training_metadata.json

@@ -1,9 +1,9 @@
 {
-  "epoch": 6,
-  "global_step": 116067,
-  "tokens_processed": 697775898,
+  "epoch": 7,
+  "global_step": 132648,
+  "tokens_processed": 797458002,
   "target_tokens": 100000000,
-  "best_similarity": 0.33396559953689575,
+  "best_similarity": 0.33421099185943604,
   "training_config": {
     "model": {
       "vocab_size": 50257,