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:c8788af72da8fcc40cfcfcca1296262409c38a45153e5b4cec43c13d569843af
|
| 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:f834df4f2c4c30805addd5f7487ab4e0091e84827bcca78f9582cab89d452789
|
| 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:b892d10f850f058579dd991265213d4a1ffcb40400672fe4b7654493a0ef8467
|
| 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 sha256:5e6bef249e61000b875336c02ffc6529325b6c910958243473dfb60b5ebf197d
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -119,3 +119,39 @@
|
|
| 119 |
{"current_steps": 119, "total_steps": 156, "loss": 0.6073, "lr": 1.6266472703396286e-06, "epoch": 2.2738853503184715, "percentage": 76.28, "elapsed_time": "0:23:26", "remaining_time": "0:07:17"}
|
| 120 |
{"current_steps": 120, "total_steps": 156, "loss": 0.6255, "lr": 1.544686755065677e-06, "epoch": 2.2929936305732483, "percentage": 76.92, "elapsed_time": "0:23:34", "remaining_time": "0:07:04"}
|
| 121 |
{"current_steps": 121, "total_steps": 156, "loss": 0.5905, "lr": 1.4644660940672628e-06, "epoch": 2.3121019108280256, "percentage": 77.56, "elapsed_time": "0:23:41", "remaining_time": "0:06:51"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 119 |
{"current_steps": 119, "total_steps": 156, "loss": 0.6073, "lr": 1.6266472703396286e-06, "epoch": 2.2738853503184715, "percentage": 76.28, "elapsed_time": "0:23:26", "remaining_time": "0:07:17"}
|
| 120 |
{"current_steps": 120, "total_steps": 156, "loss": 0.6255, "lr": 1.544686755065677e-06, "epoch": 2.2929936305732483, "percentage": 76.92, "elapsed_time": "0:23:34", "remaining_time": "0:07:04"}
|
| 121 |
{"current_steps": 121, "total_steps": 156, "loss": 0.5905, "lr": 1.4644660940672628e-06, "epoch": 2.3121019108280256, "percentage": 77.56, "elapsed_time": "0:23:41", "remaining_time": "0:06:51"}
|
| 122 |
+
{"current_steps": 122, "total_steps": 156, "loss": 0.5853, "lr": 1.3860256808630429e-06, "epoch": 2.3312101910828025, "percentage": 78.21, "elapsed_time": "0:23:52", "remaining_time": "0:06:39"}
|
| 123 |
+
{"current_steps": 123, "total_steps": 156, "loss": 0.6085, "lr": 1.3094050125632973e-06, "epoch": 2.3503184713375798, "percentage": 78.85, "elapsed_time": "0:24:06", "remaining_time": "0:06:28"}
|
| 124 |
+
{"current_steps": 124, "total_steps": 156, "loss": 0.5548, "lr": 1.234642669981946e-06, "epoch": 2.3694267515923566, "percentage": 79.49, "elapsed_time": "0:24:19", "remaining_time": "0:06:16"}
|
| 125 |
+
{"current_steps": 125, "total_steps": 156, "loss": 0.6369, "lr": 1.1617762982099446e-06, "epoch": 2.388535031847134, "percentage": 80.13, "elapsed_time": "0:24:31", "remaining_time": "0:06:04"}
|
| 126 |
+
{"current_steps": 126, "total_steps": 156, "loss": 0.5646, "lr": 1.0908425876598512e-06, "epoch": 2.4076433121019107, "percentage": 80.77, "elapsed_time": "0:24:40", "remaining_time": "0:05:52"}
|
| 127 |
+
{"current_steps": 127, "total_steps": 156, "loss": 0.6004, "lr": 1.0218772555910955e-06, "epoch": 2.426751592356688, "percentage": 81.41, "elapsed_time": "0:24:49", "remaining_time": "0:05:40"}
