sedrickkeh commited on
Commit
d6af01d
·
verified ·
1 Parent(s): d091fe7

Training in progress, epoch 1

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7786e5bec8df762e4c15465ef4a56602c01f02728359353e9fa97fe576b4fe6
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e3923de6f483afaffac780be9b2b1cca0ab330d32953c358d841b33f82ea9bd
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9940d546ac4e6c9f603f04e234225fc1ad10106ecc9040ad9e1f9d76cff46de3
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:887c9d57b356b2c65e4a658b8f936e08ea2dee5761e4805790b03eb6eec30459
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:e57f7944d68b4d3a844768f6bca9802d5af057bbab00ddb5eeea5d26ceda4681
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d25dfd0215d1e7827445f25c34638554fdb753a7034fa7af7e0b237ac9c744e0
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84341b8ecd02f3cd9bb8c2307ae82ae61bea183f2d43dd60768f0b49915f00fe
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d8b3a4444c8ba0d6fee5cc1b179958a44270708435f8ad8f6bbd8bd9cf5d6eb
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -41,3 +41,47 @@
41
  {"current_steps": 410, "total_steps": 1275, "loss": 0.5957, "lr": 5e-06, "epoch": 0.962723803933079, "percentage": 32.16, "elapsed_time": "3:37:37", "remaining_time": "7:39:08"}
42
  {"current_steps": 420, "total_steps": 1275, "loss": 0.5979, "lr": 5e-06, "epoch": 0.9862048723216906, "percentage": 32.94, "elapsed_time": "3:42:54", "remaining_time": "7:33:47"}
43
  {"current_steps": 425, "total_steps": 1275, "eval_loss": 0.6003177165985107, "epoch": 0.9979454065159965, "percentage": 33.33, "elapsed_time": "3:50:58", "remaining_time": "7:41:56"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41
  {"current_steps": 410, "total_steps": 1275, "loss": 0.5957, "lr": 5e-06, "epoch": 0.962723803933079, "percentage": 32.16, "elapsed_time": "3:37:37", "remaining_time": "7:39:08"}
42
  {"current_steps": 420, "total_steps": 1275, "loss": 0.5979, "lr": 5e-06, "epoch": 0.9862048723216906, "percentage": 32.94, "elapsed_time": "3:42:54", "remaining_time": "7:33:47"}
43
  {"current_steps": 425, "total_steps": 1275, "eval_loss": 0.6003177165985107, "epoch": 0.9979454065159965, "percentage": 33.33, "elapsed_time": "3:50:58", "remaining_time": "7:41:56"}
44
+ {"current_steps": 430, "total_steps": 1275, "loss": 0.6046, "lr": 5e-06, "epoch": 1.0099794540651599, "percentage": 33.73, "elapsed_time": "3:54:29", "remaining_time": "7:40:48"}
45
+ {"current_steps": 440, "total_steps": 1275, "loss": 0.5525, "lr": 5e-06, "epoch": 1.0334605224537716, "percentage": 34.51, "elapsed_time": "3:59:49", "remaining_time": "7:35:06"}
46
+ {"current_steps": 450, "total_steps": 1275, "loss": 0.5507, "lr": 5e-06, "epoch": 1.0569415908423834, "percentage": 35.29, "elapsed_time": "4:05:08", "remaining_time": "7:29:25"}
47
+ {"current_steps": 460, "total_steps": 1275, "loss": 0.5488, "lr": 5e-06, "epoch": 1.0804226592309951, "percentage": 36.08, "elapsed_time": "4:10:27", "remaining_time": "7:23:45"}
48
+ {"current_steps": 470, "total_steps": 1275, "loss": 0.5553, "lr": 5e-06, "epoch": 1.1039037276196066, "percentage": 36.86, "elapsed_time": "4:15:46", "remaining_time": "7:18:04"}
49
+ {"current_steps": 480, "total_steps": 1275, "loss": 0.5517, "lr": 5e-06, "epoch": 1.1273847960082184, "percentage": 37.65, "elapsed_time": "4:21:04", "remaining_time": "7:12:24"}
50
