Instructions to use Rano23/sft_ctx16384 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Rano23/sft_ctx16384 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct") model = PeftModel.from_pretrained(base_model, "Rano23/sft_ctx16384") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 20000
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +92 -0
- training_args.bin +1 -1
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 30000384
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eaca6d05370f4c25c2afbe0b8c19177ada78f5cf3f670ba5c275d85ff35c6a29
|
| 3 |
size 30000384
|
trainer_log.jsonl
CHANGED
|
@@ -3117,3 +3117,95 @@
|
|
| 3117 |
{"current_steps": 16020, "total_steps": 20345, "loss": 0.2034, "lr": 6.5732998015128884e-06, "epoch": 3.936232952451161, "percentage": 78.74, "elapsed_time": "20:20:34", "remaining_time": "5:29:31"}
|
| 3118 |
{"current_steps": 19560, "total_steps": 20345, "loss": 0.4252, "lr": 2.1436373566357182e-06, "epoch": 4.805995822582627, "percentage": 96.14, "elapsed_time": "1 day, 2:11:48", "remaining_time": "1:03:04"}
|
| 3119 |
{"current_steps": 16030, "total_steps": 20345, "loss": 0.2078, "lr": 6.544338043733272e-06, "epoch": 3.9386902567883033, "percentage": 78.79, "elapsed_time": "20:21:15", "remaining_time": "5:28:44"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3117 |
{"current_steps": 16020, "total_steps": 20345, "loss": 0.2034, "lr": 6.5732998015128884e-06, "epoch": 3.936232952451161, "percentage": 78.74, "elapsed_time": "20:20:34", "remaining_time": "5:29:31"}
|
| 3118 |
{"current_steps": 19560, "total_steps": 20345, "loss": 0.4252, "lr": 2.1436373566357182e-06, "epoch": 4.805995822582627, "percentage": 96.14, "elapsed_time": "1 day, 2:11:48", "remaining_time": "1:03:04"}
|
| 3119 |
{"current_steps": 16030, "total_steps": 20345, "loss": 0.2078, "lr": 6.544338043733272e-06, "epoch": 3.9386902567883033, "percentage": 78.79, "elapsed_time": "20:21:15", "remaining_time": "5:28:44"}
|
| 3120 |
+
{"current_steps": 19570, "total_steps": 20345, "loss": 0.4676, "lr": 2.116329874385582e-06, "epoch": 4.808453126919769, "percentage": 96.19, "elapsed_time": "1 day, 2:12:38", "remaining_time": "1:02:16"}
|
| 3121 |
+
{"current_steps": 16040, "total_steps": 20345, "loss": 0.2149, "lr": 6.515430617563964e-06, "epoch": 3.9411475611254456, "percentage": 78.84, "elapsed_time": "20:22:03", "remaining_time": "5:27:59"}
|
| 3122 |
+
{"current_steps": 19580, "total_steps": 20345, "loss": 0.4481, "lr": 2.089022392135445e-06, "epoch": 4.810910431256911, "percentage": 96.24, "elapsed_time": "1 day, 2:13:28", "remaining_time": "1:01:28"}
|
| 3123 |
+
{"current_steps": 16050, "total_steps": 20345, "loss": 0.2158, "lr": 6.486577608105507e-06, "epoch": 3.9436048654625875, "percentage": 78.89, "elapsed_time": "20:22:46", "remaining_time": "5:27:13"}
|
| 3124 |
+
{"current_steps": 16060, "total_steps": 20345, "loss": 0.2197, "lr": 6.457779100298269e-06, "epoch": 3.94606216979973, "percentage": 78.94, "elapsed_time": "20:23:31", "remaining_time": "5:26:26"}
|
| 3125 |
+
