ahmedheakl commited on
Commit
7a67841
·
verified ·
1 Parent(s): 51b00d3

Training in progress, step 3500

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eac7d4684539d4de7f0ba5e3718aea87d753d7bafc12ebbf20744247582eb595
3
  size 4968243304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9294ad5415fa197f6dcbeb08a84c1862c317a755f2e5fb279db9ed40548b531
3
  size 4968243304
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83a2c2a4249d28ff583187476e71f5d834b7ab30713f394adfdb8bbcec75a143
3
  size 4991495816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77cd03fafc2290435f805695599b5faaf30790811f9fb358280add485be6124f
3
  size 4991495816
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6c0dec75ba811ec9363d24a2bb779b5cd58539443a0025bdf4c58f21ea8ca96
3
  size 4932751040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:008d81fefbedc3549aacc02545f962e586dc4f8ba3aefc0ac7db9de9338588d6
3
  size 4932751040
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f5136383581c715398ae05a1473c435634a9141735c2b6b69f98027fe05e850
3
  size 1691924384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62f11161ef3458f4bc4ef4e0b151e1984883268506550a8b3f94c383cd313a33
3
  size 1691924384
trainer_log.jsonl CHANGED
@@ -42,3 +42,57 @@
42
  {"current_steps": 210, "total_steps": 7042, "loss": 0.5941, "lr": 5.957446808510638e-06, "epoch": 0.05964214711729622, "percentage": 2.98, "elapsed_time": "0:38:00", "remaining_time": "20:36:16"}
43
  {"current_steps": 3010, "total_steps": 7042, "loss": 0.3689, "lr": 1.4151280218381287e-05, "epoch": 0.8548707753479126, "percentage": 42.74, "elapsed_time": "9:10:36", "remaining_time": "12:17:34"}
44
  {"current_steps": 220, "total_steps": 7042, "loss": 0.5608, "lr": 6.24113475177305e-06, "epoch": 0.062482249360976995, "percentage": 3.12, "elapsed_time": "0:39:48", "remaining_time": "20:34:27"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  {"current_steps": 210, "total_steps": 7042, "loss": 0.5941, "lr": 5.957446808510638e-06, "epoch": 0.05964214711729622, "percentage": 2.98, "elapsed_time": "0:38:00", "remaining_time": "20:36:16"}
43
  {"current_steps": 3010, "total_steps": 7042, "loss": 0.3689, "lr": 1.4151280218381287e-05, "epoch": 0.8548707753479126, "percentage": 42.74, "elapsed_time": "9:10:36", "remaining_time": "12:17:34"}
44
  {"current_steps": 220, "total_steps": 7042, "loss": 0.5608, "lr": 6.24113475177305e-06, "epoch": 0.062482249360976995, "percentage": 3.12, "elapsed_time": "0:39:48", "remaining_time": "20:34:27"}
45
+ {"current_steps": 3020, "total_steps": 7042, "loss": 0.3761, "lr": 1.4106127531314261e-05, "epoch": 0.8577108775915933, "percentage": 42.89, "elapsed_time": "9:12:22", "remaining_time": "12:15:39"}
46
+ {"current_steps": 230, "total_steps": 7042, "loss": 0.5471, "lr": 6.524822695035462e-06, "epoch": 0.06532235160465777, "percentage": 3.27, "elapsed_time": "0:41:34", "remaining_time": "20:31:11"}
47
+ {"current_steps": 3030, "total_steps": 7042, "loss": 0.3772, "lr": 1.4060873927353203e-05, "epoch": 0.8605509798352741, "percentage": 43.03, "elapsed_time": "9:14:10", "remaining_time": "12:13:47"}
48
+ {"current_steps": 240, "total_steps": 7042, "loss": 0.5154, "lr": 6.808510638297873e-06, "epoch": 0.06816245384833854, "percentage": 3.41, "elapsed_time": "0:43:22", "remaining_time": "20:29:14"}
49
