Training in progress, epoch 3
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:e880ca41b15369e419ef34b32c65b74948ee34131b026884fc3294e83f0b85c0
|
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 sha256:35f6078b96d3fd32dcf7a4b40f27797f1ca3bfa440b5ded92baf161da4342773
|
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 sha256:6a0f7502a08b9a35eaeffcc16f42e270e871309d099616e4eaa40a9487610386
|
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:df5e44267d8bb9b5715c41173ed8583e1acee65eb56dc63ae04546b0e868c259
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -114,3 +114,56 @@
|
|
114 |
{"current_steps": 114, "total_steps": 364, "loss": 0.2607, "lr": 1.738628069370195e-07, "epoch": 2.178343949044586, "percentage": 31.32, "elapsed_time": "0:28:46", "remaining_time": "1:03:05"}
|
115 |
{"current_steps": 115, "total_steps": 364, "loss": 0.2503, "lr": 1.7321176624044687e-07, "epoch": 2.1974522292993632, "percentage": 31.59, "elapsed_time": "0:28:57", "remaining_time": "1:02:42"}
|
116 |
{"current_steps": 116, "total_steps": 364, "loss": 0.2509, "lr": 1.7255396811032013e-07, "epoch": 2.21656050955414, "percentage": 31.87, "elapsed_time": "0:29:12", "remaining_time": "1:02:26"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
114 |
{"current_steps": 114, "total_steps": 364, "loss": 0.2607, "lr": 1.738628069370195e-07, "epoch": 2.178343949044586, "percentage": 31.32, "elapsed_time": "0:28:46", "remaining_time": "1:03:05"}
|
115 |
{"current_steps": 115, "total_steps": 364, "loss": 0.2503, "lr": 1.7321176624044687e-07, "epoch": 2.1974522292993632, "percentage": 31.59, "elapsed_time": "0:28:57", "remaining_time": "1:02:42"}
|
116 |
{"current_steps": 116, "total_steps": 364, "loss": 0.2509, "lr": 1.7255396811032013e-07, "epoch": 2.21656050955414, "percentage": 31.87, "elapsed_time": "0:29:12", "remaining_time": "1:02:26"}
|
117 |
+
{"current_steps": 117, "total_steps": 364, "loss": 0.2502, "lr": 1.718894732612947e-07, "epoch": 2.2356687898089174, "percentage": 32.14, "elapsed_time": "0:29:27", "remaining_time": "1:02:12"}
|
118 |
+
{"current_steps": 118, "total_steps": 364, "loss": 0.2639, "lr": 1.7121834302613186e-07, "epoch": 2.254777070063694, "percentage": 32.42, "elapsed_time": "0:29:38", "remaining_time": "1:01:47"}
|
119 |
+
{"current_steps": 119, "total_steps": 364, "loss": 0.2496, "lr": 1.7054063935003812e-07, "epoch": 2.2738853503184715, "percentage": 32.69, "elapsed_time": "0:29:51", "remaining_time": "1:01:27"}
|
120 |
+
{"current_steps": 120, "total_steps": 364, "loss": 0.2507, "lr": 1.6985642478494727e-07, "epoch": 2.2929936305732483, "percentage": 32.97, "elapsed_time": "0:30:04", "remaining_time": "1:01:08"}
|
121 |
+
{"current_steps": 121, "total_steps": 364, "loss": 0.2616, "lr": 1.6916576248374716e-07, "epoch": 2.3121019108280256, "percentage": 33.24, "elapsed_time": "0:30:18", "remaining_time": "1:00:52"}
|
122 |
+
{"current_steps": 122, "total_steps": 364, "loss": 0.2554, "lr": 1.684687161944506e-07, "epoch": 2.3312101910828025, "percentage": 33.52, "elapsed_time": "0:30:32", "remaining_time": "1:00:34"}
|
123 |
+
