sedrickkeh commited on
Commit
a22eae4
·
verified ·
1 Parent(s): 34a4915

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:c8585dbe3cafc9afe449f850a4b340a092e2ed874cf00fe8a14a230f59a7d2e3
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4c68cca1dbc19be59c3dd77864b0ab007be10909cc048daf8c5a9c239df25a5
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87a11650271085d4e088af232060443668445f8cff1e444aaa99af66f52db0d9
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6822077a36df9943b646d507683a6a8052fab54ff91a3df96203f77da206ca2
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1d427fc0888b187d0c4cc154ee759e573cff189b1b35badbc7f6d8f8a406960
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7f439479593100fb98848cb073e23e0979788eb58e1c286dd4c9857fab2674e
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd683d68f8662f06a933ac754909837520aa3e2c88dcaf2cc761242478149433
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:629fe602d030b15d54b68c6a8ba54801e77629f0b0689a723465124ba2bb4888
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -96,3 +96,50 @@
96
  {"current_steps": 950, "total_steps": 1437, "loss": 0.7573, "lr": 5e-06, "epoch": 1.981230448383733, "percentage": 66.11, "elapsed_time": "15:21:35", "remaining_time": "7:52:26"}
97
  {"current_steps": 959, "total_steps": 1437, "eval_loss": 0.7946059703826904, "epoch": 2.0, "percentage": 66.74, "elapsed_time": "15:38:37", "remaining_time": "7:47:50"}
98
  {"current_steps": 960, "total_steps": 1437, "loss": 0.7947, "lr": 5e-06, "epoch": 2.002085505735141, "percentage": 66.81, "elapsed_time": "15:40:47", "remaining_time": "7:47:27"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
96
  {"current_steps": 950, "total_steps": 1437, "loss": 0.7573, "lr": 5e-06, "epoch": 1.981230448383733, "percentage": 66.11, "elapsed_time": "15:21:35", "remaining_time": "7:52:26"}
97
  {"current_steps": 959, "total_steps": 1437, "eval_loss": 0.7946059703826904, "epoch": 2.0, "percentage": 66.74, "elapsed_time": "15:38:37", "remaining_time": "7:47:50"}
98
  {"current_steps": 960, "total_steps": 1437, "loss": 0.7947, "lr": 5e-06, "epoch": 2.002085505735141, "percentage": 66.81, "elapsed_time": "15:40:47", "remaining_time": "7:47:27"}
99
+ {"current_steps": 970, "total_steps": 1437, "loss": 0.7156, "lr": 5e-06, "epoch": 2.0229405630865487, "percentage": 67.5, "elapsed_time": "15:50:23", "remaining_time": "7:37:33"}
100
+ {"current_steps": 980, "total_steps": 1437, "loss": 0.7127, "lr": 5e-06, "epoch": 2.0437956204379564, "percentage": 68.2, "elapsed_time": "16:00:00", "remaining_time": "7:27:40"}
101
+ {"current_steps": 990, "total_steps": 1437, "loss": 0.7126, "lr": 5e-06, "epoch": 2.064650677789364, "percentage": 68.89, "elapsed_time": "16:09:37", "remaining_time": "7:17:47"}
102
+ {"current_steps": 1000, "total_steps": 1437, "loss": 0.714, "lr": 5e-06, "epoch": 2.0855057351407718, "percentage": 69.59, "elapsed_time": "16:19:14", "remaining_time": "7:07:55"}
103
+ {"current_steps": 1010, "total_steps": 1437, "loss": 0.7131, "lr": 5e-06, "epoch": 2.1063607924921794, "percentage": 70.29, "elapsed_time": "16:28:50", "remaining_time": "6:58:03"}
104
+ {"current_steps": 1020, "total_steps": 1437, "loss": 0.7144, "lr": 5e-06, "epoch": 2.127215849843587, "percentage": 70.98, "elapsed_time": "16:38:27", "remaining_time": "6:48:11"}
105
+ {"current_steps": 1030, "total_steps": 1437, "loss": 0.7145, "lr": 5e-06, "epoch": 2.148070907194995, "percentage": 71.68, "elapsed_time": "16:48:02", "remaining_time": "6:38:19"}
106
+ {"current_steps": 1040, "total_steps": 1437, "loss": 0.7112, "lr": 5e-06, "epoch": 2.1689259645464025, "percentage": 72.37, "elapsed_time": "16:57:38", "remaining_time": "6:28:27"}
