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 sha256:8dee014aeb01b989280006be855b4856d095d101a59e99d363317dbb537695fa
|
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 sha256:86288d0b1548568f19554115a593385f50ca3fcd07910624203502baac33bd2f
|
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 sha256:1171cbb2531120ef43ed087b11ec320e4f70cbb1b9e1b1e716610b1c88876c7f
|
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 sha256:9c4c449cda703e337c39dcb2c4af11e5f557ffa0bb0e7d9d4e3448520bb57c95
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -120,3 +120,62 @@
|
|
120 |
{"current_steps": 120, "total_steps": 180, "loss": 0.5866, "lr": 2.4156809358433728e-05, "epoch": 1.9793814432989691, "percentage": 66.67, "elapsed_time": "2:00:32", "remaining_time": "1:00:16"}
|
121 |
{"current_steps": 121, "total_steps": 180, "loss": 0.7221, "lr": 2.3447571019794438e-05, "epoch": 1.9958762886597938, "percentage": 67.22, "elapsed_time": "2:01:30", "remaining_time": "0:59:15"}
|
122 |
{"current_steps": 122, "total_steps": 180, "loss": 0.649, "lr": 2.274455737274987e-05, "epoch": 2.0123711340206185, "percentage": 67.78, "elapsed_time": "2:04:09", "remaining_time": "0:59:01"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
120 |
{"current_steps": 120, "total_steps": 180, "loss": 0.5866, "lr": 2.4156809358433728e-05, "epoch": 1.9793814432989691, "percentage": 66.67, "elapsed_time": "2:00:32", "remaining_time": "1:00:16"}
|
121 |
{"current_steps": 121, "total_steps": 180, "loss": 0.7221, "lr": 2.3447571019794438e-05, "epoch": 1.9958762886597938, "percentage": 67.22, "elapsed_time": "2:01:30", "remaining_time": "0:59:15"}
|
122 |
{"current_steps": 122, "total_steps": 180, "loss": 0.649, "lr": 2.274455737274987e-05, "epoch": 2.0123711340206185, "percentage": 67.78, "elapsed_time": "2:04:09", "remaining_time": "0:59:01"}
|
123 |
+
{"current_steps": 123, "total_steps": 180, "loss": 0.5525, "lr": 2.2048032791981515e-05, "epoch": 2.028865979381443, "percentage": 68.33, "elapsed_time": "2:05:08", "remaining_time": "0:57:59"}
|
124 |
+
{"current_steps": 124, "total_steps": 180, "loss": 0.5518, "lr": 2.135825921189846e-05, "epoch": 2.045360824742268, "percentage": 68.89, "elapsed_time": "2:06:06", "remaining_time": "0:56:57"}
|
125 |
+
{"current_steps": 125, "total_steps": 180, "loss": 0.5537, "lr": 2.067549602813446e-05, "epoch": 2.0618556701030926, "percentage": 69.44, "elapsed_time": "2:07:05", "remaining_time": "0:55:55"}
|
126 |
+
{"current_steps": 126, "total_steps": 180, "loss": 0.5468, "lr": 2.0000000000000012e-05, "epoch": 2.0783505154639177, "percentage": 70.0, "elapsed_time": "2:08:03", "remaining_time": "0:54:53"}
|
127 |
+
{"current_steps": 127, "total_steps": 180, "loss": 0.554, "lr": 1.9332025153925486e-05, "epoch": 2.0948453608247424, "percentage": 70.56, "elapsed_time": "2:09:02", "remaining_time": "0:53:51"}
|
128 |
+
{"current_steps": 128, "total_steps": 180, "loss": 0.5481, "lr": 1.867182268793236e-05, "epoch": 2.111340206185567, "percentage": 71.11, "elapsed_time": "2:10:00", "remaining_time": "0:52:49"}
|
129 |
+
{"current_steps": 129, "total_steps": 180, "loss": 0.551, "lr": 1.8019640877167763e-05, "epoch": 2.1278350515463917, "percentage": 71.67, "elapsed_time": "2:10:59", "remaining_time": "0:51:47"}
|
130 |
+
{"current_steps": 130, "total_steps": 180, "loss": 0.5485, "lr": 1.7375724980538465e-05, "epoch": 2.1443298969072164, "percentage": 72.22, "elapsed_time": "2:11:57", "remaining_time": "0:50:45"}
