Training in progress, epoch 2

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b454d7aa1c5e260fe001807009a96637f6cfc7ebe4166e861e0dce66738c18
+oid sha256:911ef2f5c71fa34660e924bfe4c918371e73f183b06806d8fed1e83e1c19918a
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d1638c1d89f6aa761d277134a7325999c18e3346f992d020671dbd7e437778a
+oid sha256:c64755808368ff73e3557629654cfcd777c703cbe7c8e76e4af732c80445d56c
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f50fa0ec698137419dd7e2f3e9c5177700dd5a1e28fb65c9951e7eaed97a6b9
+oid sha256:2ce3df3b1338d90be56612c89df73acf4260c8bbe36d4f91aaac15a8d907d4a3
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffa6c5f59a3a9fc1f5a523ebeb8bdccacf833f4592faf81567f11a8311c70475
+oid sha256:ba258eb4a7c8aeddeda86232859a9c14157b1d37966a3305f9d3460b4acdfb14
 size 1168138808

trainer_log.jsonl

@@ -20,3 +20,15 @@
 {"current_steps": 190, "total_steps": 309, "loss": 0.454, "lr": 5e-06, "epoch": 1.8401937046004844, "percentage": 61.49, "elapsed_time": "1:43:03", "remaining_time": "1:04:32"}
 {"current_steps": 200, "total_steps": 309, "loss": 0.4499, "lr": 5e-06, "epoch": 1.937046004842615, "percentage": 64.72, "elapsed_time": "1:48:20", "remaining_time": "0:59:02"}
 {"current_steps": 206, "total_steps": 309, "eval_loss": 0.47824251651763916, "epoch": 1.9951573849878934, "percentage": 66.67, "elapsed_time": "1:52:55", "remaining_time": "0:56:27"}
+{"current_steps": 210, "total_steps": 309, "loss": 0.4671, "lr": 5e-06, "epoch": 2.0338983050847457, "percentage": 67.96, "elapsed_time": "1:56:05", "remaining_time": "0:54:43"}
+{"current_steps": 220, "total_steps": 309, "loss": 0.4066, "lr": 5e-06, "epoch": 2.1307506053268765, "percentage": 71.2, "elapsed_time": "2:01:22", "remaining_time": "0:49:06"}
+{"current_steps": 230, "total_steps": 309, "loss": 0.4113, "lr": 5e-06, "epoch": 2.2276029055690074, "percentage": 74.43, "elapsed_time": "2:06:39", "remaining_time": "0:43:30"}
+{"current_steps": 240, "total_steps": 309, "loss": 0.4081, "lr": 5e-06, "epoch": 2.324455205811138, "percentage": 77.67, "elapsed_time": "2:11:56", "remaining_time": "0:37:56"}
+{"current_steps": 250, "total_steps": 309, "loss": 0.407, "lr": 5e-06, "epoch": 2.4213075060532687, "percentage": 80.91, "elapsed_time": "2:17:11", "remaining_time": "0:32:22"}
+{"current_steps": 260, "total_steps": 309, "loss": 0.4051, "lr": 5e-06, "epoch": 2.5181598062953996, "percentage": 84.14, "elapsed_time": "2:22:26", "remaining_time": "0:26:50"}
+{"current_steps": 270, "total_steps": 309, "loss": 0.4109, "lr": 5e-06, "epoch": 2.61501210653753, "percentage": 87.38, "elapsed_time": "2:27:43", "remaining_time": "0:21:20"}
+{"current_steps": 280, "total_steps": 309, "loss": 0.3986, "lr": 5e-06, "epoch": 2.711864406779661, "percentage": 90.61, "elapsed_time": "2:33:00", "remaining_time": "0:15:50"}
+{"current_steps": 290, "total_steps": 309, "loss": 0.4115, "lr": 5e-06, "epoch": 2.8087167070217918, "percentage": 93.85, "elapsed_time": "2:38:19", "remaining_time": "0:10:22"}
+{"current_steps": 300, "total_steps": 309, "loss": 0.4124, "lr": 5e-06, "epoch": 2.9055690072639226, "percentage": 97.09, "elapsed_time": "2:43:36", "remaining_time": "0:04:54"}
+{"current_steps": 309, "total_steps": 309, "eval_loss": 0.47956007719039917, "epoch": 2.9927360774818403, "percentage": 100.0, "elapsed_time": "2:50:48", "remaining_time": "0:00:00"}
+{"current_steps": 309, "total_steps": 309, "epoch": 2.9927360774818403, "percentage": 100.0, "elapsed_time": "2:52:03", "remaining_time": "0:00:00"}