sedrickkeh
commited on
Commit
•
ef55756
1
Parent(s):
3cd9a93
Training in progress, epoch 2
Browse files- config.json.sagemaker-uploaded +0 -0
- model-00001-of-00003.safetensors +1 -1
- model-00001-of-00003.safetensors.sagemaker-uploaded +0 -0
- model-00002-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors.sagemaker-uploaded +0 -0
- model-00003-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors.sagemaker-uploaded +0 -0
- model.safetensors.index.json.sagemaker-uploaded +0 -0
- special_tokens_map.json.sagemaker-uploaded +0 -0
- tokenizer.json.sagemaker-uploaded +0 -0
- tokenizer.model.sagemaker-uploaded +0 -0
- tokenizer_config.json.sagemaker-uploaded +0 -0
- trainer_log.jsonl +104 -0
- training_args.bin.sagemaker-uploaded +0 -0
config.json.sagemaker-uploaded
ADDED
File without changes
|
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 sha256:325efa4f6d4195963b8bc5ad2bbe245dbfbdecfd6b9b4cc955c2a8a4dd404830
|
3 |
size 4943162336
|
model-00001-of-00003.safetensors.sagemaker-uploaded
ADDED
File without changes
|
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:adc1fa8e43956d15ceaa97dd7ae90c94a83a6be3b9059ce2b3195b017646a45f
|
3 |
size 4999819336
|
model-00002-of-00003.safetensors.sagemaker-uploaded
ADDED
File without changes
|
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 sha256:74ccc770dc84101b37751baf4000db43d5ddb9ac81ed4de475dcd7642231321e
|
3 |
size 4540516344
|
model-00003-of-00003.safetensors.sagemaker-uploaded
ADDED
File without changes
|
model.safetensors.index.json.sagemaker-uploaded
ADDED
File without changes
|
special_tokens_map.json.sagemaker-uploaded
ADDED
File without changes
|
tokenizer.json.sagemaker-uploaded
ADDED
File without changes
|
tokenizer.model.sagemaker-uploaded
ADDED
File without changes
|
tokenizer_config.json.sagemaker-uploaded
ADDED
File without changes
|
trainer_log.jsonl
CHANGED
@@ -104,3 +104,107 @@
|
|
104 |
{"current_steps": 1035, "total_steps": 3105, "eval_loss": 0.4186817705631256, "epoch": 0.9995171414775471, "percentage": 33.33, "elapsed_time": "2:25:25", "remaining_time": "4:50:50"}
|
105 |
{"current_steps": 1040, "total_steps": 3105, "loss": 0.3804, "learning_rate": 5e-06, "epoch": 1.0043457267020763, "percentage": 33.49, "elapsed_time": "2:26:49", "remaining_time": "4:51:31"}
|
106 |
{"current_steps": 1050, "total_steps": 3105, "loss": 0.3159, "learning_rate": 5e-06, "epoch": 1.0140028971511348, "percentage": 33.82, "elapsed_time": "2:28:11", "remaining_time": "4:50:01"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
104 |
{"current_steps": 1035, "total_steps": 3105, "eval_loss": 0.4186817705631256, "epoch": 0.9995171414775471, "percentage": 33.33, "elapsed_time": "2:25:25", "remaining_time": "4:50:50"}
|
105 |
{"current_steps": 1040, "total_steps": 3105, "loss": 0.3804, "learning_rate": 5e-06, "epoch": 1.0043457267020763, "percentage": 33.49, "elapsed_time": "2:26:49", "remaining_time": "4:51:31"}
|
106 |