|
| 128 |
+
{"current_steps": 128, "total_steps": 156, "loss": 0.6111, "lr": 9.549150281252633e-07, "epoch": 2.445859872611465, "percentage": 82.05, "elapsed_time": "0:25:01", "remaining_time": "0:05:28"}
|
| 129 |
+
{"current_steps": 129, "total_steps": 156, "loss": 0.6004, "lr": 8.899896227604509e-07, "epoch": 2.464968152866242, "percentage": 82.69, "elapsed_time": "0:25:20", "remaining_time": "0:05:18"}
|
| 130 |
+
{"current_steps": 130, "total_steps": 156, "loss": 0.5499, "lr": 8.271337313934869e-07, "epoch": 2.484076433121019, "percentage": 83.33, "elapsed_time": "0:25:26", "remaining_time": "0:05:05"}
|
| 131 |
+
{"current_steps": 131, "total_steps": 156, "loss": 0.6805, "lr": 7.663790038585794e-07, "epoch": 2.5031847133757963, "percentage": 83.97, "elapsed_time": "0:25:36", "remaining_time": "0:04:53"}
|
| 132 |
+
{"current_steps": 132, "total_steps": 156, "loss": 0.5708, "lr": 7.077560319906696e-07, "epoch": 2.522292993630573, "percentage": 84.62, "elapsed_time": "0:25:47", "remaining_time": "0:04:41"}
|
| 133 |
+
{"current_steps": 133, "total_steps": 156, "loss": 0.6088, "lr": 6.512943342215234e-07, "epoch": 2.5414012738853504, "percentage": 85.26, "elapsed_time": "0:25:58", "remaining_time": "0:04:29"}
|
| 134 |
+
{"current_steps": 134, "total_steps": 156, "loss": 0.558, "lr": 5.9702234071631e-07, "epoch": 2.5605095541401273, "percentage": 85.9, "elapsed_time": "0:26:07", "remaining_time": "0:04:17"}
|
| 135 |
+
{"current_steps": 135, "total_steps": 156, "loss": 0.5846, "lr": 5.449673790581611e-07, "epoch": 2.5796178343949046, "percentage": 86.54, "elapsed_time": "0:26:15", "remaining_time": "0:04:05"}
|
| 136 |
+
{"current_steps": 136, "total_steps": 156, "loss": 0.5835, "lr": 4.951556604879049e-07, "epoch": 2.5987261146496814, "percentage": 87.18, "elapsed_time": "0:26:26", "remaining_time": "0:03:53"}
|
| 137 |
+
{"current_steps": 137, "total_steps": 156, "loss": 0.5937, "lr": 4.4761226670592074e-07, "epoch": 2.6178343949044587, "percentage": 87.82, "elapsed_time": "0:26:33", "remaining_time": "0:03:41"}
|
| 138 |
+
{"current_steps": 138, "total_steps": 156, "loss": 0.5975, "lr": 4.0236113724274716e-07, "epoch": 2.6369426751592355, "percentage": 88.46, "elapsed_time": "0:26:42", "remaining_time": "0:03:28"}
|
| 139 |
+
{"current_steps": 139, "total_steps": 156, "loss": 0.5917, "lr": 3.5942505740480583e-07, "epoch": 2.656050955414013, "percentage": 89.1, "elapsed_time": "0:26:52", "remaining_time": "0:03:17"}
|
| 140 |
+
{"current_steps": 140, "total_steps": 156, "loss": 0.58, "lr": 3.18825646801314e-07, "epoch": 2.6751592356687897, "percentage": 89.74, "elapsed_time": "0:27:00", "remaining_time": "0:03:05"}
|
| 141 |
+
{"current_steps": 141, "total_steps": 156, "loss": 0.6181, "lr": 2.8058334845816214e-07, "epoch": 2.694267515923567, "percentage": 90.38, "elapsed_time": "0:27:10", "remaining_time": "0:02:53"}
|
| 142 |
+
{"current_steps": 142, "total_steps": 156, "loss": 0.6212, "lr": 2.447174185242324e-07, "epoch": 2.713375796178344, "percentage": 91.03, "elapsed_time": "0:27:19", "remaining_time": "0:02:41"}
