Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b4089db51dba3c7f223792ff96051949578c26e1cd177e010cc0aa729b07b67
+oid sha256:1701a394eec83a9c16e62ec2810f0b72b874d191d5ea92e6a391d94e59f62bec
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ff8ba741ea06e706717125ffea602205b7ff63df115036aa75d31a6720306e3
+oid sha256:9da9826cce678f496a1ea9e48794cc5c8a370ca05520a4697766740438acddab
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8b9b6badf82db46d1afb5e463fa9ca385e6cab4d92437e70b31d4e702e65eab
+oid sha256:1a005e67c70b300688558c9ae551f1ceb224a0037246defb2b9be6e0c48e9432
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b692598e0cddf639967ebca2de6f76b238eb32b2c42d9a157c871f5645b68a05
+oid sha256:2a4402fac937bba61a19df7dad9f40c6b804a52f9f2f24d6545bc9c5cb9b8deb
 size 1089994880

trainer_log.jsonl

@@ -20,3 +20,14 @@
 {"current_steps": 20, "total_steps": 70, "loss": 0.7161, "lr": 1.7971325072229227e-05, "epoch": 1.92, "percentage": 28.57, "elapsed_time": "0:42:22", "remaining_time": "1:45:56"}
 {"current_steps": 21, "total_steps": 70, "loss": 0.6909, "lr": 1.766044443118978e-05, "epoch": 2.016, "percentage": 30.0, "elapsed_time": "0:45:11", "remaining_time": "1:45:27"}
 {"current_steps": 22, "total_steps": 70, "loss": 0.6475, "lr": 1.7330518718298263e-05, "epoch": 2.112, "percentage": 31.43, "elapsed_time": "0:47:15", "remaining_time": "1:43:05"}
+{"current_steps": 23, "total_steps": 70, "loss": 0.6636, "lr": 1.698236818086073e-05, "epoch": 2.208, "percentage": 32.86, "elapsed_time": "0:49:20", "remaining_time": "1:40:49"}
+{"current_steps": 24, "total_steps": 70, "loss": 0.6467, "lr": 1.6616858375968596e-05, "epoch": 2.304, "percentage": 34.29, "elapsed_time": "0:51:20", "remaining_time": "1:38:24"}
+{"current_steps": 25, "total_steps": 70, "loss": 0.6541, "lr": 1.6234898018587336e-05, "epoch": 2.4, "percentage": 35.71, "elapsed_time": "0:53:33", "remaining_time": "1:36:24"}
+{"current_steps": 26, "total_steps": 70, "loss": 0.6333, "lr": 1.5837436722347902e-05, "epoch": 2.496, "percentage": 37.14, "elapsed_time": "0:55:37", "remaining_time": "1:34:08"}
+{"current_steps": 27, "total_steps": 70, "loss": 0.6312, "lr": 1.5425462638657597e-05, "epoch": 2.592, "percentage": 38.57, "elapsed_time": "0:57:40", "remaining_time": "1:31:51"}
+{"current_steps": 28, "total_steps": 70, "loss": 0.6299, "lr": 1.5000000000000002e-05, "epoch": 2.6879999999999997, "percentage": 40.0, "elapsed_time": "0:59:47", "remaining_time": "1:29:41"}
+{"current_steps": 29, "total_steps": 70, "loss": 0.6349, "lr": 1.4562106573531632e-05, "epoch": 2.784, "percentage": 41.43, "elapsed_time": "1:01:50", "remaining_time": "1:27:25"}
+{"current_steps": 30, "total_steps": 70, "loss": 0.6334, "lr": 1.4112871031306118e-05, "epoch": 2.88, "percentage": 42.86, "elapsed_time": "1:03:49", "remaining_time": "1:25:06"}
+{"current_steps": 31, "total_steps": 70, "loss": 0.6171, "lr": 1.3653410243663953e-05, "epoch": 2.976, "percentage": 44.29, "elapsed_time": "1:05:54", "remaining_time": "1:22:55"}
+{"current_steps": 32, "total_steps": 70, "loss": 0.6123, "lr": 1.3184866502516846e-05, "epoch": 3.072, "percentage": 45.71, "elapsed_time": "1:09:02", "remaining_time": "1:21:58"}
+{"current_steps": 33, "total_steps": 70, "loss": 0.5799, "lr": 1.2708404681430054e-05, "epoch": 3.168, "percentage": 47.14, "elapsed_time": "1:11:05", "remaining_time": "1:19:42"}