107
+ {"current_steps": 1050, "total_steps": 1437, "loss": 0.7182, "lr": 5e-06, "epoch": 2.18978102189781, "percentage": 73.07, "elapsed_time": "17:07:14", "remaining_time": "6:18:36"}
108
+ {"current_steps": 1060, "total_steps": 1437, "loss": 0.7189, "lr": 5e-06, "epoch": 2.210636079249218, "percentage": 73.76, "elapsed_time": "17:16:51", "remaining_time": "6:08:46"}
109
+ {"current_steps": 1070, "total_steps": 1437, "loss": 0.7222, "lr": 5e-06, "epoch": 2.2314911366006256, "percentage": 74.46, "elapsed_time": "17:26:27", "remaining_time": "5:58:55"}
110
+ {"current_steps": 1080, "total_steps": 1437, "loss": 0.7188, "lr": 5e-06, "epoch": 2.2523461939520333, "percentage": 75.16, "elapsed_time": "17:36:03", "remaining_time": "5:49:05"}
111
+ {"current_steps": 1090, "total_steps": 1437, "loss": 0.7196, "lr": 5e-06, "epoch": 2.273201251303441, "percentage": 75.85, "elapsed_time": "17:45:38", "remaining_time": "5:39:14"}
112
+ {"current_steps": 1100, "total_steps": 1437, "loss": 0.7162, "lr": 5e-06, "epoch": 2.2940563086548487, "percentage": 76.55, "elapsed_time": "17:55:15", "remaining_time": "5:29:25"}
113
+ {"current_steps": 1110, "total_steps": 1437, "loss": 0.7157, "lr": 5e-06, "epoch": 2.3149113660062564, "percentage": 77.24, "elapsed_time": "18:04:51", "remaining_time": "5:19:35"}
114
+ {"current_steps": 1120, "total_steps": 1437, "loss": 0.7164, "lr": 5e-06, "epoch": 2.335766423357664, "percentage": 77.94, "elapsed_time": "18:14:26", "remaining_time": "5:09:46"}
115
+ {"current_steps": 1130, "total_steps": 1437, "loss": 0.7204, "lr": 5e-06, "epoch": 2.356621480709072, "percentage": 78.64, "elapsed_time": "18:24:03", "remaining_time": "4:59:57"}
116
+ {"current_steps": 1140, "total_steps": 1437, "loss": 0.7172, "lr": 5e-06, "epoch": 2.3774765380604794, "percentage": 79.33, "elapsed_time": "18:33:38", "remaining_time": "4:50:07"}
117
+ {"current_steps": 1150, "total_steps": 1437, "loss": 0.7192, "lr": 5e-06, "epoch": 2.3983315954118876, "percentage": 80.03, "elapsed_time": "18:43:15", "remaining_time": "4:40:19"}
118
+ {"current_steps": 1160, "total_steps": 1437, "loss": 0.7182, "lr": 5e-06, "epoch": 2.4191866527632953, "percentage": 80.72, "elapsed_time": "18:52:51", "remaining_time": "4:30:31"}
119
+ {"current_steps": 1170, "total_steps": 1437, "loss": 0.7147, "lr": 5e-06, "epoch": 2.440041710114703, "percentage": 81.42, "elapsed_time": "19:02:27", "remaining_time": "4:20:42"}
120
+ {"current_steps": 1180, "total_steps": 1437, "loss": 0.7156, "lr": 5e-06, "epoch": 2.4608967674661106, "percentage": 82.12, "elapsed_time": "19:12:05", "remaining_time": "4:10:55"}
121
+ {"current_steps": 1190, "total_steps": 1437, "loss": 0.7203, "lr": 5e-06, "epoch": 2.4817518248175183, "percentage": 82.81, "elapsed_time": "19:21:40", "remaining_time": "4:01:07"}
122
+ {"current_steps": 1200, "total_steps": 1437, "loss": 0.721, "lr": 5e-06, "epoch": 2.502606882168926, "percentage": 83.51, "elapsed_time": "19:31:16", "remaining_time": "3:51:19"}
123
+ {"current_steps": 1210, "total_steps": 1437, "loss": 0.7186, "lr": 5e-06, "epoch": 2.5234619395203337, "percentage": 84.2, "elapsed_time": "19:40:53", "remaining_time": "3:41:32"}
124
+ {"current_steps": 1220, "total_steps": 1437, "loss": 0.7181, "lr": 5e-06, "epoch": 2.5443169968717414, "percentage": 84.9, "elapsed_time": "19:50:30", "remaining_time": "3:31:45"}
125
+ {"current_steps": 1230, "total_steps": 1437, "loss": 0.7185, "lr": 5e-06, "epoch": 2.565172054223149, "percentage": 85.59, "elapsed_time": "20:00:07", "remaining_time": "3:21:58"}
126
