Training in progress, step 100
Browse files- model-00001-of-00006.safetensors +1 -1
- model-00002-of-00006.safetensors +1 -1
- model-00003-of-00006.safetensors +1 -1
- model-00004-of-00006.safetensors +1 -1
- model-00005-of-00006.safetensors +1 -1
- model-00006-of-00006.safetensors +1 -1
- trainer_log.jsonl +102 -118
- training_args.bin +2 -2
model-00001-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4933656472
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d71eb25767550422205fe89bb697c423225ee25b93c9254bd16d6548fb017ce0
|
| 3 |
size 4933656472
|
model-00002-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4954690712
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5727b54c6a608c1cd654fb530332a3e5e298be6f7e1ae3afb37e6124bc45f6c3
|
| 3 |
size 4954690712
|
model-00003-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4902241352
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6547b62ef757ff2252f630beed71452dcb8a525a40f4bc0d6aa16cf0540f28e
|
| 3 |
size 4902241352
|
model-00004-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4771169120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:daf268d466e9891ea803f46d76b541a5f13804d9efc8ad1f36d8b71967756519
|
| 3 |
size 4771169120
|
model-00005-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4771169120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c56935fca60f62e9b15c2fed62910b34e6c0dc41627f5cc0a80d1cdc2cffc05
|
| 3 |
size 4771169120
|
model-00006-of-00006.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4986116216
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:087c22f9e41a37e59ffe9a1ce5a1ce80f3d0e002b17b22883277b247cfa3fc88
|
| 3 |
size 4986116216
|
trainer_log.jsonl
CHANGED
|
@@ -1,118 +1,102 @@
|
|
| 1 |
-
{"current_steps": 1, "total_steps":
|
| 2 |
-
{"current_steps": 2, "total_steps":
|
| 3 |
-
{"current_steps": 3, "total_steps":
|
| 4 |
-
{"current_steps": 4, "total_steps":
|
| 5 |
-
{"current_steps": 5, "total_steps":
|
| 6 |
-
{"current_steps": 6, "total_steps":
|
| 7 |
-
{"current_steps": 7, "total_steps":
|
| 8 |
-
{"current_steps": 8, "total_steps":
|
| 9 |
-
{"current_steps": 9, "total_steps":
|
| 10 |
-
{"current_steps": 10, "total_steps":
|
| 11 |
-
{"current_steps": 11, "total_steps":
|
| 12 |
-
{"current_steps": 12, "total_steps":
|
| 13 |
-
{"current_steps": 13, "total_steps":
|
| 14 |
-
{"current_steps": 14, "total_steps":
|
| 15 |
-
{"current_steps": 15, "total_steps":
|
| 16 |
-
{"current_steps": 16, "total_steps":
|
| 17 |
-
{"current_steps": 17, "total_steps":
|
| 18 |
-
{"current_steps": 18, "total_steps":
|
| 19 |
-
{"current_steps": 19, "total_steps":
|
| 20 |
-
{"current_steps": 20, "total_steps":
|
| 21 |
-
{"current_steps": 21, "total_steps":
|
| 22 |
-
{"current_steps": 22, "total_steps":
|
| 23 |
-
{"current_steps": 23, "total_steps":
|
| 24 |
-
{"current_steps": 24, "total_steps":
|
| 25 |
-
{"current_steps": 25, "total_steps":
|
| 26 |
-
{"current_steps": 26, "total_steps":
|
| 27 |
-
{"current_steps": 27, "total_steps":
|
| 28 |
-
{"current_steps": 28, "total_steps":
|
| 29 |
-
{"current_steps": 29, "total_steps":
|
| 30 |
-
{"current_steps": 30, "total_steps":
|
| 31 |
-
{"current_steps": 31, "total_steps":
|
| 32 |
-
{"current_steps": 32, "total_steps":
|
| 33 |
-
{"current_steps": 33, "total_steps":
|
| 34 |
-
{"current_steps": 34, "total_steps":
|
| 35 |
-
{"current_steps": 35, "total_steps":
|
| 36 |
-
{"current_steps": 36, "total_steps":
|
| 37 |
-
{"current_steps": 37, "total_steps":
|
| 38 |
-
{"current_steps": 38, "total_steps":
|
| 39 |
-
{"current_steps": 39, "total_steps":
|
| 40 |
-
{"current_steps": 40, "total_steps":
|
| 41 |
-
{"current_steps": 41, "total_steps":
|
| 42 |
-
{"current_steps": 42, "total_steps":
|
| 43 |
-
{"current_steps": 43, "total_steps":
|
| 44 |
-
{"current_steps": 44, "total_steps":
|
| 45 |
-
{"current_steps": 45, "total_steps":
|
| 46 |
-
{"current_steps": 46, "total_steps":
|
| 47 |
-
{"current_steps": 47, "total_steps":
|
