Training in progress, epoch 2

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7dbd1af9dfe9d22cfc64fd661512e898750682c2b6aac25738ee6b5d1246733
+oid sha256:de77d3ab9a4ea03eb1f8882911e96aa300952e4cd9ce1e00efb1150ce1abeb4e
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b82d61c9723763f7609e7e9adf1089db5beeb5f7d9c4d19f804f7a3fb95f83d
+oid sha256:a6dcdf1bc90893dfafcf679724a5d7b1abb216571859bdc3b455ec6cd35decc6
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:062a172a607a2fdf0c2111326b147db359e717814f22791d6d4bafd49f34f2f6
+oid sha256:e8dbb9e34c47972e0cacbb718e4f23ec2c363fe51b055277592322e50ec5e90c
 size 4540516344

trainer_log.jsonl

@@ -7,3 +7,13 @@
 {"current_steps": 70, "total_steps": 252, "loss": 0.5269, "lr": 4.397449556841417e-06, "epoch": 0.8333333333333334, "percentage": 27.78, "elapsed_time": "1:07:31", "remaining_time": "2:55:33"}
 {"current_steps": 80, "total_steps": 252, "loss": 0.518, "lr": 4.1823801090819264e-06, "epoch": 0.9523809523809523, "percentage": 31.75, "elapsed_time": "1:17:08", "remaining_time": "2:45:52"}
 {"current_steps": 84, "total_steps": 252, "eval_loss": 0.06437206268310547, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:22:28", "remaining_time": "2:44:57"}
+{"current_steps": 90, "total_steps": 252, "loss": 0.4982, "lr": 3.9425970160818e-06, "epoch": 1.0714285714285714, "percentage": 35.71, "elapsed_time": "1:28:57", "remaining_time": "2:40:07"}
+{"current_steps": 100, "total_steps": 252, "loss": 0.4824, "lr": 3.6822373879960433e-06, "epoch": 1.1904761904761905, "percentage": 39.68, "elapsed_time": "1:38:35", "remaining_time": "2:29:51"}
+{"current_steps": 110, "total_steps": 252, "loss": 0.4791, "lr": 3.4057933533055654e-06, "epoch": 1.3095238095238095, "percentage": 43.65, "elapsed_time": "1:48:12", "remaining_time": "2:19:41"}
+{"current_steps": 120, "total_steps": 252, "loss": 0.4752, "lr": 3.118034553643137e-06, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "1:57:50", "remaining_time": "2:09:38"}
+{"current_steps": 130, "total_steps": 252, "loss": 0.4698, "lr": 2.8239258505316425e-06, "epoch": 1.5476190476190477, "percentage": 51.59, "elapsed_time": "2:07:29", "remaining_time": "1:59:38"}
+{"current_steps": 140, "total_steps": 252, "loss": 0.4679, "lr": 2.5285416638857373e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "2:17:07", "remaining_time": "1:49:41"}
+{"current_steps": 150, "total_steps": 252, "loss": 0.4652, "lr": 2.236978420242048e-06, "epoch": 1.7857142857142856, "percentage": 59.52, "elapsed_time": "2:26:45", "remaining_time": "1:39:47"}
+{"current_steps": 160, "total_steps": 252, "loss": 0.4614, "lr": 1.9542666212969685e-06, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "2:36:22", "remaining_time": "1:29:55"}
+{"current_steps": 168, "total_steps": 252, "eval_loss": 0.06041712313890457, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:45:33", "remaining_time": "1:22:46"}
+{"current_steps": 170, "total_steps": 252, "loss": 0.4551, "lr": 1.6852840498821444e-06, "epoch": 2.0238095238095237, "percentage": 67.46, "elapsed_time": "2:48:13", "remaining_time": "1:21:08"}