{"current_steps": 19590, "total_steps": 20345, "loss": 0.4441, "lr": 2.061714909885309e-06, "epoch": 4.813367735594054, "percentage": 96.29, "elapsed_time": "1 day, 2:14:16", "remaining_time": "1:00:40"}
|
| 3126 |
+
{"current_steps": 16070, "total_steps": 20345, "loss": 0.2129, "lr": 6.429035178922155e-06, "epoch": 3.948519474136872, "percentage": 78.99, "elapsed_time": "20:24:15", "remaining_time": "5:25:40"}
|
| 3127 |
+
{"current_steps": 19600, "total_steps": 20345, "loss": 0.4738, "lr": 2.034407427635172e-06, "epoch": 4.8158250399311955, "percentage": 96.34, "elapsed_time": "1 day, 2:15:02", "remaining_time": "0:59:52"}
|
| 3128 |
+
{"current_steps": 16080, "total_steps": 20345, "loss": 0.2361, "lr": 6.4003459285963604e-06, "epoch": 3.950976778474014, "percentage": 79.04, "elapsed_time": "20:24:59", "remaining_time": "5:24:54"}
|
| 3129 |
+
{"current_steps": 19610, "total_steps": 20345, "loss": 0.4573, "lr": 2.0070999453850357e-06, "epoch": 4.818282344268337, "percentage": 96.39, "elapsed_time": "1 day, 2:15:51", "remaining_time": "0:59:03"}
|
| 3130 |
+
{"current_steps": 16090, "total_steps": 20345, "loss": 0.2134, "lr": 6.371711433779168e-06, "epoch": 3.9534340828111563, "percentage": 79.09, "elapsed_time": "20:25:43", "remaining_time": "5:24:08"}
|
| 3131 |
+
{"current_steps": 19620, "total_steps": 20345, "loss": 0.4555, "lr": 1.979792463134899e-06, "epoch": 4.82073964860548, "percentage": 96.44, "elapsed_time": "1 day, 2:16:39", "remaining_time": "0:58:15"}
|
| 3132 |
+
{"current_steps": 16100, "total_steps": 20345, "loss": 0.2148, "lr": 6.343131778767639e-06, "epoch": 3.9558913871482986, "percentage": 79.13, "elapsed_time": "20:26:32", "remaining_time": "5:23:23"}
|
| 3133 |
+
{"current_steps": 19630, "total_steps": 20345, "loss": 0.4447, "lr": 1.9524849808847624e-06, "epoch": 4.823196952942622, "percentage": 96.49, "elapsed_time": "1 day, 2:17:25", "remaining_time": "0:57:27"}
|
| 3134 |
+
{"current_steps": 16110, "total_steps": 20345, "loss": 0.2171, "lr": 6.3146070476973905e-06, "epoch": 3.9583486914854404, "percentage": 79.18, "elapsed_time": "20:27:19", "remaining_time": "5:22:38"}
|
| 3135 |
+
{"current_steps": 19640, "total_steps": 20345, "loss": 0.4527, "lr": 1.925177498634626e-06, "epoch": 4.825654257279764, "percentage": 96.53, "elapsed_time": "1 day, 2:18:13", "remaining_time": "0:56:39"}
|
| 3136 |
+
{"current_steps": 16120, "total_steps": 20345, "loss": 0.2112, "lr": 6.2861373245423824e-06, "epoch": 3.9608059958225827, "percentage": 79.23, "elapsed_time": "20:28:03", "remaining_time": "5:21:52"}
|
| 3137 |
+
{"current_steps": 19650, "total_steps": 20345, "loss": 0.4618, "lr": 1.8978700163844894e-06, "epoch": 4.828111561616907, "percentage": 96.58, "elapsed_time": "1 day, 2:19:02", "remaining_time": "0:55:50"}
|
| 3138 |
+
{"current_steps": 16130, "total_steps": 20345, "loss": 0.216, "lr": 6.257722693114584e-06, "epoch": 3.963263300159725, "percentage": 79.28, "elapsed_time": "20:28:51", "remaining_time": "5:21:07"}
|
| 3139 |
+
{"current_steps": 19660, "total_steps": 20345, "loss": 0.451, "lr": 1.8705625341343532e-06, "epoch": 4.830568865954048, "percentage": 96.63, "elapsed_time": "1 day, 2:19:51", "remaining_time": "0:55:02"}
