sedrickkeh commited on
Commit
6c9ddfb
·
verified ·
1 Parent(s): eea6561

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:baa48abddd42aacc3f3ac5b61842accd267c86b30c90ef796ee041b2b5e8c8b8
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a89031bc045e292bdb32863e19bb86e81219eac55253e833a28880b80272f3f1
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72480a6d5d47d78008a87d5a64ac9e4e3ba2f7c94a5bf116768dc4625e6789dc
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cb1a6fe2c4221073cda5e332df8cc4644d7ca0d363ec81364f836d1b13dc7b5
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e31305a9ac9c52caacb54f836a6d416c29ccbfc29a6a2c10608516a4f6aa9c7
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d9f7b3c42eb12c826c1721f29e1fd21b5b4a5b92c066f82242c4aad500d1ee6
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:f1530da3a1ad50d7ef0a26cf3639a3a5adcf1af78ddd46cd08ef0b77274144b0
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6605a3e5b17d75b41b3a0ae83ea89d71b113e6191871f613c907c74093d8812
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -55,3 +55,31 @@
55
  {"current_steps": 540, "total_steps": 831, "loss": 0.6854, "lr": 5e-06, "epoch": 1.9441944194419443, "percentage": 64.98, "elapsed_time": "8:41:54", "remaining_time": "4:41:14"}
56
  {"current_steps": 550, "total_steps": 831, "loss": 0.6894, "lr": 5e-06, "epoch": 1.9801980198019802, "percentage": 66.19, "elapsed_time": "8:51:27", "remaining_time": "4:31:31"}
57
  {"current_steps": 555, "total_steps": 831, "eval_loss": 0.7263253331184387, "epoch": 1.9981998199819984, "percentage": 66.79, "elapsed_time": "9:01:30", "remaining_time": "4:29:17"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  {"current_steps": 540, "total_steps": 831, "loss": 0.6854, "lr": 5e-06, "epoch": 1.9441944194419443, "percentage": 64.98, "elapsed_time": "8:41:54", "remaining_time": "4:41:14"}
56
  {"current_steps": 550, "total_steps": 831, "loss": 0.6894, "lr": 5e-06, "epoch": 1.9801980198019802, "percentage": 66.19, "elapsed_time": "8:51:27", "remaining_time": "4:31:31"}
57
  {"current_steps": 555, "total_steps": 831, "eval_loss": 0.7263253331184387, "epoch": 1.9981998199819984, "percentage": 66.79, "elapsed_time": "9:01:30", "remaining_time": "4:29:17"}
58
+ {"current_steps": 560, "total_steps": 831, "loss": 0.6805, "lr": 5e-06, "epoch": 2.016201620162016, "percentage": 67.39, "elapsed_time": "9:07:06", "remaining_time": "4:24:45"}
59
+ {"current_steps": 570, "total_steps": 831, "loss": 0.6302, "lr": 5e-06, "epoch": 2.052205220522052, "percentage": 68.59, "elapsed_time": "9:16:40", "remaining_time": "4:14:53"}
60
+ {"current_steps": 580, "total_steps": 831, "loss": 0.6315, "lr": 5e-06, "epoch": 2.0882088208820884, "percentage": 69.8, "elapsed_time": "9:26:12", "remaining_time": "4:05:01"}
61
+ {"current_steps": 590, "total_steps": 831, "loss": 0.6301, "lr": 5e-06, "epoch": 2.1242124212421243, "percentage": 71.0, "elapsed_time": "9:35:46", "remaining_time": "3:55:11"}
62
+ {"current_steps": 600, "total_steps": 831, "loss": 0.6298, "lr": 5e-06, "epoch": 2.16021602160216, "percentage": 72.2, "elapsed_time": "9:45:19", "remaining_time": "3:45:20"}
63
+ {"current_steps": 610, "total_steps": 831, "loss": 0.6354, "lr": 5e-06, "epoch": 2.196219621962196, "percentage": 73.41, "elapsed_time": "9:54:53", "remaining_time": "3:35:31"}
64
+ {"current_steps": 620, "total_steps": 831, "loss": 0.6319, "lr": 5e-06, "epoch": 2.232223222322232, "percentage": 74.61, "elapsed_time": "10:04:27", "remaining_time": "3:25:42"}
65
+ {"current_steps": 630, "total_steps": 831, "loss": 0.6336, "lr": 5e-06, "epoch": 2.2682268226822684, "percentage": 75.81, "elapsed_time": "10:14:00", "remaining_time": "3:15:54"}