+ {"current_steps": 1240, "total_steps": 1437, "loss": 0.7176, "lr": 5e-06, "epoch": 2.586027111574557, "percentage": 86.29, "elapsed_time": "20:09:43", "remaining_time": "3:12:11"}
127
+ {"current_steps": 1250, "total_steps": 1437, "loss": 0.7162, "lr": 5e-06, "epoch": 2.6068821689259645, "percentage": 86.99, "elapsed_time": "20:19:19", "remaining_time": "3:02:24"}
128
+ {"current_steps": 1260, "total_steps": 1437, "loss": 0.7203, "lr": 5e-06, "epoch": 2.627737226277372, "percentage": 87.68, "elapsed_time": "20:28:57", "remaining_time": "2:52:38"}
129
+ {"current_steps": 1270, "total_steps": 1437, "loss": 0.7167, "lr": 5e-06, "epoch": 2.64859228362878, "percentage": 88.38, "elapsed_time": "20:38:34", "remaining_time": "2:42:52"}
130
+ {"current_steps": 1280, "total_steps": 1437, "loss": 0.7188, "lr": 5e-06, "epoch": 2.6694473409801875, "percentage": 89.07, "elapsed_time": "20:48:10", "remaining_time": "2:33:05"}
131
+ {"current_steps": 1290, "total_steps": 1437, "loss": 0.7166, "lr": 5e-06, "epoch": 2.6903023983315952, "percentage": 89.77, "elapsed_time": "20:57:47", "remaining_time": "2:23:19"}
132
+ {"current_steps": 1300, "total_steps": 1437, "loss": 0.7189, "lr": 5e-06, "epoch": 2.7111574556830034, "percentage": 90.47, "elapsed_time": "21:07:25", "remaining_time": "2:13:33"}
133
+ {"current_steps": 1310, "total_steps": 1437, "loss": 0.7195, "lr": 5e-06, "epoch": 2.7320125130344106, "percentage": 91.16, "elapsed_time": "21:17:01", "remaining_time": "2:03:48"}
134
+ {"current_steps": 1320, "total_steps": 1437, "loss": 0.7188, "lr": 5e-06, "epoch": 2.7528675703858188, "percentage": 91.86, "elapsed_time": "21:26:38", "remaining_time": "1:54:02"}
135
+ {"current_steps": 1330, "total_steps": 1437, "loss": 0.7216, "lr": 5e-06, "epoch": 2.7737226277372264, "percentage": 92.55, "elapsed_time": "21:36:15", "remaining_time": "1:44:17"}
136
+ {"current_steps": 1340, "total_steps": 1437, "loss": 0.7208, "lr": 5e-06, "epoch": 2.794577685088634, "percentage": 93.25, "elapsed_time": "21:45:51", "remaining_time": "1:34:31"}
137
+ {"current_steps": 1350, "total_steps": 1437, "loss": 0.7155, "lr": 5e-06, "epoch": 2.815432742440042, "percentage": 93.95, "elapsed_time": "21:55:28", "remaining_time": "1:24:46"}
138
+ {"current_steps": 1360, "total_steps": 1437, "loss": 0.7233, "lr": 5e-06, "epoch": 2.8362877997914495, "percentage": 94.64, "elapsed_time": "22:05:04", "remaining_time": "1:15:01"}
139
+ {"current_steps": 1370, "total_steps": 1437, "loss": 0.7219, "lr": 5e-06, "epoch": 2.857142857142857, "percentage": 95.34, "elapsed_time": "22:14:41", "remaining_time": "1:05:16"}
140
+ {"current_steps": 1380, "total_steps": 1437, "loss": 0.718, "lr": 5e-06, "epoch": 2.877997914494265, "percentage": 96.03, "elapsed_time": "22:24:17", "remaining_time": "0:55:31"}
141
+ {"current_steps": 1390, "total_steps": 1437, "loss": 0.7196, "lr": 5e-06, "epoch": 2.8988529718456726, "percentage": 96.73, "elapsed_time": "22:33:54", "remaining_time": "0:45:46"}
142
+ {"current_steps": 1400, "total_steps": 1437, "loss": 0.7195, "lr": 5e-06, "epoch": 2.9197080291970803, "percentage": 97.43, "elapsed_time": "22:43:31", "remaining_time": "0:36:02"}
143
+ {"current_steps": 1410, "total_steps": 1437, "loss": 0.715, "lr": 5e-06, "epoch": 2.940563086548488, "percentage": 98.12, "elapsed_time": "22:53:07", "remaining_time": "0:26:17"}
144
+ {"current_steps": 1420, "total_steps": 1437, "loss": 0.7213, "lr": 5e-06, "epoch": 2.9614181438998957, "percentage": 98.82, "elapsed_time": "23:02:44", "remaining_time": "0:16:33"}
145
+ {"current_steps": 1430, "total_steps": 1437, "loss": 0.7202, "lr": 5e-06, "epoch": 2.9822732012513034, "percentage": 99.51, "elapsed_time": "23:12:21", "remaining_time": "0:06:48"}