izzcw commited on
Commit
3428551
·
verified ·
1 Parent(s): a16bd3a

Training in progress, step 1000

Browse files
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf36876619df7f10b1c94bc812485854d01338d1ea140054a746ebdb5ff071ad
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6895ee2397c529816a80838a230a9be02cac54712a15e58b40e0c01e8d8583c2
3
  size 83945296
runs/Apr30_19-57-14_8db08970-be1a-4a1c-b5b3-fa94198db698-0/events.out.tfevents.1746043104.8db08970-be1a-4a1c-b5b3-fa94198db698-0.45473.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bfbfb213f23fe99e8c4e90b5df4f01e63854d8a3313676f2b04f500fc5919fc
3
- size 39774
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0601cc0baeba98cad892e929cee8f0183975204c46bb0d27a5815abd7a71e1d
3
+ size 74174
trainer_log.jsonl CHANGED
@@ -48,3 +48,53 @@
48
  {"current_steps": 480, "total_steps": 1500, "loss": 0.027, "accuracy": 0.9625000357627869, "lr": 4.2983495008466285e-06, "epoch": 3.179401993355482, "percentage": 32.0, "elapsed_time": "2:12:31", "remaining_time": "4:41:36"}
49
  {"current_steps": 490, "total_steps": 1500, "loss": 0.0344, "accuracy": 0.953125, "lr": 4.257452643564155e-06, "epoch": 3.2458471760797343, "percentage": 32.67, "elapsed_time": "2:15:15", "remaining_time": "4:38:47"}
50
  {"current_steps": 500, "total_steps": 1500, "loss": 0.0265, "accuracy": 0.9625000357627869, "lr": 4.215604094671835e-06, "epoch": 3.3122923588039868, "percentage": 33.33, "elapsed_time": "2:18:03", "remaining_time": "4:36:07"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  {"current_steps": 480, "total_steps": 1500, "loss": 0.027, "accuracy": 0.9625000357627869, "lr": 4.2983495008466285e-06, "epoch": 3.179401993355482, "percentage": 32.0, "elapsed_time": "2:12:31", "remaining_time": "4:41:36"}
49
  {"current_steps": 490, "total_steps": 1500, "loss": 0.0344, "accuracy": 0.953125, "lr": 4.257452643564155e-06, "epoch": 3.2458471760797343, "percentage": 32.67, "elapsed_time": "2:15:15", "remaining_time": "4:38:47"}
50
  {"current_steps": 500, "total_steps": 1500, "loss": 0.0265, "accuracy": 0.9625000357627869, "lr": 4.215604094671835e-06, "epoch": 3.3122923588039868, "percentage": 33.33, "elapsed_time": "2:18:03", "remaining_time": "4:36:07"}
51
+ {"current_steps": 510, "total_steps": 1500, "loss": 0.0232, "accuracy": 0.9671874642372131, "lr": 4.172826515897146e-06, "epoch": 3.3787375415282392, "percentage": 34.0, "elapsed_time": "2:20:51", "remaining_time": "4:33:25"}
52
+ {"current_steps": 520, "total_steps": 1500, "loss": 0.0222, "accuracy": 0.96875, "lr": 4.129143072053639e-06, "epoch": 3.4451827242524917, "percentage": 34.67, "elapsed_time": "2:23:38", "remaining_time": "4:30:42"}
53
+ {"current_steps": 530, "total_steps": 1500, "loss": 0.0287, "accuracy": 0.9593750238418579, "lr": 4.084577418496775e-06, "epoch": 3.511627906976744, "percentage": 35.33, "elapsed_time": "2:26:27", "remaining_time": "4:28:03"}
54
+ {"current_steps": 540, "total_steps": 1500, "loss": 0.0328, "accuracy": 0.953125, "lr": 4.039153688314146e-06, "epoch": 3.5780730897009967, "percentage": 36.0, "elapsed_time": "2:29:15", "remaining_time": "4:25:20"}
55
+ {"current_steps": 550, "total_steps": 1500, "loss": 0.0361, "accuracy": 0.9484374523162842, "lr": 3.992896479256966e-06, "epoch": 3.644518272425249, "percentage": 36.67, "elapsed_time": "2:31:58", "remaining_time": "4:22:30"}
56