|
131 |
+
{"current_steps": 131, "total_steps": 180, "loss": 0.5513, "lr": 1.6740317148478932e-05, "epoch": 2.160824742268041, "percentage": 72.78, "elapsed_time": "2:12:56", "remaining_time": "0:49:43"}
|
132 |
+
{"current_steps": 132, "total_steps": 180, "loss": 0.546, "lr": 1.6113656331888563e-05, "epoch": 2.177319587628866, "percentage": 73.33, "elapsed_time": "2:13:55", "remaining_time": "0:48:41"}
|
133 |
+
{"current_steps": 133, "total_steps": 180, "loss": 0.5507, "lr": 1.5495978192271887e-05, "epoch": 2.193814432989691, "percentage": 73.89, "elapsed_time": "2:14:53", "remaining_time": "0:47:40"}
|
134 |
+
{"current_steps": 134, "total_steps": 180, "loss": 0.5474, "lr": 1.4887515013116067e-05, "epoch": 2.2103092783505156, "percentage": 74.44, "elapsed_time": "2:15:52", "remaining_time": "0:46:38"}
|
135 |
+
{"current_steps": 135, "total_steps": 180, "loss": 0.5466, "lr": 1.4288495612538427e-05, "epoch": 2.2268041237113403, "percentage": 75.0, "elapsed_time": "2:16:50", "remaining_time": "0:45:36"}
|
136 |
+
{"current_steps": 136, "total_steps": 180, "loss": 0.5546, "lr": 1.369914525723746e-05, "epoch": 2.243298969072165, "percentage": 75.56, "elapsed_time": "2:17:49", "remaining_time": "0:44:35"}
|
137 |
+
{"current_steps": 137, "total_steps": 180, "loss": 0.5443, "lr": 1.3119685577779105e-05, "epoch": 2.2597938144329897, "percentage": 76.11, "elapsed_time": "2:18:47", "remaining_time": "0:43:33"}
|
138 |
+
{"current_steps": 138, "total_steps": 180, "loss": 0.5499, "lr": 1.2550334485250661e-05, "epoch": 2.2762886597938143, "percentage": 76.67, "elapsed_time": "2:19:46", "remaining_time": "0:42:32"}
|
139 |
+
{"current_steps": 139, "total_steps": 180, "loss": 0.5479, "lr": 1.1991306089313261e-05, "epoch": 2.292783505154639, "percentage": 77.22, "elapsed_time": "2:20:44", "remaining_time": "0:41:30"}
|
140 |
+
{"current_steps": 140, "total_steps": 180, "loss": 0.5489, "lr": 1.1442810617684046e-05, "epoch": 2.3092783505154637, "percentage": 77.78, "elapsed_time": "2:21:43", "remaining_time": "0:40:29"}
|
141 |
+
{"current_steps": 141, "total_steps": 180, "loss": 0.5499, "lr": 1.0905054337078051e-05, "epoch": 2.325773195876289, "percentage": 78.33, "elapsed_time": "2:22:41", "remaining_time": "0:39:28"}
|
142 |
+
{"current_steps": 142, "total_steps": 180, "loss": 0.5469, "lr": 1.0378239475639823e-05, "epoch": 2.3422680412371135, "percentage": 78.89, "elapsed_time": "2:23:40", "remaining_time": "0:38:26"}
|
143 |
+
{"current_steps": 143, "total_steps": 180, "loss": 0.5533, "lr": 9.862564146893571e-06, "epoch": 2.358762886597938, "percentage": 79.44, "elapsed_time": "2:24:39", "remaining_time": "0:37:25"}
|
144 |
+
{"current_steps": 144, "total_steps": 180, "loss": 0.5492, "lr": 9.358222275240884e-06, "epoch": 2.375257731958763, "percentage": 80.0, "elapsed_time": "2:25:37", "remaining_time": "0:36:24"}
|
145 |
+
{"current_steps": 145, "total_steps": 180, "loss": 0.549, "lr": 8.8654035230336e-06, "epoch": 2.3917525773195876, "percentage": 80.56, "elapsed_time": "2:26:36", "remaining_time": "0:35:23"}
|
146 |
+
{"current_steps": 146, "total_steps": 180, "loss": 0.5472, "lr": 8.384293219249633e-06, "epoch": 2.4082474226804123, "percentage": 81.11, "elapsed_time": "2:27:34", "remaining_time": "0:34:22"}
|
147 |
+
{"current_steps": 147, "total_steps": 180, "loss": 0.5439, "lr": 7.915072289798247e-06, "epoch": 2.424742268041237, "percentage": 81.67, "elapsed_time": "2:28:33", "remaining_time": "0:33:20"}