+ {"current_steps": 3040, "total_steps": 7042, "loss": 0.3742, "lr": 1.4015520518702526e-05, "epoch": 0.8633910820789549, "percentage": 43.17, "elapsed_time": "9:15:58", "remaining_time": "12:11:55"}
50
+ {"current_steps": 250, "total_steps": 7042, "loss": 0.5133, "lr": 7.092198581560285e-06, "epoch": 0.07100255609201932, "percentage": 3.55, "elapsed_time": "0:45:10", "remaining_time": "20:27:08"}
51
+ {"current_steps": 3050, "total_steps": 7042, "loss": 0.373, "lr": 1.3970068420019552e-05, "epoch": 0.8662311843226356, "percentage": 43.31, "elapsed_time": "9:17:45", "remaining_time": "12:10:01"}
52
+ {"current_steps": 260, "total_steps": 7042, "loss": 0.5024, "lr": 7.375886524822695e-06, "epoch": 0.07384265833570008, "percentage": 3.69, "elapsed_time": "0:46:58", "remaining_time": "20:25:11"}
53
+ {"current_steps": 3060, "total_steps": 7042, "loss": 0.3762, "lr": 1.392451874838713e-05, "epoch": 0.8690712865663164, "percentage": 43.45, "elapsed_time": "9:19:35", "remaining_time": "12:08:11"}
54
+ {"current_steps": 3070, "total_steps": 7042, "loss": 0.3647, "lr": 1.3878872623286169e-05, "epoch": 0.8719113888099972, "percentage": 43.6, "elapsed_time": "9:21:22", "remaining_time": "12:06:18"}
55
+ {"current_steps": 3080, "total_steps": 7042, "loss": 0.3738, "lr": 1.3833131166568132e-05, "epoch": 0.8747514910536779, "percentage": 43.74, "elapsed_time": "9:23:09", "remaining_time": "12:04:25"}
56
+ {"current_steps": 3090, "total_steps": 7042, "loss": 0.3715, "lr": 1.3787295502427456e-05, "epoch": 0.8775915932973587, "percentage": 43.88, "elapsed_time": "9:24:59", "remaining_time": "12:02:35"}
57
+ {"current_steps": 3100, "total_steps": 7042, "loss": 0.3641, "lr": 1.3741366757373928e-05, "epoch": 0.8804316955410395, "percentage": 44.02, "elapsed_time": "9:26:47", "remaining_time": "12:00:44"}
58
+ {"current_steps": 3110, "total_steps": 7042, "loss": 0.3759, "lr": 1.369534606020501e-05, "epoch": 0.8832717977847202, "percentage": 44.16, "elapsed_time": "9:28:36", "remaining_time": "11:58:53"}
59
+ {"current_steps": 3120, "total_steps": 7042, "loss": 0.3771, "lr": 1.364923454197807e-05, "epoch": 0.886111900028401, "percentage": 44.31, "elapsed_time": "9:30:26", "remaining_time": "11:57:04"}
60
+ {"current_steps": 3130, "total_steps": 7042, "loss": 0.3818, "lr": 1.36030333359826e-05, "epoch": 0.8889520022720818, "percentage": 44.45, "elapsed_time": "9:32:15", "remaining_time": "11:55:13"}
61
+ {"current_steps": 3140, "total_steps": 7042, "loss": 0.3813, "lr": 1.3556743577712363e-05, "epoch": 0.8917921045157625, "percentage": 44.59, "elapsed_time": "9:34:06", "remaining_time": "11:53:25"}
62
+ {"current_steps": 3150, "total_steps": 7042, "loss": 0.3783, "lr": 1.3510366404837499e-05, "epoch": 0.8946322067594433, "percentage": 44.73, "elapsed_time": "9:35:55", "remaining_time": "11:51:34"}
63
+ {"current_steps": 3160, "total_steps": 7042, "loss": 0.3688, "lr": 1.3463902957176526e-05, "epoch": 0.8974723090031241, "percentage": 44.87, "elapsed_time": "9:37:46", "remaining_time": "11:49:46"}
64
+ {"current_steps": 3170, "total_steps": 7042, "loss": 0.3799, "lr": 1.341735437666836e-05, "epoch": 0.9003124112468048, "percentage": 45.02, "elapsed_time": "9:39:33", "remaining_time": "11:47:54"}
65
+ {"current_steps": 3180, "total_steps": 7042, "loss": 0.3666, "lr": 1.337072180734425e-05, "epoch": 0.9031525134904856, "percentage": 45.16, "elapsed_time": "9:41:20", "remaining_time": "11:46:01"}
