Training in progress, step 4500
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 4968243304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:983b7ab8e5b35c70b4db2fae38c8015b43df4fe6383a6ef3f28f5937f8f99847
|
3 |
size 4968243304
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4991495816
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d7d726763f094faa1185f2b893aefee0b30af6dcd7e4de0df5159ca0b8e8d7f
|
3 |
size 4991495816
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4932751040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f95c1310cc681be63f98021fddba1024afec1ff005d55cf80e5ddf32258e4c9
|
3 |
size 4932751040
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1691924384
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0422f016f5459c6ec20282be5a92b47e6f7d97d1f48827b0b1899846e5bd47bb
|
3 |
size 1691924384
|
trainer_log.jsonl
CHANGED
@@ -146,3 +146,53 @@
|
|
146 |
{"current_steps": 3990, "total_steps": 7042, "loss": 0.318, "lr": 9.42276770685305e-06, "epoch": 1.1332007952286283, "percentage": 56.66, "elapsed_time": "12:09:07", "remaining_time": "9:17:43"}
|
147 |
{"current_steps": 4000, "total_steps": 7042, "loss": 0.316, "lr": 9.373282270763087e-06, "epoch": 1.136040897472309, "percentage": 56.8, "elapsed_time": "12:10:56", "remaining_time": "9:15:52"}
|
148 |
{"current_steps": 4010, "total_steps": 7042, "loss": 0.3122, "lr": 9.323812237605977e-06, "epoch": 1.1388809997159899, "percentage": 56.94, "elapsed_time": "12:13:50", "remaining_time": "9:14:51"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
146 |
{"current_steps": 3990, "total_steps": 7042, "loss": 0.318, "lr": 9.42276770685305e-06, "epoch": 1.1332007952286283, "percentage": 56.66, "elapsed_time": "12:09:07", "remaining_time": "9:17:43"}
|
147 |
{"current_steps": 4000, "total_steps": 7042, "loss": 0.316, "lr": 9.373282270763087e-06, "epoch": 1.136040897472309, "percentage": 56.8, "elapsed_time": "12:10:56", "remaining_time": "9:15:52"}
|
148 |
{"current_steps": 4010, "total_steps": 7042, "loss": 0.3122, "lr": 9.323812237605977e-06, "epoch": 1.1388809997159899, "percentage": 56.94, "elapsed_time": "12:13:50", "remaining_time": "9:14:51"}
|
149 |
+
{"current_steps": 4020, "total_steps": 7042, "loss": 0.3107, "lr": 9.274358823213938e-06, "epoch": 1.1417211019596705, "percentage": 57.09, "elapsed_time": "12:15:40", "remaining_time": "9:13:02"}
|
150 |
+
{"current_steps": 4030, "total_steps": 7042, "loss": 0.3166, "lr": 9.224923243010722e-06, "epoch": 1.1445612042033513, "percentage": 57.23, "elapsed_time": "12:17:30", "remaining_time": "9:11:12"}
|
151 |
+
{"current_steps": 4040, "total_steps": 7042, "loss": 0.3119, "lr": 9.175506711981782e-06, "epoch": 1.147401306447032, "percentage": 57.37, "elapsed_time": "12:19:17", "remaining_time": "9:09:20"}
|
152 |
+
{"current_steps": 4050, "total_steps": 7042, "loss": 0.3086, "lr": 9.1261104446444e-06, "epoch": 1.150241408690713, "percentage": 57.51, "elapsed_time": "12:21:07", "remaining_time": "9:07:31"}
|
153 |
+
{"current_steps": 4060, "total_steps": 7042, "loss": 0.3181, "lr": 9.076735655017822e-06, "epoch": 1.1530815109343937, "percentage": 57.65, "elapsed_time": "12:22:55", "remaining_time": "9:05:39"}
