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 sha256:4afc0aa6a3c0a754ed6b1ec1bb178951e6ba278a32213dfec6a56fb9ac977879
|
| 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 sha256:093f2f2e6aa4f18017b5cdd99c2c9a54481be1584a8c6edef14e0335645bac46
|
| 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:cf893ccf79c5735ea730c5265b3321eb655c6e1ffc7fa6f23b542fb902e60ccf
|
| 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:ff547db10a3557554763b0f24504410e1db11061cfdaaa6b33f4f078ab63ef31
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -25,3 +25,29 @@
|
|
| 25 |
{"current_steps": 25, "total_steps": 78, "loss": 0.8334, "lr": 8.613974319136959e-06, "epoch": 0.9584664536741214, "percentage": 32.05, "elapsed_time": "0:39:33", "remaining_time": "1:23:51"}
|
| 26 |
{"current_steps": 26, "total_steps": 78, "loss": 0.8659, "lr": 8.455313244934324e-06, "epoch": 0.9968051118210862, "percentage": 33.33, "elapsed_time": "0:40:56", "remaining_time": "1:21:53"}
|
| 27 |
{"current_steps": 27, "total_steps": 78, "loss": 1.3682, "lr": 8.289693629698564e-06, "epoch": 1.035143769968051, "percentage": 34.62, "elapsed_time": "0:43:19", "remaining_time": "1:21:49"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
{"current_steps": 25, "total_steps": 78, "loss": 0.8334, "lr": 8.613974319136959e-06, "epoch": 0.9584664536741214, "percentage": 32.05, "elapsed_time": "0:39:33", "remaining_time": "1:23:51"}
|
| 26 |
{"current_steps": 26, "total_steps": 78, "loss": 0.8659, "lr": 8.455313244934324e-06, "epoch": 0.9968051118210862, "percentage": 33.33, "elapsed_time": "0:40:56", "remaining_time": "1:21:53"}
|
| 27 |
{"current_steps": 27, "total_steps": 78, "loss": 1.3682, "lr": 8.289693629698564e-06, "epoch": 1.035143769968051, "percentage": 34.62, "elapsed_time": "0:43:19", "remaining_time": "1:21:49"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 78, "loss": 0.7633, "lr": 8.117449009293668e-06, "epoch": 1.073482428115016, "percentage": 35.9, "elapsed_time": "0:44:55", "remaining_time": "1:20:12"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 78, "loss": 0.7596, "lr": 7.938926261462366e-06, "epoch": 1.1118210862619808, "percentage": 37.18, "elapsed_time": "0:46:39", "remaining_time": "1:18:50"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 78, "loss": 0.8484, "lr": 7.754484907260513e-06, "epoch": 1.1501597444089458, "percentage": 38.46, "elapsed_time": "0:48:21", "remaining_time": "1:17:22"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 78, "loss": 0.7711, "lr": 7.564496387029532e-06, "epoch": 1.1884984025559104, "percentage": 39.74, "elapsed_time": "0:50:03", "remaining_time": "1:15:54"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 78, "loss": 0.7035, "lr": 7.369343312364994e-06, "epoch": 1.2268370607028753, "percentage": 41.03, "elapsed_time": "0:51:34", "remaining_time": "1:14:08"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 78, "loss": 0.8469, "lr": 7.169418695587791e-06, "epoch": 1.2651757188498403, "percentage": 42.31, "elapsed_time": "0:53:30", "remaining_time": "1:12:57"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 78, "loss": 0.7636, "lr": 6.965125158269619e-06, "epoch": 1.3035143769968052, "percentage": 43.59, "elapsed_time": "0:55:13", "remaining_time": "1:11:27"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 78, "loss": 0.729, "lr": 6.7568741204067145e-06, "epoch": 1.34185303514377, "percentage": 44.87, "elapsed_time": "0:56:59", "remaining_time": "1:10:01"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 78, "loss": 0.7501, "lr": 6.545084971874738e-06, "epoch": 1.3801916932907348, "percentage": 46.15, "elapsed_time": "0:58:21", "remaining_time": "1:08:05"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 78, "loss": 0.7599, "lr": 6.330184227833376e-06, "epoch": 1.4185303514376997, "percentage": 47.44, "elapsed_time": "0:59:54", "remaining_time": "1:06:22"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 78, "loss": 0.8, "lr": 6.112604669781572e-06, "epoch": 1.4568690095846646, "percentage": 48.72, "elapsed_time": "1:01:50", "remaining_time": "1:05:05"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 78, "loss": 0.8194, "lr": 5.892784473993184e-06, "epoch": 1.4952076677316293, "percentage": 50.0, "elapsed_time": "1:03:23", "remaining_time": "1:03:23"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 78, "loss": 0.8215, "lr": 5.671166329088278e-06, "epoch": 1.5335463258785942, "percentage": 51.28, "elapsed_time": "1:05:13", "remaining_time": "1:01:58"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 78, "loss": 0.7256, "lr": 5.448196544517168e-06, "epoch": 1.571884984025559, "percentage": 52.56, "elapsed_time": "1:06:36", "remaining_time": "1:00:06"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 78, "loss": 0.7466, "lr": 5.224324151752575e-06, "epoch": 1.610223642172524, "percentage": 53.85, "elapsed_time": "1:07:59", "remaining_time": "0:58:16"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 78, "loss": 0.7235, "lr": 5e-06, "epoch": 1.648562300319489, "percentage": 55.13, "elapsed_time": "1:09:13", "remaining_time": "0:56:20"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 78, "loss": 0.821, "lr": 4.775675848247427e-06, "epoch": 1.6869009584664538, "percentage": 56.41, "elapsed_time": "1:10:46", "remaining_time": "0:54:41"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 78, "loss": 0.7045, "lr": 4.551803455482833e-06, "epoch": 1.7252396166134185, "percentage": 57.69, "elapsed_time": "1:12:17", "remaining_time": "0:53:00"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 78, "loss": 0.821, "lr": 4.3288336709117246e-06, "epoch": 1.7635782747603834, "percentage": 58.97, "elapsed_time": "1:14:03", "remaining_time": "0:51:31"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 78, "loss": 0.7941, "lr": 4.107215526006818e-06, "epoch": 1.8019169329073481, "percentage": 60.26, "elapsed_time": "1:15:27", "remaining_time": "0:49:46"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 78, "loss": 0.7763, "lr": 3.887395330218429e-06, "epoch": 1.840255591054313, "percentage": 61.54, "elapsed_time": "1:16:57", "remaining_time": "0:48:06"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 78, "loss": 0.7556, "lr": 3.669815772166625e-06, "epoch": 1.878594249201278, "percentage": 62.82, "elapsed_time": "1:18:26", "remaining_time": "0:46:25"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 78, "loss": 0.6809, "lr": 3.4549150281252635e-06, "epoch": 1.9169329073482428, "percentage": 64.1, "elapsed_time": "1:19:51", "remaining_time": "0:44:43"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 78, "loss": 0.7219, "lr": 3.2431258795932863e-06, "epoch": 1.9552715654952078, "percentage": 65.38, "elapsed_time": "1:21:32", "remaining_time": "0:43:10"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 78, "loss": 0.775, "lr": 3.0348748417303826e-06, "epoch": 1.9936102236421727, "percentage": 66.67, "elapsed_time": "1:23:03", "remaining_time": "0:41:31"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 78, "loss": 1.1184, "lr": 2.83058130441221e-06, "epoch": 2.0319488817891376, "percentage": 67.95, "elapsed_time": "1:25:44", "remaining_time": "0:40:26"}
|