66
+ {"current_steps": 3190, "total_steps": 7042, "loss": 0.3767, "lr": 1.3324006395299624e-05, "epoch": 0.9059926157341665, "percentage": 45.3, "elapsed_time": "9:43:08", "remaining_time": "11:44:09"}
67
+ {"current_steps": 3200, "total_steps": 7042, "loss": 0.3701, "lr": 1.3277209288665977e-05, "epoch": 0.9088327179778471, "percentage": 45.44, "elapsed_time": "9:44:55", "remaining_time": "11:42:16"}
68
+ {"current_steps": 3210, "total_steps": 7042, "loss": 0.3789, "lr": 1.3230331637582605e-05, "epoch": 0.911672820221528, "percentage": 45.58, "elapsed_time": "9:46:43", "remaining_time": "11:40:25"}
69
+ {"current_steps": 3220, "total_steps": 7042, "loss": 0.3753, "lr": 1.3183374594168368e-05, "epoch": 0.9145129224652088, "percentage": 45.73, "elapsed_time": "9:48:31", "remaining_time": "11:38:33"}
70
+ {"current_steps": 3230, "total_steps": 7042, "loss": 0.3719, "lr": 1.3136339312493346e-05, "epoch": 0.9173530247088896, "percentage": 45.87, "elapsed_time": "9:50:18", "remaining_time": "11:36:40"}
71
+ {"current_steps": 3240, "total_steps": 7042, "loss": 0.3641, "lr": 1.3089226948550513e-05, "epoch": 0.9201931269525703, "percentage": 46.01, "elapsed_time": "9:52:07", "remaining_time": "11:34:50"}
72
+ {"current_steps": 3250, "total_steps": 7042, "loss": 0.3628, "lr": 1.3042038660227294e-05, "epoch": 0.9230332291962511, "percentage": 46.15, "elapsed_time": "9:53:54", "remaining_time": "11:32:56"}
73
+ {"current_steps": 3260, "total_steps": 7042, "loss": 0.3796, "lr": 1.2994775607277117e-05, "epoch": 0.9258733314399319, "percentage": 46.29, "elapsed_time": "9:55:45", "remaining_time": "11:31:08"}
74
+ {"current_steps": 3270, "total_steps": 7042, "loss": 0.3707, "lr": 1.2947438951290914e-05, "epoch": 0.9287134336836126, "percentage": 46.44, "elapsed_time": "9:57:33", "remaining_time": "11:29:17"}
75
+ {"current_steps": 3280, "total_steps": 7042, "loss": 0.3723, "lr": 1.290002985566857e-05, "epoch": 0.9315535359272934, "percentage": 46.58, "elapsed_time": "9:59:22", "remaining_time": "11:27:27"}
76
+ {"current_steps": 3290, "total_steps": 7042, "loss": 0.3692, "lr": 1.2852549485590333e-05, "epoch": 0.9343936381709742, "percentage": 46.72, "elapsed_time": "10:01:09", "remaining_time": "11:25:34"}
77
+ {"current_steps": 3300, "total_steps": 7042, "loss": 0.3794, "lr": 1.2804999007988164e-05, "epoch": 0.9372337404146549, "percentage": 46.86, "elapsed_time": "10:03:00", "remaining_time": "11:23:46"}
78
+ {"current_steps": 3310, "total_steps": 7042, "loss": 0.3703, "lr": 1.2757379591517078e-05, "epoch": 0.9400738426583357, "percentage": 47.0, "elapsed_time": "10:04:47", "remaining_time": "11:21:53"}
79
+ {"current_steps": 3320, "total_steps": 7042, "loss": 0.3755, "lr": 1.2709692406526402e-05, "epoch": 0.9429139449020165, "percentage": 47.15, "elapsed_time": "10:06:36", "remaining_time": "11:20:03"}
80
+ {"current_steps": 3330, "total_steps": 7042, "loss": 0.3712, "lr": 1.2661938625031023e-05, "epoch": 0.9457540471456972, "percentage": 47.29, "elapsed_time": "10:08:24", "remaining_time": "11:18:12"}
81
+ {"current_steps": 3340, "total_steps": 7042, "loss": 0.3678, "lr": 1.2614119420682578e-05, "epoch": 0.948594149389378, "percentage": 47.43, "elapsed_time": "10:10:13", "remaining_time": "11:16:22"}
82