| 48 |
-
{"current_steps": 48, "total_steps":
|
| 49 |
-
{"current_steps": 49, "total_steps":
|
| 50 |
-
{"current_steps": 50, "total_steps":
|
| 51 |
-
{"current_steps": 51, "total_steps":
|
| 52 |
-
{"current_steps": 52, "total_steps":
|
| 53 |
-
{"current_steps": 53, "total_steps":
|
| 54 |
-
{"current_steps": 54, "total_steps":
|
| 55 |
-
{"current_steps": 55, "total_steps":
|
| 56 |
-
{"current_steps": 56, "total_steps":
|
| 57 |
-
{"current_steps": 57, "total_steps":
|
| 58 |
-
{"current_steps": 58, "total_steps":
|
| 59 |
-
{"current_steps": 59, "total_steps":
|
| 60 |
-
{"current_steps": 60, "total_steps":
|
| 61 |
-
{"current_steps": 61, "total_steps":
|
| 62 |
-
{"current_steps": 62, "total_steps":
|
| 63 |
-
{"current_steps": 63, "total_steps":
|
| 64 |
-
{"current_steps": 64, "total_steps":
|
| 65 |
-
{"current_steps": 65, "total_steps":
|
| 66 |
-
{"current_steps": 66, "total_steps":
|
| 67 |
-
{"current_steps": 67, "total_steps":
|
| 68 |
-
{"current_steps": 68, "total_steps":
|
| 69 |
-
{"current_steps": 69, "total_steps":
|
| 70 |
-
{"current_steps": 70, "total_steps":
|
| 71 |
-
{"current_steps": 71, "total_steps":
|
| 72 |
-
{"current_steps": 72, "total_steps":
|
| 73 |
-
{"current_steps": 73, "total_steps":
|
| 74 |
-
{"current_steps": 74, "total_steps":
|
| 75 |
-
{"current_steps": 75, "total_steps":
|
| 76 |
-
{"current_steps": 76, "total_steps":
|
| 77 |
-
{"current_steps": 77, "total_steps":
|
| 78 |
-
{"current_steps": 78, "total_steps":
|
| 79 |
-
{"current_steps": 79, "total_steps":
|
| 80 |
-
{"current_steps": 80, "total_steps":
|
| 81 |
-
{"current_steps": 81, "total_steps":
|
| 82 |
-
{"current_steps": 82, "total_steps":
|
| 83 |
-
{"current_steps": 83, "total_steps":
|
| 84 |
-
{"current_steps": 84, "total_steps":
|
| 85 |
-
{"current_steps": 85, "total_steps":
|
| 86 |
-
{"current_steps": 86, "total_steps":
|
| 87 |
-
{"current_steps": 87, "total_steps":
|
| 88 |
-
{"current_steps": 88, "total_steps":
|
| 89 |
-
{"current_steps": 89, "total_steps":
|
| 90 |
-
{"current_steps": 90, "total_steps":
|
| 91 |
-
{"current_steps": 91, "total_steps":
|
| 92 |
-
{"current_steps": 92, "total_steps":
|
| 93 |
-
{"current_steps": 93, "total_steps":
|
| 94 |
-
{"current_steps": 94, "total_steps":
|
| 95 |
-
{"current_steps": 95, "total_steps":
|
| 96 |
-
{"current_steps": 96, "total_steps":
|
| 97 |
-
{"current_steps": 97, "total_steps":
|
| 98 |
-
{"current_steps": 98, "total_steps":
|
| 99 |
-
{"current_steps": 99, "total_steps":
|
| 100 |
-
{"current_steps": 100, "total_steps":
|
| 101 |
-
{"current_steps": 101, "total_steps":
|
| 102 |
-
{"current_steps": 102, "total_steps":
|
| 103 |
-
{"current_steps": 103, "total_steps": 117, "loss": 1.8015, "lr": 3.87400575837657e-07, "epoch": 0.8803418803418803, "percentage": 88.03, "elapsed_time": "5:28:04", "remaining_time": "0:44:35"}
|
| 104 |
-
{"current_steps": 104, "total_steps": 117, "loss": 1.7987, "lr": 3.346382300868134e-07, "epoch": 0.8888888888888888, "percentage": 88.89, "elapsed_time": "5:31:14", "remaining_time": "0:41:24"}
|
| 105 |
-
{"current_steps": 105, "total_steps": 117, "loss": 1.801, "lr": 2.85612772694579e-07, "epoch": 0.8974358974358975, "percentage": 89.74, "elapsed_time": "5:34:25", "remaining_time": "0:38:13"}
|
| 106 |
-
{"current_steps": 106, "total_steps": 117, "loss": 1.797, "lr": 2.403634723543674e-07, "epoch": 0.905982905982906, "percentage": 90.6, "elapsed_time": "5:37:36", "remaining_time": "0:35:02"}
|
| 107 |
-
{"current_steps": 107, "total_steps": 117, "loss": 1.7963, "lr": 1.989265731115525e-07, "epoch": 0.9145299145299145, "percentage": 91.45, "elapsed_time": "5:40:48", "remaining_time": "0:31:51"}
|
| 108 |
-
{"current_steps": 108, "total_steps": 117, "loss": 1.7919, "lr": 1.6133526533250566e-07, "epoch": 0.9230769230769231, "percentage": 92.31, "elapsed_time": "5:43:58", "remaining_time": "0:28:39"}
|
| 109 |
-