{"current_steps": 1050, "total_steps": 3105, "loss": 0.3159, "learning_rate": 5e-06, "epoch": 1.0140028971511348, "percentage": 33.82, "elapsed_time": "2:28:11", "remaining_time": "4:50:01"}
|
107 |
+
{"current_steps": 1060, "total_steps": 3105, "loss": 0.3138, "learning_rate": 5e-06, "epoch": 1.0236600676001932, "percentage": 34.14, "elapsed_time": "2:29:33", "remaining_time": "4:48:31"}
|
108 |
+
{"current_steps": 1070, "total_steps": 3105, "loss": 0.3146, "learning_rate": 5e-06, "epoch": 1.0333172380492515, "percentage": 34.46, "elapsed_time": "2:30:55", "remaining_time": "4:47:01"}
|
109 |
+
{"current_steps": 1080, "total_steps": 3105, "loss": 0.3101, "learning_rate": 5e-06, "epoch": 1.04297440849831, "percentage": 34.78, "elapsed_time": "2:32:16", "remaining_time": "4:45:31"}
|
110 |
+
{"current_steps": 1090, "total_steps": 3105, "loss": 0.3152, "learning_rate": 5e-06, "epoch": 1.0526315789473684, "percentage": 35.1, "elapsed_time": "2:33:39", "remaining_time": "4:44:03"}
|
111 |
+
{"current_steps": 1100, "total_steps": 3105, "loss": 0.3211, "learning_rate": 5e-06, "epoch": 1.0622887493964268, "percentage": 35.43, "elapsed_time": "2:35:01", "remaining_time": "4:42:34"}
|
112 |
+
{"current_steps": 1110, "total_steps": 3105, "loss": 0.3185, "learning_rate": 5e-06, "epoch": 1.0719459198454853, "percentage": 35.75, "elapsed_time": "2:36:23", "remaining_time": "4:41:05"}
|
113 |
+
{"current_steps": 1120, "total_steps": 3105, "loss": 0.3177, "learning_rate": 5e-06, "epoch": 1.0816030902945437, "percentage": 36.07, "elapsed_time": "2:37:46", "remaining_time": "4:39:37"}
|
114 |
+
{"current_steps": 1130, "total_steps": 3105, "loss": 0.319, "learning_rate": 5e-06, "epoch": 1.0912602607436022, "percentage": 36.39, "elapsed_time": "2:39:08", "remaining_time": "4:38:08"}
|
115 |
+
{"current_steps": 1140, "total_steps": 3105, "loss": 0.3183, "learning_rate": 5e-06, "epoch": 1.1009174311926606, "percentage": 36.71, "elapsed_time": "2:40:30", "remaining_time": "4:36:39"}
|
116 |
+
{"current_steps": 1150, "total_steps": 3105, "loss": 0.3206, "learning_rate": 5e-06, "epoch": 1.110574601641719, "percentage": 37.04, "elapsed_time": "2:41:52", "remaining_time": "4:35:11"}
|
117 |
+
{"current_steps": 1160, "total_steps": 3105, "loss": 0.3161, "learning_rate": 5e-06, "epoch": 1.1202317720907775, "percentage": 37.36, "elapsed_time": "2:43:14", "remaining_time": "4:33:42"}
|
118 |
+
{"current_steps": 1170, "total_steps": 3105, "loss": 0.3176, "learning_rate": 5e-06, "epoch": 1.1298889425398357, "percentage": 37.68, "elapsed_time": "2:44:36", "remaining_time": "4:32:13"}
|
119 |
+
{"current_steps": 1180, "total_steps": 3105, "loss": 0.3206, "learning_rate": 5e-06, "epoch": 1.1395461129888942, "percentage": 38.0, "elapsed_time": "2:45:58", "remaining_time": "4:30:45"}
|
120 |
+
{"current_steps": 1190, "total_steps": 3105, "loss": 0.3189, "learning_rate": 5e-06, "epoch": 1.1492032834379526, "percentage": 38.33, "elapsed_time": "2:47:20", "remaining_time": "4:29:17"}
|
121 |
+
