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:
|
3 |
size 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:466cefe8a3fcf1adeed46ecb0bac9201f66dec96c227f51b35017b88e088fc14
|
3 |
size 83945296
|
runs/Apr30_20-33-10_23785362-f75e-450a-adba-3563dd4046d5-0/events.out.tfevents.1746045263.23785362-f75e-450a-adba-3563dd4046d5-0.1022.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95ac65bf88f90eb29a2e1eac183362b547111746dd97f9b694f1e7acae691354
|
3 |
+
size 74204
|
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": "2:11:59", "remaining_time": "4:40:29"}
|
49 |
{"current_steps": 490, "total_steps": 1500, "loss": 0.0349, "accuracy": 0.953125, "lr": 4.257452643564155e-06, "epoch": 3.2458471760797343, "percentage": 32.67, "elapsed_time": "2:14:43", "remaining_time": "4:37:40"}
|
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": "2:17:30", "remaining_time": "4:35:01"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "2:11:59", "remaining_time": "4:40:29"}
|
49 |
{"current_steps": 490, "total_steps": 1500, "loss": 0.0349, "accuracy": 0.953125, "lr": 4.257452643564155e-06, "epoch": 3.2458471760797343, "percentage": 32.67, "elapsed_time": "2:14:43", "remaining_time": "4:37:40"}
|
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": "2:17:30", "remaining_time": "4:35:01"}
|
51 |
+
{"current_steps": 510, "total_steps": 1500, "loss": 0.0233, "accuracy": 0.9671874642372131, "lr": 4.172826515897146e-06, "epoch": 3.3787375415282392, "percentage": 34.0, "elapsed_time": "2:20:17", "remaining_time": "4:32:20"}
|
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": "2:23:04", "remaining_time": "4:29:37"}
|
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": "2:25:52", "remaining_time": "4:26:58"}
|
54 |
+
{"current_steps": 540, "total_steps": 1500, "loss": 0.0329, "accuracy": 0.953125, "lr": 4.039153688314146e-06, "epoch": 3.5780730897009967, "percentage": 36.0, "elapsed_time": "2:28:38", "remaining_time": "4:24:15"}
|
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": "2:31:22", "remaining_time": "4:21:27"}
|
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": "2:34:09", "remaining_time": "4:18:46"}
|
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": "2:36:54", "remaining_time": "4:15:59"}
|
58 |
+
{"current_steps": 580, "total_steps": 1500, "loss": 0.028, "accuracy": 0.9609374403953552, "lr": 3.849376644878783e-06, "epoch": 3.8438538205980066, "percentage": 38.67, "elapsed_time": "2:39:41", "remaining_time": "4:13:18"}
|
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": "2:42:27", "remaining_time": "4:10:34"}
|
60 |
+
{"current_steps": 600, "total_steps": 1500, "loss": 0.0357, "accuracy": 0.949999988079071, "lr": 3.7500000000000005e-06, "epoch": 3.9767441860465116, "percentage": 40.0, "elapsed_time": "2:45:12", "remaining_time": "4:07:48"}
|
61 |
+
{"current_steps": 610, "total_steps": 1500, "loss": 0.034, "accuracy": 0.9490132331848145, "lr": 3.699282783125616e-06, "epoch": 4.039867109634551, "percentage": 40.67, "elapsed_time": "2:47:51", "remaining_time": "4:04:54"}
|
62 |
+
{"current_steps": 620, "total_steps": 1500, "loss": 0.0199, "accuracy": 0.971875011920929, "lr": 3.6479161334675294e-06, "epoch": 4.106312292358804, "percentage": 41.33, "elapsed_time": "2:50:33", "remaining_time": "4:02:04"}
|
63 |
+
{"current_steps": 630, "total_steps": 1500, "loss": 0.0251, "accuracy": 0.964062511920929, "lr": 3.595927866972694e-06, "epoch": 4.172757475083056, "percentage": 42.0, "elapsed_time": "2:53:17", "remaining_time": "3:59:18"}
|
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": "2:56:03", "remaining_time": "3:56:34"}
|
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": "2:58:49", "remaining_time": "3:53:51"}
|
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": "3:01:31", "remaining_time": "3:51:01"}
|
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": "3:04:15", "remaining_time": "3:48:15"}
|
68 |
+
{"current_steps": 680, "total_steps": 1500, "loss": 0.0233, "accuracy": 0.9671875238418579, "lr": 3.3276585447123957e-06, "epoch": 4.504983388704319, "percentage": 45.33, "elapsed_time": "3:06:59", "remaining_time": "3:45:29"}