+ {"current_steps": 490, "total_steps": 1275, "loss": 0.5513, "lr": 5e-06, "epoch": 1.1508658643968301, "percentage": 38.43, "elapsed_time": "4:26:21", "remaining_time": "7:06:43"}
51
+ {"current_steps": 500, "total_steps": 1275, "loss": 0.5565, "lr": 5e-06, "epoch": 1.1743469327854417, "percentage": 39.22, "elapsed_time": "4:31:38", "remaining_time": "7:01:02"}
52
+ {"current_steps": 510, "total_steps": 1275, "loss": 0.5508, "lr": 5e-06, "epoch": 1.1978280011740534, "percentage": 40.0, "elapsed_time": "4:36:56", "remaining_time": "6:55:24"}
53
+ {"current_steps": 520, "total_steps": 1275, "loss": 0.5513, "lr": 5e-06, "epoch": 1.2213090695626652, "percentage": 40.78, "elapsed_time": "4:42:11", "remaining_time": "6:49:43"}
54
+ {"current_steps": 530, "total_steps": 1275, "loss": 0.5538, "lr": 5e-06, "epoch": 1.2447901379512767, "percentage": 41.57, "elapsed_time": "4:47:29", "remaining_time": "6:44:06"}
55
+ {"current_steps": 540, "total_steps": 1275, "loss": 0.5442, "lr": 5e-06, "epoch": 1.2682712063398884, "percentage": 42.35, "elapsed_time": "4:52:47", "remaining_time": "6:38:31"}
56
+ {"current_steps": 550, "total_steps": 1275, "loss": 0.5566, "lr": 5e-06, "epoch": 1.2917522747285002, "percentage": 43.14, "elapsed_time": "4:58:05", "remaining_time": "6:32:56"}
57
+ {"current_steps": 560, "total_steps": 1275, "loss": 0.5494, "lr": 5e-06, "epoch": 1.3152333431171117, "percentage": 43.92, "elapsed_time": "5:03:20", "remaining_time": "6:27:17"}
58
+ {"current_steps": 570, "total_steps": 1275, "loss": 0.5471, "lr": 5e-06, "epoch": 1.3387144115057235, "percentage": 44.71, "elapsed_time": "5:08:38", "remaining_time": "6:21:44"}
59
+ {"current_steps": 580, "total_steps": 1275, "loss": 0.552, "lr": 5e-06, "epoch": 1.3621954798943352, "percentage": 45.49, "elapsed_time": "5:13:56", "remaining_time": "6:16:11"}
60
+ {"current_steps": 590, "total_steps": 1275, "loss": 0.5505, "lr": 5e-06, "epoch": 1.385676548282947, "percentage": 46.27, "elapsed_time": "5:19:14", "remaining_time": "6:10:38"}
61
+ {"current_steps": 600, "total_steps": 1275, "loss": 0.5498, "lr": 5e-06, "epoch": 1.4091576166715585, "percentage": 47.06, "elapsed_time": "5:24:31", "remaining_time": "6:05:05"}
62
+ {"current_steps": 610, "total_steps": 1275, "loss": 0.5562, "lr": 5e-06, "epoch": 1.4326386850601702, "percentage": 47.84, "elapsed_time": "5:29:49", "remaining_time": "5:59:33"}
63
+ {"current_steps": 620, "total_steps": 1275, "loss": 0.5555, "lr": 5e-06, "epoch": 1.456119753448782, "percentage": 48.63, "elapsed_time": "5:35:07", "remaining_time": "5:54:02"}
64
+ {"current_steps": 630, "total_steps": 1275, "loss": 0.544, "lr": 5e-06, "epoch": 1.4796008218373937, "percentage": 49.41, "elapsed_time": "5:40:26", "remaining_time": "5:48:32"}
65
+ {"current_steps": 640, "total_steps": 1275, "loss": 0.5451, "lr": 5e-06, "epoch": 1.5030818902260052, "percentage": 50.2, "elapsed_time": "5:45:44", "remaining_time": "5:43:02"}
66
+ {"current_steps": 650, "total_steps": 1275, "loss": 0.5587, "lr": 5e-06, "epoch": 1.526562958614617, "percentage": 50.98, "elapsed_time": "5:51:02", "remaining_time": "5:37:32"}
67
+ {"current_steps": 660, "total_steps": 1275, "loss": 0.5518, "lr": 5e-06, "epoch": 1.5500440270032287, "percentage": 51.76, "elapsed_time": "5:56:21", "remaining_time": "5:32:03"}
68
+ {"current_steps": 670, "total_steps": 1275, "loss": 0.5526, "lr": 5e-06, "epoch": 1.5735250953918403, "percentage": 52.55, "elapsed_time": "6:01:40", "remaining_time": "5:26:35"}
69