{"current_steps": 109, "total_steps": 117, "loss": 1.7973, "lr": 1.2761965911958385e-07, "epoch": 0.9316239316239316, "percentage": 93.16, "elapsed_time": "5:47:09", "remaining_time": "0:25:28"}
|
| 110 |
-
{"current_steps": 110, "total_steps": 117, "loss": 1.7944, "lr": 9.780676019336632e-08, "epoch": 0.9401709401709402, "percentage": 94.02, "elapsed_time": "5:50:21", "remaining_time": "0:22:17"}
|
| 111 |
-
{"current_steps": 111, "total_steps": 117, "loss": 1.7929, "lr": 7.192044826145772e-08, "epoch": 0.9487179487179487, "percentage": 94.87, "elapsed_time": "5:53:32", "remaining_time": "0:19:06"}
|
| 112 |
-
{"current_steps": 112, "total_steps": 117, "loss": 1.7953, "lr": 4.998145789118114e-08, "epoch": 0.9572649572649573, "percentage": 95.73, "elapsed_time": "5:56:42", "remaining_time": "0:15:55"}
|
| 113 |
-
{"current_steps": 113, "total_steps": 117, "loss": 1.794, "lr": 3.2007361901485455e-08, "epoch": 0.9658119658119658, "percentage": 96.58, "elapsed_time": "5:59:52", "remaining_time": "0:12:44"}
|
| 114 |
-
{"current_steps": 114, "total_steps": 117, "loss": 1.7915, "lr": 1.8012557287367394e-08, "epoch": 0.9743589743589743, "percentage": 97.44, "elapsed_time": "6:03:04", "remaining_time": "0:09:33"}
|
| 115 |
-
{"current_steps": 115, "total_steps": 117, "loss": 1.7899, "lr": 8.008253688084888e-09, "epoch": 0.9829059829059829, "percentage": 98.29, "elapsed_time": "6:06:15", "remaining_time": "0:06:22"}
|
| 116 |
-
{"current_steps": 116, "total_steps": 117, "loss": 1.7893, "lr": 2.002464408392135e-09, "epoch": 0.9914529914529915, "percentage": 99.15, "elapsed_time": "6:09:26", "remaining_time": "0:03:11"}
|
| 117 |
-
{"current_steps": 117, "total_steps": 117, "loss": 1.7864, "lr": 0.0, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "6:12:36", "remaining_time": "0:00:00"}
|
| 118 |
-
{"current_steps": 117, "total_steps": 117, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "6:15:35", "remaining_time": "0:00:00"}
|
|
|
|
| 1 |
+
{"current_steps": 1, "total_steps": 550, "loss": 1.8898, "lr": 3.5714285714285716e-07, "epoch": 0.0018177686889343332, "percentage": 0.18, "elapsed_time": "0:03:25", "remaining_time": "1 day, 7:20:22"}
|
| 2 |
+
{"current_steps": 2, "total_steps": 550, "loss": 1.8867, "lr": 7.142857142857143e-07, "epoch": 0.0036355373778686664, "percentage": 0.36, "elapsed_time": "0:06:40", "remaining_time": "1 day, 6:30:39"}
|
| 3 |
+
{"current_steps": 3, "total_steps": 550, "loss": 1.8848, "lr": 1.0714285714285714e-06, "epoch": 0.0054533060668029995, "percentage": 0.55, "elapsed_time": "0:09:52", "remaining_time": "1 day, 5:59:21"}
|
| 4 |
+
{"current_steps": 4, "total_steps": 550, "loss": 1.888, "lr": 1.4285714285714286e-06, "epoch": 0.007271074755737333, "percentage": 0.73, "elapsed_time": "0:13:03", "remaining_time": "1 day, 5:43:05"}
|
| 5 |
+
{"current_steps": 5, "total_steps": 550, "loss": 1.8816, "lr": 1.7857142857142859e-06, "epoch": 0.009088843444671665, "percentage": 0.91, "elapsed_time": "0:16:16", "remaining_time": "1 day, 5:33:54"}
|
| 6 |
+
{"current_steps": 6, "total_steps": 550, "loss": 1.8851, "lr": 2.1428571428571427e-06, "epoch": 0.010906612133605999, "percentage": 1.09, "elapsed_time": "0:19:27", "remaining_time": "1 day, 5:24:27"}
|
| 7 |
+
{"current_steps": 7, "total_steps": 550, "loss": 1.8799, "lr": 2.5e-06, "epoch": 0.012724380822540331, "percentage": 1.27, "elapsed_time": "0:22:39", "remaining_time": "1 day, 5:17:57"}
|
| 8 |
+
{"current_steps": 8, "total_steps": 550, "loss": 1.8785, "lr": 2.8571428571428573e-06, "epoch": 0.014542149511474665, "percentage": 1.45, "elapsed_time": "0:25:51", "remaining_time": "1 day, 5:12:11"}
|
| 9 |
+
{"current_steps": 9, "total_steps": 550, "loss": 1.8763, "lr": 3.2142857142857147e-06, "epoch": 0.016359918200409, "percentage": 1.64, "elapsed_time": "0:29:03", "remaining_time": "1 day, 5:06:30"}
|
| 10 |
+
{"current_steps": 10, "total_steps": 550, "loss": 1.8676, "lr": 3.5714285714285718e-06, "epoch": 0.01817768688934333, "percentage": 1.82, "elapsed_time": "0:32:13", "remaining_time": "1 day, 5:00:21"}