{"current_steps": 1200, "total_steps": 3105, "loss": 0.3176, "learning_rate": 5e-06, "epoch": 1.158860453887011, "percentage": 38.65, "elapsed_time": "2:48:42", "remaining_time": "4:27:49"}
|
122 |
+
{"current_steps": 1210, "total_steps": 3105, "loss": 0.3256, "learning_rate": 5e-06, "epoch": 1.1685176243360695, "percentage": 38.97, "elapsed_time": "2:50:04", "remaining_time": "4:26:21"}
|
123 |
+
{"current_steps": 1220, "total_steps": 3105, "loss": 0.3194, "learning_rate": 5e-06, "epoch": 1.178174794785128, "percentage": 39.29, "elapsed_time": "2:51:26", "remaining_time": "4:24:53"}
|
124 |
+
{"current_steps": 1230, "total_steps": 3105, "loss": 0.315, "learning_rate": 5e-06, "epoch": 1.1878319652341864, "percentage": 39.61, "elapsed_time": "2:52:49", "remaining_time": "4:23:26"}
|
125 |
+
{"current_steps": 1240, "total_steps": 3105, "loss": 0.3203, "learning_rate": 5e-06, "epoch": 1.1974891356832449, "percentage": 39.94, "elapsed_time": "2:54:12", "remaining_time": "4:22:00"}
|
126 |
+
{"current_steps": 1250, "total_steps": 3105, "loss": 0.3182, "learning_rate": 5e-06, "epoch": 1.2071463061323033, "percentage": 40.26, "elapsed_time": "2:55:34", "remaining_time": "4:20:33"}
|
127 |
+
{"current_steps": 1260, "total_steps": 3105, "loss": 0.3204, "learning_rate": 5e-06, "epoch": 1.2168034765813616, "percentage": 40.58, "elapsed_time": "2:56:56", "remaining_time": "4:19:06"}
|
128 |
+
{"current_steps": 1270, "total_steps": 3105, "loss": 0.3194, "learning_rate": 5e-06, "epoch": 1.22646064703042, "percentage": 40.9, "elapsed_time": "2:58:19", "remaining_time": "4:17:39"}
|
129 |
+
{"current_steps": 1280, "total_steps": 3105, "loss": 0.3164, "learning_rate": 5e-06, "epoch": 1.2361178174794785, "percentage": 41.22, "elapsed_time": "2:59:42", "remaining_time": "4:16:13"}
|
130 |
+
{"current_steps": 1290, "total_steps": 3105, "loss": 0.3195, "learning_rate": 5e-06, "epoch": 1.245774987928537, "percentage": 41.55, "elapsed_time": "3:01:04", "remaining_time": "4:14:46"}
|
131 |
+
{"current_steps": 1300, "total_steps": 3105, "loss": 0.3206, "learning_rate": 5e-06, "epoch": 1.2554321583775954, "percentage": 41.87, "elapsed_time": "3:02:27", "remaining_time": "4:13:20"}
|
132 |
+
{"current_steps": 1310, "total_steps": 3105, "loss": 0.3174, "learning_rate": 5e-06, "epoch": 1.2650893288266538, "percentage": 42.19, "elapsed_time": "3:03:50", "remaining_time": "4:11:53"}
|
133 |
+
{"current_steps": 1320, "total_steps": 3105, "loss": 0.3212, "learning_rate": 5e-06, "epoch": 1.2747464992757123, "percentage": 42.51, "elapsed_time": "3:05:13", "remaining_time": "4:10:27"}
|
134 |
+
{"current_steps": 1330, "total_steps": 3105, "loss": 0.3185, "learning_rate": 5e-06, "epoch": 1.2844036697247707, "percentage": 42.83, "elapsed_time": "3:06:36", "remaining_time": "4:09:02"}
|
135 |
+
{"current_steps": 1340, "total_steps": 3105, "loss": 0.3195, "learning_rate": 5e-06, "epoch": 1.2940608401738292, "percentage": 43.16, "elapsed_time": "3:07:59", "remaining_time": "4:07:36"}
|
136 |
+