|
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": "3:09:42", "remaining_time": "3:42:42"}
|
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": "3:12:25", "remaining_time": "3:39:54"}
|
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": "3:15:10", "remaining_time": "3:37:10"}
|
72 |
+
{"current_steps": 720, "total_steps": 1500, "loss": 0.0327, "accuracy": 0.9546875357627869, "lr": 3.1048047389991693e-06, "epoch": 4.770764119601329, "percentage": 48.0, "elapsed_time": "3:17:55", "remaining_time": "3:34:24"}
|
73 |
+
{"current_steps": 730, "total_steps": 1500, "loss": 0.024, "accuracy": 0.9656250476837158, "lr": 3.0481965604697582e-06, "epoch": 4.837209302325581, "percentage": 48.67, "elapsed_time": "3:20:36", "remaining_time": "3:31:35"}
|
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": "3:23:19", "remaining_time": "3:28:49"}
|
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": "3:26:02", "remaining_time": "3:26:02"}
|
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": "3:28:40", "remaining_time": "3:23:11"}
|
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": "3:31:26", "remaining_time": "3:20:27"}
|
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": "3:34:13", "remaining_time": "3:17:44"}
|
79 |
+
{"current_steps": 790, "total_steps": 1500, "loss": 0.0338, "accuracy": 0.9515625238418579, "lr": 2.703396686669646e-06, "epoch": 5.232558139534884, "percentage": 52.67, "elapsed_time": "3:37:03", "remaining_time": "3:15:04"}
|
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": "3:39:51", "remaining_time": "3:12:22"}
|
81 |
+
{"current_steps": 810, "total_steps": 1500, "loss": 0.0203, "accuracy": 0.9718750715255737, "lr": 2.587248741756253e-06, "epoch": 5.365448504983389, "percentage": 54.0, "elapsed_time": "3:42:35", "remaining_time": "3:09:36"}
|
82 |
+
{"current_steps": 820, "total_steps": 1500, "loss": 0.0197, "accuracy": 0.9734375476837158, "lr": 2.5290881645034932e-06, "epoch": 5.431893687707642, "percentage": 54.67, "elapsed_time": "3:45:18", "remaining_time": "3:06:50"}
|
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": "3:48:05", "remaining_time": "3:04:07"}
|
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": "3:50:51", "remaining_time": "3:01:23"}
|
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": "3:53:39", "remaining_time": "2:58:40"}
|
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": "3:56:23", "remaining_time": "2:55:55"}
|
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": "3:59:09", "remaining_time": "2:53:11"}
|
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": "4:01:56", "remaining_time": "2:50:27"}
|
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": "4:04:41", "remaining_time": "2:47:42"}
|
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": "4:07:27", "remaining_time": "2:44:58"}
|
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": "4:10:06", "remaining_time": "2:42:09"}
|
92 |
+
{"current_steps": 920, "total_steps": 1500, "loss": 0.0274, "accuracy": 0.9609375596046448, "lr": 1.9518034395302413e-06, "epoch": 6.093023255813954, "percentage": 61.33, "elapsed_time": "4:12:53", "remaining_time": "2:39:26"}
|
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": "4:15:38", "remaining_time": "2:36:40"}
|
94 |
+
{"current_steps": 940, "total_steps": 1500, "loss": 0.0299, "accuracy": 0.9578125476837158, "lr": 1.8389145949069953e-06, "epoch": 6.225913621262459, "percentage": 62.67, "elapsed_time": "4:18:20", "remaining_time": "2:33:54"}
|
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": "4:21:03", "remaining_time": "2:31:08"}
|
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": "4:23:46", "remaining_time": "2:28:22"}
|
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": "4:26:31", "remaining_time": "2:25:37"}
|
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": "4:29:17", "remaining_time": "2:22:53"}
|
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": "4:32:04", "remaining_time": "2:20:09"}
|
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": "4:34:49", "remaining_time": "2:17:24"}
|