|
| 143 |
+
{"current_steps": 143, "total_steps": 156, "loss": 0.6067, "lr": 2.1124591657534776e-07, "epoch": 2.732484076433121, "percentage": 91.67, "elapsed_time": "0:27:32", "remaining_time": "0:02:30"}
|
| 144 |
+
{"current_steps": 144, "total_steps": 156, "loss": 0.545, "lr": 1.801856965207338e-07, "epoch": 2.7515923566878984, "percentage": 92.31, "elapsed_time": "0:27:42", "remaining_time": "0:02:18"}
|
| 145 |
+
{"current_steps": 145, "total_steps": 156, "loss": 0.5746, "lr": 1.5155239811656562e-07, "epoch": 2.770700636942675, "percentage": 92.95, "elapsed_time": "0:27:50", "remaining_time": "0:02:06"}
|
| 146 |
+
{"current_steps": 146, "total_steps": 156, "loss": 0.6175, "lr": 1.253604390908819e-07, "epoch": 2.789808917197452, "percentage": 93.59, "elapsed_time": "0:28:05", "remaining_time": "0:01:55"}
|
| 147 |
+
{"current_steps": 147, "total_steps": 156, "loss": 0.6413, "lr": 1.0162300788382263e-07, "epoch": 2.8089171974522293, "percentage": 94.23, "elapsed_time": "0:28:17", "remaining_time": "0:01:43"}
|
| 148 |
+
{"current_steps": 148, "total_steps": 156, "loss": 0.5595, "lr": 8.035205700685167e-08, "epoch": 2.8280254777070066, "percentage": 94.87, "elapsed_time": "0:28:28", "remaining_time": "0:01:32"}
|
| 149 |
+
{"current_steps": 149, "total_steps": 156, "loss": 0.5932, "lr": 6.15582970243117e-08, "epoch": 2.8471337579617835, "percentage": 95.51, "elapsed_time": "0:28:53", "remaining_time": "0:01:21"}
|
| 150 |
+
{"current_steps": 150, "total_steps": 156, "loss": 0.583, "lr": 4.52511911603265e-08, "epoch": 2.8662420382165603, "percentage": 96.15, "elapsed_time": "0:29:06", "remaining_time": "0:01:09"}
|
| 151 |
+
{"current_steps": 151, "total_steps": 156, "loss": 0.5961, "lr": 3.143895053378698e-08, "epoch": 2.8853503184713376, "percentage": 96.79, "elapsed_time": "0:29:13", "remaining_time": "0:00:58"}
|
| 152 |
+
{"current_steps": 152, "total_steps": 156, "loss": 0.5726, "lr": 2.012853002380466e-08, "epoch": 2.904458598726115, "percentage": 97.44, "elapsed_time": "0:29:25", "remaining_time": "0:00:46"}
|
| 153 |
+
{"current_steps": 153, "total_steps": 156, "loss": 0.6533, "lr": 1.132562476771959e-08, "epoch": 2.9235668789808917, "percentage": 98.08, "elapsed_time": "0:29:55", "remaining_time": "0:00:35"}
|
| 154 |
+
{"current_steps": 154, "total_steps": 156, "loss": 0.5776, "lr": 5.034667293427053e-09, "epoch": 2.9426751592356686, "percentage": 98.72, "elapsed_time": "0:30:04", "remaining_time": "0:00:23"}
|
| 155 |
+
{"current_steps": 155, "total_steps": 156, "loss": 0.5784, "lr": 1.2588252874673469e-09, "epoch": 2.961783439490446, "percentage": 99.36, "elapsed_time": "0:30:11", "remaining_time": "0:00:11"}
|
| 156 |
+
{"current_steps": 156, "total_steps": 156, "loss": 0.6064, "lr": 0.0, "epoch": 2.980891719745223, "percentage": 100.0, "elapsed_time": "0:30:19", "remaining_time": "0:00:00"}
|
| 157 |
+
{"current_steps": 156, "total_steps": 156, "epoch": 2.980891719745223, "percentage": 100.0, "elapsed_time": "0:31:50", "remaining_time": "0:00:00"}
|