66
+ {"current_steps": 640, "total_steps": 831, "loss": 0.6345, "lr": 5e-06, "epoch": 2.3042304230423043, "percentage": 77.02, "elapsed_time": "10:23:34", "remaining_time": "3:06:05"}
67
+ {"current_steps": 650, "total_steps": 831, "loss": 0.6363, "lr": 5e-06, "epoch": 2.34023402340234, "percentage": 78.22, "elapsed_time": "10:33:07", "remaining_time": "2:56:18"}
68
+ {"current_steps": 660, "total_steps": 831, "loss": 0.6313, "lr": 5e-06, "epoch": 2.376237623762376, "percentage": 79.42, "elapsed_time": "10:42:42", "remaining_time": "2:46:31"}
69
+ {"current_steps": 670, "total_steps": 831, "loss": 0.6357, "lr": 5e-06, "epoch": 2.412241224122412, "percentage": 80.63, "elapsed_time": "10:52:16", "remaining_time": "2:36:44"}
70
+ {"current_steps": 680, "total_steps": 831, "loss": 0.6383, "lr": 5e-06, "epoch": 2.4482448244824484, "percentage": 81.83, "elapsed_time": "11:01:50", "remaining_time": "2:26:58"}
71
+ {"current_steps": 690, "total_steps": 831, "loss": 0.6376, "lr": 5e-06, "epoch": 2.4842484248424843, "percentage": 83.03, "elapsed_time": "11:11:23", "remaining_time": "2:17:11"}
72
+ {"current_steps": 700, "total_steps": 831, "loss": 0.6358, "lr": 5e-06, "epoch": 2.5202520252025202, "percentage": 84.24, "elapsed_time": "11:20:57", "remaining_time": "2:07:26"}
73
+ {"current_steps": 710, "total_steps": 831, "loss": 0.6346, "lr": 5e-06, "epoch": 2.556255625562556, "percentage": 85.44, "elapsed_time": "11:30:30", "remaining_time": "1:57:40"}
74
+ {"current_steps": 720, "total_steps": 831, "loss": 0.6341, "lr": 5e-06, "epoch": 2.592259225922592, "percentage": 86.64, "elapsed_time": "11:40:03", "remaining_time": "1:47:55"}
75
+ {"current_steps": 730, "total_steps": 831, "loss": 0.6345, "lr": 5e-06, "epoch": 2.6282628262826284, "percentage": 87.85, "elapsed_time": "11:49:36", "remaining_time": "1:38:10"}
76
+ {"current_steps": 740, "total_steps": 831, "loss": 0.6346, "lr": 5e-06, "epoch": 2.6642664266426643, "percentage": 89.05, "elapsed_time": "11:59:08", "remaining_time": "1:28:26"}
77
+ {"current_steps": 750, "total_steps": 831, "loss": 0.6319, "lr": 5e-06, "epoch": 2.7002700270027002, "percentage": 90.25, "elapsed_time": "12:08:42", "remaining_time": "1:18:41"}
78
+ {"current_steps": 760, "total_steps": 831, "loss": 0.636, "lr": 5e-06, "epoch": 2.736273627362736, "percentage": 91.46, "elapsed_time": "12:18:13", "remaining_time": "1:08:57"}
79
+ {"current_steps": 770, "total_steps": 831, "loss": 0.6426, "lr": 5e-06, "epoch": 2.772277227722772, "percentage": 92.66, "elapsed_time": "12:27:46", "remaining_time": "0:59:14"}
80
+ {"current_steps": 780, "total_steps": 831, "loss": 0.632, "lr": 5e-06, "epoch": 2.8082808280828084, "percentage": 93.86, "elapsed_time": "12:37:18", "remaining_time": "0:49:30"}
81
+ {"current_steps": 790, "total_steps": 831, "loss": 0.6349, "lr": 5e-06, "epoch": 2.8442844284428443, "percentage": 95.07, "elapsed_time": "12:46:52", "remaining_time": "0:39:47"}
82
+ {"current_steps": 800, "total_steps": 831, "loss": 0.6382, "lr": 5e-06, "epoch": 2.8802880288028803, "percentage": 96.27, "elapsed_time": "12:56:26", "remaining_time": "0:30:05"}
83
+ {"current_steps": 810, "total_steps": 831, "loss": 0.6362, "lr": 5e-06, "epoch": 2.916291629162916, "percentage": 97.47, "elapsed_time": "13:06:00", "remaining_time": "0:20:22"}
84
+ {"current_steps": 820, "total_steps": 831, "loss": 0.6357, "lr": 5e-06, "epoch": 2.952295229522952, "percentage": 98.68, "elapsed_time": "13:15:32", "remaining_time": "0:10:40"}
85
+ {"current_steps": 830, "total_steps": 831, "loss": 0.6329, "lr": 5e-06, "epoch": 2.9882988298829884, "percentage": 99.88, "elapsed_time": "13:25:04", "remaining_time": "0:00:58"}