sedrickkeh commited on
Commit
faa929b
·
verified ·
1 Parent(s): a088b0c

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 sha256:88102df1af702accf9f60adb3c66d8658ed69340863acb6231537ee511a3f072
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8acf0572326f706eac212a1e9d4b9a76f2f6407b87a1fb5146a30058816b44aa
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:ab758585bf8e78a70cb797c06819ad1a37fe534e8671850df5376c324d534673
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5ebf8656e6471f40e3861f5b4c6344bcd282f2ead293e2ecb679957f81f0763
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:f63e937f5b2707ae39997170f8912ad4efa80144a2c4c21865ecbcb84d59c1d5
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eaa35e92a02f49ae1dd59585a998e6da748aa019959bbe924a82c8df0308e4c
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:fb20d687bc1863199d849b1340b5330c3fb7c5623b7e91d3dbc2f6df0f5f4272
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eabda9b2b3fce68eb18daecdc66905844383d7e9953f508f9116d0dd2169e5b7
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -53,3 +53,29 @@
53
  {"current_steps": 520, "total_steps": 795, "loss": 0.7, "lr": 5e-06, "epoch": 1.9585687382297552, "percentage": 65.41, "elapsed_time": "8:24:35", "remaining_time": "4:26:51"}
54
  {"current_steps": 530, "total_steps": 795, "loss": 0.6959, "lr": 5e-06, "epoch": 1.9962335216572504, "percentage": 66.67, "elapsed_time": "8:34:10", "remaining_time": "4:17:05"}
55
  {"current_steps": 531, "total_steps": 795, "eval_loss": 0.7400202751159668, "epoch": 2.0, "percentage": 66.79, "elapsed_time": "8:39:45", "remaining_time": "4:18:24"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
  {"current_steps": 520, "total_steps": 795, "loss": 0.7, "lr": 5e-06, "epoch": 1.9585687382297552, "percentage": 65.41, "elapsed_time": "8:24:35", "remaining_time": "4:26:51"}
54
  {"current_steps": 530, "total_steps": 795, "loss": 0.6959, "lr": 5e-06, "epoch": 1.9962335216572504, "percentage": 66.67, "elapsed_time": "8:34:10", "remaining_time": "4:17:05"}
55
  {"current_steps": 531, "total_steps": 795, "eval_loss": 0.7400202751159668, "epoch": 2.0, "percentage": 66.79, "elapsed_time": "8:39:45", "remaining_time": "4:18:24"}
56
+ {"current_steps": 540, "total_steps": 795, "loss": 0.6778, "lr": 5e-06, "epoch": 2.0338983050847457, "percentage": 67.92, "elapsed_time": "8:49:38", "remaining_time": "4:10:06"}
57
+ {"current_steps": 550, "total_steps": 795, "loss": 0.6449, "lr": 5e-06, "epoch": 2.071563088512241, "percentage": 69.18, "elapsed_time": "8:59:13", "remaining_time": "4:00:12"}
58
+ {"current_steps": 560, "total_steps": 795, "loss": 0.6411, "lr": 5e-06, "epoch": 2.109227871939736, "percentage": 70.44, "elapsed_time": "9:08:48", "remaining_time": "3:50:18"}
59
+ {"current_steps": 570, "total_steps": 795, "loss": 0.642, "lr": 5e-06, "epoch": 2.146892655367232, "percentage": 71.7, "elapsed_time": "9:18:23", "remaining_time": "3:40:25"}
60
+ {"current_steps": 580, "total_steps": 795, "loss": 0.6437, "lr": 5e-06, "epoch": 2.184557438794727, "percentage": 72.96, "elapsed_time": "9:27:59", "remaining_time": "3:30:32"}
61
+ {"current_steps": 590, "total_steps": 795, "loss": 0.6436, "lr": 5e-06, "epoch": 2.2222222222222223, "percentage": 74.21, "elapsed_time": "9:37:34", "remaining_time": "3:20:41"}
62
+ {"current_steps": 600, "total_steps": 795, "loss": 0.645, "lr": 5e-06, "epoch": 2.2598870056497176, "percentage": 75.47, "elapsed_time": "9:47:10", "remaining_time": "3:10:49"}