{"current_steps": 1350, "total_steps": 3105, "loss": 0.3181, "learning_rate": 5e-06, "epoch": 1.3037180106228874, "percentage": 43.48, "elapsed_time": "3:09:22", "remaining_time": "4:06:10"}
|
137 |
+
{"current_steps": 1360, "total_steps": 3105, "loss": 0.3203, "learning_rate": 5e-06, "epoch": 1.3133751810719458, "percentage": 43.8, "elapsed_time": "3:10:45", "remaining_time": "4:04:45"}
|
138 |
+
{"current_steps": 1370, "total_steps": 3105, "loss": 0.3226, "learning_rate": 5e-06, "epoch": 1.3230323515210043, "percentage": 44.12, "elapsed_time": "3:12:08", "remaining_time": "4:03:19"}
|
139 |
+
{"current_steps": 1380, "total_steps": 3105, "loss": 0.3237, "learning_rate": 5e-06, "epoch": 1.3326895219700627, "percentage": 44.44, "elapsed_time": "3:13:31", "remaining_time": "4:01:54"}
|
140 |
+
{"current_steps": 1390, "total_steps": 3105, "loss": 0.3223, "learning_rate": 5e-06, "epoch": 1.3423466924191212, "percentage": 44.77, "elapsed_time": "3:14:54", "remaining_time": "4:00:28"}
|
141 |
+
{"current_steps": 1400, "total_steps": 3105, "loss": 0.3231, "learning_rate": 5e-06, "epoch": 1.3520038628681796, "percentage": 45.09, "elapsed_time": "3:16:17", "remaining_time": "3:59:02"}
|
142 |
+
{"current_steps": 1410, "total_steps": 3105, "loss": 0.3239, "learning_rate": 5e-06, "epoch": 1.361661033317238, "percentage": 45.41, "elapsed_time": "3:17:40", "remaining_time": "3:57:37"}
|
143 |
+
{"current_steps": 1420, "total_steps": 3105, "loss": 0.3218, "learning_rate": 5e-06, "epoch": 1.3713182037662965, "percentage": 45.73, "elapsed_time": "3:19:03", "remaining_time": "3:56:12"}
|
144 |
+
{"current_steps": 1430, "total_steps": 3105, "loss": 0.322, "learning_rate": 5e-06, "epoch": 1.380975374215355, "percentage": 46.05, "elapsed_time": "3:20:26", "remaining_time": "3:54:46"}
|
145 |
+
{"current_steps": 1440, "total_steps": 3105, "loss": 0.3145, "learning_rate": 5e-06, "epoch": 1.3906325446644132, "percentage": 46.38, "elapsed_time": "3:21:49", "remaining_time": "3:53:21"}
|
146 |
+
{"current_steps": 1450, "total_steps": 3105, "loss": 0.3178, "learning_rate": 5e-06, "epoch": 1.4002897151134719, "percentage": 46.7, "elapsed_time": "3:23:12", "remaining_time": "3:51:55"}
|
147 |
+
{"current_steps": 1460, "total_steps": 3105, "loss": 0.3243, "learning_rate": 5e-06, "epoch": 1.4099468855625301, "percentage": 47.02, "elapsed_time": "3:24:35", "remaining_time": "3:50:30"}
|
148 |
+
{"current_steps": 1470, "total_steps": 3105, "loss": 0.3211, "learning_rate": 5e-06, "epoch": 1.4196040560115886, "percentage": 47.34, "elapsed_time": "3:25:58", "remaining_time": "3:49:05"}
|
149 |
+
{"current_steps": 1480, "total_steps": 3105, "loss": 0.3221, "learning_rate": 5e-06, "epoch": 1.429261226460647, "percentage": 47.67, "elapsed_time": "3:27:21", "remaining_time": "3:47:40"}
|
150 |
+
{"current_steps": 1490, "total_steps": 3105, "loss": 0.3259, "learning_rate": 5e-06, "epoch": 1.4389183969097055, "percentage": 47.99, "elapsed_time": "3:28:44", "remaining_time": "3:46:14"}
|
151 |
+
