sedrickkeh commited on
Commit
afa5798
·
verified ·
1 Parent(s): 74084b7

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:e452268fe49fb276f71236d223f5c35f5d7850cdfc5fe3d9e3fa4df62a8fda48
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ebb1e0cecf87252c61e1ff9c5e25d8cdd40421f1e5eba72c36b7a11952b0e31
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:c3e06b85ed5a9da0399f59ddb5a938089895097fa8664cda4ba86e846c926808
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8982aa073e4b83eac079d940e628e3eafa845ab39a0c14eeda3cfde14401c71a
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f5a8421521e92b334d5b002bc581d85f60c6f36509f62eb875300d8f0ca5bf7
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5efcd422160e190e0e301e85432e3f17fcd7b266d8fc34e1443fc02e507a49e1
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:340ba731d80a5f68438a0cc62f4ff4440950984f1c8ad7aa5bf1c225fc31102a
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f530da81bce34af21a73aef123428d191c417a0cc678a636a6d8a1e960315479
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -53,3 +53,30 @@
53
  {"current_steps": 520, "total_steps": 804, "loss": 0.6822, "lr": 5e-06, "epoch": 1.9384902143522833, "percentage": 64.68, "elapsed_time": "8:28:07", "remaining_time": "4:37:30"}
54
  {"current_steps": 530, "total_steps": 804, "loss": 0.6865, "lr": 5e-06, "epoch": 1.9757688723205966, "percentage": 65.92, "elapsed_time": "8:37:47", "remaining_time": "4:27:41"}
55
  {"current_steps": 536, "total_steps": 804, "eval_loss": 0.7287164330482483, "epoch": 1.9981360671015844, "percentage": 66.67, "elapsed_time": "8:48:47", "remaining_time": "4:24:23"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
  {"current_steps": 520, "total_steps": 804, "loss": 0.6822, "lr": 5e-06, "epoch": 1.9384902143522833, "percentage": 64.68, "elapsed_time": "8:28:07", "remaining_time": "4:37:30"}
54
  {"current_steps": 530, "total_steps": 804, "loss": 0.6865, "lr": 5e-06, "epoch": 1.9757688723205966, "percentage": 65.92, "elapsed_time": "8:37:47", "remaining_time": "4:27:41"}
55
  {"current_steps": 536, "total_steps": 804, "eval_loss": 0.7287164330482483, "epoch": 1.9981360671015844, "percentage": 66.67, "elapsed_time": "8:48:47", "remaining_time": "4:24:23"}
56
+ {"current_steps": 540, "total_steps": 804, "loss": 0.7188, "lr": 5e-06, "epoch": 2.0130475302889095, "percentage": 67.16, "elapsed_time": "8:53:23", "remaining_time": "4:20:46"}
57
+ {"current_steps": 550, "total_steps": 804, "loss": 0.6374, "lr": 5e-06, "epoch": 2.050326188257223, "percentage": 68.41, "elapsed_time": "9:03:02", "remaining_time": "4:10:47"}
58
+ {"current_steps": 560, "total_steps": 804, "loss": 0.627, "lr": 5e-06, "epoch": 2.0876048462255357, "percentage": 69.65, "elapsed_time": "9:12:40", "remaining_time": "4:00:48"}
59
+ {"current_steps": 570, "total_steps": 804, "loss": 0.6339, "lr": 5e-06, "epoch": 2.124883504193849, "percentage": 70.9, "elapsed_time": "9:22:19", "remaining_time": "3:50:50"}
60
+ {"current_steps": 580, "total_steps": 804, "loss": 0.6367, "lr": 5e-06, "epoch": 2.1621621621621623, "percentage": 72.14, "elapsed_time": "9:31:58", "remaining_time": "3:40:54"}
61
+ {"current_steps": 590, "total_steps": 804, "loss": 0.6361, "lr": 5e-06, "epoch": 2.199440820130475, "percentage": 73.38, "elapsed_time": "9:41:39", "remaining_time": "3:30:58"}
62
+ {"current_steps": 600, "total_steps": 804, "loss": 0.6361, "lr": 5e-06, "epoch": 2.2367194780987885, "percentage": 74.63, "elapsed_time": "9:51:18", "remaining_time": "3:21:02"}
63