|
| 11 |
+
{"current_steps": 11, "total_steps": 550, "loss": 1.8634, "lr": 3.928571428571429e-06, "epoch": 0.019995455578277664, "percentage": 2.0, "elapsed_time": "0:35:25", "remaining_time": "1 day, 4:55:59"}
|
| 12 |
+
{"current_steps": 12, "total_steps": 550, "loss": 1.864, "lr": 4.2857142857142855e-06, "epoch": 0.021813224267211998, "percentage": 2.18, "elapsed_time": "0:38:36", "remaining_time": "1 day, 4:50:54"}
|
| 13 |
+
{"current_steps": 13, "total_steps": 550, "loss": 1.8647, "lr": 4.642857142857144e-06, "epoch": 0.02363099295614633, "percentage": 2.36, "elapsed_time": "0:41:46", "remaining_time": "1 day, 4:45:46"}
|
| 14 |
+
{"current_steps": 14, "total_steps": 550, "loss": 1.8605, "lr": 5e-06, "epoch": 0.025448761645080663, "percentage": 2.55, "elapsed_time": "0:44:56", "remaining_time": "1 day, 4:40:44"}
|
| 15 |
+
{"current_steps": 15, "total_steps": 550, "loss": 1.8648, "lr": 5.357142857142857e-06, "epoch": 0.027266530334014997, "percentage": 2.73, "elapsed_time": "0:48:07", "remaining_time": "1 day, 4:36:38"}
|
| 16 |
+
{"current_steps": 16, "total_steps": 550, "loss": 1.8536, "lr": 5.7142857142857145e-06, "epoch": 0.02908429902294933, "percentage": 2.91, "elapsed_time": "0:51:17", "remaining_time": "1 day, 4:32:06"}
|
| 17 |
+
{"current_steps": 17, "total_steps": 550, "loss": 1.8485, "lr": 6.071428571428571e-06, "epoch": 0.03090206771188366, "percentage": 3.09, "elapsed_time": "0:54:29", "remaining_time": "1 day, 4:28:19"}
|
| 18 |
+
{"current_steps": 18, "total_steps": 550, "loss": 1.8536, "lr": 6.4285714285714295e-06, "epoch": 0.032719836400818, "percentage": 3.27, "elapsed_time": "0:57:39", "remaining_time": "1 day, 4:23:56"}
|
| 19 |
+
{"current_steps": 19, "total_steps": 550, "loss": 1.8491, "lr": 6.785714285714287e-06, "epoch": 0.03453760508975233, "percentage": 3.45, "elapsed_time": "1:00:49", "remaining_time": "1 day, 4:19:43"}
|
| 20 |
+
{"current_steps": 20, "total_steps": 550, "loss": 1.8361, "lr": 7.1428571428571436e-06, "epoch": 0.03635537377868666, "percentage": 3.64, "elapsed_time": "1:03:59", "remaining_time": "1 day, 4:15:34"}
|
| 21 |
+
{"current_steps": 21, "total_steps": 550, "loss": 1.8522, "lr": 7.500000000000001e-06, "epoch": 0.038173142467621, "percentage": 3.82, "elapsed_time": "1:07:10", "remaining_time": "1 day, 4:12:12"}
|
| 22 |
+
{"current_steps": 22, "total_steps": 550, "loss": 1.8391, "lr": 7.857142857142858e-06, "epoch": 0.03999091115655533, "percentage": 4.0, "elapsed_time": "1:10:21", "remaining_time": "1 day, 4:08:33"}
|
| 23 |
+
{"current_steps": 23, "total_steps": 550, "loss": 1.8345, "lr": 8.214285714285714e-06, "epoch": 0.04180867984548966, "percentage": 4.18, "elapsed_time": "1:13:33", "remaining_time": "1 day, 4:05:29"}
|
| 24 |
+
{"current_steps": 24, "total_steps": 550, "loss": 1.8342, "lr": 8.571428571428571e-06, "epoch": 0.043626448534423996, "percentage": 4.36, "elapsed_time": "1:16:45", "remaining_time": "1 day, 4:02:12"}
|
| 25 |
+
{"current_steps": 25, "total_steps": 550, "loss": 1.8399, "lr": 8.92857142857143e-06, "epoch": 0.04544421722335833, "percentage": 4.55, "elapsed_time": "1:19:54", "remaining_time": "1 day, 3:58:10"}
|
| 26 |
+
{"current_steps": 26, "total_steps": 550, "loss": 1.833, "lr": 9.285714285714288e-06, "epoch": 0.04726198591229266, "percentage": 4.73, "elapsed_time": "1:23:06", "remaining_time": "1 day, 3:54:55"}
|
| 27 |
+
