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 sha256:968334dd51f340378cbb9bf5b113695e7f687dc95e8acac0dedf4acc918b92a5
|
| 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:f2591ac318fab7f5ac4cc0c6b5216053f0fc72bfcb71eead696c102e0e0f6179
|
| 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 sha256:0ed739ce4fd6eb6d7d891bc52d5964ea98a506841fd4e5e72a4ed16086e638a1
|
| 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:fedb9e410ef6c07af267341a84022dbd5419a990503ac10d2e88969e21f56a9c
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -40,3 +40,30 @@
|
|
| 40 |
{"current_steps": 40, "total_steps": 78, "loss": 0.6891, "lr": 5.671166329088278e-06, "epoch": 1.518987341772152, "percentage": 51.28, "elapsed_time": "0:07:20", "remaining_time": "0:06:58"}
|
| 41 |
{"current_steps": 41, "total_steps": 78, "loss": 0.6183, "lr": 5.448196544517168e-06, "epoch": 1.5569620253164556, "percentage": 52.56, "elapsed_time": "0:07:28", "remaining_time": "0:06:44"}
|
| 42 |
{"current_steps": 42, "total_steps": 78, "loss": 0.7234, "lr": 5.224324151752575e-06, "epoch": 1.5949367088607596, "percentage": 53.85, "elapsed_time": "0:07:42", "remaining_time": "0:06:36"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
{"current_steps": 40, "total_steps": 78, "loss": 0.6891, "lr": 5.671166329088278e-06, "epoch": 1.518987341772152, "percentage": 51.28, "elapsed_time": "0:07:20", "remaining_time": "0:06:58"}
|
| 41 |
{"current_steps": 41, "total_steps": 78, "loss": 0.6183, "lr": 5.448196544517168e-06, "epoch": 1.5569620253164556, "percentage": 52.56, "elapsed_time": "0:07:28", "remaining_time": "0:06:44"}
|
| 42 |
{"current_steps": 42, "total_steps": 78, "loss": 0.7234, "lr": 5.224324151752575e-06, "epoch": 1.5949367088607596, "percentage": 53.85, "elapsed_time": "0:07:42", "remaining_time": "0:06:36"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 78, "loss": 0.6443, "lr": 5e-06, "epoch": 1.6329113924050633, "percentage": 55.13, "elapsed_time": "0:07:56", "remaining_time": "0:06:27"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 78, "loss": 0.7151, "lr": 4.775675848247427e-06, "epoch": 1.6708860759493671, "percentage": 56.41, "elapsed_time": "0:08:09", "remaining_time": "0:06:17"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 78, "loss": 0.7331, "lr": 4.551803455482833e-06, "epoch": 1.7088607594936709, "percentage": 57.69, "elapsed_time": "0:08:17", "remaining_time": "0:06:04"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 78, "loss": 0.7688, "lr": 4.3288336709117246e-06, "epoch": 1.7468354430379747, "percentage": 58.97, "elapsed_time": "0:08:28", "remaining_time": "0:05:53"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 78, "loss": 0.6973, "lr": 4.107215526006818e-06, "epoch": 1.7848101265822784, "percentage": 60.26, "elapsed_time": "0:08:36", "remaining_time": "0:05:40"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 78, "loss": 0.6475, "lr": 3.887395330218429e-06, "epoch": 1.8227848101265822, "percentage": 61.54, "elapsed_time": "0:08:43", "remaining_time": "0:05:27"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 78, "loss": 0.6481, "lr": 3.669815772166625e-06, "epoch": 1.8607594936708862, "percentage": 62.82, "elapsed_time": "0:08:53", "remaining_time": "0:05:15"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 78, "loss": 0.6982, "lr": 3.4549150281252635e-06, "epoch": 1.8987341772151898, "percentage": 64.1, "elapsed_time": "0:09:04", "remaining_time": "0:05:04"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 78, "loss": 0.6517, "lr": 3.2431258795932863e-06, "epoch": 1.9367088607594938, "percentage": 65.38, "elapsed_time": "0:09:11", "remaining_time": "0:04:52"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 78, "loss": 0.7307, "lr": 3.0348748417303826e-06, "epoch": 1.9746835443037973, "percentage": 66.67, "elapsed_time": "0:09:21", "remaining_time": "0:04:40"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 78, "loss": 1.0404, "lr": 2.83058130441221e-06, "epoch": 2.0126582278481013, "percentage": 67.95, "elapsed_time": "0:10:58", "remaining_time": "0:05:10"}