{"current_steps": 1500, "total_steps": 3105, "loss": 0.3192, "learning_rate": 5e-06, "epoch": 1.448575567358764, "percentage": 48.31, "elapsed_time": "3:30:06", "remaining_time": "3:44:49"}
|
152 |
+
{"current_steps": 1510, "total_steps": 3105, "loss": 0.3198, "learning_rate": 5e-06, "epoch": 1.4582327378078224, "percentage": 48.63, "elapsed_time": "3:31:28", "remaining_time": "3:43:23"}
|
153 |
+
{"current_steps": 1520, "total_steps": 3105, "loss": 0.3242, "learning_rate": 5e-06, "epoch": 1.4678899082568808, "percentage": 48.95, "elapsed_time": "3:32:50", "remaining_time": "3:41:57"}
|
154 |
+
{"current_steps": 1530, "total_steps": 3105, "loss": 0.3229, "learning_rate": 5e-06, "epoch": 1.477547078705939, "percentage": 49.28, "elapsed_time": "3:34:13", "remaining_time": "3:40:31"}
|
155 |
+
{"current_steps": 1540, "total_steps": 3105, "loss": 0.3258, "learning_rate": 5e-06, "epoch": 1.4872042491549977, "percentage": 49.6, "elapsed_time": "3:35:35", "remaining_time": "3:39:05"}
|
156 |
+
{"current_steps": 1550, "total_steps": 3105, "loss": 0.3218, "learning_rate": 5e-06, "epoch": 1.496861419604056, "percentage": 49.92, "elapsed_time": "3:36:58", "remaining_time": "3:37:40"}
|
157 |
+
{"current_steps": 1560, "total_steps": 3105, "loss": 0.3203, "learning_rate": 5e-06, "epoch": 1.5065185900531144, "percentage": 50.24, "elapsed_time": "3:38:20", "remaining_time": "3:36:14"}
|
158 |
+
{"current_steps": 1570, "total_steps": 3105, "loss": 0.3233, "learning_rate": 5e-06, "epoch": 1.5161757605021728, "percentage": 50.56, "elapsed_time": "3:39:43", "remaining_time": "3:34:49"}
|
159 |
+
{"current_steps": 1580, "total_steps": 3105, "loss": 0.32, "learning_rate": 5e-06, "epoch": 1.5258329309512313, "percentage": 50.89, "elapsed_time": "3:41:06", "remaining_time": "3:33:24"}
|
160 |
+
{"current_steps": 1590, "total_steps": 3105, "loss": 0.3255, "learning_rate": 5e-06, "epoch": 1.5354901014002897, "percentage": 51.21, "elapsed_time": "3:42:27", "remaining_time": "3:31:57"}
|
161 |
+
{"current_steps": 1600, "total_steps": 3105, "loss": 0.325, "learning_rate": 5e-06, "epoch": 1.5451472718493482, "percentage": 51.53, "elapsed_time": "3:43:48", "remaining_time": "3:30:31"}
|
162 |
+
{"current_steps": 1610, "total_steps": 3105, "loss": 0.3195, "learning_rate": 5e-06, "epoch": 1.5548044422984066, "percentage": 51.85, "elapsed_time": "3:45:10", "remaining_time": "3:29:05"}
|
163 |
+
{"current_steps": 1620, "total_steps": 3105, "loss": 0.324, "learning_rate": 5e-06, "epoch": 1.5644616127474649, "percentage": 52.17, "elapsed_time": "3:46:32", "remaining_time": "3:27:39"}
|
164 |
+
{"current_steps": 1630, "total_steps": 3105, "loss": 0.319, "learning_rate": 5e-06, "epoch": 1.5741187831965235, "percentage": 52.5, "elapsed_time": "3:47:54", "remaining_time": "3:26:14"}
|
165 |
+
{"current_steps": 1640, "total_steps": 3105, "loss": 0.319, "learning_rate": 5e-06, "epoch": 1.5837759536455818, "percentage": 52.82, "elapsed_time": "3:49:16", "remaining_time": "3:24:48"}
|
166 |
+
