Training checkpoint 166000 - 1.7B tokens

README.md

@@ -18,9 +18,9 @@ pipeline_tag: text-generation
 
 ## Current Training Status
 
-- **Training Step**: 164,000
-- **Tokens Processed**: 1.68B tokens
-- **Current Loss**: 4.6331
+- **Training Step**: 166,000
+- **Tokens Processed**: 1.70B tokens
+- **Current Loss**: 4.6296
 - **Spike Rate**: 0.0504
 - **Learning Rate**: 1.96e-04
 
@@ -54,7 +54,7 @@ This represents ongoing training of the first large-scale spiking neural network
 from huggingface_hub import hf_hub_download
 checkpoint = hf_hub_download(
     repo_id="rootxhacker/piking-llm-5b-3epochs-exp",
-    filename="checkpoint_164000.pt"
+    filename="checkpoint_166000.pt"
 )
 
 # Load with custom spiking model code
@@ -65,4 +65,4 @@ checkpoint = hf_hub_download(
 
 **🔬 This is live research in progress! Check back for updates as training continues.**
 
-**Training Progress**: 11.2% complete towards 15B tokens
+**Training Progress**: 11.3% complete towards 15B tokens

checkpoint_166000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f86157fcfa2f8f27adcce08a686fa738af9416b8177045632b058645948b8c
+size 999026666

config.json

@@ -4,11 +4,11 @@
   "hidden_size": 768,
   "num_layers": 12,
   "max_seq_length": 1024,
-  "training_step": 164000,
-  "tokens_processed": 1679360000,
-  "loss": 4.63306390764847,
-  "spike_rate": 0.050395141075132543,
-  "learning_rate": 0.00019568966573544215,
-  "epoch": 0.335872,
-  "progress_percent": 11.19576199448404
+  "training_step": 166000,
+  "tokens_processed": 1699840000,
+  "loss": 4.629632774566047,
+  "spike_rate": 0.05042637310659528,
+  "learning_rate": 0.000195561685502401,
+  "epoch": 0.339968,
+  "progress_percent": 11.332295677343602
 }