sedrickkeh commited on
Commit
34a4915
·
verified ·
1 Parent(s): 3343861

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 sha256:5deead95d0b324de7fdd1c96efe48a3849991a537c8956ca07f122956b32b7c5
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8585dbe3cafc9afe449f850a4b340a092e2ed874cf00fe8a14a230f59a7d2e3
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ef2f37c0ad9edfc14a58ebdc3b6a4edfaa2de8c6469828ccff5ca8e452aaea3
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a11650271085d4e088af232060443668445f8cff1e444aaa99af66f52db0d9
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:a35c074fa297b93792fa11f3ed7765b99abf333004a7428926772b574cb9f93e
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1d427fc0888b187d0c4cc154ee759e573cff189b1b35badbc7f6d8f8a406960
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23fbcd90114034fecc852b84e3c7a0919955341adca66951cd7582648860d68d
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd683d68f8662f06a933ac754909837520aa3e2c88dcaf2cc761242478149433
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -47,3 +47,52 @@
47
  {"current_steps": 470, "total_steps": 1437, "loss": 0.8049, "lr": 5e-06, "epoch": 0.9801876955161627, "percentage": 32.71, "elapsed_time": "7:30:56", "remaining_time": "15:27:47"}
48
  {"current_steps": 479, "total_steps": 1437, "eval_loss": 0.8077179789543152, "epoch": 0.9989572471324296, "percentage": 33.33, "elapsed_time": "7:48:30", "remaining_time": "15:37:01"}
49
  {"current_steps": 480, "total_steps": 1437, "loss": 0.8452, "lr": 5e-06, "epoch": 1.0010427528675705, "percentage": 33.4, "elapsed_time": "7:50:10", "remaining_time": "15:37:25"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  {"current_steps": 470, "total_steps": 1437, "loss": 0.8049, "lr": 5e-06, "epoch": 0.9801876955161627, "percentage": 32.71, "elapsed_time": "7:30:56", "remaining_time": "15:27:47"}
48
  {"current_steps": 479, "total_steps": 1437, "eval_loss": 0.8077179789543152, "epoch": 0.9989572471324296, "percentage": 33.33, "elapsed_time": "7:48:30", "remaining_time": "15:37:01"}
49
  {"current_steps": 480, "total_steps": 1437, "loss": 0.8452, "lr": 5e-06, "epoch": 1.0010427528675705, "percentage": 33.4, "elapsed_time": "7:50:10", "remaining_time": "15:37:25"}
50
+ {"current_steps": 490, "total_steps": 1437, "loss": 0.7627, "lr": 5e-06, "epoch": 1.0218978102189782, "percentage": 34.1, "elapsed_time": "7:59:46", "remaining_time": "15:27:13"}
51
+ {"current_steps": 500, "total_steps": 1437, "loss": 0.7631, "lr": 5e-06, "epoch": 1.0427528675703859, "percentage": 34.79, "elapsed_time": "8:09:22", "remaining_time": "15:17:05"}
52
+ {"current_steps": 510, "total_steps": 1437, "loss": 0.7592, "lr": 5e-06, "epoch": 1.0636079249217936, "percentage": 35.49, "elapsed_time": "8:18:59", "remaining_time": "15:06:59"}
53
+ {"current_steps": 520, "total_steps": 1437, "loss": 0.7646, "lr": 5e-06, "epoch": 1.0844629822732013, "percentage": 36.19, "elapsed_time": "8:28:34", "remaining_time": "14:56:50"}
54
+ {"current_steps": 530, "total_steps": 1437, "loss": 0.7623, "lr": 5e-06, "epoch": 1.105318039624609, "percentage": 36.88, "elapsed_time": "8:38:10", "remaining_time": "14:46:46"}
55
+ {"current_steps": 540, "total_steps": 1437, "loss": 0.7605, "lr": 5e-06, "epoch": 1.1261730969760166, "percentage": 37.58, "elapsed_time": "8:47:46", "remaining_time": "14:36:40"}
56
+ {"current_steps": 550, "total_steps": 1437, "loss": 0.7632, "lr": 5e-06, "epoch": 1.1470281543274243, "percentage": 38.27, "elapsed_time": "8:57:21", "remaining_time": "14:26:37"}
57