{"current_steps": 1650, "total_steps": 3105, "loss": 0.3246, "learning_rate": 5e-06, "epoch": 1.5934331240946402, "percentage": 53.14, "elapsed_time": "3:50:39", "remaining_time": "3:23:23"}
|
167 |
+
{"current_steps": 1660, "total_steps": 3105, "loss": 0.325, "learning_rate": 5e-06, "epoch": 1.6030902945436987, "percentage": 53.46, "elapsed_time": "3:52:01", "remaining_time": "3:21:58"}
|
168 |
+
{"current_steps": 1670, "total_steps": 3105, "loss": 0.3249, "learning_rate": 5e-06, "epoch": 1.6127474649927571, "percentage": 53.78, "elapsed_time": "3:53:23", "remaining_time": "3:20:33"}
|
169 |
+
{"current_steps": 1680, "total_steps": 3105, "loss": 0.3174, "learning_rate": 5e-06, "epoch": 1.6224046354418156, "percentage": 54.11, "elapsed_time": "3:54:46", "remaining_time": "3:19:08"}
|
170 |
+
{"current_steps": 1690, "total_steps": 3105, "loss": 0.32, "learning_rate": 5e-06, "epoch": 1.632061805890874, "percentage": 54.43, "elapsed_time": "3:56:08", "remaining_time": "3:17:43"}
|
171 |
+
{"current_steps": 1700, "total_steps": 3105, "loss": 0.3251, "learning_rate": 5e-06, "epoch": 1.6417189763399325, "percentage": 54.75, "elapsed_time": "3:57:30", "remaining_time": "3:16:17"}
|
172 |
+
{"current_steps": 1710, "total_steps": 3105, "loss": 0.3251, "learning_rate": 5e-06, "epoch": 1.6513761467889907, "percentage": 55.07, "elapsed_time": "3:58:51", "remaining_time": "3:14:51"}
|
173 |
+
{"current_steps": 1720, "total_steps": 3105, "loss": 0.3217, "learning_rate": 5e-06, "epoch": 1.6610333172380494, "percentage": 55.39, "elapsed_time": "4:00:13", "remaining_time": "3:13:26"}
|
174 |
+
{"current_steps": 1730, "total_steps": 3105, "loss": 0.3241, "learning_rate": 5e-06, "epoch": 1.6706904876871076, "percentage": 55.72, "elapsed_time": "4:01:34", "remaining_time": "3:12:00"}
|
175 |
+
{"current_steps": 1740, "total_steps": 3105, "loss": 0.3216, "learning_rate": 5e-06, "epoch": 1.6803476581361663, "percentage": 56.04, "elapsed_time": "4:02:56", "remaining_time": "3:10:35"}
|
176 |
+
{"current_steps": 1750, "total_steps": 3105, "loss": 0.3228, "learning_rate": 5e-06, "epoch": 1.6900048285852245, "percentage": 56.36, "elapsed_time": "4:04:18", "remaining_time": "3:09:09"}
|
177 |
+
{"current_steps": 1760, "total_steps": 3105, "loss": 0.3219, "learning_rate": 5e-06, "epoch": 1.699661999034283, "percentage": 56.68, "elapsed_time": "4:05:40", "remaining_time": "3:07:45"}
|
178 |
+
{"current_steps": 1770, "total_steps": 3105, "loss": 0.3204, "learning_rate": 5e-06, "epoch": 1.7093191694833414, "percentage": 57.0, "elapsed_time": "4:07:02", "remaining_time": "3:06:19"}
|
179 |
+
{"current_steps": 1780, "total_steps": 3105, "loss": 0.3225, "learning_rate": 5e-06, "epoch": 1.7189763399323998, "percentage": 57.33, "elapsed_time": "4:08:24", "remaining_time": "3:04:54"}
|
180 |
+
{"current_steps": 1790, "total_steps": 3105, "loss": 0.3275, "learning_rate": 5e-06, "epoch": 1.7286335103814583, "percentage": 57.65, "elapsed_time": "4:09:45", "remaining_time": "3:03:29"}
|
181 |
+