{"current_steps": 123, "total_steps": 364, "loss": 0.2559, "lr": 1.6776535025431129e-07, "epoch": 2.3503184713375798, "percentage": 33.79, "elapsed_time": "0:30:42", "remaining_time": "1:00:09"}
|
124 |
+
{"current_steps": 124, "total_steps": 364, "loss": 0.2603, "lr": 1.6705572958388573e-07, "epoch": 2.3694267515923566, "percentage": 34.07, "elapsed_time": "0:30:55", "remaining_time": "0:59:52"}
|
125 |
+
{"current_steps": 125, "total_steps": 364, "loss": 0.2439, "lr": 1.6633991968104092e-07, "epoch": 2.388535031847134, "percentage": 34.34, "elapsed_time": "0:31:11", "remaining_time": "0:59:38"}
|
126 |
+
{"current_steps": 126, "total_steps": 364, "loss": 0.2514, "lr": 1.6561798661490902e-07, "epoch": 2.4076433121019107, "percentage": 34.62, "elapsed_time": "0:31:21", "remaining_time": "0:59:14"}
|
127 |
+
{"current_steps": 127, "total_steps": 364, "loss": 0.2522, "lr": 1.6488999701978902e-07, "epoch": 2.426751592356688, "percentage": 34.89, "elapsed_time": "0:31:34", "remaining_time": "0:58:55"}
|
128 |
+
{"current_steps": 128, "total_steps": 364, "loss": 0.2634, "lr": 1.6415601808899658e-07, "epoch": 2.445859872611465, "percentage": 35.16, "elapsed_time": "0:31:48", "remaining_time": "0:58:39"}
|
129 |
+
{"current_steps": 129, "total_steps": 364, "loss": 0.2523, "lr": 1.63416117568662e-07, "epoch": 2.464968152866242, "percentage": 35.44, "elapsed_time": "0:32:02", "remaining_time": "0:58:22"}
|
130 |
+
{"current_steps": 130, "total_steps": 364, "loss": 0.2519, "lr": 1.6267036375147723e-07, "epoch": 2.484076433121019, "percentage": 35.71, "elapsed_time": "0:32:18", "remaining_time": "0:58:09"}
|
131 |
+
{"current_steps": 131, "total_steps": 364, "loss": 0.257, "lr": 1.6191882547039266e-07, "epoch": 2.5031847133757963, "percentage": 35.99, "elapsed_time": "0:32:32", "remaining_time": "0:57:52"}
|
132 |
+
{"current_steps": 132, "total_steps": 364, "loss": 0.2647, "lr": 1.6116157209226352e-07, "epoch": 2.522292993630573, "percentage": 36.26, "elapsed_time": "0:32:48", "remaining_time": "0:57:39"}
|
133 |
+
{"current_steps": 133, "total_steps": 364, "loss": 0.2647, "lr": 1.6039867351144777e-07, "epoch": 2.5414012738853504, "percentage": 36.54, "elapsed_time": "0:33:00", "remaining_time": "0:57:19"}
|
134 |
+
{"current_steps": 134, "total_steps": 364, "loss": 0.2559, "lr": 1.5963020014335436e-07, "epoch": 2.5605095541401273, "percentage": 36.81, "elapsed_time": "0:33:15", "remaining_time": "0:57:04"}
|
135 |
+
{"current_steps": 135, "total_steps": 364, "loss": 0.2473, "lr": 1.5885622291794428e-07, "epoch": 2.5796178343949046, "percentage": 37.09, "elapsed_time": "0:33:25", "remaining_time": "0:56:42"}
|
136 |
+
{"current_steps": 136, "total_steps": 364, "loss": 0.2564, "lr": 1.580768132731837e-07, "epoch": 2.5987261146496814, "percentage": 37.36, "elapsed_time": "0:33:39", "remaining_time": "0:56:25"}
|
137 |
+
{"current_steps": 137, "total_steps": 364, "loss": 0.2593, "lr": 1.5729204314845e-07, "epoch": 2.6178343949044587, "percentage": 37.64, "elapsed_time": "0:33:50", "remaining_time": "0:56:03"}
|
138 |
+
{"current_steps": 138, "total_steps": 364, "loss": 0.2618, "lr": 1.56501984977892e-07, "epoch": 2.6369426751592355, "percentage": 37.91, "elapsed_time": "0:34:01", "remaining_time": "0:55:43"}