|
| 3140 |
+
{"current_steps": 16140, "total_steps": 20345, "loss": 0.2118, "lr": 6.229363237063832e-06, "epoch": 3.965720604496867, "percentage": 79.33, "elapsed_time": "20:29:35", "remaining_time": "5:20:20"}
|
| 3141 |
+
{"current_steps": 19670, "total_steps": 20345, "loss": 0.4605, "lr": 1.8432550518842163e-06, "epoch": 4.83302617029119, "percentage": 96.68, "elapsed_time": "1 day, 2:20:39", "remaining_time": "0:54:14"}
|
| 3142 |
+
{"current_steps": 16150, "total_steps": 20345, "loss": 0.2191, "lr": 6.2010590398774965e-06, "epoch": 3.9681779088340092, "percentage": 79.38, "elapsed_time": "20:30:18", "remaining_time": "5:19:34"}
|
| 3143 |
+
{"current_steps": 19680, "total_steps": 20345, "loss": 0.4705, "lr": 1.8159475696340799e-06, "epoch": 4.835483474628333, "percentage": 96.73, "elapsed_time": "1 day, 2:21:27", "remaining_time": "0:53:26"}
|
| 3144 |
+
{"current_steps": 16160, "total_steps": 20345, "loss": 0.2095, "lr": 6.172810184880282e-06, "epoch": 3.970635213171151, "percentage": 79.43, "elapsed_time": "20:31:01", "remaining_time": "5:18:48"}
|
| 3145 |
+
{"current_steps": 19690, "total_steps": 20345, "loss": 0.4453, "lr": 1.7886400873839433e-06, "epoch": 4.837940778965475, "percentage": 96.78, "elapsed_time": "1 day, 2:22:14", "remaining_time": "0:52:38"}
|
| 3146 |
+
{"current_steps": 16170, "total_steps": 20345, "loss": 0.2059, "lr": 6.144616755233984e-06, "epoch": 3.9730925175082934, "percentage": 79.48, "elapsed_time": "20:31:45", "remaining_time": "5:18:01"}
|
| 3147 |
+
{"current_steps": 19700, "total_steps": 20345, "loss": 0.4324, "lr": 1.7613326051338068e-06, "epoch": 4.840398083302617, "percentage": 96.83, "elapsed_time": "1 day, 2:23:01", "remaining_time": "0:51:49"}
|
| 3148 |
+
{"current_steps": 16180, "total_steps": 20345, "loss": 0.2064, "lr": 6.116478833937214e-06, "epoch": 3.9755498218454357, "percentage": 79.53, "elapsed_time": "20:32:27", "remaining_time": "5:17:15"}
|
| 3149 |
+
{"current_steps": 19710, "total_steps": 20345, "loss": 0.4549, "lr": 1.7340251228836702e-06, "epoch": 4.8428553876397595, "percentage": 96.88, "elapsed_time": "1 day, 2:23:51", "remaining_time": "0:51:01"}
|
| 3150 |
+
{"current_steps": 16190, "total_steps": 20345, "loss": 0.1977, "lr": 6.088396503825181e-06, "epoch": 3.9780071261825776, "percentage": 79.58, "elapsed_time": "20:33:12", "remaining_time": "5:16:29"}
|
| 3151 |
+
{"current_steps": 16200, "total_steps": 20345, "loss": 0.2048, "lr": 6.060369847569425e-06, "epoch": 3.98046443051972, "percentage": 79.63, "elapsed_time": "20:33:52", "remaining_time": "5:15:42"}
|
| 3152 |
+
{"current_steps": 19720, "total_steps": 20345, "loss": 0.4465, "lr": 1.7067176406335338e-06, "epoch": 4.845312691976901, "percentage": 96.93, "elapsed_time": "1 day, 2:24:38", "remaining_time": "0:50:13"}
|
| 3153 |
+
{"current_steps": 16210, "total_steps": 20345, "loss": 0.2052, "lr": 6.032398947677617e-06, "epoch": 3.982921734856862, "percentage": 79.68, "elapsed_time": "20:34:34", "remaining_time": "5:14:55"}
|
| 3154 |
+