{"current_steps": 1800, "total_steps": 3105, "loss": 0.3261, "learning_rate": 5e-06, "epoch": 1.7382906808305165, "percentage": 57.97, "elapsed_time": "4:11:07", "remaining_time": "3:02:03"}
|
182 |
+
{"current_steps": 1810, "total_steps": 3105, "loss": 0.3247, "learning_rate": 5e-06, "epoch": 1.7479478512795752, "percentage": 58.29, "elapsed_time": "4:12:29", "remaining_time": "3:00:38"}
|
183 |
+
{"current_steps": 1820, "total_steps": 3105, "loss": 0.3237, "learning_rate": 5e-06, "epoch": 1.7576050217286334, "percentage": 58.62, "elapsed_time": "4:13:51", "remaining_time": "2:59:14"}
|
184 |
+
{"current_steps": 1830, "total_steps": 3105, "loss": 0.3218, "learning_rate": 5e-06, "epoch": 1.767262192177692, "percentage": 58.94, "elapsed_time": "4:15:14", "remaining_time": "2:57:49"}
|
185 |
+
{"current_steps": 1840, "total_steps": 3105, "loss": 0.3239, "learning_rate": 5e-06, "epoch": 1.7769193626267503, "percentage": 59.26, "elapsed_time": "4:16:37", "remaining_time": "2:56:25"}
|
186 |
+
{"current_steps": 1850, "total_steps": 3105, "loss": 0.3267, "learning_rate": 5e-06, "epoch": 1.7865765330758088, "percentage": 59.58, "elapsed_time": "4:17:59", "remaining_time": "2:55:01"}
|
187 |
+
{"current_steps": 1860, "total_steps": 3105, "loss": 0.322, "learning_rate": 5e-06, "epoch": 1.7962337035248672, "percentage": 59.9, "elapsed_time": "4:19:22", "remaining_time": "2:53:36"}
|
188 |
+
{"current_steps": 1870, "total_steps": 3105, "loss": 0.3246, "learning_rate": 5e-06, "epoch": 1.8058908739739257, "percentage": 60.23, "elapsed_time": "4:20:45", "remaining_time": "2:52:12"}
|
189 |
+
{"current_steps": 1880, "total_steps": 3105, "loss": 0.3226, "learning_rate": 5e-06, "epoch": 1.8155480444229841, "percentage": 60.55, "elapsed_time": "4:22:07", "remaining_time": "2:50:48"}
|
190 |
+
{"current_steps": 1890, "total_steps": 3105, "loss": 0.3236, "learning_rate": 5e-06, "epoch": 1.8252052148720423, "percentage": 60.87, "elapsed_time": "4:23:30", "remaining_time": "2:49:23"}
|
191 |
+
{"current_steps": 1900, "total_steps": 3105, "loss": 0.3228, "learning_rate": 5e-06, "epoch": 1.834862385321101, "percentage": 61.19, "elapsed_time": "4:24:53", "remaining_time": "2:47:59"}
|
192 |
+
{"current_steps": 1910, "total_steps": 3105, "loss": 0.3241, "learning_rate": 5e-06, "epoch": 1.8445195557701592, "percentage": 61.51, "elapsed_time": "4:26:15", "remaining_time": "2:46:35"}
|
193 |
+
{"current_steps": 1920, "total_steps": 3105, "loss": 0.3259, "learning_rate": 5e-06, "epoch": 1.854176726219218, "percentage": 61.84, "elapsed_time": "4:27:38", "remaining_time": "2:45:11"}
|
194 |
+
{"current_steps": 1930, "total_steps": 3105, "loss": 0.3239, "learning_rate": 5e-06, "epoch": 1.8638338966682761, "percentage": 62.16, "elapsed_time": "4:29:00", "remaining_time": "2:43:46"}
|
195 |
+
{"current_steps": 1940, "total_steps": 3105, "loss": 0.3237, "learning_rate": 5e-06, "epoch": 1.8734910671173346, "percentage": 62.48, "elapsed_time": "4:30:22", "remaining_time": "2:42:22"}
|
196 |
+