|
139 |
+
{"current_steps": 139, "total_steps": 364, "loss": 0.2702, "lr": 1.5570671168374436e-07, "epoch": 2.656050955414013, "percentage": 38.19, "elapsed_time": "0:34:15", "remaining_time": "0:55:26"}
|
140 |
+
{"current_steps": 140, "total_steps": 364, "loss": 0.2604, "lr": 1.5490629666959666e-07, "epoch": 2.6751592356687897, "percentage": 38.46, "elapsed_time": "0:34:30", "remaining_time": "0:55:12"}
|
141 |
+
{"current_steps": 141, "total_steps": 364, "loss": 0.2671, "lr": 1.5410081381361829e-07, "epoch": 2.694267515923567, "percentage": 38.74, "elapsed_time": "0:34:43", "remaining_time": "0:54:54"}
|
142 |
+
{"current_steps": 142, "total_steps": 364, "loss": 0.2535, "lr": 1.5329033746173973e-07, "epoch": 2.713375796178344, "percentage": 39.01, "elapsed_time": "0:34:55", "remaining_time": "0:54:35"}
|
143 |
+
{"current_steps": 143, "total_steps": 364, "loss": 0.252, "lr": 1.5247494242079021e-07, "epoch": 2.732484076433121, "percentage": 39.29, "elapsed_time": "0:35:09", "remaining_time": "0:54:20"}
|
144 |
+
{"current_steps": 144, "total_steps": 364, "loss": 0.2517, "lr": 1.5165470395159313e-07, "epoch": 2.7515923566878984, "percentage": 39.56, "elapsed_time": "0:35:24", "remaining_time": "0:54:06"}
|
145 |
+
{"current_steps": 145, "total_steps": 364, "loss": 0.2485, "lr": 1.5082969776201945e-07, "epoch": 2.770700636942675, "percentage": 39.84, "elapsed_time": "0:35:36", "remaining_time": "0:53:47"}
|
146 |
+
{"current_steps": 146, "total_steps": 364, "loss": 0.2549, "lr": 1.5e-07, "epoch": 2.789808917197452, "percentage": 40.11, "elapsed_time": "0:35:50", "remaining_time": "0:53:30"}
|
147 |
+
{"current_steps": 147, "total_steps": 364, "loss": 0.2526, "lr": 1.4916568724649686e-07, "epoch": 2.8089171974522293, "percentage": 40.38, "elapsed_time": "0:36:03", "remaining_time": "0:53:13"}
|
148 |
+
{"current_steps": 148, "total_steps": 364, "loss": 0.2569, "lr": 1.4832683650843506e-07, "epoch": 2.8280254777070066, "percentage": 40.66, "elapsed_time": "0:36:16", "remaining_time": "0:52:55"}
|
149 |
+
{"current_steps": 149, "total_steps": 364, "loss": 0.2543, "lr": 1.4748352521159491e-07, "epoch": 2.8471337579617835, "percentage": 40.93, "elapsed_time": "0:36:27", "remaining_time": "0:52:36"}
|
150 |
+
{"current_steps": 150, "total_steps": 364, "loss": 0.2414, "lr": 1.4663583119346538e-07, "epoch": 2.8662420382165603, "percentage": 41.21, "elapsed_time": "0:36:43", "remaining_time": "0:52:23"}
|
151 |
+
{"current_steps": 151, "total_steps": 364, "loss": 0.2645, "lr": 1.4578383269606002e-07, "epoch": 2.8853503184713376, "percentage": 41.48, "elapsed_time": "0:36:57", "remaining_time": "0:52:07"}
|
152 |
+
{"current_steps": 152, "total_steps": 364, "loss": 0.2524, "lr": 1.4492760835869502e-07, "epoch": 2.904458598726115, "percentage": 41.76, "elapsed_time": "0:37:12", "remaining_time": "0:51:54"}
|
153 |
+
{"current_steps": 153, "total_steps": 364, "loss": 0.2399, "lr": 1.4406723721073087e-07, "epoch": 2.9235668789808917, "percentage": 42.03, "elapsed_time": "0:37:26", "remaining_time": "0:51:37"}
|
154 |
+