|
148 |
+
{"current_steps": 148, "total_steps": 180, "loss": 0.5465, "lr": 7.457917189481301e-06, "epoch": 2.441237113402062, "percentage": 82.22, "elapsed_time": "2:29:31", "remaining_time": "0:32:19"}
|
149 |
+
{"current_steps": 149, "total_steps": 180, "loss": 0.5454, "lr": 7.0129998356357295e-06, "epoch": 2.4577319587628867, "percentage": 82.78, "elapsed_time": "2:30:30", "remaining_time": "0:31:18"}
|
150 |
+
{"current_steps": 150, "total_steps": 180, "loss": 0.5532, "lr": 6.58048754348255e-06, "epoch": 2.4742268041237114, "percentage": 83.33, "elapsed_time": "2:31:28", "remaining_time": "0:30:17"}
|
151 |
+
{"current_steps": 151, "total_steps": 180, "loss": 0.5462, "lr": 6.160542963206357e-06, "epoch": 2.490721649484536, "percentage": 83.89, "elapsed_time": "2:32:27", "remaining_time": "0:29:16"}
|
152 |
+
{"current_steps": 152, "total_steps": 180, "loss": 0.5467, "lr": 5.753324018789346e-06, "epoch": 2.507216494845361, "percentage": 84.44, "elapsed_time": "2:33:26", "remaining_time": "0:28:15"}
|
153 |
+
{"current_steps": 153, "total_steps": 180, "loss": 0.5464, "lr": 5.358983848622452e-06, "epoch": 2.5237113402061855, "percentage": 85.0, "elapsed_time": "2:34:24", "remaining_time": "0:27:14"}
|
154 |
+
{"current_steps": 154, "total_steps": 180, "loss": 0.5437, "lr": 4.97767074791637e-06, "epoch": 2.54020618556701, "percentage": 85.56, "elapsed_time": "2:35:23", "remaining_time": "0:26:14"}
|
155 |
+
{"current_steps": 155, "total_steps": 180, "loss": 0.5477, "lr": 4.609528112933688e-06, "epoch": 2.556701030927835, "percentage": 86.11, "elapsed_time": "2:36:21", "remaining_time": "0:25:13"}
|
156 |
+
{"current_steps": 156, "total_steps": 180, "loss": 0.5469, "lr": 4.254694387063514e-06, "epoch": 2.5731958762886595, "percentage": 86.67, "elapsed_time": "2:37:20", "remaining_time": "0:24:12"}
|
157 |
+
{"current_steps": 157, "total_steps": 180, "loss": 0.5482, "lr": 3.913303008758491e-06, "epoch": 2.5896907216494847, "percentage": 87.22, "elapsed_time": "2:38:18", "remaining_time": "0:23:11"}
|
158 |
+
{"current_steps": 158, "total_steps": 180, "loss": 0.5463, "lr": 3.585482361354138e-06, "epoch": 2.6061855670103093, "percentage": 87.78, "elapsed_time": "2:39:17", "remaining_time": "0:22:10"}
|
159 |
+
{"current_steps": 159, "total_steps": 180, "loss": 0.549, "lr": 3.2713557247890447e-06, "epoch": 2.622680412371134, "percentage": 88.33, "elapsed_time": "2:40:15", "remaining_time": "0:21:10"}
|
160 |
+
{"current_steps": 160, "total_steps": 180, "loss": 0.5447, "lr": 2.9710412292443868e-06, "epoch": 2.6391752577319587, "percentage": 88.89, "elapsed_time": "2:41:14", "remaining_time": "0:20:09"}
|
161 |
+
{"current_steps": 161, "total_steps": 180, "loss": 0.5499, "lr": 2.6846518107199782e-06, "epoch": 2.6556701030927834, "percentage": 89.44, "elapsed_time": "2:42:12", "remaining_time": "0:19:08"}
|
162 |
+
{"current_steps": 162, "total_steps": 180, "loss": 0.5476, "lr": 2.4122951685636674e-06, "epoch": 2.6721649484536085, "percentage": 90.0, "elapsed_time": "2:43:11", "remaining_time": "0:18:07"}
|
163 |
+
{"current_steps": 163, "total_steps": 180, "loss": 0.5468, "lr": 2.1540737249699893e-06, "epoch": 2.688659793814433, "percentage": 90.56, "elapsed_time": "2:44:09", "remaining_time": "0:17:07"}
|
164 |
+
{"current_steps": 164, "total_steps": 180, "loss": 0.5447, "lr": 1.9100845864633875e-06, "epoch": 2.705154639175258, "percentage": 91.11, "elapsed_time": "2:45:08", "remaining_time": "0:16:06"}