{"current_steps": 19730, "total_steps": 20345, "loss": 0.4372, "lr": 1.679410158383397e-06, "epoch": 4.847769996314043, "percentage": 96.98, "elapsed_time": "1 day, 2:25:26", "remaining_time": "0:49:25"}
|
| 3155 |
+
{"current_steps": 16220, "total_steps": 20345, "loss": 0.2045, "lr": 6.004483886493265e-06, "epoch": 3.985379039194004, "percentage": 79.72, "elapsed_time": "20:35:17", "remaining_time": "5:14:09"}
|
| 3156 |
+
{"current_steps": 19740, "total_steps": 20345, "loss": 0.4687, "lr": 1.6521026761332607e-06, "epoch": 4.850227300651186, "percentage": 97.03, "elapsed_time": "1 day, 2:26:17", "remaining_time": "0:48:37"}
|
| 3157 |
+
{"current_steps": 16230, "total_steps": 20345, "loss": 0.2153, "lr": 5.976624746195495e-06, "epoch": 3.9878363435311464, "percentage": 79.77, "elapsed_time": "20:35:58", "remaining_time": "5:13:22"}
|
| 3158 |
+
{"current_steps": 19750, "total_steps": 20345, "loss": 0.4602, "lr": 1.6247951938831239e-06, "epoch": 4.852684604988328, "percentage": 97.08, "elapsed_time": "1 day, 2:27:06", "remaining_time": "0:47:48"}
|
| 3159 |
+
{"current_steps": 16240, "total_steps": 20345, "loss": 0.2245, "lr": 5.94882160879881e-06, "epoch": 3.990293647868288, "percentage": 79.82, "elapsed_time": "20:36:43", "remaining_time": "5:12:36"}
|
| 3160 |
+
{"current_steps": 19760, "total_steps": 20345, "loss": 0.455, "lr": 1.5974877116329875e-06, "epoch": 4.85514190932547, "percentage": 97.12, "elapsed_time": "1 day, 2:27:54", "remaining_time": "0:47:00"}
|
| 3161 |
+
{"current_steps": 16250, "total_steps": 20345, "loss": 0.1963, "lr": 5.9210745561528416e-06, "epoch": 3.9927509522054305, "percentage": 79.87, "elapsed_time": "20:37:22", "remaining_time": "5:11:49"}
|
| 3162 |
+
{"current_steps": 19770, "total_steps": 20345, "loss": 0.4436, "lr": 1.5701802293828508e-06, "epoch": 4.8575992136626125, "percentage": 97.17, "elapsed_time": "1 day, 2:28:45", "remaining_time": "0:46:12"}
|
| 3163 |
+
{"current_steps": 16260, "total_steps": 20345, "loss": 0.2148, "lr": 5.893383669942132e-06, "epoch": 3.995208256542573, "percentage": 79.92, "elapsed_time": "20:38:05", "remaining_time": "5:11:02"}
|
| 3164 |
+
{"current_steps": 16270, "total_steps": 20345, "loss": 0.2155, "lr": 5.865749031685852e-06, "epoch": 3.9976655608797147, "percentage": 79.97, "elapsed_time": "20:38:50", "remaining_time": "5:10:16"}
|
| 3165 |
+
{"current_steps": 19780, "total_steps": 20345, "loss": 0.4495, "lr": 1.5428727471327144e-06, "epoch": 4.860056517999754, "percentage": 97.22, "elapsed_time": "1 day, 2:29:36", "remaining_time": "0:45:24"}
|
| 3166 |
+
{"current_steps": 16280, "total_steps": 20345, "loss": 0.2053, "lr": 5.83817072273759e-06, "epoch": 4.0, "percentage": 80.02, "elapsed_time": "20:39:33", "remaining_time": "5:09:30"}
|
| 3167 |
+
{"current_steps": 19790, "total_steps": 20345, "loss": 0.4676, "lr": 1.515565264882578e-06, "epoch": 4.862513822336896, "percentage": 97.27, "elapsed_time": "1 day, 2:30:24", "remaining_time": "0:44:36"}
|
| 3168 |
+
{"current_steps": 16290, "total_steps": 20345, "loss": 0.1475, "lr": 5.810648824285133e-06, "epoch": 4.002457304337142, "percentage": 80.07, "elapsed_time": "20:40:14", "remaining_time": "5:08:43"}
|
| 3169 |
+
