Training in progress, epoch 5
Browse files
model-00001-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4943162336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f63484fe890a5ea23922823b6ac7818e12c706a090ee22be94f31cd4c7a7611
|
| 3 |
size 4943162336
|
model-00002-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4999819336
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a689c53e55abce352efcf83f63ca1a75b3606f882dc2052799a2eb24632db26
|
| 3 |
size 4999819336
|
model-00003-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4540516344
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38abd12fc3352d606fa20773232da8d313ea310601b822e98297c65988e7ed27
|
| 3 |
size 4540516344
|
trainer_log.jsonl
CHANGED
|
@@ -200,3 +200,54 @@
|
|
| 200 |
{"current_steps": 1970, "total_steps": 2470, "loss": 0.3182, "lr": 5e-06, "epoch": 3.9878542510121457, "percentage": 79.76, "elapsed_time": "7:58:51", "remaining_time": "2:01:32"}
|
| 201 |
{"current_steps": 1976, "total_steps": 2470, "eval_loss": 0.3246242105960846, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "8:02:24", "remaining_time": "2:00:36"}
|
| 202 |
{"current_steps": 1980, "total_steps": 2470, "loss": 0.2774, "lr": 5e-06, "epoch": 4.008097165991903, "percentage": 80.16, "elapsed_time": "8:04:10", "remaining_time": "1:59:49"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 200 |
{"current_steps": 1970, "total_steps": 2470, "loss": 0.3182, "lr": 5e-06, "epoch": 3.9878542510121457, "percentage": 79.76, "elapsed_time": "7:58:51", "remaining_time": "2:01:32"}
|
| 201 |
{"current_steps": 1976, "total_steps": 2470, "eval_loss": 0.3246242105960846, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "8:02:24", "remaining_time": "2:00:36"}
|
| 202 |
{"current_steps": 1980, "total_steps": 2470, "loss": 0.2774, "lr": 5e-06, "epoch": 4.008097165991903, "percentage": 80.16, "elapsed_time": "8:04:10", "remaining_time": "1:59:49"}
|
| 203 |
+
{"current_steps": 1990, "total_steps": 2470, "loss": 0.2123, "lr": 5e-06, "epoch": 4.02834008097166, "percentage": 80.57, "elapsed_time": "8:06:33", "remaining_time": "1:57:21"}
|
| 204 |
+
{"current_steps": 2000, "total_steps": 2470, "loss": 0.2057, "lr": 5e-06, "epoch": 4.048582995951417, "percentage": 80.97, "elapsed_time": "8:08:56", "remaining_time": "1:54:54"}
|
| 205 |
+
{"current_steps": 2010, "total_steps": 2470, "loss": 0.2061, "lr": 5e-06, "epoch": 4.068825910931174, "percentage": 81.38, "elapsed_time": "8:11:19", "remaining_time": "1:52:26"}
|
| 206 |
+
{"current_steps": 2020, "total_steps": 2470, "loss": 0.2058, "lr": 5e-06, "epoch": 4.089068825910931, "percentage": 81.78, "elapsed_time": "8:13:43", "remaining_time": "1:49:59"}
|
| 207 |
+
{"current_steps": 2030, "total_steps": 2470, "loss": 0.2076, "lr": 5e-06, "epoch": 4.109311740890688, "percentage": 82.19, "elapsed_time": "8:16:06", "remaining_time": "1:47:31"}
|
| 208 |
+
{"current_steps": 2040, "total_steps": 2470, "loss": 0.2055, "lr": 5e-06, "epoch": 4.129554655870446, "percentage": 82.59, "elapsed_time": "8:18:29", "remaining_time": "1:45:04"}
|
| 209 |
+
{"current_steps": 2050, "total_steps": 2470, "loss": 0.2073, "lr": 5e-06, "epoch": 4.149797570850202, "percentage": 83.0, "elapsed_time": "8:20:52", "remaining_time": "1:42:37"}
|
| 210 |
+
{"current_steps": 2060, "total_steps": 2470, "loss": 0.2084, "lr": 5e-06, "epoch": 4.17004048582996, "percentage": 83.4, "elapsed_time": "8:23:15", "remaining_time": "1:40:09"}
|
| 211 |
+
{"current_steps": 2070, "total_steps": 2470, "loss": 0.209, "lr": 5e-06, "epoch": 4.190283400809717, "percentage": 83.81, "elapsed_time": "8:25:39", "remaining_time": "1:37:42"}
|
| 212 |
+
{"current_steps": 2080, "total_steps": 2470, "loss": 0.2127, "lr": 5e-06, "epoch": 4.2105263157894735, "percentage": 84.21, "elapsed_time": "8:28:02", "remaining_time": "1:35:15"}
|
| 213 |
+