|
| 54 |
+
{"current_steps": 54, "total_steps": 78, "loss": 0.6627, "lr": 2.6306566876350072e-06, "epoch": 2.050632911392405, "percentage": 69.23, "elapsed_time": "0:11:07", "remaining_time": "0:04:56"}
|
| 55 |
+
{"current_steps": 55, "total_steps": 78, "loss": 0.6245, "lr": 2.43550361297047e-06, "epoch": 2.088607594936709, "percentage": 70.51, "elapsed_time": "0:11:17", "remaining_time": "0:04:43"}
|
| 56 |
+
{"current_steps": 56, "total_steps": 78, "loss": 0.6195, "lr": 2.245515092739488e-06, "epoch": 2.1265822784810124, "percentage": 71.79, "elapsed_time": "0:11:24", "remaining_time": "0:04:28"}
|
| 57 |
+
{"current_steps": 57, "total_steps": 78, "loss": 0.6018, "lr": 2.061073738537635e-06, "epoch": 2.1645569620253164, "percentage": 73.08, "elapsed_time": "0:11:35", "remaining_time": "0:04:16"}
|
| 58 |
+
{"current_steps": 58, "total_steps": 78, "loss": 0.6285, "lr": 1.8825509907063328e-06, "epoch": 2.2025316455696204, "percentage": 74.36, "elapsed_time": "0:11:45", "remaining_time": "0:04:03"}
|
| 59 |
+
{"current_steps": 59, "total_steps": 78, "loss": 0.5301, "lr": 1.7103063703014372e-06, "epoch": 2.240506329113924, "percentage": 75.64, "elapsed_time": "0:11:54", "remaining_time": "0:03:49"}
|
| 60 |
+
{"current_steps": 60, "total_steps": 78, "loss": 0.6759, "lr": 1.544686755065677e-06, "epoch": 2.278481012658228, "percentage": 76.92, "elapsed_time": "0:12:06", "remaining_time": "0:03:37"}
|
| 61 |
+
{"current_steps": 61, "total_steps": 78, "loss": 0.6941, "lr": 1.3860256808630429e-06, "epoch": 2.3164556962025316, "percentage": 78.21, "elapsed_time": "0:12:15", "remaining_time": "0:03:24"}
|
| 62 |
+
{"current_steps": 62, "total_steps": 78, "loss": 0.6191, "lr": 1.234642669981946e-06, "epoch": 2.3544303797468356, "percentage": 79.49, "elapsed_time": "0:12:23", "remaining_time": "0:03:11"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 78, "loss": 0.6541, "lr": 1.0908425876598512e-06, "epoch": 2.392405063291139, "percentage": 80.77, "elapsed_time": "0:12:31", "remaining_time": "0:02:58"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 78, "loss": 0.5554, "lr": 9.549150281252633e-07, "epoch": 2.430379746835443, "percentage": 82.05, "elapsed_time": "0:12:40", "remaining_time": "0:02:46"}
|
| 65 |
+
{"current_steps": 65, "total_steps": 78, "loss": 0.678, "lr": 8.271337313934869e-07, "epoch": 2.4683544303797467, "percentage": 83.33, "elapsed_time": "0:12:50", "remaining_time": "0:02:34"}
|
| 66 |
+
{"current_steps": 66, "total_steps": 78, "loss": 0.6257, "lr": 7.077560319906696e-07, "epoch": 2.5063291139240507, "percentage": 84.62, "elapsed_time": "0:13:06", "remaining_time": "0:02:23"}
|
| 67 |
+
{"current_steps": 67, "total_steps": 78, "loss": 0.5732, "lr": 5.9702234071631e-07, "epoch": 2.5443037974683547, "percentage": 85.9, "elapsed_time": "0:13:11", "remaining_time": "0:02:10"}
|
| 68 |
+
{"current_steps": 68, "total_steps": 78, "loss": 0.6665, "lr": 4.951556604879049e-07, "epoch": 2.5822784810126582, "percentage": 87.18, "elapsed_time": "0:13:25", "remaining_time": "0:01:58"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 78, "loss": 0.547, "lr": 4.0236113724274716e-07, "epoch": 2.620253164556962, "percentage": 88.46, "elapsed_time": "0:13:33", "remaining_time": "0:01:46"}
|