|
154 |
+
{"current_steps": 4070, "total_steps": 7042, "loss": 0.3178, "lr": 9.027383556593443e-06, "epoch": 1.1559216131780743, "percentage": 57.8, "elapsed_time": "12:24:41", "remaining_time": "9:03:47"}
|
155 |
+
{"current_steps": 4080, "total_steps": 7042, "loss": 0.3175, "lr": 8.978055362304974e-06, "epoch": 1.158761715421755, "percentage": 57.94, "elapsed_time": "12:26:29", "remaining_time": "9:01:56"}
|
156 |
+
{"current_steps": 4090, "total_steps": 7042, "loss": 0.3041, "lr": 8.928752284498616e-06, "epoch": 1.161601817665436, "percentage": 58.08, "elapsed_time": "12:28:18", "remaining_time": "9:00:06"}
|
157 |
+
{"current_steps": 4100, "total_steps": 7042, "loss": 0.3094, "lr": 8.879475534903292e-06, "epoch": 1.1644419199091167, "percentage": 58.22, "elapsed_time": "12:30:06", "remaining_time": "8:58:15"}
|
158 |
+
{"current_steps": 4110, "total_steps": 7042, "loss": 0.3102, "lr": 8.83022632460086e-06, "epoch": 1.1672820221527975, "percentage": 58.36, "elapsed_time": "12:31:54", "remaining_time": "8:56:23"}
|
159 |
+
{"current_steps": 4120, "total_steps": 7042, "loss": 0.3098, "lr": 8.781005863996318e-06, "epoch": 1.1701221243964783, "percentage": 58.51, "elapsed_time": "12:33:42", "remaining_time": "8:54:32"}
|
160 |
+
{"current_steps": 4130, "total_steps": 7042, "loss": 0.3149, "lr": 8.731815362788097e-06, "epoch": 1.1729622266401591, "percentage": 58.65, "elapsed_time": "12:35:31", "remaining_time": "8:52:42"}
|
161 |
+
{"current_steps": 4140, "total_steps": 7042, "loss": 0.3221, "lr": 8.682656029938304e-06, "epoch": 1.1758023288838397, "percentage": 58.79, "elapsed_time": "12:37:20", "remaining_time": "8:50:52"}
|
162 |
+
{"current_steps": 4150, "total_steps": 7042, "loss": 0.3109, "lr": 8.633529073643015e-06, "epoch": 1.1786424311275205, "percentage": 58.93, "elapsed_time": "12:39:08", "remaining_time": "8:49:01"}
|
163 |
+
{"current_steps": 4160, "total_steps": 7042, "loss": 0.3113, "lr": 8.58443570130259e-06, "epoch": 1.1814825333712013, "percentage": 59.07, "elapsed_time": "12:40:53", "remaining_time": "8:47:07"}
|
164 |
+
{"current_steps": 4170, "total_steps": 7042, "loss": 0.3192, "lr": 8.535377119491992e-06, "epoch": 1.1843226356148822, "percentage": 59.22, "elapsed_time": "12:42:42", "remaining_time": "8:45:18"}
|
165 |
+
{"current_steps": 4180, "total_steps": 7042, "loss": 0.3101, "lr": 8.486354533931114e-06, "epoch": 1.187162737858563, "percentage": 59.36, "elapsed_time": "12:44:32", "remaining_time": "8:43:28"}
|
166 |
+
{"current_steps": 4190, "total_steps": 7042, "loss": 0.3189, "lr": 8.437369149455188e-06, "epoch": 1.1900028401022438, "percentage": 59.5, "elapsed_time": "12:46:18", "remaining_time": "8:41:36"}
|
167 |
+
{"current_steps": 4200, "total_steps": 7042, "loss": 0.309, "lr": 8.388422169985133e-06, "epoch": 1.1928429423459244, "percentage": 59.64, "elapsed_time": "12:48:09", "remaining_time": "8:39:47"}
|
168 |
+
{"current_steps": 4210, "total_steps": 7042, "loss": 0.3129, "lr": 8.33951479849799e-06, "epoch": 1.1956830445896052, "percentage": 59.78, "elapsed_time": "12:50:00", "remaining_time": "8:37:58"}
