Training in progress, step 6188

logs/attn_loss_fn=None, attn_weight=0, gradient_accumulation_steps=1, hs_loss_fn=0, hs_weight=0, learning_rate=0.0004, lr_scheduler_type=constant_with_warmup, max_grad_norm=1.0, num_warmup_steps=0, optim=p/events.out.tfevents.1723837622.5f530b1cf724

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2bf6a6ead10c5a772ebac8c915bc36bc9842bde1d9fc9dfdc766ca668be1b6e
+size 113471

logs/attn_loss_fn=None, attn_weight=0, gradient_accumulation_steps=1, hs_loss_fn=0, hs_weight=0, learning_rate=0.0004, lr_scheduler_type=constant_with_warmup, max_grad_norm=1.0, num_warmup_steps=0, optim=p/events.out.tfevents.1723837870.5f530b1cf724

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1dc174baf3542fd82cc738c3b27f2ff99a71cf40d50a27b20fd29b3505fc2df
+size 2932929

logs/attn_loss_fn=None, attn_weight=0, gradient_accumulation_steps=1, hs_loss_fn=0, hs_weight=0, learning_rate=0.0004, lr_scheduler_type=constant_with_warmup, max_grad_norm=1.0, optim=paged_lion_32bit, per/events.out.tfevents.1723837213.5f530b1cf724

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af6372c99dcd5a721168a26bd2581a892246e65acb46458f81ddf575c800b972
+size 714457

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8236f27d280355613977dc6c414af33af3bdd274e5415fb794aefca02c5a068
+oid sha256:f0b3129753a4f1e6ef5479486773acadac9a831104535e30cbc2eee571eed746
 size 137033984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c33a90eb9480aa927cbf21869e27f2394679c91d8cf35b2f8474deddabfd3300
+oid sha256:6aea223113d76d2e61cb7ff49e4eee5740de5d8273e780264bd6bdc29d927c29
 size 1017948232