{"current_steps": 27, "total_steps": 550, "loss": 1.8342, "lr": 9.642857142857144e-06, "epoch": 0.049079754601226995, "percentage": 4.91, "elapsed_time": "1:26:17", "remaining_time": "1 day, 3:51:20"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 550, "loss": 1.8313, "lr": 1e-05, "epoch": 0.050897523290161326, "percentage": 5.09, "elapsed_time": "1:29:29", "remaining_time": "1 day, 3:48:31"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 550, "loss": 1.8291, "lr": 9.999909448127131e-06, "epoch": 0.05271529197909566, "percentage": 5.27, "elapsed_time": "1:32:39", "remaining_time": "1 day, 3:44:39"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 550, "loss": 1.8185, "lr": 9.999637795788383e-06, "epoch": 0.054533060668029994, "percentage": 5.45, "elapsed_time": "1:35:49", "remaining_time": "1 day, 3:41:01"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 550, "loss": 1.8261, "lr": 9.999185052823207e-06, "epoch": 0.056350829356964324, "percentage": 5.64, "elapsed_time": "1:38:59", "remaining_time": "1 day, 3:37:25"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 550, "loss": 1.8237, "lr": 9.99855123563029e-06, "epoch": 0.05816859804589866, "percentage": 5.82, "elapsed_time": "1:42:10", "remaining_time": "1 day, 3:33:57"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 550, "loss": 1.827, "lr": 9.997736367166967e-06, "epoch": 0.05998636673483299, "percentage": 6.0, "elapsed_time": "1:45:21", "remaining_time": "1 day, 3:30:44"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 550, "loss": 1.8257, "lr": 9.996740476948386e-06, "epoch": 0.06180413542376732, "percentage": 6.18, "elapsed_time": "1:48:32", "remaining_time": "1 day, 3:27:15"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 550, "loss": 1.819, "lr": 9.995563601046434e-06, "epoch": 0.06362190411270166, "percentage": 6.36, "elapsed_time": "1:51:42", "remaining_time": "1 day, 3:23:49"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 550, "loss": 1.8136, "lr": 9.994205782088438e-06, "epoch": 0.065439672801636, "percentage": 6.55, "elapsed_time": "1:54:54", "remaining_time": "1 day, 3:20:37"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 550, "loss": 1.8206, "lr": 9.99266706925562e-06, "epoch": 0.06725744149057032, "percentage": 6.73, "elapsed_time": "1:58:06", "remaining_time": "1 day, 3:17:37"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 550, "loss": 1.8281, "lr": 9.990947518281312e-06, "epoch": 0.06907521017950466, "percentage": 6.91, "elapsed_time": "2:01:16", "remaining_time": "1 day, 3:13:59"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 550, "loss": 1.82, "lr": 9.989047191448934e-06, "epoch": 0.070892978868439, "percentage": 7.09, "elapsed_time": "2:04:25", "remaining_time": "1 day, 3:10:23"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 550, "loss": 1.8079, "lr": 9.986966157589751e-06, "epoch": 0.07271074755737332, "percentage": 7.27, "elapsed_time": "2:07:37", "remaining_time": "1 day, 3:07:09"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 550, "loss": 1.8088, "lr": 9.984704492080366e-06, "epoch": 0.07452851624630766, "percentage": 7.45, "elapsed_time": "2:10:48", "remaining_time": "1 day, 3:03:56"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 550, "loss": 1.8153, "lr": 9.982262276840002e-06, "epoch": 0.076346284935242, "percentage": 7.64, "elapsed_time": "2:14:00", "remaining_time": "1 day, 3:00:49"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 550, "loss": 1.8082, "lr": 9.979639600327522e-06, "epoch": 0.07816405362417632, "percentage": 7.82, "elapsed_time": "2:17:10", "remaining_time": "1 day, 2:57:27"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 550, "loss": 1.8087, "lr": 9.976836557538234e-06, "epoch": 0.07998182231311066, "percentage": 8.0, "elapsed_time": "2:20:22", "remaining_time": "1 day, 2:54:18"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 550, "loss": 1.8132, "lr": 9.973853250000449e-06, "epoch": 0.081799591002045, "percentage": 8.18, "elapsed_time": "2:23:31", "remaining_time": "1 day, 2:50:41"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 550, "loss": 1.8077, "lr": 9.970689785771798e-06, "epoch": 0.08361735969097932, "percentage": 8.36, "elapsed_time": "2:26:44", "remaining_time": "1 day, 2:47:48"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 550, "loss": 1.8063, "lr": 9.967346279435328e-06, "epoch": 0.08543512837991366, "percentage": 8.55, "elapsed_time": "2:29:54", "remaining_time": "1 day, 2:44:17"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 550, "loss": 