sedrickkeh commited on
Commit
3081e54
·
verified ·
1 Parent(s): bab6812

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:f9e36223b0d353686e41aa6eb6ed436ed2d2e4afec3e618dbf7ffe0b034ed1d9
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbb45aabe18ecd56fc879b9dde485ee6b3812de5cb08f7c38da74f2b68afbb1c
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e196fa1c7fee26766d4db9372399ca8b0dde990e7c1641236f6d38fd67debea
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97b9bbc59f89b93aa4fd6eaa7a6b8845c1b710cc3305ccf69c7fc6ff3e7814fa
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a157968a1f58383d582c2627bb4054c086544b8ca202409ce071c9febb7fc71
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77854f1cebfd73d6c25c0c6fc1aba52f2f4c05f904800f4c06c8a853394b6338
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:893089594c0bc690c0835d7cc13da54c5906242c4d365c940e7a0a950ecd50a4
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79e0c265f458915e7e1b4b8b83b84bb4373af055caad922c28acdc7e003b2668
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -62,3 +62,34 @@
62
  {"current_steps": 610, "total_steps": 930, "loss": 0.6462, "lr": 5e-06, "epoch": 1.966156325543916, "percentage": 65.59, "elapsed_time": "5:30:42", "remaining_time": "2:53:29"}
63
  {"current_steps": 620, "total_steps": 930, "loss": 0.6425, "lr": 5e-06, "epoch": 1.9983883964544722, "percentage": 66.67, "elapsed_time": "5:36:03", "remaining_time": "2:48:01"}
64
  {"current_steps": 620, "total_steps": 930, "eval_loss": 0.6802473068237305, "epoch": 1.9983883964544722, "percentage": 66.67, "elapsed_time": "5:39:51", "remaining_time": "2:49:55"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
  {"current_steps": 610, "total_steps": 930, "loss": 0.6462, "lr": 5e-06, "epoch": 1.966156325543916, "percentage": 65.59, "elapsed_time": "5:30:42", "remaining_time": "2:53:29"}
63
  {"current_steps": 620, "total_steps": 930, "loss": 0.6425, "lr": 5e-06, "epoch": 1.9983883964544722, "percentage": 66.67, "elapsed_time": "5:36:03", "remaining_time": "2:48:01"}
64
  {"current_steps": 620, "total_steps": 930, "eval_loss": 0.6802473068237305, "epoch": 1.9983883964544722, "percentage": 66.67, "elapsed_time": "5:39:51", "remaining_time": "2:49:55"}
65
+ {"current_steps": 630, "total_steps": 930, "loss": 0.6494, "lr": 5e-06, "epoch": 2.0306204673650283, "percentage": 67.74, "elapsed_time": "5:46:14", "remaining_time": "2:44:52"}
66
+ {"current_steps": 640, "total_steps": 930, "loss": 0.6008, "lr": 5e-06, "epoch": 2.062852538275584, "percentage": 68.82, "elapsed_time": "5:51:33", "remaining_time": "2:39:17"}
67
+ {"current_steps": 650, "total_steps": 930, "loss": 0.5985, "lr": 5e-06, "epoch": 2.09508460918614, "percentage": 69.89, "elapsed_time": "5:56:52", "remaining_time": "2:33:43"}
68
+ {"current_steps": 660, "total_steps": 930, "loss": 0.5942, "lr": 5e-06, "epoch": 2.1273166800966963, "percentage": 70.97, "elapsed_time": "6:02:12", "remaining_time": "2:28:10"}
69
+ {"current_steps": 670, "total_steps": 930, "loss": 0.6033, "lr": 5e-06, "epoch": 2.1595487510072524, "percentage": 72.04, "elapsed_time": "6:07:30", "remaining_time": "2:22:37"}
70
+ {"current_steps": 680, "total_steps": 930, "loss": 0.6023, "lr": 5e-06, "epoch": 2.191780821917808, "percentage": 73.12, "elapsed_time": "6:12:51", "remaining_time": "2:17:04"}
71
+ {"current_steps": 690, "total_steps": 930, "loss": 0.5963, "lr": 5e-06, "epoch": 2.2240128928283642, "percentage": 74.19, "elapsed_time": "6:18:12", "remaining_time": "2:11:33"}
72
+ {"current_steps": 700, "total_steps": 930, "loss": 0.5965, "lr": 5e-06, "epoch": 2.2562449637389204, "percentage": 75.27, "elapsed_time": "6:23:33", "remaining_time": "2:06:01"}
73
+ {"current_steps": 710, "total_steps": 930, "loss": 0.5937, "lr": 5e-06, "epoch": 2.288477034649476, "percentage": 76.34, "elapsed_time": "6:28:51", "remaining_time": "2:00:29"}
74
