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:fabf027ba92e22bb01ad5ecb85a98c574b3a3a6dd05489ee450d917a17d26e8d
|
| 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:c5c94fbed56ea1d70a71ef431ddabefb1216e30f39727744825bd1ca50fc3300
|
| 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 sha256:9dc870590bbd23bb2dd2f6f4f823459184cd3806c6a961e37964a25bc3261307
|
| 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:e87b508429bb3ccde79de73fd41d2a8ef32eb4abb2cc50bd4f324ffa586a9db2
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -22,3 +22,26 @@
|
|
| 22 |
{"current_steps": 22, "total_steps": 69, "loss": 0.558, "lr": 3.44958557445824e-05, "epoch": 0.9386666666666666, "percentage": 31.88, "elapsed_time": "0:46:47", "remaining_time": "1:39:57"}
|
| 23 |
{"current_steps": 23, "total_steps": 69, "loss": 0.5874, "lr": 3.377933838151374e-05, "epoch": 0.9813333333333333, "percentage": 33.33, "elapsed_time": "0:48:34", "remaining_time": "1:37:09"}
|
| 24 |
{"current_steps": 24, "total_steps": 69, "loss": 0.9271, "lr": 3.302744965444445e-05, "epoch": 1.0293333333333334, "percentage": 34.78, "elapsed_time": "0:51:28", "remaining_time": "1:36:30"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
{"current_steps": 22, "total_steps": 69, "loss": 0.558, "lr": 3.44958557445824e-05, "epoch": 0.9386666666666666, "percentage": 31.88, "elapsed_time": "0:46:47", "remaining_time": "1:39:57"}
|
| 23 |
{"current_steps": 23, "total_steps": 69, "loss": 0.5874, "lr": 3.377933838151374e-05, "epoch": 0.9813333333333333, "percentage": 33.33, "elapsed_time": "0:48:34", "remaining_time": "1:37:09"}
|
| 24 |
{"current_steps": 24, "total_steps": 69, "loss": 0.9271, "lr": 3.302744965444445e-05, "epoch": 1.0293333333333334, "percentage": 34.78, "elapsed_time": "0:51:28", "remaining_time": "1:36:30"}
|
| 25 |
+
{"current_steps": 25, "total_steps": 69, "loss": 0.4964, "lr": 3.224211965095326e-05, "epoch": 1.072, "percentage": 36.23, "elapsed_time": "0:53:38", "remaining_time": "1:34:23"}
|
| 26 |
+
{"current_steps": 26, "total_steps": 69, "loss": 0.5165, "lr": 3.142536430189585e-05, "epoch": 1.1146666666666667, "percentage": 37.68, "elapsed_time": "0:56:02", "remaining_time": "1:32:41"}
|
| 27 |
+
{"current_steps": 27, "total_steps": 69, "loss": 0.531, "lr": 3.057928020653925e-05, "epoch": 1.1573333333333333, "percentage": 39.13, "elapsed_time": "0:58:10", "remaining_time": "1:30:29"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 69, "loss": 0.5187, "lr": 2.9706039250621626e-05, "epoch": 1.2, "percentage": 40.58, "elapsed_time": "1:00:27", "remaining_time": "1:28:31"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 69, "loss": 0.4887, "lr": 2.880788303115269e-05, "epoch": 1.2426666666666666, "percentage": 42.03, "elapsed_time": "1:02:24", "remaining_time": "1:26:05"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 69, "loss": 0.4694, "lr": 2.7887117102266373e-05, "epoch": 1.2853333333333334, "percentage": 43.48, "elapsed_time": "1:04:37", "remaining_time": "1:24:00"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 69, "loss": 0.5415, "lr": 2.6946105056896406e-05, "epoch": 1.328, "percentage": 44.93, "elapsed_time": "1:06:45", "remaining_time": "1:21:49"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 69, "loss": 0.5016, "lr": 2.5987262459467168e-05, "epoch": 1.3706666666666667, "percentage": 46.38, "elapsed_time": "1:09:05", "remaining_time": "1:19:52"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 69, "loss": 0.4744, "lr": 2.5013050645174414e-05, "epoch": 1.4133333333333333, "percentage": 47.83, "elapsed_time": "1:11:00", "remaining_time": "1:17:27"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 69, "loss": 0.467, "lr": 2.4025970401773204e-05, "epoch": 1.456, "percentage": 49.28, "elapsed_time": "1:12:53", "remaining_time": "1:15:01"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 69, "loss": 0.4996, "lr": 2.3028555550091536e-05, "epoch": 1.4986666666666666, "percentage": 50.72, "elapsed_time": "1:15:02", "remaining_time": "1:12:54"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 69, "loss": 0.4754, "lr": 2.2023366439748647e-05, "epoch": 1.5413333333333332, "percentage": 52.17, "elapsed_time": "1:17:03", "remaining_time": "1:10:37"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 69, "loss": 0.528, "lr": 2.1012983376774255e-05, "epoch": 1.584, "percentage": 53.62, "elapsed_time": "1:19:12", "remaining_time": "1:08:30"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 69, "loss": 0.4599, "lr": 2e-05, "epoch": 1.6266666666666667, "percentage": 55.07, "elapsed_time": "1:21:13", "remaining_time": "1:06:16"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 69, "loss": 0.5027, "lr": 1.8987016623225748e-05, "epoch": 1.6693333333333333, "percentage": 56.52, "elapsed_time": "1:23:22", "remaining_time": "1:04:08"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 69, "loss": 0.4798, "lr": 1.797663356025136e-05, "epoch": 1.712, "percentage": 57.97, "elapsed_time": "1:25:36", "remaining_time": "1:02:04"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 69, "loss": 0.5042, "lr": 1.6971444449908474e-05, "epoch": 1.7546666666666666, "percentage": 59.42, "elapsed_time": "1:27:38", "remaining_time": "0:59:51"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 69, "loss": 0.4788, "lr": 1.5974029598226796e-05, "epoch": 1.7973333333333334, "percentage": 60.87, "elapsed_time": "1:29:33", "remaining_time": "0:57:34"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 69, "loss": 0.4341, "lr": 1.498694935482559e-05, "epoch": 1.8399999999999999, "percentage": 62.32, "elapsed_time": "1:31:35", "remaining_time": "0:55:23"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 69, "loss": 0.4981, "lr": 1.4012737540532842e-05, "epoch": 1.8826666666666667, "percentage": 63.77, "elapsed_time": "1:33:46", "remaining_time": "0:53:17"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 69, "loss": 0.4696, "lr": 1.3053894943103598e-05, "epoch": 1.9253333333333333, "percentage": 65.22, "elapsed_time": "1:35:57", "remaining_time": "0:51:10"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 69, "loss": 0.4505, "lr": 1.2112882897733634e-05, "epoch": 1.968, "percentage": 66.67, "elapsed_time": "1:38:10", "remaining_time": "0:49:05"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 69, "loss": 0.7496, "lr": 1.1192116968847313e-05, "epoch": 2.016, "percentage": 68.12, "elapsed_time": "1:41:22", "remaining_time": "0:47:27"}
|