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:aa41c6debb995633a6c373f903f9996243192d8e9fdf972bf59ceba38a141916
|
| 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 sha256:7b1162e8f31de1b9fc0a44ed9ac4b558134dc7116304e0f202f6d9049c2c7949
|
| 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:c9a3744f7f66f698555407c3d6b11bfae32f99b6daa09e53272307a8cc4d0ed4
|
| 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:cc05891a7799838cb813ebbd290069cbc2c7c7eb2a4d4677461523e0d8b79f74
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -26,3 +26,29 @@
|
|
| 26 |
{"current_steps": 26, "total_steps": 78, "loss": 0.8892, "lr": 8.455313244934324e-06, "epoch": 0.9968051118210862, "percentage": 33.33, "elapsed_time": "0:22:37", "remaining_time": "0:45:14"}
|
| 27 |
{"current_steps": 27, "total_steps": 78, "loss": 1.6425, "lr": 8.289693629698564e-06, "epoch": 1.035143769968051, "percentage": 34.62, "elapsed_time": "0:24:21", "remaining_time": "0:46:01"}
|
| 28 |
{"current_steps": 28, "total_steps": 78, "loss": 0.8882, "lr": 8.117449009293668e-06, "epoch": 1.073482428115016, "percentage": 35.9, "elapsed_time": "0:25:16", "remaining_time": "0:45:07"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
{"current_steps": 26, "total_steps": 78, "loss": 0.8892, "lr": 8.455313244934324e-06, "epoch": 0.9968051118210862, "percentage": 33.33, "elapsed_time": "0:22:37", "remaining_time": "0:45:14"}
|
| 27 |
{"current_steps": 27, "total_steps": 78, "loss": 1.6425, "lr": 8.289693629698564e-06, "epoch": 1.035143769968051, "percentage": 34.62, "elapsed_time": "0:24:21", "remaining_time": "0:46:01"}
|
| 28 |
{"current_steps": 28, "total_steps": 78, "loss": 0.8882, "lr": 8.117449009293668e-06, "epoch": 1.073482428115016, "percentage": 35.9, "elapsed_time": "0:25:16", "remaining_time": "0:45:07"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 78, "loss": 0.8174, "lr": 7.938926261462366e-06, "epoch": 1.1118210862619808, "percentage": 37.18, "elapsed_time": "0:26:03", "remaining_time": "0:44:01"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 78, "loss": 0.8943, "lr": 7.754484907260513e-06, "epoch": 1.1501597444089458, "percentage": 38.46, "elapsed_time": "0:27:06", "remaining_time": "0:43:21"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 78, "loss": 0.9146, "lr": 7.564496387029532e-06, "epoch": 1.1884984025559104, "percentage": 39.74, "elapsed_time": "0:28:06", "remaining_time": "0:42:36"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 78, "loss": 0.8061, "lr": 7.369343312364994e-06, "epoch": 1.2268370607028753, "percentage": 41.03, "elapsed_time": "0:28:46", "remaining_time": "0:41:22"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 78, "loss": 0.9283, "lr": 7.169418695587791e-06, "epoch": 1.2651757188498403, "percentage": 42.31, "elapsed_time": "0:29:34", "remaining_time": "0:40:19"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 78, "loss": 0.8699, "lr": 6.965125158269619e-06, "epoch": 1.3035143769968052, "percentage": 43.59, "elapsed_time": "0:30:20", "remaining_time": "0:39:15"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 78, "loss": 0.8696, "lr": 6.7568741204067145e-06, "epoch": 1.34185303514377, "percentage": 44.87, "elapsed_time": "0:31:21", "remaining_time": "0:38:31"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 78, "loss": 0.883, "lr": 6.545084971874738e-06, "epoch": 1.3801916932907348, "percentage": 46.15, "elapsed_time": "0:32:13", "remaining_time": "0:37:36"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 78, "loss": 0.844, "lr": 6.330184227833376e-06, "epoch": 1.4185303514376997, "percentage": 47.44, "elapsed_time": "0:33:10", "remaining_time": "0:36:45"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 78, "loss": 0.9176, "lr": 6.112604669781572e-06, "epoch": 1.4568690095846646, "percentage": 48.72, "elapsed_time": "0:34:01", "remaining_time": "0:35:48"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 78, "loss": 0.8606, "lr": 5.892784473993184e-06, "epoch": 1.4952076677316293, "percentage": 50.0, "elapsed_time": "0:34:56", "remaining_time": "0:34:56"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 78, "loss": 0.8542, "lr": 5.671166329088278e-06, "epoch": 1.5335463258785942, "percentage": 51.28, "elapsed_time": "0:35:43", "remaining_time": "0:33:55"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 78, "loss": 0.8272, "lr": 5.448196544517168e-06, "epoch": 1.571884984025559, "percentage": 52.56, "elapsed_time": "0:36:38", "remaining_time": "0:33:03"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 78, "loss": 0.8341, "lr": 5.224324151752575e-06, "epoch": 1.610223642172524, "percentage": 53.85, "elapsed_time": "0:37:33", "remaining_time": "0:32:11"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 78, "loss": 0.8258, "lr": 5e-06, "epoch": 1.648562300319489, "percentage": 55.13, "elapsed_time": "0:38:14", "remaining_time": "0:31:07"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 78, "loss": 0.8092, "lr": 4.775675848247427e-06, "epoch": 1.6869009584664538, "percentage": 56.41, "elapsed_time": "0:39:03", "remaining_time": "0:30:11"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 78, "loss": 0.8257, "lr": 4.551803455482833e-06, "epoch": 1.7252396166134185, "percentage": 57.69, "elapsed_time": "0:39:50", "remaining_time": "0:29:13"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 78, "loss": 0.9231, "lr": 4.3288336709117246e-06, "epoch": 1.7635782747603834, "percentage": 58.97, "elapsed_time": "0:40:54", "remaining_time": "0:28:27"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 78, "loss": 0.8637, "lr": 4.107215526006818e-06, "epoch": 1.8019169329073481, "percentage": 60.26, "elapsed_time": "0:42:01", "remaining_time": "0:27:43"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 78, "loss": 0.8697, "lr": 3.887395330218429e-06, "epoch": 1.840255591054313, "percentage": 61.54, "elapsed_time": "0:42:55", "remaining_time": "0:26:49"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 78, "loss": 0.8528, "lr": 3.669815772166625e-06, "epoch": 1.878594249201278, "percentage": 62.82, "elapsed_time": "0:43:48", "remaining_time": "0:25:55"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 78, "loss": 0.8719, "lr": 3.4549150281252635e-06, "epoch": 1.9169329073482428, "percentage": 64.1, "elapsed_time": "0:44:38", "remaining_time": "0:25:00"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 78, "loss": 0.8398, "lr": 3.2431258795932863e-06, "epoch": 1.9552715654952078, "percentage": 65.38, "elapsed_time": "0:45:28", "remaining_time": "0:24:04"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 78, "loss": 0.8779, "lr": 3.0348748417303826e-06, "epoch": 1.9936102236421727, "percentage": 66.67, "elapsed_time": "0:46:15", "remaining_time": "0:23:07"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 78, "loss": 1.4471, "lr": 2.83058130441221e-06, "epoch": 2.0319488817891376, "percentage": 67.95, "elapsed_time": "0:48:18", "remaining_time": "0:22:47"}
|
| 54 |
+
{"current_steps": 54, "total_steps": 78, "loss": 0.8478, "lr": 2.6306566876350072e-06, "epoch": 2.070287539936102, "percentage": 69.23, "elapsed_time": "0:49:15", "remaining_time": "0:21:53"}
|