{"current_steps": 154, "total_steps": 364, "loss": 0.2491, "lr": 1.4320279866427796e-07, "epoch": 2.9426751592356686, "percentage": 42.31, "elapsed_time": "0:37:40", "remaining_time": "0:51:22"}
|
155 |
+
{"current_steps": 155, "total_steps": 364, "loss": 0.2556, "lr": 1.4233437250686693e-07, "epoch": 2.961783439490446, "percentage": 42.58, "elapsed_time": "0:37:53", "remaining_time": "0:51:05"}
|
156 |
+
{"current_steps": 156, "total_steps": 364, "loss": 0.242, "lr": 1.4146203889408418e-07, "epoch": 2.980891719745223, "percentage": 42.86, "elapsed_time": "0:38:08", "remaining_time": "0:50:51"}
|
157 |
+
{"current_steps": 157, "total_steps": 364, "loss": 0.2584, "lr": 1.4058587834217354e-07, "epoch": 3.0, "percentage": 43.13, "elapsed_time": "0:38:22", "remaining_time": "0:50:36"}
|
158 |
+
{"current_steps": 158, "total_steps": 364, "loss": 0.2591, "lr": 1.397059717206048e-07, "epoch": 3.0191082802547773, "percentage": 43.41, "elapsed_time": "0:40:18", "remaining_time": "0:52:33"}
|
159 |
+
{"current_steps": 159, "total_steps": 364, "loss": 0.2587, "lr": 1.3882240024460924e-07, "epoch": 3.038216560509554, "percentage": 43.68, "elapsed_time": "0:40:31", "remaining_time": "0:52:14"}
|
160 |
+
{"current_steps": 160, "total_steps": 364, "loss": 0.2603, "lr": 1.3793524546768356e-07, "epoch": 3.0573248407643314, "percentage": 43.96, "elapsed_time": "0:40:45", "remaining_time": "0:51:57"}
|
161 |
+
{"current_steps": 161, "total_steps": 364, "loss": 0.2594, "lr": 1.370445892740626e-07, "epoch": 3.0764331210191083, "percentage": 44.23, "elapsed_time": "0:41:00", "remaining_time": "0:51:42"}
|
162 |
+
{"current_steps": 162, "total_steps": 364, "loss": 0.2538, "lr": 1.361505138711613e-07, "epoch": 3.0955414012738856, "percentage": 44.51, "elapsed_time": "0:41:13", "remaining_time": "0:51:24"}
|
163 |
+
{"current_steps": 163, "total_steps": 364, "loss": 0.2658, "lr": 1.3525310178198706e-07, "epoch": 3.1146496815286624, "percentage": 44.78, "elapsed_time": "0:41:25", "remaining_time": "0:51:04"}
|
164 |
+
{"current_steps": 164, "total_steps": 364, "loss": 0.2495, "lr": 1.343524358375229e-07, "epoch": 3.1337579617834397, "percentage": 45.05, "elapsed_time": "0:41:40", "remaining_time": "0:50:49"}
|
165 |
+
{"current_steps": 165, "total_steps": 364, "loss": 0.2574, "lr": 1.3344859916908204e-07, "epoch": 3.1528662420382165, "percentage": 45.33, "elapsed_time": "0:41:52", "remaining_time": "0:50:30"}
|
166 |
+
{"current_steps": 166, "total_steps": 364, "loss": 0.2548, "lr": 1.325416752006351e-07, "epoch": 3.171974522292994, "percentage": 45.6, "elapsed_time": "0:42:05", "remaining_time": "0:50:12"}
|
167 |
+
{"current_steps": 167, "total_steps": 364, "loss": 0.248, "lr": 1.3163174764110982e-07, "epoch": 3.1910828025477707, "percentage": 45.88, "elapsed_time": "0:42:15", "remaining_time": "0:49:50"}
|
168 |
+
{"current_steps": 168, "total_steps": 364, "loss": 0.2469, "lr": 1.3071890047666496e-07, "epoch": 3.210191082802548, "percentage": 46.15, "elapsed_time": "0:42:30", "remaining_time": "0:49:35"}
|
169 |
+
{"current_steps": 169, "total_steps": 364, "loss": 0.2433, "lr": 1.2980321796293835e-07, "epoch": 3.229299363057325, "percentage": 46.43, "elapsed_time": "0:42:42", "remaining_time": "0:49:16"}
|