{"current_steps": 19800, "total_steps": 20345, "loss": 0.4545, "lr": 1.4882577826324413e-06, "epoch": 4.864971126674039, "percentage": 97.32, "elapsed_time": "1 day, 2:31:13", "remaining_time": "0:43:47"}
|
| 3170 |
+
{"current_steps": 16300, "total_steps": 20345, "loss": 0.159, "lr": 5.783183417350147e-06, "epoch": 4.004914608674285, "percentage": 80.12, "elapsed_time": "20:40:55", "remaining_time": "5:07:56"}
|
| 3171 |
+
{"current_steps": 19810, "total_steps": 20345, "loss": 0.4576, "lr": 1.4609503003823047e-06, "epoch": 4.867428431011181, "percentage": 97.37, "elapsed_time": "1 day, 2:32:03", "remaining_time": "0:42:59"}
|
| 3172 |
+
{"current_steps": 16310, "total_steps": 20345, "loss": 0.1612, "lr": 5.7557745827880485e-06, "epoch": 4.0073719130114265, "percentage": 80.17, "elapsed_time": "20:41:40", "remaining_time": "5:07:11"}
|
| 3173 |
+
{"current_steps": 19820, "total_steps": 20345, "loss": 0.4699, "lr": 1.4336428181321683e-06, "epoch": 4.869885735348323, "percentage": 97.42, "elapsed_time": "1 day, 2:32:52", "remaining_time": "0:42:11"}
|
| 3174 |
+
{"current_steps": 16320, "total_steps": 20345, "loss": 0.1398, "lr": 5.728422401287676e-06, "epoch": 4.009829217348568, "percentage": 80.22, "elapsed_time": "20:42:24", "remaining_time": "5:06:24"}
|
| 3175 |
+
{"current_steps": 19830, "total_steps": 20345, "loss": 0.4598, "lr": 1.4063353358820317e-06, "epoch": 4.872343039685465, "percentage": 97.47, "elapsed_time": "1 day, 2:33:41", "remaining_time": "0:41:23"}
|
| 3176 |
+
{"current_steps": 16330, "total_steps": 20345, "loss": 0.148, "lr": 5.701126953371091e-06, "epoch": 4.012286521685711, "percentage": 80.27, "elapsed_time": "20:43:05", "remaining_time": "5:05:37"}
|
| 3177 |
+
{"current_steps": 19840, "total_steps": 20345, "loss": 0.4386, "lr": 1.379027853631895e-06, "epoch": 4.874800344022607, "percentage": 97.52, "elapsed_time": "1 day, 2:34:31", "remaining_time": "0:40:35"}
|
| 3178 |
+
{"current_steps": 16340, "total_steps": 20345, "loss": 0.1657, "lr": 5.673888319393358e-06, "epoch": 4.014743826022853, "percentage": 80.31, "elapsed_time": "20:43:53", "remaining_time": "5:04:52"}
|
| 3179 |
+
{"current_steps": 19850, "total_steps": 20345, "loss": 0.4618, "lr": 1.3517203713817588e-06, "epoch": 4.877257648359749, "percentage": 97.57, "elapsed_time": "1 day, 2:35:18", "remaining_time": "0:39:46"}
|
| 3180 |
+
{"current_steps": 16350, "total_steps": 20345, "loss": 0.1613, "lr": 5.646706579542269e-06, "epoch": 4.017201130359995, "percentage": 80.36, "elapsed_time": "20:44:41", "remaining_time": "5:04:07"}
|
| 3181 |
+
{"current_steps": 19860, "total_steps": 20345, "loss": 0.4552, "lr": 1.3244128891316222e-06, "epoch": 4.879714952696892, "percentage": 97.62, "elapsed_time": "1 day, 2:36:07", "remaining_time": "0:38:58"}
|
| 3182 |
+
{"current_steps": 16360, "total_steps": 20345, "loss": 0.1624, "lr": 5.619581813838123e-06, "epoch": 4.019658434697138, "percentage": 80.41, "elapsed_time": "20:45:27", "remaining_time": "5:03:22"}
|
| 3183 |
+
{"current_steps": 16370, "total_steps": 20345, "loss": 0.1545, "lr": 5.592514102133495e-06, "epoch": 4.022115739034279, "percentage": 80.46, "elapsed_time": "20:46:10", "remaining_time": "5:02:35"}