+ {"current_steps": 560, "total_steps": 1500, "loss": 0.0263, "accuracy": 0.9625000357627869, "lr": 3.945830840419966e-06, "epoch": 3.7109634551495017, "percentage": 37.33, "elapsed_time": "2:34:47", "remaining_time": "4:19:49"}
57
+ {"current_steps": 570, "total_steps": 1500, "loss": 0.0383, "accuracy": 0.9453125, "lr": 3.897982258676867e-06, "epoch": 3.777408637873754, "percentage": 38.0, "elapsed_time": "2:37:31", "remaining_time": "4:17:01"}
58
+ {"current_steps": 580, "total_steps": 1500, "loss": 0.0279, "accuracy": 0.9609374403953552, "lr": 3.849376644878783e-06, "epoch": 3.8438538205980066, "percentage": 38.67, "elapsed_time": "2:40:19", "remaining_time": "4:14:19"}
59
+ {"current_steps": 590, "total_steps": 1500, "loss": 0.0223, "accuracy": 0.9703125357627869, "lr": 3.8000403198230385e-06, "epoch": 3.910299003322259, "percentage": 39.33, "elapsed_time": "2:43:06", "remaining_time": "4:11:34"}
60
+ {"current_steps": 600, "total_steps": 1500, "loss": 0.0359, "accuracy": 0.949999988079071, "lr": 3.7500000000000005e-06, "epoch": 3.9767441860465116, "percentage": 40.0, "elapsed_time": "2:45:52", "remaining_time": "4:08:48"}
61
+ {"current_steps": 610, "total_steps": 1500, "loss": 0.0344, "accuracy": 0.9490132331848145, "lr": 3.699282783125616e-06, "epoch": 4.039867109634551, "percentage": 40.67, "elapsed_time": "2:48:31", "remaining_time": "4:05:53"}
62
+ {"current_steps": 620, "total_steps": 1500, "loss": 0.02, "accuracy": 0.971875011920929, "lr": 3.6479161334675294e-06, "epoch": 4.106312292358804, "percentage": 41.33, "elapsed_time": "2:51:14", "remaining_time": "4:03:02"}
63
+ {"current_steps": 630, "total_steps": 1500, "loss": 0.0253, "accuracy": 0.964062511920929, "lr": 3.595927866972694e-06, "epoch": 4.172757475083056, "percentage": 42.0, "elapsed_time": "2:53:59", "remaining_time": "4:00:16"}
64
+ {"current_steps": 640, "total_steps": 1500, "loss": 0.0339, "accuracy": 0.9515625238418579, "lr": 3.543346136204545e-06, "epoch": 4.239202657807309, "percentage": 42.67, "elapsed_time": "2:56:45", "remaining_time": "3:57:31"}
65
+ {"current_steps": 650, "total_steps": 1500, "loss": 0.0264, "accuracy": 0.9624999761581421, "lr": 3.4901994150978926e-06, "epoch": 4.305647840531561, "percentage": 43.33, "elapsed_time": "2:59:32", "remaining_time": "3:54:47"}
66
+ {"current_steps": 660, "total_steps": 1500, "loss": 0.0416, "accuracy": 0.940625011920929, "lr": 3.436516483539781e-06, "epoch": 4.372093023255814, "percentage": 44.0, "elapsed_time": "3:02:14", "remaining_time": "3:51:56"}
67
+ {"current_steps": 670, "total_steps": 1500, "loss": 0.0243, "accuracy": 0.965624988079071, "lr": 3.3823264117846722e-06, "epoch": 4.438538205980066, "percentage": 44.67, "elapsed_time": "3:04:59", "remaining_time": "3:49:10"}
68
+ {"current_steps": 680, "total_steps": 1500, "loss": 0.0232, "accuracy": 0.9671875238418579, "lr": 3.3276585447123957e-06, "epoch": 4.504983388704319, "percentage": 45.33, "elapsed_time": "3:07:44", "remaining_time": "3:46:23"}
69
+ {"current_steps": 690, "total_steps": 1500, "loss": 0.0295, "accuracy": 0.9578125476837158, "lr": 3.272542485937369e-06, "epoch": 4.571428571428571, "percentage": 46.0, "elapsed_time": "3:10:28", "remaining_time": "3:43:35"}
70
+ {"current_steps": 700, "total_steps": 1500, "loss": 0.0346, "accuracy": 0.9515625238418579, "lr": 3.217008081777726e-06, "epoch": 4.637873754152824, "percentage": 46.67, "elapsed_time": "3:13:11", "remaining_time": "3:40:47"}
71
