Training in progress, epoch 1

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa183634b1db9776671d93c253ae7881421724c366652c210aeea7b5d894788
+oid sha256:ebbe14efe580784ef2d4a8d10c70ae1941a7481e531e14d86299a7db46b5ce3a
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7937446cf533a8eb70a89be197b8f7f795241a3f29bdd8615f4732f9163baf80
+oid sha256:bde40f127fb70ad4b2cce347d8e8efda6b8c51d0d5d925cba6b936f6910e8a58
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7bbe168c4e498982c48f88561d1f7f5d93d4f5a1aebbbfc42a6d1b105734660
+oid sha256:fd281ac452aa1b0c543d92e0b78e8cff8976da44b829aabaf0727adabc941d15
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09b7eb9383cd60b35e081e5f711b9f6b5f0e6496877afcd5a2b93109dd5b0eff
+oid sha256:e01304b587dd6f964fca04068c3ec50100379a2645a618a43038cf6c309f9b31
 size 1168138808

trainer_log.jsonl

@@ -4,3 +4,10 @@
 {"current_steps": 40, "total_steps": 165, "loss": 0.6256, "lr": 5e-06, "epoch": 0.7223476297968398, "percentage": 24.24, "elapsed_time": "0:21:29", "remaining_time": "1:07:10"}
 {"current_steps": 50, "total_steps": 165, "loss": 0.6154, "lr": 5e-06, "epoch": 0.9029345372460497, "percentage": 30.3, "elapsed_time": "0:26:48", "remaining_time": "1:01:39"}
 {"current_steps": 55, "total_steps": 165, "eval_loss": 0.5993303656578064, "epoch": 0.9932279909706546, "percentage": 33.33, "elapsed_time": "0:30:18", "remaining_time": "1:00:36"}
+{"current_steps": 60, "total_steps": 165, "loss": 0.6293, "lr": 5e-06, "epoch": 1.0835214446952597, "percentage": 36.36, "elapsed_time": "0:33:58", "remaining_time": "0:59:27"}
+{"current_steps": 70, "total_steps": 165, "loss": 0.5656, "lr": 5e-06, "epoch": 1.2641083521444696, "percentage": 42.42, "elapsed_time": "0:39:17", "remaining_time": "0:53:20"}
+{"current_steps": 80, "total_steps": 165, "loss": 0.5588, "lr": 5e-06, "epoch": 1.4446952595936795, "percentage": 48.48, "elapsed_time": "0:44:38", "remaining_time": "0:47:25"}
+{"current_steps": 90, "total_steps": 165, "loss": 0.561, "lr": 5e-06, "epoch": 1.6252821670428894, "percentage": 54.55, "elapsed_time": "0:49:57", "remaining_time": "0:41:37"}
+{"current_steps": 100, "total_steps": 165, "loss": 0.5526, "lr": 5e-06, "epoch": 1.8058690744920993, "percentage": 60.61, "elapsed_time": "0:55:15", "remaining_time": "0:35:54"}
+{"current_steps": 110, "total_steps": 165, "loss": 0.5525, "lr": 5e-06, "epoch": 1.9864559819413092, "percentage": 66.67, "elapsed_time": "1:00:34", "remaining_time": "0:30:17"}
+{"current_steps": 110, "total_steps": 165, "eval_loss": 0.5813493132591248, "epoch": 1.9864559819413092, "percentage": 66.67, "elapsed_time": "1:01:33", "remaining_time": "0:30:46"}