{"current_steps": 1950, "total_steps": 3105, "loss": 0.3202, "learning_rate": 5e-06, "epoch": 1.883148237566393, "percentage": 62.8, "elapsed_time": "4:31:45", "remaining_time": "2:40:58"}
|
197 |
+
{"current_steps": 1960, "total_steps": 3105, "loss": 0.3185, "learning_rate": 5e-06, "epoch": 1.8928054080154515, "percentage": 63.12, "elapsed_time": "4:33:08", "remaining_time": "2:39:34"}
|
198 |
+
{"current_steps": 1970, "total_steps": 3105, "loss": 0.323, "learning_rate": 5e-06, "epoch": 1.90246257846451, "percentage": 63.45, "elapsed_time": "4:34:31", "remaining_time": "2:38:10"}
|
199 |
+
{"current_steps": 1980, "total_steps": 3105, "loss": 0.3234, "learning_rate": 5e-06, "epoch": 1.9121197489135682, "percentage": 63.77, "elapsed_time": "4:35:54", "remaining_time": "2:36:46"}
|
200 |
+
{"current_steps": 1990, "total_steps": 3105, "loss": 0.322, "learning_rate": 5e-06, "epoch": 1.9217769193626268, "percentage": 64.09, "elapsed_time": "4:37:17", "remaining_time": "2:35:22"}
|
201 |
+
{"current_steps": 2000, "total_steps": 3105, "loss": 0.3247, "learning_rate": 5e-06, "epoch": 1.931434089811685, "percentage": 64.41, "elapsed_time": "4:38:40", "remaining_time": "2:33:58"}
|
202 |
+
{"current_steps": 2010, "total_steps": 3105, "loss": 0.3248, "learning_rate": 5e-06, "epoch": 1.9410912602607437, "percentage": 64.73, "elapsed_time": "4:40:03", "remaining_time": "2:32:33"}
|
203 |
+
{"current_steps": 2020, "total_steps": 3105, "loss": 0.3233, "learning_rate": 5e-06, "epoch": 1.950748430709802, "percentage": 65.06, "elapsed_time": "4:41:25", "remaining_time": "2:31:09"}
|
204 |
+
{"current_steps": 2030, "total_steps": 3105, "loss": 0.3311, "learning_rate": 5e-06, "epoch": 1.9604056011588604, "percentage": 65.38, "elapsed_time": "4:42:47", "remaining_time": "2:29:45"}
|
205 |
+
{"current_steps": 2040, "total_steps": 3105, "loss": 0.3224, "learning_rate": 5e-06, "epoch": 1.9700627716079189, "percentage": 65.7, "elapsed_time": "4:44:09", "remaining_time": "2:28:20"}
|
206 |
+
{"current_steps": 2050, "total_steps": 3105, "loss": 0.3245, "learning_rate": 5e-06, "epoch": 1.9797199420569773, "percentage": 66.02, "elapsed_time": "4:45:32", "remaining_time": "2:26:56"}
|
207 |
+
{"current_steps": 2060, "total_steps": 3105, "loss": 0.3283, "learning_rate": 5e-06, "epoch": 1.9893771125060358, "percentage": 66.34, "elapsed_time": "4:46:54", "remaining_time": "2:25:32"}
|
208 |
+
{"current_steps": 2070, "total_steps": 3105, "loss": 0.326, "learning_rate": 5e-06, "epoch": 1.999034282955094, "percentage": 66.67, "elapsed_time": "4:48:17", "remaining_time": "2:24:08"}
|
209 |
+
{"current_steps": 2071, "total_steps": 3105, "eval_loss": 0.41363242268562317, "epoch": 2.0, "percentage": 66.7, "elapsed_time": "4:51:29", "remaining_time": "2:25:31"}
|
210 |
+
{"current_steps": 2080, "total_steps": 3105, "loss": 0.2222, "learning_rate": 5e-06, "epoch": 2.0086914534041527, "percentage": 66.99, "elapsed_time": "4:53:37", "remaining_time": "2:24:41"}
|
training_args.bin.sagemaker-uploaded
ADDED
File without changes
|