+ {"current_steps": 610, "total_steps": 804, "loss": 0.6369, "lr": 5e-06, "epoch": 2.2739981360671018, "percentage": 75.87, "elapsed_time": "10:00:59", "remaining_time": "3:11:07"}
64
+ {"current_steps": 620, "total_steps": 804, "loss": 0.639, "lr": 5e-06, "epoch": 2.3112767940354146, "percentage": 77.11, "elapsed_time": "10:10:38", "remaining_time": "3:01:13"}
65
+ {"current_steps": 630, "total_steps": 804, "loss": 0.6411, "lr": 5e-06, "epoch": 2.348555452003728, "percentage": 78.36, "elapsed_time": "10:20:19", "remaining_time": "2:51:19"}
66
+ {"current_steps": 640, "total_steps": 804, "loss": 0.6368, "lr": 5e-06, "epoch": 2.385834109972041, "percentage": 79.6, "elapsed_time": "10:29:59", "remaining_time": "2:41:26"}
67
+ {"current_steps": 650, "total_steps": 804, "loss": 0.6351, "lr": 5e-06, "epoch": 2.423112767940354, "percentage": 80.85, "elapsed_time": "10:39:39", "remaining_time": "2:31:33"}
68
+ {"current_steps": 660, "total_steps": 804, "loss": 0.634, "lr": 5e-06, "epoch": 2.4603914259086674, "percentage": 82.09, "elapsed_time": "10:49:19", "remaining_time": "2:21:40"}
69
+ {"current_steps": 670, "total_steps": 804, "loss": 0.6404, "lr": 5e-06, "epoch": 2.4976700838769803, "percentage": 83.33, "elapsed_time": "10:59:00", "remaining_time": "2:11:48"}
70
+ {"current_steps": 680, "total_steps": 804, "loss": 0.6421, "lr": 5e-06, "epoch": 2.5349487418452936, "percentage": 84.58, "elapsed_time": "11:08:40", "remaining_time": "2:01:56"}
71
+ {"current_steps": 690, "total_steps": 804, "loss": 0.6369, "lr": 5e-06, "epoch": 2.572227399813607, "percentage": 85.82, "elapsed_time": "11:18:19", "remaining_time": "1:52:04"}
72
+ {"current_steps": 700, "total_steps": 804, "loss": 0.6376, "lr": 5e-06, "epoch": 2.60950605778192, "percentage": 87.06, "elapsed_time": "11:28:00", "remaining_time": "1:42:13"}
73
+ {"current_steps": 710, "total_steps": 804, "loss": 0.6368, "lr": 5e-06, "epoch": 2.646784715750233, "percentage": 88.31, "elapsed_time": "11:37:38", "remaining_time": "1:32:21"}
74
+ {"current_steps": 720, "total_steps": 804, "loss": 0.6375, "lr": 5e-06, "epoch": 2.684063373718546, "percentage": 89.55, "elapsed_time": "11:47:16", "remaining_time": "1:22:30"}
75
+ {"current_steps": 730, "total_steps": 804, "loss": 0.6398, "lr": 5e-06, "epoch": 2.7213420316868593, "percentage": 90.8, "elapsed_time": "11:56:55", "remaining_time": "1:12:40"}
76
+ {"current_steps": 740, "total_steps": 804, "loss": 0.6378, "lr": 5e-06, "epoch": 2.7586206896551726, "percentage": 92.04, "elapsed_time": "12:06:34", "remaining_time": "1:02:50"}
77
+ {"current_steps": 750, "total_steps": 804, "loss": 0.6413, "lr": 5e-06, "epoch": 2.7958993476234855, "percentage": 93.28, "elapsed_time": "12:16:14", "remaining_time": "0:53:00"}
78
+ {"current_steps": 760, "total_steps": 804, "loss": 0.641, "lr": 5e-06, "epoch": 2.8331780055917988, "percentage": 94.53, "elapsed_time": "12:25:53", "remaining_time": "0:43:10"}
79
+ {"current_steps": 770, "total_steps": 804, "loss": 0.6388, "lr": 5e-06, "epoch": 2.8704566635601116, "percentage": 95.77, "elapsed_time": "12:35:33", "remaining_time": "0:33:21"}
80
+ {"current_steps": 780, "total_steps": 804, "loss": 0.6391, "lr": 5e-06, "epoch": 2.907735321528425, "percentage": 97.01, "elapsed_time": "12:45:12", "remaining_time": "0:23:32"}
81
+ {"current_steps": 790, "total_steps": 804, "loss": 0.6352, "lr": 5e-06, "epoch": 2.9450139794967383, "percentage": 98.26, "elapsed_time": "12:54:51", "remaining_time": "0:13:43"}
82
+ {"current_steps": 800, "total_steps": 804, "loss": 0.6415, "lr": 5e-06, "epoch": 2.982292637465051, "percentage": 99.5, "elapsed_time": "13:04:31", "remaining_time": "0:03:55"}