+ {"current_steps": 560, "total_steps": 1437, "loss": 0.7603, "lr": 5e-06, "epoch": 1.167883211678832, "percentage": 38.97, "elapsed_time": "9:06:57", "remaining_time": "14:16:35"}
58
+ {"current_steps": 570, "total_steps": 1437, "loss": 0.7608, "lr": 5e-06, "epoch": 1.1887382690302397, "percentage": 39.67, "elapsed_time": "9:16:34", "remaining_time": "14:06:35"}
59
+ {"current_steps": 580, "total_steps": 1437, "loss": 0.7638, "lr": 5e-06, "epoch": 1.2095933263816476, "percentage": 40.36, "elapsed_time": "9:26:11", "remaining_time": "13:56:35"}
60
+ {"current_steps": 590, "total_steps": 1437, "loss": 0.7674, "lr": 5e-06, "epoch": 1.2304483837330553, "percentage": 41.06, "elapsed_time": "9:35:47", "remaining_time": "13:46:35"}
61
+ {"current_steps": 600, "total_steps": 1437, "loss": 0.7649, "lr": 5e-06, "epoch": 1.251303441084463, "percentage": 41.75, "elapsed_time": "9:45:23", "remaining_time": "13:36:37"}
62
+ {"current_steps": 610, "total_steps": 1437, "loss": 0.7659, "lr": 5e-06, "epoch": 1.2721584984358707, "percentage": 42.45, "elapsed_time": "9:55:00", "remaining_time": "13:26:40"}
63
+ {"current_steps": 620, "total_steps": 1437, "loss": 0.7668, "lr": 5e-06, "epoch": 1.2930135557872784, "percentage": 43.15, "elapsed_time": "10:04:36", "remaining_time": "13:16:43"}
64
+ {"current_steps": 630, "total_steps": 1437, "loss": 0.7591, "lr": 5e-06, "epoch": 1.313868613138686, "percentage": 43.84, "elapsed_time": "10:14:12", "remaining_time": "13:06:46"}
65
+ {"current_steps": 640, "total_steps": 1437, "loss": 0.7637, "lr": 5e-06, "epoch": 1.3347236704900938, "percentage": 44.54, "elapsed_time": "10:23:49", "remaining_time": "12:56:51"}
66
+ {"current_steps": 650, "total_steps": 1437, "loss": 0.7621, "lr": 5e-06, "epoch": 1.3555787278415017, "percentage": 45.23, "elapsed_time": "10:33:25", "remaining_time": "12:46:55"}
67
+ {"current_steps": 660, "total_steps": 1437, "loss": 0.7616, "lr": 5e-06, "epoch": 1.3764337851929094, "percentage": 45.93, "elapsed_time": "10:43:02", "remaining_time": "12:37:01"}
68
+ {"current_steps": 670, "total_steps": 1437, "loss": 0.7679, "lr": 5e-06, "epoch": 1.397288842544317, "percentage": 46.62, "elapsed_time": "10:52:38", "remaining_time": "12:27:07"}
69
+ {"current_steps": 680, "total_steps": 1437, "loss": 0.7626, "lr": 5e-06, "epoch": 1.4181438998957248, "percentage": 47.32, "elapsed_time": "11:02:14", "remaining_time": "12:17:13"}
70
+ {"current_steps": 690, "total_steps": 1437, "loss": 0.7636, "lr": 5e-06, "epoch": 1.4389989572471324, "percentage": 48.02, "elapsed_time": "11:11:51", "remaining_time": "12:07:22"}
71
+ {"current_steps": 700, "total_steps": 1437, "loss": 0.7616, "lr": 5e-06, "epoch": 1.4598540145985401, "percentage": 48.71, "elapsed_time": "11:21:29", "remaining_time": "11:57:30"}
72
+ {"current_steps": 710, "total_steps": 1437, "loss": 0.7647, "lr": 5e-06, "epoch": 1.4807090719499478, "percentage": 49.41, "elapsed_time": "11:31:06", "remaining_time": "11:47:39"}
73
+ {"current_steps": 720, "total_steps": 1437, "loss": 0.7598, "lr": 5e-06, "epoch": 1.5015641293013555, "percentage": 50.1, "elapsed_time": "11:40:43", "remaining_time": "11:37:48"}
74
+ {"current_steps": 730, "total_steps": 1437, "loss": 0.7629, "lr": 5e-06, "epoch": 1.5224191866527632, "percentage": 50.8, "elapsed_time": "11:50:19", "remaining_time": "11:27:56"}
75
+ {"current_steps": 740, "total_steps": 1437, "loss": 0.7656, "lr": 5e-06, "epoch": 1.543274244004171, "percentage": 51.5, "elapsed_time": "11:59:55", "remaining_time": "11:18:05"}
76
+ {"current_steps": 750, "total_steps": 1437, "loss": 0.7634, "lr": 5e-06, "epoch": 1.5641293013555786, "percentage": 52.19, "elapsed_time": "12:09:31", "remaining_time": "11:08:14"}
