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 sha256:61a399db71442cd13acb2f7cd95c3b89f8bd05296249020a355822addd3ccf63
|
| 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 sha256:970b7108f161867676c7cdbae5b341bfb26c5075a497eeb278ef01b622974406
|
| 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 sha256:484154b2aa42bb6f67c3e604f6daa4acfc8c1b816644a552dc237218b916b60d
|
| 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:ce65b12bcf71e3ed4b902a7a102b196b5d837fa2b3fc7f10b13f523ab3db26b7
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -25,3 +25,29 @@
|
|
| 25 |
{"current_steps": 25, "total_steps": 78, "loss": 0.9744, "lr": 8.613974319136959e-06, "epoch": 0.9584664536741214, "percentage": 32.05, "elapsed_time": "0:39:49", "remaining_time": "1:24:26"}
|
| 26 |
{"current_steps": 26, "total_steps": 78, "loss": 0.9422, "lr": 8.455313244934324e-06, "epoch": 0.9968051118210862, "percentage": 33.33, "elapsed_time": "0:41:27", "remaining_time": "1:22:55"}
|
| 27 |
{"current_steps": 27, "total_steps": 78, "loss": 1.6755, "lr": 8.289693629698564e-06, "epoch": 1.035143769968051, "percentage": 34.62, "elapsed_time": "0:43:51", "remaining_time": "1:22:50"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
{"current_steps": 25, "total_steps": 78, "loss": 0.9744, "lr": 8.613974319136959e-06, "epoch": 0.9584664536741214, "percentage": 32.05, "elapsed_time": "0:39:49", "remaining_time": "1:24:26"}
|
| 26 |
{"current_steps": 26, "total_steps": 78, "loss": 0.9422, "lr": 8.455313244934324e-06, "epoch": 0.9968051118210862, "percentage": 33.33, "elapsed_time": "0:41:27", "remaining_time": "1:22:55"}
|
| 27 |
{"current_steps": 27, "total_steps": 78, "loss": 1.6755, "lr": 8.289693629698564e-06, "epoch": 1.035143769968051, "percentage": 34.62, "elapsed_time": "0:43:51", "remaining_time": "1:22:50"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 78, "loss": 0.9068, "lr": 8.117449009293668e-06, "epoch": 1.073482428115016, "percentage": 35.9, "elapsed_time": "0:45:22", "remaining_time": "1:21:01"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 78, "loss": 0.9196, "lr": 7.938926261462366e-06, "epoch": 1.1118210862619808, "percentage": 37.18, "elapsed_time": "0:46:57", "remaining_time": "1:19:19"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 78, "loss": 0.8498, "lr": 7.754484907260513e-06, "epoch": 1.1501597444089458, "percentage": 38.46, "elapsed_time": "0:48:32", "remaining_time": "1:17:40"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 78, "loss": 0.9391, "lr": 7.564496387029532e-06, "epoch": 1.1884984025559104, "percentage": 39.74, "elapsed_time": "0:50:17", "remaining_time": "1:16:15"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 78, "loss": 0.9358, "lr": 7.369343312364994e-06, "epoch": 1.2268370607028753, "percentage": 41.03, "elapsed_time": "0:51:58", "remaining_time": "1:14:42"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 78, "loss": 0.8565, "lr": 7.169418695587791e-06, "epoch": 1.2651757188498403, "percentage": 42.31, "elapsed_time": "0:53:37", "remaining_time": "1:13:07"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 78, "loss": 0.9579, "lr": 6.965125158269619e-06, "epoch": 1.3035143769968052, "percentage": 43.59, "elapsed_time": "0:55:08", "remaining_time": "1:11:21"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 78, "loss": 0.899, "lr": 6.7568741204067145e-06, "epoch": 1.34185303514377, "percentage": 44.87, "elapsed_time": "0:56:52", "remaining_time": "1:09:52"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 78, "loss": 0.87, "lr": 6.545084971874738e-06, "epoch": 1.3801916932907348, "percentage": 46.15, "elapsed_time": "0:58:25", "remaining_time": "1:08:09"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 78, "loss": 0.8848, "lr": 6.330184227833376e-06, "epoch": 1.4185303514376997, "percentage": 47.44, "elapsed_time": "1:00:01", "remaining_time": "1:06:30"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 78, "loss": 0.8321, "lr": 6.112604669781572e-06, "epoch": 1.4568690095846646, "percentage": 48.72, "elapsed_time": "1:01:29", "remaining_time": "1:04:43"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 78, "loss": 0.9334, "lr": 5.892784473993184e-06, "epoch": 1.4952076677316293, "percentage": 50.0, "elapsed_time": "1:03:15", "remaining_time": "1:03:15"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 78, "loss": 0.878, "lr": 5.671166329088278e-06, "epoch": 1.5335463258785942, "percentage": 51.28, "elapsed_time": "1:04:47", "remaining_time": "1:01:32"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 78, "loss": 0.8616, "lr": 5.448196544517168e-06, "epoch": 1.571884984025559, "percentage": 52.56, "elapsed_time": "1:06:19", "remaining_time": "0:59:51"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 78, "loss": 0.8622, "lr": 5.224324151752575e-06, "epoch": 1.610223642172524, "percentage": 53.85, "elapsed_time": "1:07:51", "remaining_time": "0:58:10"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 78, "loss": 0.9181, "lr": 5e-06, "epoch": 1.648562300319489, "percentage": 55.13, "elapsed_time": "1:09:30", "remaining_time": "0:56:34"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 78, "loss": 0.907, "lr": 4.775675848247427e-06, "epoch": 1.6869009584664538, "percentage": 56.41, "elapsed_time": "1:11:18", "remaining_time": "0:55:06"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 78, "loss": 0.9012, "lr": 4.551803455482833e-06, "epoch": 1.7252396166134185, "percentage": 57.69, "elapsed_time": "1:13:00", "remaining_time": "0:53:32"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 78, "loss": 0.9178, "lr": 4.3288336709117246e-06, "epoch": 1.7635782747603834, "percentage": 58.97, "elapsed_time": "1:14:39", "remaining_time": "0:51:55"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 78, "loss": 0.8262, "lr": 4.107215526006818e-06, "epoch": 1.8019169329073481, "percentage": 60.26, "elapsed_time": "1:16:13", "remaining_time": "0:50:16"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 78, "loss": 0.9191, "lr": 3.887395330218429e-06, "epoch": 1.840255591054313, "percentage": 61.54, "elapsed_time": "1:17:51", "remaining_time": "0:48:39"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 78, "loss": 0.8733, "lr": 3.669815772166625e-06, "epoch": 1.878594249201278, "percentage": 62.82, "elapsed_time": "1:19:24", "remaining_time": "0:47:00"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 78, "loss": 0.8584, "lr": 3.4549150281252635e-06, "epoch": 1.9169329073482428, "percentage": 64.1, "elapsed_time": "1:20:53", "remaining_time": "0:45:17"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 78, "loss": 0.8232, "lr": 3.2431258795932863e-06, "epoch": 1.9552715654952078, "percentage": 65.38, "elapsed_time": "1:22:16", "remaining_time": "0:43:33"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 78, "loss": 0.8291, "lr": 3.0348748417303826e-06, "epoch": 1.9936102236421727, "percentage": 66.67, "elapsed_time": "1:23:52", "remaining_time": "0:41:56"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 78, "loss": 1.5904, "lr": 2.83058130441221e-06, "epoch": 2.0319488817891376, "percentage": 67.95, "elapsed_time": "1:26:38", "remaining_time": "0:40:52"}
|