Training in progress, epoch 1
Browse files
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4877660776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef0eac6ae46b83124b134f37cbc90a3a5328b39f4d0b94f74831472b97783402
|
| 3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4932751008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cdc9a479492b730e96b977d043f31df3307dcd74d511a435a53ddd58956120b
|
| 3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4330865200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2e5e4d991a24dc790b8fad4a03caa6bf352e1c16429872e8e91767a32a49a53
|
| 3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1089994880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce259139bcb809fc5546930bb4159c86c6c34d5e0a0a657114189d0190dced50
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -31,3 +31,34 @@
|
|
| 31 |
{"current_steps": 31, "total_steps": 93, "loss": 0.5595, "lr": 3.400768269742702e-05, "epoch": 0.992, "percentage": 33.33, "elapsed_time": "0:49:10", "remaining_time": "1:38:20"}
|
| 32 |
{"current_steps": 32, "total_steps": 93, "loss": 0.919, "lr": 3.345745048745838e-05, "epoch": 1.024, "percentage": 34.41, "elapsed_time": "0:51:38", "remaining_time": "1:38:26"}
|
| 33 |
{"current_steps": 33, "total_steps": 93, "loss": 0.4404, "lr": 3.288794060929754e-05, "epoch": 1.056, "percentage": 35.48, "elapsed_time": "0:53:19", "remaining_time": "1:36:56"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
{"current_steps": 31, "total_steps": 93, "loss": 0.5595, "lr": 3.400768269742702e-05, "epoch": 0.992, "percentage": 33.33, "elapsed_time": "0:49:10", "remaining_time": "1:38:20"}
|
| 32 |
{"current_steps": 32, "total_steps": 93, "loss": 0.919, "lr": 3.345745048745838e-05, "epoch": 1.024, "percentage": 34.41, "elapsed_time": "0:51:38", "remaining_time": "1:38:26"}
|
| 33 |
{"current_steps": 33, "total_steps": 93, "loss": 0.4404, "lr": 3.288794060929754e-05, "epoch": 1.056, "percentage": 35.48, "elapsed_time": "0:53:19", "remaining_time": "1:36:56"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 93, "loss": 0.4984, "lr": 3.229996888035908e-05, "epoch": 1.088, "percentage": 36.56, "elapsed_time": "0:55:06", "remaining_time": "1:35:38"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 93, "loss": 0.4807, "lr": 3.169437756448095e-05, "epoch": 1.12, "percentage": 37.63, "elapsed_time": "0:56:49", "remaining_time": "1:34:09"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 93, "loss": 0.4703, "lr": 3.107203416538969e-05, "epoch": 1.152, "percentage": 38.71, "elapsed_time": "0:58:25", "remaining_time": "1:32:30"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 93, "loss": 0.4739, "lr": 3.0433830184009694e-05, "epoch": 1.184, "percentage": 39.78, "elapsed_time": "1:00:04", "remaining_time": "1:30:55"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 93, "loss": 0.4525, "lr": 2.9780679841396668e-05, "epoch": 1.216, "percentage": 40.86, "elapsed_time": "1:01:45", "remaining_time": "1:29:22"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 93, "loss": 0.4987, "lr": 2.9113518769124836e-05, "epoch": 1.248, "percentage": 41.94, "elapsed_time": "1:03:07", "remaining_time": "1:27:23"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 93, "loss": 0.4475, "lr": 2.843330266900368e-05, "epoch": 1.28, "percentage": 43.01, "elapsed_time": "1:04:49", "remaining_time": "1:25:53"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 93, "loss": 0.4667, "lr": 2.774100594404435e-05, "epoch": 1.312, "percentage": 44.09, "elapsed_time": "1:06:20", "remaining_time": "1:24:08"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 93, "loss": 0.4916, "lr": 2.703762030263666e-05, "epoch": 1.3439999999999999, "percentage": 45.16, "elapsed_time": "1:08:07", "remaining_time": "1:22:43"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 93, "loss": 0.4771, "lr": 2.632415333793648e-05, "epoch": 1.376, "percentage": 46.24, "elapsed_time": "1:09:51", "remaining_time": "1:21:13"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 93, "loss": 