1.8036, "lr": 9.963822852095344e-06, "epoch": 0.08725289706884799, "percentage": 8.73, "elapsed_time": "2:33:03", "remaining_time": "1 day, 2:40:45"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 550, "loss": 1.8135, "lr": 9.960119631373023e-06, "epoch": 0.08907066575778232, "percentage": 8.91, "elapsed_time": "2:36:13", "remaining_time": "1 day, 2:37:20"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 550, "loss": 1.8115, "lr": 9.95623675140179e-06, "epoch": 0.09088843444671665, "percentage": 9.09, "elapsed_time": "2:39:24", "remaining_time": "1 day, 2:34:08"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 550, "loss": 1.8087, "lr": 9.952174352822474e-06, "epoch": 0.09270620313565099, "percentage": 9.27, "elapsed_time": "2:42:36", "remaining_time": "1 day, 2:30:56"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 550, "loss": 1.8093, "lr": 9.947932582778188e-06, "epoch": 0.09452397182458531, "percentage": 9.45, "elapsed_time": "2:45:46", "remaining_time": "1 day, 2:27:34"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 550, "loss": 1.8008, "lr": 9.943511594909024e-06, "epoch": 0.09634174051351965, "percentage": 9.64, "elapsed_time": "2:48:59", "remaining_time": "1 day, 2:24:38"}
|
| 54 |
+
{"current_steps": 54, "total_steps": 550, "loss": 1.8075, "lr": 9.938911549346473e-06, "epoch": 0.09815950920245399, "percentage": 9.82, "elapsed_time": "2:52:08", "remaining_time": "1 day, 2:21:05"}
|
| 55 |
+
{"current_steps": 55, "total_steps": 550, "loss": 1.8065, "lr": 9.934132612707631e-06, "epoch": 0.09997727789138833, "percentage": 10.0, "elapsed_time": "2:55:18", "remaining_time": "1 day, 2:17:44"}
|
| 56 |
+
{"current_steps": 56, "total_steps": 550, "loss": 1.8066, "lr": 9.929174958089167e-06, "epoch": 0.10179504658032265, "percentage": 10.18, "elapsed_time": "2:58:28", "remaining_time": "1 day, 2:14:23"}
|
| 57 |
+
{"current_steps": 57, "total_steps": 550, "loss": 1.8089, "lr": 9.924038765061042e-06, "epoch": 0.10361281526925699, "percentage": 10.36, "elapsed_time": "3:01:38", "remaining_time": "1 day, 2:11:03"}
|
| 58 |
+
{"current_steps": 58, "total_steps": 550, "loss": 1.8063, "lr": 9.918724219660013e-06, "epoch": 0.10543058395819133, "percentage": 10.55, "elapsed_time": "3:04:49", "remaining_time": "1 day, 2:07:51"}
|
| 59 |
+
{"current_steps": 59, "total_steps": 550, "loss": 1.7952, "lr": 9.913231514382902e-06, "epoch": 0.10724835264712565, "percentage": 10.73, "elapsed_time": "3:08:02", "remaining_time": "1 day, 2:04:51"}
|
| 60 |
+
{"current_steps": 60, "total_steps": 550, "loss": 1.797, "lr": 9.907560848179607e-06, "epoch": 0.10906612133605999, "percentage": 10.91, "elapsed_time": "3:11:14", "remaining_time": "1 day, 2:01:48"}
|
| 61 |
+
{"current_steps": 61, "total_steps": 550, "loss": 1.7966, "lr": 9.901712426445901e-06, "epoch": 0.11088389002499432, "percentage": 11.09, "elapsed_time": "3:14:24", "remaining_time": "1 day, 1:58:26"}
|
| 62 |
+
{"current_steps": 62, "total_steps": 550, "loss": 1.8097, "lr": 9.895686461016007e-06, "epoch": 0.11270165871392865, "percentage": 11.27, "elapsed_time": "3:17:34", "remaining_time": "1 day, 1:55:04"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 550, "loss": 1.7984, "lr": 9.889483170154903e-06, "epoch": 0.11451942740286299, "percentage": 11.45, "elapsed_time": "3:20:44", "remaining_time": "1 day, 1:51:46"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 550, "loss": 1.8013, "lr": 9.883102778550434e-06, "epoch": 0.11633719609179732, "percentage": 11.64, "elapsed_time": "3:23:54", "remaining_time": "1 day, 1:48:25"}
|
| 65 |
+
{"current_steps": 65, "total_steps": 550, "loss": 1.7993, "lr": 9.876545517305163e-06, "epoch": 0.11815496478073165, "percentage": 11.82, "elapsed_time": "3:27:04", "remaining_time": "1 day, 1:45:04"}
|
| 66 |
+
{"current_steps": 66, "total_steps": 550, "loss": 1.7968, "lr": 9.869811623928001e-06, "epoch": 0.11997273346966598, "percentage": 12.0, "elapsed_time": "3:30:14", "remaining_time": "1 day, 1:41:45"}