{"current_steps": 2090, "total_steps": 2470, "loss": 0.2123, "lr": 5e-06, "epoch": 4.230769230769231, "percentage": 84.62, "elapsed_time": "8:30:25", "remaining_time": "1:32:48"}
|
| 214 |
+
{"current_steps": 2100, "total_steps": 2470, "loss": 0.2108, "lr": 5e-06, "epoch": 4.251012145748988, "percentage": 85.02, "elapsed_time": "8:32:48", "remaining_time": "1:30:21"}
|
| 215 |
+
{"current_steps": 2110, "total_steps": 2470, "loss": 0.2139, "lr": 5e-06, "epoch": 4.271255060728745, "percentage": 85.43, "elapsed_time": "8:35:12", "remaining_time": "1:27:54"}
|
| 216 |
+
{"current_steps": 2120, "total_steps": 2470, "loss": 0.2146, "lr": 5e-06, "epoch": 4.291497975708502, "percentage": 85.83, "elapsed_time": "8:37:35", "remaining_time": "1:25:27"}
|
| 217 |
+
{"current_steps": 2130, "total_steps": 2470, "loss": 0.2145, "lr": 5e-06, "epoch": 4.3117408906882595, "percentage": 86.23, "elapsed_time": "8:39:58", "remaining_time": "1:23:00"}
|
| 218 |
+
{"current_steps": 2140, "total_steps": 2470, "loss": 0.2168, "lr": 5e-06, "epoch": 4.331983805668016, "percentage": 86.64, "elapsed_time": "8:42:22", "remaining_time": "1:20:33"}
|
| 219 |
+
{"current_steps": 2150, "total_steps": 2470, "loss": 0.2151, "lr": 5e-06, "epoch": 4.352226720647773, "percentage": 87.04, "elapsed_time": "8:44:45", "remaining_time": "1:18:06"}
|
| 220 |
+
{"current_steps": 2160, "total_steps": 2470, "loss": 0.2148, "lr": 5e-06, "epoch": 4.372469635627531, "percentage": 87.45, "elapsed_time": "8:47:08", "remaining_time": "1:15:39"}
|
| 221 |
+
{"current_steps": 2170, "total_steps": 2470, "loss": 0.2159, "lr": 5e-06, "epoch": 4.392712550607287, "percentage": 87.85, "elapsed_time": "8:49:31", "remaining_time": "1:13:12"}
|
| 222 |
+
{"current_steps": 2180, "total_steps": 2470, "loss": 0.2179, "lr": 5e-06, "epoch": 4.412955465587045, "percentage": 88.26, "elapsed_time": "8:51:55", "remaining_time": "1:10:45"}
|
| 223 |
+
{"current_steps": 2190, "total_steps": 2470, "loss": 0.2173, "lr": 5e-06, "epoch": 4.433198380566802, "percentage": 88.66, "elapsed_time": "8:54:18", "remaining_time": "1:08:18"}
|
| 224 |
+
{"current_steps": 2200, "total_steps": 2470, "loss": 0.2156, "lr": 5e-06, "epoch": 4.4534412955465585, "percentage": 89.07, "elapsed_time": "8:56:42", "remaining_time": "1:05:52"}
|
| 225 |
+
{"current_steps": 2210, "total_steps": 2470, "loss": 0.2188, "lr": 5e-06, "epoch": 4.473684210526316, "percentage": 89.47, "elapsed_time": "8:59:05", "remaining_time": "1:03:25"}
|
| 226 |
+
{"current_steps": 2220, "total_steps": 2470, "loss": 0.2191, "lr": 5e-06, "epoch": 4.493927125506072, "percentage": 89.88, "elapsed_time": "9:01:28", "remaining_time": "1:00:58"}
|
| 227 |
+
{"current_steps": 2230, "total_steps": 2470, "loss": 0.2201, "lr": 5e-06, "epoch": 4.51417004048583, "percentage": 90.28, "elapsed_time": "9:03:52", "remaining_time": "0:58:31"}
|
| 228 |
+
{"current_steps": 2240, "total_steps": 2470, "loss": 0.22, "lr": 5e-06, "epoch": 4.534412955465587, "percentage": 90.69, "elapsed_time": "9:06:15", "remaining_time": "0:56:05"}
|
| 229 |
+
{"current_steps": 2250, "total_steps": 2470, "loss": 0.2185, "lr": 5e-06, "epoch": 4.554655870445345, "percentage": 91.09, "elapsed_time": "9:08:38", "remaining_time": "0:53:38"}
|
| 230 |
+
{"current_steps": 2260, "total_steps": 2470, "loss": 0.2213, "lr": 5e-06, "epoch": 4.574898785425101, "percentage": 91.5, "elapsed_time": "9:11:01", "remaining_time": "0:51:12"}
|
| 231 |
+
{"current_steps": 2270, "total_steps": 2470, "loss": 0.2221, "lr": 5e-06, "epoch": 4.5951417004048585, "percentage": 91.9, "elapsed_time": "9:13:25", "remaining_time": "0:48:45"}
|
| 232 |
+
{"current_steps": 2280, "total_steps": 2470, "loss": 0.2214, "lr": 5e-06, "epoch": 4.615384615384615, "percentage": 92.31, "elapsed_time": "9:15:48", "remaining_time": "0:46:19"}
|
| 233 |
+