77
+ {"current_steps": 760, "total_steps": 1437, "loss": 0.7624, "lr": 5e-06, "epoch": 1.5849843587069863, "percentage": 52.89, "elapsed_time": "12:19:08", "remaining_time": "10:58:24"}
78
+ {"current_steps": 770, "total_steps": 1437, "loss": 0.7601, "lr": 5e-06, "epoch": 1.6058394160583942, "percentage": 53.58, "elapsed_time": "12:28:44", "remaining_time": "10:48:35"}
79
+ {"current_steps": 780, "total_steps": 1437, "loss": 0.7598, "lr": 5e-06, "epoch": 1.6266944734098019, "percentage": 54.28, "elapsed_time": "12:38:21", "remaining_time": "10:38:46"}
80
+ {"current_steps": 790, "total_steps": 1437, "loss": 0.7582, "lr": 5e-06, "epoch": 1.6475495307612096, "percentage": 54.98, "elapsed_time": "12:47:57", "remaining_time": "10:28:56"}
81
+ {"current_steps": 800, "total_steps": 1437, "loss": 0.7621, "lr": 5e-06, "epoch": 1.6684045881126173, "percentage": 55.67, "elapsed_time": "12:57:33", "remaining_time": "10:19:08"}
82
+ {"current_steps": 810, "total_steps": 1437, "loss": 0.7624, "lr": 5e-06, "epoch": 1.6892596454640252, "percentage": 56.37, "elapsed_time": "13:07:09", "remaining_time": "10:09:19"}
83
+ {"current_steps": 820, "total_steps": 1437, "loss": 0.7621, "lr": 5e-06, "epoch": 1.7101147028154329, "percentage": 57.06, "elapsed_time": "13:16:45", "remaining_time": "9:59:30"}
84
+ {"current_steps": 830, "total_steps": 1437, "loss": 0.7615, "lr": 5e-06, "epoch": 1.7309697601668406, "percentage": 57.76, "elapsed_time": "13:26:21", "remaining_time": "9:49:42"}
85
+ {"current_steps": 840, "total_steps": 1437, "loss": 0.759, "lr": 5e-06, "epoch": 1.7518248175182483, "percentage": 58.46, "elapsed_time": "13:35:57", "remaining_time": "9:39:54"}
86
+ {"current_steps": 850, "total_steps": 1437, "loss": 0.7623, "lr": 5e-06, "epoch": 1.772679874869656, "percentage": 59.15, "elapsed_time": "13:45:32", "remaining_time": "9:30:06"}
87
+ {"current_steps": 860, "total_steps": 1437, "loss": 0.7561, "lr": 5e-06, "epoch": 1.7935349322210636, "percentage": 59.85, "elapsed_time": "13:55:08", "remaining_time": "9:20:19"}
88
+ {"current_steps": 870, "total_steps": 1437, "loss": 0.763, "lr": 5e-06, "epoch": 1.8143899895724713, "percentage": 60.54, "elapsed_time": "14:04:44", "remaining_time": "9:10:32"}
89
+ {"current_steps": 880, "total_steps": 1437, "loss": 0.7581, "lr": 5e-06, "epoch": 1.835245046923879, "percentage": 61.24, "elapsed_time": "14:14:21", "remaining_time": "9:00:46"}
90
+ {"current_steps": 890, "total_steps": 1437, "loss": 0.7639, "lr": 5e-06, "epoch": 1.8561001042752867, "percentage": 61.93, "elapsed_time": "14:23:59", "remaining_time": "8:51:00"}
91
+ {"current_steps": 900, "total_steps": 1437, "loss": 0.7588, "lr": 5e-06, "epoch": 1.8769551616266944, "percentage": 62.63, "elapsed_time": "14:33:35", "remaining_time": "8:41:14"}
92
+ {"current_steps": 910, "total_steps": 1437, "loss": 0.7676, "lr": 5e-06, "epoch": 1.897810218978102, "percentage": 63.33, "elapsed_time": "14:43:11", "remaining_time": "8:31:28"}
93
+ {"current_steps": 920, "total_steps": 1437, "loss": 0.7621, "lr": 5e-06, "epoch": 1.9186652763295098, "percentage": 64.02, "elapsed_time": "14:52:48", "remaining_time": "8:21:42"}
94
+ {"current_steps": 930, "total_steps": 1437, "loss": 0.7582, "lr": 5e-06, "epoch": 1.9395203336809175, "percentage": 64.72, "elapsed_time": "15:02:23", "remaining_time": "8:11:56"}
95
+ {"current_steps": 940, "total_steps": 1437, "loss": 0.7607, "lr": 5e-06, "epoch": 1.9603753910323254, "percentage": 65.41, "elapsed_time": "15:11:59", "remaining_time": "8:02:11"}
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"}