63
+ {"current_steps": 610, "total_steps": 795, "loss": 0.6457, "lr": 5e-06, "epoch": 2.297551789077213, "percentage": 76.73, "elapsed_time": "9:56:46", "remaining_time": "3:00:59"}
64
+ {"current_steps": 620, "total_steps": 795, "loss": 0.6455, "lr": 5e-06, "epoch": 2.335216572504708, "percentage": 77.99, "elapsed_time": "10:06:21", "remaining_time": "2:51:08"}
65
+ {"current_steps": 630, "total_steps": 795, "loss": 0.6462, "lr": 5e-06, "epoch": 2.3728813559322033, "percentage": 79.25, "elapsed_time": "10:15:56", "remaining_time": "2:41:19"}
66
+ {"current_steps": 640, "total_steps": 795, "loss": 0.6507, "lr": 5e-06, "epoch": 2.4105461393596985, "percentage": 80.5, "elapsed_time": "10:25:31", "remaining_time": "2:31:29"}
67
+ {"current_steps": 650, "total_steps": 795, "loss": 0.6466, "lr": 5e-06, "epoch": 2.4482109227871938, "percentage": 81.76, "elapsed_time": "10:35:06", "remaining_time": "2:21:40"}
68
+ {"current_steps": 660, "total_steps": 795, "loss": 0.6436, "lr": 5e-06, "epoch": 2.4858757062146895, "percentage": 83.02, "elapsed_time": "10:44:41", "remaining_time": "2:11:52"}
69
+ {"current_steps": 670, "total_steps": 795, "loss": 0.648, "lr": 5e-06, "epoch": 2.5235404896421847, "percentage": 84.28, "elapsed_time": "10:54:16", "remaining_time": "2:02:04"}
70
+ {"current_steps": 680, "total_steps": 795, "loss": 0.6477, "lr": 5e-06, "epoch": 2.56120527306968, "percentage": 85.53, "elapsed_time": "11:03:51", "remaining_time": "1:52:16"}
71
+ {"current_steps": 690, "total_steps": 795, "loss": 0.6456, "lr": 5e-06, "epoch": 2.598870056497175, "percentage": 86.79, "elapsed_time": "11:13:27", "remaining_time": "1:42:28"}
72
+ {"current_steps": 700, "total_steps": 795, "loss": 0.6459, "lr": 5e-06, "epoch": 2.6365348399246704, "percentage": 88.05, "elapsed_time": "11:23:03", "remaining_time": "1:32:42"}
73
+ {"current_steps": 710, "total_steps": 795, "loss": 0.6459, "lr": 5e-06, "epoch": 2.6741996233521657, "percentage": 89.31, "elapsed_time": "11:32:39", "remaining_time": "1:22:55"}
74
+ {"current_steps": 720, "total_steps": 795, "loss": 0.6498, "lr": 5e-06, "epoch": 2.711864406779661, "percentage": 90.57, "elapsed_time": "11:42:15", "remaining_time": "1:13:09"}
75
+ {"current_steps": 730, "total_steps": 795, "loss": 0.651, "lr": 5e-06, "epoch": 2.7495291902071566, "percentage": 91.82, "elapsed_time": "11:51:50", "remaining_time": "1:03:22"}
76
+ {"current_steps": 740, "total_steps": 795, "loss": 0.6507, "lr": 5e-06, "epoch": 2.7871939736346514, "percentage": 93.08, "elapsed_time": "12:01:25", "remaining_time": "0:53:37"}
77
+ {"current_steps": 750, "total_steps": 795, "loss": 0.652, "lr": 5e-06, "epoch": 2.824858757062147, "percentage": 94.34, "elapsed_time": "12:11:00", "remaining_time": "0:43:51"}
78
+ {"current_steps": 760, "total_steps": 795, "loss": 0.651, "lr": 5e-06, "epoch": 2.8625235404896423, "percentage": 95.6, "elapsed_time": "12:20:36", "remaining_time": "0:34:06"}
79
+ {"current_steps": 770, "total_steps": 795, "loss": 0.6464, "lr": 5e-06, "epoch": 2.9001883239171375, "percentage": 96.86, "elapsed_time": "12:30:11", "remaining_time": "0:24:21"}
80
+ {"current_steps": 780, "total_steps": 795, "loss": 0.6448, "lr": 5e-06, "epoch": 2.937853107344633, "percentage": 98.11, "elapsed_time": "12:39:46", "remaining_time": "0:14:36"}
81
+ {"current_steps": 790, "total_steps": 795, "loss": 0.6504, "lr": 5e-06, "epoch": 2.975517890772128, "percentage": 99.37, "elapsed_time": "12:49:21", "remaining_time": "0:04:52"}