{"current_steps": 2290, "total_steps": 2470, "loss": 0.2237, "lr": 5e-06, "epoch": 4.635627530364372, "percentage": 92.71, "elapsed_time": "9:18:11", "remaining_time": "0:43:52"}
|
| 234 |
+
{"current_steps": 2300, "total_steps": 2470, "loss": 0.2249, "lr": 5e-06, "epoch": 4.65587044534413, "percentage": 93.12, "elapsed_time": "9:20:35", "remaining_time": "0:41:26"}
|
| 235 |
+
{"current_steps": 2310, "total_steps": 2470, "loss": 0.2265, "lr": 5e-06, "epoch": 4.676113360323887, "percentage": 93.52, "elapsed_time": "9:22:58", "remaining_time": "0:38:59"}
|
| 236 |
+
{"current_steps": 2320, "total_steps": 2470, "loss": 0.2265, "lr": 5e-06, "epoch": 4.696356275303644, "percentage": 93.93, "elapsed_time": "9:25:21", "remaining_time": "0:36:33"}
|
| 237 |
+
{"current_steps": 2330, "total_steps": 2470, "loss": 0.2252, "lr": 5e-06, "epoch": 4.716599190283401, "percentage": 94.33, "elapsed_time": "9:27:45", "remaining_time": "0:34:06"}
|
| 238 |
+
{"current_steps": 2340, "total_steps": 2470, "loss": 0.2234, "lr": 5e-06, "epoch": 4.7368421052631575, "percentage": 94.74, "elapsed_time": "9:30:08", "remaining_time": "0:31:40"}
|
| 239 |
+
{"current_steps": 2350, "total_steps": 2470, "loss": 0.2243, "lr": 5e-06, "epoch": 4.757085020242915, "percentage": 95.14, "elapsed_time": "9:32:31", "remaining_time": "0:29:14"}
|
| 240 |
+
{"current_steps": 2360, "total_steps": 2470, "loss": 0.2246, "lr": 5e-06, "epoch": 4.777327935222672, "percentage": 95.55, "elapsed_time": "9:34:55", "remaining_time": "0:26:47"}
|
| 241 |
+
{"current_steps": 2370, "total_steps": 2470, "loss": 0.2276, "lr": 5e-06, "epoch": 4.797570850202429, "percentage": 95.95, "elapsed_time": "9:37:18", "remaining_time": "0:24:21"}
|
| 242 |
+
{"current_steps": 2380, "total_steps": 2470, "loss": 0.2257, "lr": 5e-06, "epoch": 4.817813765182186, "percentage": 96.36, "elapsed_time": "9:39:42", "remaining_time": "0:21:55"}
|
| 243 |
+
{"current_steps": 2390, "total_steps": 2470, "loss": 0.2253, "lr": 5e-06, "epoch": 4.838056680161944, "percentage": 96.76, "elapsed_time": "9:42:05", "remaining_time": "0:19:29"}
|
| 244 |
+
{"current_steps": 2400, "total_steps": 2470, "loss": 0.2294, "lr": 5e-06, "epoch": 4.8582995951417, "percentage": 97.17, "elapsed_time": "9:44:29", "remaining_time": "0:17:02"}
|
| 245 |
+
{"current_steps": 2410, "total_steps": 2470, "loss": 0.2307, "lr": 5e-06, "epoch": 4.8785425101214575, "percentage": 97.57, "elapsed_time": "9:46:52", "remaining_time": "0:14:36"}
|
| 246 |
+
{"current_steps": 2420, "total_steps": 2470, "loss": 0.2293, "lr": 5e-06, "epoch": 4.898785425101215, "percentage": 97.98, "elapsed_time": "9:49:15", "remaining_time": "0:12:10"}
|
| 247 |
+
{"current_steps": 2430, "total_steps": 2470, "loss": 0.2285, "lr": 5e-06, "epoch": 4.919028340080971, "percentage": 98.38, "elapsed_time": "9:51:39", "remaining_time": "0:09:44"}
|
| 248 |
+
{"current_steps": 2440, "total_steps": 2470, "loss": 0.2306, "lr": 5e-06, "epoch": 4.939271255060729, "percentage": 98.79, "elapsed_time": "9:54:02", "remaining_time": "0:07:18"}
|
| 249 |
+
{"current_steps": 2450, "total_steps": 2470, "loss": 0.2277, "lr": 5e-06, "epoch": 4.959514170040486, "percentage": 99.19, "elapsed_time": "9:56:25", "remaining_time": "0:04:52"}
|
| 250 |
+
{"current_steps": 2460, "total_steps": 2470, "loss": 0.2312, "lr": 5e-06, "epoch": 4.979757085020243, "percentage": 99.6, "elapsed_time": "9:58:49", "remaining_time": "0:02:26"}
|
| 251 |
+
{"current_steps": 2470, "total_steps": 2470, "loss": 0.2292, "lr": 5e-06, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "10:01:11", "remaining_time": "0:00:00"}
|
| 252 |
+
{"current_steps": 2470, "total_steps": 2470, "eval_loss": 0.37886306643486023, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "10:04:07", "remaining_time": "0:00:00"}
|
| 253 |
+
{"current_steps": 2470, "total_steps": 2470, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "10:04:48", "remaining_time": "0:00:00"}
|