|
| 67 |
+
{"current_steps": 67, "total_steps": 550, "loss": 1.7947, "lr": 9.862901342325617e-06, "epoch": 0.12179050215860032, "percentage": 12.18, "elapsed_time": "3:33:25", "remaining_time": "1 day, 1:38:35"}
|
| 68 |
+
{"current_steps": 68, "total_steps": 550, "loss": 1.8011, "lr": 9.855814922793583e-06, "epoch": 0.12360827084753465, "percentage": 12.36, "elapsed_time": "3:36:35", "remaining_time": "1 day, 1:35:12"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 550, "loss": 1.7956, "lr": 9.848552622007326e-06, "epoch": 0.125426039536469, "percentage": 12.55, "elapsed_time": "3:39:44", "remaining_time": "1 day, 1:31:51"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 550, "loss": 1.7961, "lr": 9.841114703012817e-06, "epoch": 0.12724380822540332, "percentage": 12.73, "elapsed_time": "3:42:55", "remaining_time": "1 day, 1:28:35"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 550, "loss": 1.7981, "lr": 9.83350143521706e-06, "epoch": 0.12906157691433764, "percentage": 12.91, "elapsed_time": "3:46:06", "remaining_time": "1 day, 1:25:26"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 550, "loss": 1.8042, "lr": 9.82571309437831e-06, "epoch": 0.130879345603272, "percentage": 13.09, "elapsed_time": "3:49:17", "remaining_time": "1 day, 1:22:11"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 550, "loss": 1.793, "lr": 9.817749962596115e-06, "epoch": 0.13269711429220632, "percentage": 13.27, "elapsed_time": "3:52:27", "remaining_time": "1 day, 1:18:54"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 550, "loss": 1.8074, "lr": 9.809612328301071e-06, "epoch": 0.13451488298114064, "percentage": 13.45, "elapsed_time": "3:55:36", "remaining_time": "1 day, 1:15:31"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 550, "loss": 1.7973, "lr": 9.801300486244385e-06, "epoch": 0.136332651670075, "percentage": 13.64, "elapsed_time": "3:58:45", "remaining_time": "1 day, 1:12:07"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 550, "loss": 1.7973, "lr": 9.792814737487207e-06, "epoch": 0.13815042035900932, "percentage": 13.82, "elapsed_time": "4:01:54", "remaining_time": "1 day, 1:08:47"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 550, "loss": 1.7986, "lr": 9.784155389389713e-06, "epoch": 0.13996818904794364, "percentage": 14.0, "elapsed_time": "4:05:04", "remaining_time": "1 day, 1:05:24"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 550, "loss": 1.7937, "lr": 9.775322755599979e-06, "epoch": 0.141785957736878, "percentage": 14.18, "elapsed_time": "4:08:13", "remaining_time": "1 day, 1:02:02"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 550, "loss": 1.7976, "lr": 9.766317156042615e-06, "epoch": 0.14360372642581232, "percentage": 14.36, "elapsed_time": "4:11:21", "remaining_time": "1 day, 0:58:37"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 550, "loss": 1.7915, "lr": 9.757138916907184e-06, "epoch": 0.14542149511474664, "percentage": 14.55, "elapsed_time": "4:14:31", "remaining_time": "1 day, 0:55:21"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 550, "loss": 1.8053, "lr": 9.747788370636389e-06, "epoch": 0.147239263803681, "percentage": 14.73, "elapsed_time": "4:17:40", "remaining_time": "1 day, 0:52:00"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 550, "loss": 1.7908, "lr": 9.738265855914014e-06, "epoch": 0.14905703249261532, "percentage": 14.91, "elapsed_time": "4:20:50", "remaining_time": "1 day, 0:48:42"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 550, "loss": 1.7888, "lr": 9.728571717652677e-06, "epoch": 0.15087480118154964, "percentage": 15.09, "elapsed_time": "4:23:59", "remaining_time": "1 day, 0:45:22"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 550, "loss": 1.7911, "lr": 9.718706306981332e-06, "epoch": 0.152692569870484, "percentage": 15.27, "elapsed_time": "4:27:08", "remaining_time": "1 day, 0:41:57"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 550, "loss": 1.8017, "lr": 