|
169 |
+
{"current_steps": 4220, "total_steps": 7042, "loss": 0.3151, "lr": 8.29064823699735e-06, "epoch": 1.198523146833286, "percentage": 59.93, "elapsed_time": "12:51:46", "remaining_time": "8:36:05"}
|
170 |
+
{"current_steps": 4230, "total_steps": 7042, "loss": 0.3183, "lr": 8.241823686483803e-06, "epoch": 1.2013632490769668, "percentage": 60.07, "elapsed_time": "12:53:37", "remaining_time": "8:34:16"}
|
171 |
+
{"current_steps": 4240, "total_steps": 7042, "loss": 0.3103, "lr": 8.193042346925436e-06, "epoch": 1.2042033513206476, "percentage": 60.21, "elapsed_time": "12:55:25", "remaining_time": "8:32:26"}
|
172 |
+
{"current_steps": 4250, "total_steps": 7042, "loss": 0.3225, "lr": 8.144305417228338e-06, "epoch": 1.2070434535643284, "percentage": 60.35, "elapsed_time": "12:57:16", "remaining_time": "8:30:37"}
|
173 |
+
{"current_steps": 4260, "total_steps": 7042, "loss": 0.3094, "lr": 8.095614095207114e-06, "epoch": 1.209883555808009, "percentage": 60.49, "elapsed_time": "12:59:03", "remaining_time": "8:28:46"}
|
174 |
+
{"current_steps": 4270, "total_steps": 7042, "loss": 0.3201, "lr": 8.046969577555476e-06, "epoch": 1.2127236580516898, "percentage": 60.64, "elapsed_time": "13:00:54", "remaining_time": "8:26:57"}
|
175 |
+
{"current_steps": 4280, "total_steps": 7042, "loss": 0.3117, "lr": 7.998373059816822e-06, "epoch": 1.2155637602953706, "percentage": 60.78, "elapsed_time": "13:02:42", "remaining_time": "8:25:06"}
|
176 |
+
{"current_steps": 4290, "total_steps": 7042, "loss": 0.3145, "lr": 7.949825736354833e-06, "epoch": 1.2184038625390514, "percentage": 60.92, "elapsed_time": "13:04:29", "remaining_time": "8:23:14"}
|
177 |
+
{"current_steps": 4300, "total_steps": 7042, "loss": 0.3087, "lr": 7.901328800324149e-06, "epoch": 1.2212439647827322, "percentage": 61.06, "elapsed_time": "13:06:17", "remaining_time": "8:21:24"}
|
178 |
+
{"current_steps": 4310, "total_steps": 7042, "loss": 0.3174, "lr": 7.85288344364103e-06, "epoch": 1.224084067026413, "percentage": 61.2, "elapsed_time": "13:08:05", "remaining_time": "8:19:33"}
|
179 |
+
{"current_steps": 4320, "total_steps": 7042, "loss": 0.3188, "lr": 7.80449085695405e-06, "epoch": 1.2269241692700938, "percentage": 61.35, "elapsed_time": "13:09:54", "remaining_time": "8:17:42"}
|
180 |
+
{"current_steps": 4330, "total_steps": 7042, "loss": 0.3072, "lr": 7.756152229614858e-06, "epoch": 1.2297642715137744, "percentage": 61.49, "elapsed_time": "13:11:41", "remaining_time": "8:15:51"}
|
181 |
+
{"current_steps": 4340, "total_steps": 7042, "loss": 0.3171, "lr": 7.707868749648945e-06, "epoch": 1.2326043737574552, "percentage": 61.63, "elapsed_time": "13:13:28", "remaining_time": "8:14:00"}
|
182 |
+
{"current_steps": 4350, "total_steps": 7042, "loss": 0.3083, "lr": 7.659641603726413e-06, "epoch": 1.235444476001136, "percentage": 61.77, "elapsed_time": "13:15:15", "remaining_time": "8:12:08"}
|
183 |
+
{"current_steps": 4360, "total_steps": 7042, "loss": 0.3216, "lr": 7.611471977132855e-06, "epoch": 1.2382845782448169, "percentage": 61.91, "elapsed_time": "13:17:05", "remaining_time": "8:10:18"}