|
| 3184 |
+
{"current_steps": 19870, "total_steps": 20345, "loss": 0.4426, "lr": 1.2971054068814855e-06, "epoch": 4.882172257034034, "percentage": 97.67, "elapsed_time": "1 day, 2:36:56", "remaining_time": "0:38:10"}
|
| 3185 |
+
{"current_steps": 16380, "total_steps": 20345, "loss": 0.1714, "lr": 5.565503524113016e-06, "epoch": 4.024573043371421, "percentage": 80.51, "elapsed_time": "20:46:56", "remaining_time": "5:01:50"}
|
| 3186 |
+
{"current_steps": 19880, "total_steps": 20345, "loss": 0.4539, "lr": 1.2697979246313491e-06, "epoch": 4.884629561371176, "percentage": 97.71, "elapsed_time": "1 day, 2:37:47", "remaining_time": "0:37:22"}
|
| 3187 |
+
{"current_steps": 16390, "total_steps": 20345, "loss": 0.1593, "lr": 5.538550159293101e-06, "epoch": 4.027030347708564, "percentage": 80.56, "elapsed_time": "20:47:41", "remaining_time": "5:01:04"}
|
| 3188 |
+
{"current_steps": 19890, "total_steps": 20345, "loss": 0.448, "lr": 1.2424904423812125e-06, "epoch": 4.8870868657083175, "percentage": 97.76, "elapsed_time": "1 day, 2:38:37", "remaining_time": "0:36:34"}
|
| 3189 |
+
{"current_steps": 16400, "total_steps": 20345, "loss": 0.1663, "lr": 5.511654087021737e-06, "epoch": 4.029487652045706, "percentage": 80.61, "elapsed_time": "20:48:30", "remaining_time": "5:00:19"}
|
| 3190 |
+
{"current_steps": 19900, "total_steps": 20345, "loss": 0.4333, "lr": 1.215182960131076e-06, "epoch": 4.88954417004546, "percentage": 97.81, "elapsed_time": "1 day, 2:39:25", "remaining_time": "0:35:45"}
|
| 3191 |
+
{"current_steps": 16410, "total_steps": 20345, "loss": 0.162, "lr": 5.4848153864782595e-06, "epoch": 4.031944956382848, "percentage": 80.66, "elapsed_time": "20:49:15", "remaining_time": "4:59:33"}
|
| 3192 |
+
{"current_steps": 19910, "total_steps": 20345, "loss": 0.4594, "lr": 1.1878754778809394e-06, "epoch": 4.892001474382602, "percentage": 97.86, "elapsed_time": "1 day, 2:40:12", "remaining_time": "0:34:57"}
|
| 3193 |
+
{"current_steps": 16420, "total_steps": 20345, "loss": 0.1595, "lr": 5.458034136673102e-06, "epoch": 4.0344022607199905, "percentage": 80.71, "elapsed_time": "20:50:02", "remaining_time": "4:58:48"}
|
| 3194 |
+
{"current_steps": 19920, "total_steps": 20345, "loss": 0.4523, "lr": 1.1605679956308028e-06, "epoch": 4.894458778719745, "percentage": 97.91, "elapsed_time": "1 day, 2:41:00", "remaining_time": "0:34:09"}
|
| 3195 |
+
{"current_steps": 16430, "total_steps": 20345, "loss": 0.152, "lr": 5.431310416447552e-06, "epoch": 4.036859565057132, "percentage": 80.76, "elapsed_time": "20:50:48", "remaining_time": "4:58:02"}
|
| 3196 |
+
{"current_steps": 19930, "total_steps": 20345, "loss": 0.4393, "lr": 1.1332605133806664e-06, "epoch": 4.896916083056887, "percentage": 97.96, "elapsed_time": "1 day, 2:41:48", "remaining_time": "0:33:21"}
|
| 3197 |
+
{"current_steps": 16440, "total_steps": 20345, "loss": 0.1553, "lr": 5.4046443044735775e-06, "epoch": 4.039316869394274, "percentage": 80.81, "elapsed_time": "20:51:29", "remaining_time": "4:57:16"}
|
| 3198 |
+
