Training in progress, epoch 2
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 sha256:7fb8bd1e9bb9427addec290612be58d94e4fff28a3eb2ae6edc846a3ac18346a
|
| 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 sha256:6783d0d69939a86a56477d312b7e455734144d2c4549ab673fbd9561760cb58d
|
| 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 sha256:4d7d166414a8b1cd1ae63d7bded5f60f39730bddd66f6ecbe3dde86c77d490c8
|
| 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 sha256:032a66f6d5f8705fcd059c1c1ce6c6f6d61507ac0540a4d45d2afc8ed524cc5b
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -25,3 +25,29 @@
|
|
| 25 |
{"current_steps": 25, "total_steps": 78, "loss": 0.95, "lr": 8.613974319136959e-06, "epoch": 0.9615384615384616, "percentage": 32.05, "elapsed_time": "0:39:12", "remaining_time": "1:23:06"}
|
| 26 |
{"current_steps": 26, "total_steps": 78, "loss": 0.9302, "lr": 8.455313244934324e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:40:32", "remaining_time": "1:21:05"}
|
| 27 |
{"current_steps": 27, "total_steps": 78, "loss": 0.9184, "lr": 8.289693629698564e-06, "epoch": 1.0384615384615385, "percentage": 34.62, "elapsed_time": "0:43:09", "remaining_time": "1:21:32"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
{"current_steps": 25, "total_steps": 78, "loss": 0.95, "lr": 8.613974319136959e-06, "epoch": 0.9615384615384616, "percentage": 32.05, "elapsed_time": "0:39:12", "remaining_time": "1:23:06"}
|
| 26 |
{"current_steps": 26, "total_steps": 78, "loss": 0.9302, "lr": 8.455313244934324e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:40:32", "remaining_time": "1:21:05"}
|
| 27 |
{"current_steps": 27, "total_steps": 78, "loss": 0.9184, "lr": 8.289693629698564e-06, "epoch": 1.0384615384615385, "percentage": 34.62, "elapsed_time": "0:43:09", "remaining_time": "1:21:32"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 78, "loss": 0.9135, "lr": 8.117449009293668e-06, "epoch": 1.0769230769230769, "percentage": 35.9, "elapsed_time": "0:44:40", "remaining_time": "1:19:46"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 78, "loss": 0.8805, "lr": 7.938926261462366e-06, "epoch": 1.1153846153846154, "percentage": 37.18, "elapsed_time": "0:46:15", "remaining_time": "1:18:08"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 78, "loss": 0.8966, "lr": 7.754484907260513e-06, "epoch": 1.1538461538461537, "percentage": 38.46, "elapsed_time": "0:47:44", "remaining_time": "1:16:23"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 78, "loss": 0.8821, "lr": 7.564496387029532e-06, "epoch": 1.1923076923076923, "percentage": 39.74, "elapsed_time": "0:49:10", "remaining_time": "1:14:33"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 78, "loss": 0.8761, "lr": 7.369343312364994e-06, "epoch": 1.2307692307692308, "percentage": 41.03, "elapsed_time": "0:50:42", "remaining_time": "1:12:53"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 78, "loss": 0.8529, "lr": 7.169418695587791e-06, "epoch": 1.2692307692307692, "percentage": 42.31, "elapsed_time": "0:52:07", "remaining_time": "1:11:05"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 78, "loss": 0.9053, "lr": 6.965125158269619e-06, "epoch": 1.3076923076923077, "percentage": 43.59, "elapsed_time": "0:53:51", "remaining_time": "1:09:42"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 78, "loss": 0.9207, "lr": 6.7568741204067145e-06, "epoch": 1.3461538461538463, "percentage": 44.87, "elapsed_time": "0:55:32", "remaining_time": "1:08:14"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 78, "loss": 0.8847, "lr": 6.545084971874738e-06, "epoch": 1.3846153846153846, "percentage": 46.15, "elapsed_time": "0:56:55", "remaining_time": "1:06:25"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 78, "loss": 0.8799, "lr": 6.330184227833376e-06, "epoch": 1.4230769230769231, "percentage": 47.44, "elapsed_time": "0:58:23", "remaining_time": "1:04:42"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 78, "loss": 0.8546, "lr": 6.112604669781572e-06, "epoch": 1.4615384615384617, "percentage": 48.72, "elapsed_time": "0:59:35", "remaining_time": "1:02:43"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 78, "loss": 0.8679, "lr": 5.892784473993184e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "1:01:01", "remaining_time": "1:01:01"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 78, "loss": 0.919, "lr": 5.671166329088278e-06, "epoch": 1.5384615384615383, "percentage": 51.28, "elapsed_time": "1:02:42", "remaining_time": "0:59:34"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 78, "loss": 0.8837, "lr": 5.448196544517168e-06, "epoch": 1.5769230769230769, "percentage": 52.56, "elapsed_time": "1:04:17", "remaining_time": "0:58:00"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 78, "loss": 0.9065, "lr": 5.224324151752575e-06, "epoch": 1.6153846153846154, "percentage": 53.85, "elapsed_time": "1:05:59", "remaining_time": "0:56:33"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 78, "loss": 0.9107, "lr": 5e-06, "epoch": 1.6538461538461537, "percentage": 55.13, "elapsed_time": "1:07:45", "remaining_time": "0:55:08"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 78, "loss": 0.891, "lr": 4.775675848247427e-06, "epoch": 1.6923076923076923, "percentage": 56.41, "elapsed_time": "1:09:18", "remaining_time": "0:53:33"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 78, "loss": 0.8803, "lr": 4.551803455482833e-06, "epoch": 1.7307692307692308, "percentage": 57.69, "elapsed_time": "1:10:47", "remaining_time": "0:51:54"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 78, "loss": 0.8856, "lr": 4.3288336709117246e-06, "epoch": 1.7692307692307692, "percentage": 58.97, "elapsed_time": "1:12:22", "remaining_time": "0:50:21"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 78, "loss": 0.8768, "lr": 4.107215526006818e-06, "epoch": 1.8076923076923077, "percentage": 60.26, "elapsed_time": "1:13:55", "remaining_time": "0:48:45"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 78, "loss": 0.8983, "lr": 3.887395330218429e-06, "epoch": 1.8461538461538463, "percentage": 61.54, "elapsed_time": "1:15:21", "remaining_time": "0:47:05"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 78, "loss": 0.9199, "lr": 3.669815772166625e-06, "epoch": 1.8846153846153846, "percentage": 62.82, "elapsed_time": "1:17:13", "remaining_time": "0:45:41"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 78, "loss": 0.8637, "lr": 3.4549150281252635e-06, "epoch": 1.9230769230769231, "percentage": 64.1, "elapsed_time": "1:18:32", "remaining_time": "0:43:59"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 78, "loss": 0.8961, "lr": 3.2431258795932863e-06, "epoch": 1.9615384615384617, "percentage": 65.38, "elapsed_time": "1:19:56", "remaining_time": "0:42:19"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 78, "loss": 0.8782, "lr": 3.0348748417303826e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:21:28", "remaining_time": "0:40:44"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 78, "loss": 0.8562, "lr": 2.83058130441221e-06, "epoch": 2.0384615384615383, "percentage": 67.95, "elapsed_time": "1:24:07", "remaining_time": "0:39:40"}
|