Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfe292f59f84a99ed4df6c78ad25352ec0ad9ce4dd630101a3b11bc9996b7e09
+oid sha256:0b04f264e27860068112de2eeed2747e1a05b02eb1df6edfa1739ce89a347277
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3118d2482c35958502a9cf97875b0fa0f8ed54251ca3a0eb14361ddf971daa37
+oid sha256:02a66df03e9422bd4dc47136ad518faa0d2d426eab1dfdc467eb81e83e875784
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb17be43589aabda8ef4240a159dc230bc05d1280e300c2cfa5ecd3519d29226
+oid sha256:91d413ad583d945f6380b0e8875c2e445db6bad7a2e5b25e5cca847bd3523fcb
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ff48e715b98d2c6d1eade2e34d7fb8986433865ec50ae0ad2f7a5baf95c1155
+oid sha256:431860c1b82f4a9b5bc5539558a4be45fa1d3b0ac50c8a6b59336a2aff5fc69b
 size 1089994880

trainer_log.jsonl

@@ -20,3 +20,14 @@
 {"current_steps": 20, "total_steps": 70, "loss": 0.7113, "lr": 1.7971325072229227e-05, "epoch": 1.92, "percentage": 28.57, "elapsed_time": "0:33:51", "remaining_time": "1:24:39"}
 {"current_steps": 21, "total_steps": 70, "loss": 0.7026, "lr": 1.766044443118978e-05, "epoch": 2.016, "percentage": 30.0, "elapsed_time": "0:36:15", "remaining_time": "1:24:36"}
 {"current_steps": 22, "total_steps": 70, "loss": 0.6638, "lr": 1.7330518718298263e-05, "epoch": 2.112, "percentage": 31.43, "elapsed_time": "0:37:59", "remaining_time": "1:22:52"}
+{"current_steps": 23, "total_steps": 70, "loss": 0.6567, "lr": 1.698236818086073e-05, "epoch": 2.208, "percentage": 32.86, "elapsed_time": "0:39:34", "remaining_time": "1:20:52"}
+{"current_steps": 24, "total_steps": 70, "loss": 0.6487, "lr": 1.6616858375968596e-05, "epoch": 2.304, "percentage": 34.29, "elapsed_time": "0:41:15", "remaining_time": "1:19:04"}
+{"current_steps": 25, "total_steps": 70, "loss": 0.6344, "lr": 1.6234898018587336e-05, "epoch": 2.4, "percentage": 35.71, "elapsed_time": "0:42:55", "remaining_time": "1:17:15"}
+{"current_steps": 26, "total_steps": 70, "loss": 0.6484, "lr": 1.5837436722347902e-05, "epoch": 2.496, "percentage": 37.14, "elapsed_time": "0:44:26", "remaining_time": "1:15:12"}
+{"current_steps": 27, "total_steps": 70, "loss": 0.6299, "lr": 1.5425462638657597e-05, "epoch": 2.592, "percentage": 38.57, "elapsed_time": "0:46:03", "remaining_time": "1:13:21"}
+{"current_steps": 28, "total_steps": 70, "loss": 0.6169, "lr": 1.5000000000000002e-05, "epoch": 2.6879999999999997, "percentage": 40.0, "elapsed_time": "0:47:36", "remaining_time": "1:11:24"}
+{"current_steps": 29, "total_steps": 70, "loss": 0.6405, "lr": 1.4562106573531632e-05, "epoch": 2.784, "percentage": 41.43, "elapsed_time": "0:49:12", "remaining_time": "1:09:34"}
+{"current_steps": 30, "total_steps": 70, "loss": 0.6093, "lr": 1.4112871031306118e-05, "epoch": 2.88, "percentage": 42.86, "elapsed_time": "0:50:49", "remaining_time": "1:07:45"}
+{"current_steps": 31, "total_steps": 70, "loss": 0.6015, "lr": 1.3653410243663953e-05, "epoch": 2.976, "percentage": 44.29, "elapsed_time": "0:52:28", "remaining_time": "1:06:00"}
+{"current_steps": 32, "total_steps": 70, "loss": 0.5864, "lr": 1.3184866502516846e-05, "epoch": 3.072, "percentage": 45.71, "elapsed_time": "0:54:57", "remaining_time": "1:05:15"}
+{"current_steps": 33, "total_steps": 70, "loss": 0.5867, "lr": 1.2708404681430054e-05, "epoch": 3.168, "percentage": 47.14, "elapsed_time": "0:56:33", "remaining_time": "1:03:24"}