{"current_steps": 19940, "total_steps": 20345, "loss": 0.4465, "lr": 1.1059530311305297e-06, "epoch": 4.899373387394029, "percentage": 98.01, "elapsed_time": "1 day, 2:42:34", "remaining_time": "0:32:32"}
|
| 3199 |
+
{"current_steps": 16450, "total_steps": 20345, "loss": 0.154, "lr": 5.378035879253496e-06, "epoch": 4.041774173731417, "percentage": 80.86, "elapsed_time": "20:52:08", "remaining_time": "4:56:28"}
|
| 3200 |
+
{"current_steps": 19950, "total_steps": 20345, "loss": 0.4446, "lr": 1.0786455488803933e-06, "epoch": 4.9018306917311705, "percentage": 98.06, "elapsed_time": "1 day, 2:43:21", "remaining_time": "0:31:44"}
|
| 3201 |
+
{"current_steps": 16460, "total_steps": 20345, "loss": 0.1432, "lr": 5.351485219119854e-06, "epoch": 4.044231478068559, "percentage": 80.9, "elapsed_time": "20:52:52", "remaining_time": "4:55:42"}
|
| 3202 |
+
{"current_steps": 19960, "total_steps": 20345, "loss": 0.4526, "lr": 1.0513380666302567e-06, "epoch": 4.904287996068313, "percentage": 98.11, "elapsed_time": "1 day, 2:44:07", "remaining_time": "0:30:56"}
|
| 3203 |
+
{"current_steps": 16470, "total_steps": 20345, "loss": 0.156, "lr": 5.324992402235115e-06, "epoch": 4.046688782405701, "percentage": 80.95, "elapsed_time": "20:53:38", "remaining_time": "4:54:57"}
|
| 3204 |
+
{"current_steps": 19970, "total_steps": 20345, "loss": 0.4667, "lr": 1.02403058438012e-06, "epoch": 4.906745300405455, "percentage": 98.16, "elapsed_time": "1 day, 2:44:57", "remaining_time": "0:30:08"}
|
| 3205 |
+
{"current_steps": 16480, "total_steps": 20345, "loss": 0.1742, "lr": 5.298557506591456e-06, "epoch": 4.0491460867428435, "percentage": 81.0, "elapsed_time": "20:54:24", "remaining_time": "4:54:11"}
|
| 3206 |
+
{"current_steps": 19980, "total_steps": 20345, "loss": 0.4383, "lr": 9.967231021299836e-07, "epoch": 4.909202604742598, "percentage": 98.21, "elapsed_time": "1 day, 2:45:45", "remaining_time": "0:29:20"}
|
| 3207 |
+
{"current_steps": 16490, "total_steps": 20345, "loss": 0.1425, "lr": 5.272180610010566e-06, "epoch": 4.051603391079985, "percentage": 81.05, "elapsed_time": "20:55:10", "remaining_time": "4:53:25"}
|
| 3208 |
+
{"current_steps": 19990, "total_steps": 20345, "loss": 0.4473, "lr": 9.694156198798472e-07, "epoch": 4.91165990907974, "percentage": 98.26, "elapsed_time": "1 day, 2:46:36", "remaining_time": "0:28:31"}
|
| 3209 |
+
{"current_steps": 16500, "total_steps": 20345, "loss": 0.1479, "lr": 5.24586179014335e-06, "epoch": 4.054060695417127, "percentage": 81.1, "elapsed_time": "20:55:54", "remaining_time": "4:52:39"}
|
| 3210 |
+
{"current_steps": 16510, "total_steps": 20345, "loss": 0.1545, "lr": 5.219601124469781e-06, "epoch": 4.05651799975427, "percentage": 81.15, "elapsed_time": "20:56:39", "remaining_time": "4:51:54"}
|
| 3211 |
+
{"current_steps": 20000, "total_steps": 20345, "loss": 0.4735, "lr": 9.421081376297107e-07, "epoch": 4.914117213416882, "percentage": 98.3, "elapsed_time": "1 day, 2:47:27", "remaining_time": "0:27:43"}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7608
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f39350b4101b7515fcbe007f72323706b73b4a8d02336061d37302741b35be8
|
| 3 |
size 7608
|