+ {"current_steps": 3350, "total_steps": 7042, "loss": 0.3869, "lr": 1.2566235968740617e-05, "epoch": 0.9514342516330588, "percentage": 47.57, "elapsed_time": "10:12:02", "remaining_time": "11:14:31"}
83
+ {"current_steps": 3360, "total_steps": 7042, "loss": 0.3688, "lr": 1.2518289446043708e-05, "epoch": 0.9542743538767395, "percentage": 47.71, "elapsed_time": "10:13:51", "remaining_time": "11:12:40"}
84
+ {"current_steps": 3370, "total_steps": 7042, "loss": 0.3697, "lr": 1.2470281030980514e-05, "epoch": 0.9571144561204203, "percentage": 47.86, "elapsed_time": "10:15:43", "remaining_time": "11:10:54"}
85
+ {"current_steps": 3380, "total_steps": 7042, "loss": 0.3715, "lr": 1.2422211903460845e-05, "epoch": 0.9599545583641012, "percentage": 48.0, "elapsed_time": "10:17:35", "remaining_time": "11:09:07"}
86
+ {"current_steps": 3390, "total_steps": 7042, "loss": 0.364, "lr": 1.2374083244886643e-05, "epoch": 0.9627946606077818, "percentage": 48.14, "elapsed_time": "10:19:21", "remaining_time": "11:07:13"}
87
+ {"current_steps": 3400, "total_steps": 7042, "loss": 0.3676, "lr": 1.2325896238122958e-05, "epoch": 0.9656347628514627, "percentage": 48.28, "elapsed_time": "10:21:09", "remaining_time": "11:05:21"}
88
+ {"current_steps": 3410, "total_steps": 7042, "loss": 0.3773, "lr": 1.2277652067468864e-05, "epoch": 0.9684748650951435, "percentage": 48.42, "elapsed_time": "10:22:58", "remaining_time": "11:03:31"}
89
+ {"current_steps": 3420, "total_steps": 7042, "loss": 0.3653, "lr": 1.222935191862837e-05, "epoch": 0.9713149673388242, "percentage": 48.57, "elapsed_time": "10:24:45", "remaining_time": "11:01:39"}
90
+ {"current_steps": 3430, "total_steps": 7042, "loss": 0.3684, "lr": 1.2180996978681262e-05, "epoch": 0.974155069582505, "percentage": 48.71, "elapsed_time": "10:26:35", "remaining_time": "10:59:50"}
91
+ {"current_steps": 3440, "total_steps": 7042, "loss": 0.3708, "lr": 1.2132588436053942e-05, "epoch": 0.9769951718261858, "percentage": 48.85, "elapsed_time": "10:28:23", "remaining_time": "10:57:59"}
92
+ {"current_steps": 3450, "total_steps": 7042, "loss": 0.3643, "lr": 1.2084127480490206e-05, "epoch": 0.9798352740698665, "percentage": 48.99, "elapsed_time": "10:30:12", "remaining_time": "10:56:08"}
93
+ {"current_steps": 3460, "total_steps": 7042, "loss": 0.3671, "lr": 1.203561530302201e-05, "epoch": 0.9826753763135473, "percentage": 49.13, "elapsed_time": "10:32:01", "remaining_time": "10:54:18"}
94
+ {"current_steps": 3470, "total_steps": 7042, "loss": 0.3622, "lr": 1.1987053095940204e-05, "epoch": 0.9855154785572281, "percentage": 49.28, "elapsed_time": "10:33:49", "remaining_time": "10:52:27"}
95
+ {"current_steps": 3480, "total_steps": 7042, "loss": 0.377, "lr": 1.1938442052765225e-05, "epoch": 0.9883555808009088, "percentage": 49.42, "elapsed_time": "10:35:40", "remaining_time": "10:50:39"}
96
+ {"current_steps": 3490, "total_steps": 7042, "loss": 0.3669, "lr": 1.188978336821775e-05, "epoch": 0.9911956830445896, "percentage": 49.56, "elapsed_time": "10:37:27", "remaining_time": "10:48:47"}
97
+ {"current_steps": 3500, "total_steps": 7042, "loss": 0.3713, "lr": 1.1841078238189352e-05, "epoch": 0.9940357852882704, "percentage": 49.7, "elapsed_time": "10:39:15", "remaining_time": "10:46:55"}
98
+ {"current_steps": 3510, "total_steps": 7042, "loss": 0.3677, "lr": 1.1792327859713104e-05, "epoch": 0.9968758875319511, "percentage": 49.84, "elapsed_time": "10:42:08", "remaining_time": "10:46:09"}