+ {"current_steps": 710, "total_steps": 1500, "loss": 0.0294, "accuracy": 0.957812488079071, "lr": 3.1610854050930063e-06, "epoch": 4.704318936877076, "percentage": 47.33, "elapsed_time": "3:15:58", "remaining_time": "3:38:02"}
72
+ {"current_steps": 720, "total_steps": 1500, "loss": 0.0328, "accuracy": 0.9546875357627869, "lr": 3.1048047389991693e-06, "epoch": 4.770764119601329, "percentage": 48.0, "elapsed_time": "3:18:42", "remaining_time": "3:35:16"}
73
+ {"current_steps": 730, "total_steps": 1500, "loss": 0.0242, "accuracy": 0.9656250476837158, "lr": 3.0481965604697582e-06, "epoch": 4.837209302325581, "percentage": 48.67, "elapsed_time": "3:21:24", "remaining_time": "3:32:26"}
74
+ {"current_steps": 740, "total_steps": 1500, "loss": 0.0306, "accuracy": 0.956250011920929, "lr": 2.9912915238320755e-06, "epoch": 4.903654485049834, "percentage": 49.33, "elapsed_time": "3:24:08", "remaining_time": "3:29:39"}
75
+ {"current_steps": 750, "total_steps": 1500, "loss": 0.0305, "accuracy": 0.9562500715255737, "lr": 2.9341204441673267e-06, "epoch": 4.970099667774086, "percentage": 50.0, "elapsed_time": "3:26:52", "remaining_time": "3:26:52"}
76
+ {"current_steps": 760, "total_steps": 1500, "loss": 0.023, "accuracy": 0.9654605388641357, "lr": 2.876714280623708e-06, "epoch": 5.033222591362127, "percentage": 50.67, "elapsed_time": "3:29:31", "remaining_time": "3:24:00"}
77
+ {"current_steps": 770, "total_steps": 1500, "loss": 0.0359, "accuracy": 0.9484374523162842, "lr": 2.8191041196514874e-06, "epoch": 5.099667774086379, "percentage": 51.33, "elapsed_time": "3:32:18", "remaining_time": "3:21:16"}
78
+ {"current_steps": 780, "total_steps": 1500, "loss": 0.0338, "accuracy": 0.953125, "lr": 2.761321158169134e-06, "epoch": 5.166112956810632, "percentage": 52.0, "elapsed_time": "3:35:05", "remaining_time": "3:18:32"}
79
+ {"current_steps": 790, "total_steps": 1500, "loss": 0.0339, "accuracy": 0.9515625238418579, "lr": 2.703396686669646e-06, "epoch": 5.232558139534884, "percentage": 52.67, "elapsed_time": "3:37:55", "remaining_time": "3:15:51"}
80
+ {"current_steps": 800, "total_steps": 1500, "loss": 0.0305, "accuracy": 0.9562499523162842, "lr": 2.6453620722761897e-06, "epoch": 5.299003322259137, "percentage": 53.33, "elapsed_time": "3:40:44", "remaining_time": "3:13:08"}
81
+ {"current_steps": 810, "total_steps": 1500, "loss": 0.0202, "accuracy": 0.9718750715255737, "lr": 2.587248741756253e-06, "epoch": 5.365448504983389, "percentage": 54.0, "elapsed_time": "3:43:29", "remaining_time": "3:10:22"}
82
+ {"current_steps": 820, "total_steps": 1500, "loss": 0.0196, "accuracy": 0.9734375476837158, "lr": 2.5290881645034932e-06, "epoch": 5.431893687707642, "percentage": 54.67, "elapsed_time": "3:46:13", "remaining_time": "3:07:35"}
83
+ {"current_steps": 830, "total_steps": 1500, "loss": 0.024, "accuracy": 0.9656250476837158, "lr": 2.470911835496508e-06, "epoch": 5.498338870431894, "percentage": 55.33, "elapsed_time": "3:49:01", "remaining_time": "3:04:52"}
84
+ {"current_steps": 840, "total_steps": 1500, "loss": 0.0351, "accuracy": 0.9500000476837158, "lr": 2.4127512582437486e-06, "epoch": 5.5647840531561465, "percentage": 56.0, "elapsed_time": "3:51:47", "remaining_time": "3:02:07"}
85
+ {"current_steps": 850, "total_steps": 1500, "loss": 0.023, "accuracy": 0.9671875238418579, "lr": 2.3546379277238107e-06, "epoch": 5.631229235880399, "percentage": 56.67, "elapsed_time": "3:54:35", "remaining_time": "2:59:23"}
86