+ {"current_steps": 680, "total_steps": 1275, "loss": 0.5478, "lr": 5e-06, "epoch": 1.597006163780452, "percentage": 53.33, "elapsed_time": "6:07:00", "remaining_time": "5:21:07"}
70
+ {"current_steps": 690, "total_steps": 1275, "loss": 0.5481, "lr": 5e-06, "epoch": 1.6204872321690638, "percentage": 54.12, "elapsed_time": "6:12:19", "remaining_time": "5:15:39"}
71
+ {"current_steps": 700, "total_steps": 1275, "loss": 0.5515, "lr": 5e-06, "epoch": 1.6439683005576753, "percentage": 54.9, "elapsed_time": "6:17:37", "remaining_time": "5:10:11"}
72
+ {"current_steps": 710, "total_steps": 1275, "loss": 0.5505, "lr": 5e-06, "epoch": 1.667449368946287, "percentage": 55.69, "elapsed_time": "6:22:55", "remaining_time": "5:04:43"}
73
+ {"current_steps": 720, "total_steps": 1275, "loss": 0.5496, "lr": 5e-06, "epoch": 1.6909304373348988, "percentage": 56.47, "elapsed_time": "6:28:14", "remaining_time": "4:59:15"}
74
+ {"current_steps": 730, "total_steps": 1275, "loss": 0.5484, "lr": 5e-06, "epoch": 1.7144115057235103, "percentage": 57.25, "elapsed_time": "6:33:33", "remaining_time": "4:53:48"}
75
+ {"current_steps": 740, "total_steps": 1275, "loss": 0.5483, "lr": 5e-06, "epoch": 1.737892574112122, "percentage": 58.04, "elapsed_time": "6:38:51", "remaining_time": "4:48:21"}
76
+ {"current_steps": 750, "total_steps": 1275, "loss": 0.5531, "lr": 5e-06, "epoch": 1.7613736425007338, "percentage": 58.82, "elapsed_time": "6:44:09", "remaining_time": "4:42:54"}
77
+ {"current_steps": 760, "total_steps": 1275, "loss": 0.5487, "lr": 5e-06, "epoch": 1.7848547108893453, "percentage": 59.61, "elapsed_time": "6:49:26", "remaining_time": "4:37:26"}
78
+ {"current_steps": 770, "total_steps": 1275, "loss": 0.5485, "lr": 5e-06, "epoch": 1.8083357792779573, "percentage": 60.39, "elapsed_time": "6:54:44", "remaining_time": "4:32:00"}
79
+ {"current_steps": 780, "total_steps": 1275, "loss": 0.5518, "lr": 5e-06, "epoch": 1.8318168476665688, "percentage": 61.18, "elapsed_time": "7:00:03", "remaining_time": "4:26:34"}
80
+ {"current_steps": 790, "total_steps": 1275, "loss": 0.5467, "lr": 5e-06, "epoch": 1.8552979160551804, "percentage": 61.96, "elapsed_time": "7:05:20", "remaining_time": "4:21:07"}
81
+ {"current_steps": 800, "total_steps": 1275, "loss": 0.5468, "lr": 5e-06, "epoch": 1.8787789844437923, "percentage": 62.75, "elapsed_time": "7:10:38", "remaining_time": "4:15:41"}
82
+ {"current_steps": 810, "total_steps": 1275, "loss": 0.5488, "lr": 5e-06, "epoch": 1.9022600528324038, "percentage": 63.53, "elapsed_time": "7:15:55", "remaining_time": "4:10:15"}
83
+ {"current_steps": 820, "total_steps": 1275, "loss": 0.5458, "lr": 5e-06, "epoch": 1.9257411212210156, "percentage": 64.31, "elapsed_time": "7:21:13", "remaining_time": "4:04:49"}
84
+ {"current_steps": 830, "total_steps": 1275, "loss": 0.5447, "lr": 5e-06, "epoch": 1.9492221896096273, "percentage": 65.1, "elapsed_time": "7:26:28", "remaining_time": "3:59:22"}
85
+ {"current_steps": 840, "total_steps": 1275, "loss": 0.5398, "lr": 5e-06, "epoch": 1.9727032579982389, "percentage": 65.88, "elapsed_time": "7:31:45", "remaining_time": "3:53:56"}
86
+ {"current_steps": 850, "total_steps": 1275, "loss": 0.547, "lr": 5e-06, "epoch": 1.9961843263868506, "percentage": 66.67, "elapsed_time": "7:37:03", "remaining_time": "3:48:31"}
87
+ {"current_steps": 851, "total_steps": 1275, "eval_loss": 0.5846751928329468, "epoch": 1.9985324332257117, "percentage": 66.75, "elapsed_time": "7:42:41", "remaining_time": "3:50:31"}