+ {"current_steps": 720, "total_steps": 930, "loss": 0.607, "lr": 5e-06, "epoch": 2.320709105560032, "percentage": 77.42, "elapsed_time": "6:34:10", "remaining_time": "1:54:58"}
75
+ {"current_steps": 730, "total_steps": 930, "loss": 0.599, "lr": 5e-06, "epoch": 2.3529411764705883, "percentage": 78.49, "elapsed_time": "6:39:29", "remaining_time": "1:49:27"}
76
+ {"current_steps": 740, "total_steps": 930, "loss": 0.6001, "lr": 5e-06, "epoch": 2.385173247381144, "percentage": 79.57, "elapsed_time": "6:44:49", "remaining_time": "1:43:56"}
77
+ {"current_steps": 750, "total_steps": 930, "loss": 0.6067, "lr": 5e-06, "epoch": 2.4174053182917, "percentage": 80.65, "elapsed_time": "6:50:09", "remaining_time": "1:38:26"}
78
+ {"current_steps": 760, "total_steps": 930, "loss": 0.6024, "lr": 5e-06, "epoch": 2.4496373892022563, "percentage": 81.72, "elapsed_time": "6:55:30", "remaining_time": "1:32:56"}
79
+ {"current_steps": 770, "total_steps": 930, "loss": 0.6008, "lr": 5e-06, "epoch": 2.4818694601128124, "percentage": 82.8, "elapsed_time": "7:00:49", "remaining_time": "1:27:26"}
80
+ {"current_steps": 780, "total_steps": 930, "loss": 0.6015, "lr": 5e-06, "epoch": 2.514101531023368, "percentage": 83.87, "elapsed_time": "7:06:09", "remaining_time": "1:21:57"}
81
+ {"current_steps": 790, "total_steps": 930, "loss": 0.5997, "lr": 5e-06, "epoch": 2.546333601933924, "percentage": 84.95, "elapsed_time": "7:11:28", "remaining_time": "1:16:27"}
82
+ {"current_steps": 800, "total_steps": 930, "loss": 0.6004, "lr": 5e-06, "epoch": 2.5785656728444803, "percentage": 86.02, "elapsed_time": "7:16:49", "remaining_time": "1:10:59"}
83
+ {"current_steps": 810, "total_steps": 930, "loss": 0.6022, "lr": 5e-06, "epoch": 2.610797743755036, "percentage": 87.1, "elapsed_time": "7:22:10", "remaining_time": "1:05:30"}
84
+ {"current_steps": 820, "total_steps": 930, "loss": 0.6034, "lr": 5e-06, "epoch": 2.643029814665592, "percentage": 88.17, "elapsed_time": "7:27:30", "remaining_time": "1:00:01"}
85
+ {"current_steps": 830, "total_steps": 930, "loss": 0.6013, "lr": 5e-06, "epoch": 2.6752618855761483, "percentage": 89.25, "elapsed_time": "7:32:48", "remaining_time": "0:54:33"}
86
+ {"current_steps": 840, "total_steps": 930, "loss": 0.6005, "lr": 5e-06, "epoch": 2.7074939564867044, "percentage": 90.32, "elapsed_time": "7:38:06", "remaining_time": "0:49:04"}
87
+ {"current_steps": 850, "total_steps": 930, "loss": 0.6062, "lr": 5e-06, "epoch": 2.73972602739726, "percentage": 91.4, "elapsed_time": "7:43:25", "remaining_time": "0:43:36"}
88
+ {"current_steps": 860, "total_steps": 930, "loss": 0.6048, "lr": 5e-06, "epoch": 2.7719580983078163, "percentage": 92.47, "elapsed_time": "7:48:46", "remaining_time": "0:38:09"}
89
+ {"current_steps": 870, "total_steps": 930, "loss": 0.605, "lr": 5e-06, "epoch": 2.8041901692183724, "percentage": 93.55, "elapsed_time": "7:54:07", "remaining_time": "0:32:41"}
90
+ {"current_steps": 880, "total_steps": 930, "loss": 0.6032, "lr": 5e-06, "epoch": 2.836422240128928, "percentage": 94.62, "elapsed_time": "7:59:25", "remaining_time": "0:27:14"}
91
+ {"current_steps": 890, "total_steps": 930, "loss": 0.6002, "lr": 5e-06, "epoch": 2.868654311039484, "percentage": 95.7, "elapsed_time": "8:04:45", "remaining_time": "0:21:47"}
92
+ {"current_steps": 900, "total_steps": 930, "loss": 0.6005, "lr": 5e-06, "epoch": 2.9008863819500403, "percentage": 96.77, "elapsed_time": "8:10:05", "remaining_time": "0:16:20"}
93
+ {"current_steps": 910, "total_steps": 930, "loss": 0.6027, "lr": 5e-06, "epoch": 2.9331184528605965, "percentage": 97.85, "elapsed_time": "8:15:26", "remaining_time": "0:10:53"}
94
+ {"current_steps": 920, "total_steps": 930, "loss": 0.6023, "lr": 5e-06, "epoch": 2.965350523771152, "percentage": 98.92, "elapsed_time": "8:20:46", "remaining_time": "0:05:26"}
95
+ {"current_steps": 930, "total_steps": 930, "loss": 0.605, "lr": 5e-06, "epoch": 2.9975825946817083, "percentage": 100.0, "elapsed_time": "8:26:06", "remaining_time": "0:00:00"}