+ {"current_steps": 860, "total_steps": 1500, "loss": 0.0393, "accuracy": 0.9437499642372131, "lr": 2.296603313330355e-06, "epoch": 5.6976744186046515, "percentage": 57.33, "elapsed_time": "3:57:21", "remaining_time": "2:56:38"}
87
+ {"current_steps": 870, "total_steps": 1500, "loss": 0.0326, "accuracy": 0.9531249403953552, "lr": 2.238678841830867e-06, "epoch": 5.764119601328904, "percentage": 58.0, "elapsed_time": "4:00:08", "remaining_time": "2:53:53"}
88
+ {"current_steps": 880, "total_steps": 1500, "loss": 0.0294, "accuracy": 0.957812488079071, "lr": 2.1808958803485134e-06, "epoch": 5.8305647840531565, "percentage": 58.67, "elapsed_time": "4:02:55", "remaining_time": "2:51:09"}
89
+ {"current_steps": 890, "total_steps": 1500, "loss": 0.0284, "accuracy": 0.9593750238418579, "lr": 2.1232857193762923e-06, "epoch": 5.897009966777409, "percentage": 59.33, "elapsed_time": "4:05:40", "remaining_time": "2:48:23"}
90
+ {"current_steps": 900, "total_steps": 1500, "loss": 0.0316, "accuracy": 0.9546875357627869, "lr": 2.0658795558326745e-06, "epoch": 5.9634551495016614, "percentage": 60.0, "elapsed_time": "4:08:27", "remaining_time": "2:45:38"}
91
+ {"current_steps": 910, "total_steps": 1500, "loss": 0.0176, "accuracy": 0.9736842513084412, "lr": 2.0087084761679245e-06, "epoch": 6.026578073089701, "percentage": 60.67, "elapsed_time": "4:11:07", "remaining_time": "2:42:48"}
92
+ {"current_steps": 920, "total_steps": 1500, "loss": 0.0273, "accuracy": 0.9609375596046448, "lr": 1.9518034395302413e-06, "epoch": 6.093023255813954, "percentage": 61.33, "elapsed_time": "4:13:54", "remaining_time": "2:40:04"}
93
+ {"current_steps": 930, "total_steps": 1500, "loss": 0.0261, "accuracy": 0.9625000357627869, "lr": 1.895195261000831e-06, "epoch": 6.159468438538206, "percentage": 62.0, "elapsed_time": "4:16:40", "remaining_time": "2:37:18"}
94
+ {"current_steps": 940, "total_steps": 1500, "loss": 0.0298, "accuracy": 0.9578125476837158, "lr": 1.8389145949069953e-06, "epoch": 6.225913621262459, "percentage": 62.67, "elapsed_time": "4:19:23", "remaining_time": "2:34:31"}
95
+ {"current_steps": 950, "total_steps": 1500, "loss": 0.0284, "accuracy": 0.9593750238418579, "lr": 1.7829919182222752e-06, "epoch": 6.292358803986711, "percentage": 63.33, "elapsed_time": "4:22:06", "remaining_time": "2:31:44"}
96
+ {"current_steps": 960, "total_steps": 1500, "loss": 0.0327, "accuracy": 0.9546874761581421, "lr": 1.7274575140626318e-06, "epoch": 6.358803986710964, "percentage": 64.0, "elapsed_time": "4:24:50", "remaining_time": "2:28:58"}
97
+ {"current_steps": 970, "total_steps": 1500, "loss": 0.0316, "accuracy": 0.9546874761581421, "lr": 1.6723414552876052e-06, "epoch": 6.425249169435216, "percentage": 64.67, "elapsed_time": "4:27:35", "remaining_time": "2:26:12"}
98
+ {"current_steps": 980, "total_steps": 1500, "loss": 0.0274, "accuracy": 0.9609375, "lr": 1.6176735882153284e-06, "epoch": 6.4916943521594686, "percentage": 65.33, "elapsed_time": "4:30:22", "remaining_time": "2:23:27"}
99
+ {"current_steps": 990, "total_steps": 1500, "loss": 0.0326, "accuracy": 0.953125, "lr": 1.56348351646022e-06, "epoch": 6.558139534883721, "percentage": 66.0, "elapsed_time": "4:33:10", "remaining_time": "2:20:43"}
100
+ {"current_steps": 1000, "total_steps": 1500, "loss": 0.025, "accuracy": 0.9640624523162842, "lr": 1.509800584902108e-06, "epoch": 6.6245847176079735, "percentage": 66.67, "elapsed_time": "4:35:56", "remaining_time": "2:17:58"}