Training in progress, epoch 9

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90acb670b5270db7dba4a3c836ad1d9ed85664a42a3897b66b607703e7e24f73
+oid sha256:ad4bec8c90fefd5971aaefdfbefa54def6692dcea7a28d2087b843bf1723383d
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4ffc27b3f17ca96e292a8d7b3275c1fe5c46e08099cbc9a1b1d9bff7f462871
+oid sha256:464e14b0d2d171429b144239eb2f6d34a3ce1e32fcd148ce1d352e0b311d9286
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83e2929f298e6336ed712c2dea588810cd80bbd24ce5e1f9fb7aa10d9251ade6
+oid sha256:18cf1b80ded517107ce113b0c6a4e7d8cf9a5820669a7b531987b7574206948e
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc50e8a7fa05d58d7bdfe24a16032eb266f3c6c74b504de19de31e0b385f75c1
+oid sha256:d9dc1ef66fb4636fe8718c372344fcf80b86f3460ebe991645090874787d7404
 size 1089994880

trainer_log.jsonl

@@ -82,3 +82,13 @@
 {"current_steps": 82, "total_steps": 150, "loss": 0.0039, "lr": 2.0232705316027946e-05, "epoch": 8.2, "percentage": 54.67, "elapsed_time": "0:55:17", "remaining_time": "0:45:51"}
 {"current_steps": 83, "total_steps": 150, "loss": 0.005, "lr": 1.9767294683972064e-05, "epoch": 8.3, "percentage": 55.33, "elapsed_time": "0:55:56", "remaining_time": "0:45:09"}
 {"current_steps": 84, "total_steps": 150, "loss": 0.0057, "lr": 1.930201006594999e-05, "epoch": 8.4, "percentage": 56.0, "elapsed_time": "0:56:36", "remaining_time": "0:44:28"}
+{"current_steps": 85, "total_steps": 150, "loss": 0.0041, "lr": 1.8837103421790486e-05, "epoch": 8.5, "percentage": 56.67, "elapsed_time": "0:57:10", "remaining_time": "0:43:43"}
+{"current_steps": 86, "total_steps": 150, "loss": 0.017, "lr": 1.837282650664284e-05, "epoch": 8.6, "percentage": 57.33, "elapsed_time": "0:57:45", "remaining_time": "0:42:59"}
+{"current_steps": 87, "total_steps": 150, "loss": 0.0043, "lr": 1.7909430734646936e-05, "epoch": 8.7, "percentage": 58.0, "elapsed_time": "0:58:14", "remaining_time": "0:42:10"}
+{"current_steps": 88, "total_steps": 150, "loss": 0.0057, "lr": 1.7447167042788108e-05, "epoch": 8.8, "percentage": 58.67, "elapsed_time": "0:58:49", "remaining_time": "0:41:26"}
+{"current_steps": 89, "total_steps": 150, "loss": 0.0049, "lr": 1.698628575501034e-05, "epoch": 8.9, "percentage": 59.33, "elapsed_time": "0:59:33", "remaining_time": "0:40:49"}
+{"current_steps": 90, "total_steps": 150, "loss": 0.0038, "lr": 1.6527036446661396e-05, "epoch": 9.0, "percentage": 60.0, "elapsed_time": "1:00:02", "remaining_time": "0:40:01"}
+{"current_steps": 91, "total_steps": 150, "loss": 0.0016, "lr": 1.6069667809343396e-05, "epoch": 9.1, "percentage": 60.67, "elapsed_time": "1:01:42", "remaining_time": "0:40:00"}
+{"current_steps": 92, "total_steps": 150, "loss": 0.0014, "lr": 1.561442751624193e-05, "epoch": 9.2, "percentage": 61.33, "elapsed_time": "1:02:03", "remaining_time": "0:39:07"}
+{"current_steps": 93, "total_steps": 150, "loss": 0.0014, "lr": 1.5161562088006649e-05, "epoch": 9.3, "percentage": 62.0, "elapsed_time": "1:02:36", "remaining_time": "0:38:22"}
+{"current_steps": 94, "total_steps": 150, "loss": 0.0019, "lr": 1.4711316759255963e-05, "epoch": 9.4, "percentage": 62.67, "elapsed_time": "1:03:03", "remaining_time": "0:37:33"}