|
165 |
+
{"current_steps": 165, "total_steps": 180, "loss": 0.547, "lr": 1.6804195073804442e-06, "epoch": 2.7216494845360826, "percentage": 91.67, "elapsed_time": "2:46:07", "remaining_time": "0:15:06"}
|
166 |
+
{"current_steps": 166, "total_steps": 180, "loss": 0.548, "lr": 1.4651648553647869e-06, "epoch": 2.7381443298969073, "percentage": 92.22, "elapsed_time": "2:47:05", "remaining_time": "0:14:05"}
|
167 |
+
{"current_steps": 167, "total_steps": 180, "loss": 0.5424, "lr": 1.2644015788877684e-06, "epoch": 2.754639175257732, "percentage": 92.78, "elapsed_time": "2:48:04", "remaining_time": "0:13:05"}
|
168 |
+
{"current_steps": 168, "total_steps": 180, "loss": 0.5426, "lr": 1.0782051768070477e-06, "epoch": 2.7711340206185566, "percentage": 93.33, "elapsed_time": "2:49:02", "remaining_time": "0:12:04"}
|
169 |
+
{"current_steps": 169, "total_steps": 180, "loss": 0.5423, "lr": 9.066456699745774e-07, "epoch": 2.7876288659793813, "percentage": 93.89, "elapsed_time": "2:50:01", "remaining_time": "0:11:03"}
|
170 |
+
{"current_steps": 170, "total_steps": 180, "loss": 0.5491, "lr": 7.497875749046124e-07, "epoch": 2.804123711340206, "percentage": 94.44, "elapsed_time": "2:50:59", "remaining_time": "0:10:03"}
|
171 |
+
{"current_steps": 171, "total_steps": 180, "loss": 0.5466, "lr": 6.076898795116792e-07, "epoch": 2.8206185567010307, "percentage": 95.0, "elapsed_time": "2:51:58", "remaining_time": "0:09:03"}
|
172 |
+
{"current_steps": 172, "total_steps": 180, "loss": 0.5481, "lr": 4.804060209276396e-07, "epoch": 2.837113402061856, "percentage": 95.56, "elapsed_time": "2:52:56", "remaining_time": "0:08:02"}
|
173 |
+
{"current_steps": 173, "total_steps": 180, "loss": 0.5466, "lr": 3.679838654061874e-07, "epoch": 2.8536082474226805, "percentage": 96.11, "elapsed_time": "2:53:55", "remaining_time": "0:07:02"}
|
174 |
+
{"current_steps": 174, "total_steps": 180, "loss": 0.5481, "lr": 2.704656903222791e-07, "epoch": 2.870103092783505, "percentage": 96.67, "elapsed_time": "2:54:53", "remaining_time": "0:06:01"}
|
175 |
+
{"current_steps": 175, "total_steps": 180, "loss": 0.5488, "lr": 1.8788816827336686e-07, "epoch": 2.88659793814433, "percentage": 97.22, "elapsed_time": "2:55:52", "remaining_time": "0:05:01"}
|
176 |
+
{"current_steps": 176, "total_steps": 180, "loss": 0.5457, "lr": 1.2028235328831906e-07, "epoch": 2.9030927835051545, "percentage": 97.78, "elapsed_time": "2:56:51", "remaining_time": "0:04:01"}
|
177 |
+
{"current_steps": 177, "total_steps": 180, "loss": 0.5482, "lr": 6.767366914927298e-08, "epoch": 2.9195876288659792, "percentage": 98.33, "elapsed_time": "2:57:49", "remaining_time": "0:03:00"}
|
178 |
+
{"current_steps": 178, "total_steps": 180, "loss": 0.5468, "lr": 3.0081899830798345e-08, "epoch": 2.9360824742268044, "percentage": 98.89, "elapsed_time": "2:58:48", "remaining_time": "0:02:00"}
|
179 |
+
{"current_steps": 179, "total_steps": 180, "loss": 0.5457, "lr": 7.521182059946342e-09, "epoch": 2.952577319587629, "percentage": 99.44, "elapsed_time": "2:59:46", "remaining_time": "0:01:00"}
|
180 |
+
{"current_steps": 180, "total_steps": 180, "loss": 0.5454, "lr": 0.0, "epoch": 2.9690721649484537, "percentage": 100.0, "elapsed_time": "3:00:45", "remaining_time": "0:00:00"}
|
181 |
+
{"current_steps": 180, "total_steps": 180, "epoch": 2.9690721649484537, "percentage": 100.0, "elapsed_time": "3:02:09", "remaining_time": "0:00:00"}
|