|
184 |
+
{"current_steps": 4370, "total_steps": 7042, "loss": 0.3137, "lr": 7.563361053740191e-06, "epoch": 1.2411246804884977, "percentage": 62.06, "elapsed_time": "13:18:58", "remaining_time": "8:08:31"}
|
185 |
+
{"current_steps": 4380, "total_steps": 7042, "loss": 0.3182, "lr": 7.515310015977591e-06, "epoch": 1.2439647827321783, "percentage": 62.2, "elapsed_time": "13:20:51", "remaining_time": "8:06:44"}
|
186 |
+
{"current_steps": 4390, "total_steps": 7042, "loss": 0.3127, "lr": 7.467320044802409e-06, "epoch": 1.246804884975859, "percentage": 62.34, "elapsed_time": "13:22:42", "remaining_time": "8:04:54"}
|
187 |
+
{"current_steps": 4400, "total_steps": 7042, "loss": 0.3042, "lr": 7.419392319671142e-06, "epoch": 1.2496449872195399, "percentage": 62.48, "elapsed_time": "13:24:27", "remaining_time": "8:03:02"}
|
188 |
+
{"current_steps": 4410, "total_steps": 7042, "loss": 0.3198, "lr": 7.371528018510472e-06, "epoch": 1.2524850894632207, "percentage": 62.62, "elapsed_time": "13:26:17", "remaining_time": "8:01:12"}
|
189 |
+
{"current_steps": 4420, "total_steps": 7042, "loss": 0.3036, "lr": 7.323728317688296e-06, "epoch": 1.2553251917069015, "percentage": 62.77, "elapsed_time": "13:28:05", "remaining_time": "7:59:21"}
|
190 |
+
{"current_steps": 4430, "total_steps": 7042, "loss": 0.313, "lr": 7.27599439198482e-06, "epoch": 1.2581652939505823, "percentage": 62.91, "elapsed_time": "13:29:54", "remaining_time": "7:57:32"}
|
191 |
+
{"current_steps": 4440, "total_steps": 7042, "loss": 0.309, "lr": 7.228327414563683e-06, "epoch": 1.261005396194263, "percentage": 63.05, "elapsed_time": "13:31:46", "remaining_time": "7:55:43"}
|
192 |
+
{"current_steps": 4450, "total_steps": 7042, "loss": 0.3076, "lr": 7.180728556943128e-06, "epoch": 1.2638454984379437, "percentage": 63.19, "elapsed_time": "13:33:36", "remaining_time": "7:53:54"}
|
193 |
+
{"current_steps": 4460, "total_steps": 7042, "loss": 0.316, "lr": 7.133198988967205e-06, "epoch": 1.2666856006816245, "percentage": 63.33, "elapsed_time": "13:35:22", "remaining_time": "7:52:02"}
|
194 |
+
{"current_steps": 4470, "total_steps": 7042, "loss": 0.3116, "lr": 7.085739878777027e-06, "epoch": 1.2695257029253053, "percentage": 63.48, "elapsed_time": "13:37:08", "remaining_time": "7:50:10"}
|
195 |
+
{"current_steps": 4480, "total_steps": 7042, "loss": 0.3059, "lr": 7.038352392782057e-06, "epoch": 1.2723658051689861, "percentage": 63.62, "elapsed_time": "13:39:00", "remaining_time": "7:48:21"}
|
196 |
+
{"current_steps": 4490, "total_steps": 7042, "loss": 0.3118, "lr": 6.991037695631429e-06, "epoch": 1.275205907412667, "percentage": 63.76, "elapsed_time": "13:40:50", "remaining_time": "7:46:32"}
|
197 |
+
{"current_steps": 4500, "total_steps": 7042, "loss": 0.3068, "lr": 6.943796950185344e-06, "epoch": 1.2780460096563475, "percentage": 63.9, "elapsed_time": "13:42:40", "remaining_time": "7:44:43"}
|
198 |
+
{"current_steps": 4510, "total_steps": 7042, "loss": 0.3086, "lr": 6.896631317486484e-06, "epoch": 1.2808861119000283, "percentage": 64.04, "elapsed_time": "13:45:30", "remaining_time": "7:43:27"}
|