0.407, "lr": 2.5601627084498146e-05, "epoch": 1.408, "percentage": 47.31, "elapsed_time": "1:11:12", "remaining_time": "1:19:17"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 93, "loss": 0.4442, "lr": 2.4871076554219838e-05, "epoch": 1.44, "percentage": 48.39, "elapsed_time": "1:12:33", "remaining_time": "1:17:23"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 93, "loss": 0.5223, "lr": 2.413354825369906e-05, "epoch": 1.472, "percentage": 49.46, "elapsed_time": "1:14:12", "remaining_time": "1:15:49"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 93, "loss": 0.42, "lr": 2.3390098685121938e-05, "epoch": 1.504, "percentage": 50.54, "elapsed_time": "1:15:51", "remaining_time": "1:14:14"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 93, "loss": 0.4665, "lr": 2.264179283283405e-05, "epoch": 1.536, "percentage": 51.61, "elapsed_time": "1:17:15", "remaining_time": "1:12:25"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 93, "loss": 0.4445, "lr": 2.1889702637760627e-05, "epoch": 1.568, "percentage": 52.69, "elapsed_time": "1:18:56", "remaining_time": "1:10:53"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 93, "loss": 0.5221, "lr": 2.1134905461861486e-05, "epoch": 1.6, "percentage": 53.76, "elapsed_time": "1:20:34", "remaining_time": "1:09:17"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 93, "loss": 0.4218, "lr": 2.0378482544820383e-05, "epoch": 1.6320000000000001, "percentage": 54.84, "elapsed_time": "1:21:59", "remaining_time": "1:07:31"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 93, "loss": 0.476, "lr": 1.9621517455179627e-05, "epoch": 1.6640000000000001, "percentage": 55.91, "elapsed_time": "1:23:37", "remaining_time": "1:05:55"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 93, "loss": 0.4275, "lr": 1.886509453813852e-05, "epoch": 1.696, "percentage": 56.99, "elapsed_time": "1:25:18", "remaining_time": "1:04:22"}
|
| 54 |
+
{"current_steps": 54, "total_steps": 93, "loss": 0.4757, "lr": 1.8110297362239376e-05, "epoch": 1.728, "percentage": 58.06, "elapsed_time": "1:26:51", "remaining_time": "1:02:44"}
|
| 55 |
+
{"current_steps": 55, "total_steps": 93, "loss": 0.4757, "lr": 1.735820716716596e-05, "epoch": 1.76, "percentage": 59.14, "elapsed_time": "1:28:29", "remaining_time": "1:01:08"}
|
| 56 |
+
{"current_steps": 56, "total_steps": 93, "loss": 0.4182, "lr": 1.660990131487807e-05, "epoch": 1.792, "percentage": 60.22, "elapsed_time": "1:29:53", "remaining_time": "0:59:23"}
|
| 57 |
+
{"current_steps": 57, "total_steps": 93, "loss": 0.4731, "lr": 1.586645174630094e-05, "epoch": 1.8239999999999998, "percentage": 61.29, "elapsed_time": "1:31:29", "remaining_time": "0:57:46"}
|
| 58 |
+
{"current_steps": 58, "total_steps": 93, "loss": 0.4271, "lr": 1.5128923445780163e-05, "epoch": 1.8559999999999999, "percentage": 62.37, "elapsed_time": "1:32:58", "remaining_time": "0:56:06"}
|
| 59 |
+
{"current_steps": 59, "total_steps": 93, "loss": 0.4644, "lr": 1.4398372915501862e-05, "epoch": 1.888, "percentage": 63.44, "elapsed_time": "1:34:46", "remaining_time": "0:54:36"}
|
| 60 |
+
{"current_steps": 60, "total_steps": 93, "loss": 0.4071, "lr": 1.3675846662063521e-05, "epoch": 1.92, "percentage": 64.52, "elapsed_time": "1:36:19", "remaining_time": "0:52:58"}
|
| 61 |
+
{"current_steps": 61, "total_steps": 93, "loss": 0.4561, "lr": 1.296237969736334e-05, "epoch": 1.952, "percentage": 65.59, "elapsed_time": "1:37:51", "remaining_time": "0:51:19"}
|
| 62 |
+
{"current_steps": 62, "total_steps": 93, "loss": 0.3817, "lr": 1.2258994055955658e-05, "epoch": 1.984, "percentage": 66.67, "elapsed_time": "1:39:33", "remaining_time": "0:49:46"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 93, "loss": 0.7898, "lr": 1.156669733099632e-05, "epoch": 2.016, "percentage": 67.74, "elapsed_time": "1:42:17", "remaining_time": "0:48:42"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 93, "loss": 0.3525, "lr": 1.0886481230875172e-05, "epoch": 2.048, "percentage": 68.82, "elapsed_time": "1:43:52", "remaining_time": "0:47:03"}
|