9.708669981232542e-06, "epoch": 0.15451033855941831, "percentage": 15.45, "elapsed_time": "4:30:16", "remaining_time": "1 day, 0:38:31"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 550, "loss": 1.7979, "lr": 9.698463103929542e-06, "epoch": 0.15632810724835264, "percentage": 15.64, "elapsed_time": "4:33:24", "remaining_time": "1 day, 0:35:08"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 550, "loss": 1.7872, "lr": 9.688086044773079e-06, "epoch": 0.158145875937287, "percentage": 15.82, "elapsed_time": "4:36:34", "remaining_time": "1 day, 0:31:54"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 550, "loss": 1.794, "lr": 9.677539179628005e-06, "epoch": 0.1599636446262213, "percentage": 16.0, "elapsed_time": "4:39:43", "remaining_time": "1 day, 0:28:34"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 550, "loss": 1.7981, "lr": 9.66682289050968e-06, "epoch": 0.16178141331515564, "percentage": 16.18, "elapsed_time": "4:42:53", "remaining_time": "1 day, 0:25:20"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 550, "loss": 1.7943, "lr": 9.655937565570124e-06, "epoch": 0.16359918200409, "percentage": 16.36, "elapsed_time": "4:46:05", "remaining_time": "1 day, 0:22:15"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 550, "loss": 1.7873, "lr": 9.644883599083959e-06, "epoch": 0.1654169506930243, "percentage": 16.55, "elapsed_time": "4:49:15", "remaining_time": "1 day, 0:19:01"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 550, "loss": 1.7959, "lr": 9.63366139143413e-06, "epoch": 0.16723471938195864, "percentage": 16.73, "elapsed_time": "4:52:27", "remaining_time": "1 day, 0:15:54"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 550, "loss": 1.7883, "lr": 9.622271349097413e-06, "epoch": 0.169052488070893, "percentage": 16.91, "elapsed_time": "4:55:38", "remaining_time": "1 day, 0:12:47"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 550, "loss": 1.7864, "lr": 9.610713884629667e-06, "epoch": 0.1708702567598273, "percentage": 17.09, "elapsed_time": "4:58:50", "remaining_time": "1 day, 0:09:41"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 550, "loss": 1.7871, "lr": 9.598989416650915e-06, "epoch": 0.17268802544876163, "percentage": 17.27, "elapsed_time": "5:02:02", "remaining_time": "1 day, 0:06:36"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 550, "loss": 1.7804, "lr": 9.587098369830171e-06, "epoch": 0.17450579413769599, "percentage": 17.45, "elapsed_time": "5:05:15", "remaining_time": "1 day, 0:03:36"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 550, "loss": 1.7858, "lr": 9.575041174870062e-06, "epoch": 0.1763235628266303, "percentage": 17.64, "elapsed_time": "5:08:26", "remaining_time": "1 day, 0:00:28"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 550, "loss": 1.7823, "lr": 9.562818268491216e-06, "epoch": 0.17814133151556463, "percentage": 17.82, "elapsed_time": "5:11:39", "remaining_time": "23:57:25"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 550, "loss": 1.7882, "lr": 9.550430093416465e-06, "epoch": 0.17995910020449898, "percentage": 18.0, "elapsed_time": "5:14:48", "remaining_time": "23:54:08"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 550, "loss": 1.7836, "lr": 9.537877098354787e-06, "epoch": 0.1817768688934333, "percentage": 18.18, "elapsed_time": "5:17:58", "remaining_time": "23:50:52"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 550, "loss": 1.7843, "lr": 9.525159737985066e-06, "epoch": 0.18359463758236763, "percentage": 18.36, "elapsed_time": "5:24:39", "remaining_time": "1 day, 0:03:17"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 550, "loss": 1.7835, "lr": 9.512278472939627e-06, "epoch": 0.18541240627130198, "percentage": 18.55, "elapsed_time": "5:27:49", "remaining_time": "23:59:51"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_args.bin
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:b3f7716b5bb67b032e521b14589c540c09ad80ea315f78f0457c4ad79c3ed75e
|
| 3 |
+
size 7672
|