sedrickkeh
commited on
Commit
•
f40fa5b
1
Parent(s):
4e31465
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:
|
3 |
size 4877660776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27ad665f470504e9db848d6dcb809104f181cfc6cf49d32bd33f4f263095a84d
|
3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4932751008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88828ac4a2b80c860ab7cac4c7948ec32aca7f5b7b57e575ce7d7b1b7d15e4eb
|
3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4330865200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a963fd3be8396e15f6a84011744db43c4935d72154621fae1b156ed0a2df811
|
3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1089994880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:731ce75386a65aa48026737f16b75c06aacdfc403ff17a3178d9585b304fab81
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -43,3 +43,47 @@
|
|
43 |
{"current_steps": 430, "total_steps": 1314, "loss": 0.6345, "learning_rate": 5e-06, "epoch": 0.98005698005698, "percentage": 32.72, "elapsed_time": "6:16:41", "remaining_time": "12:54:23"}
|
44 |
{"current_steps": 438, "total_steps": 1314, "eval_loss": 0.6251533031463623, "epoch": 0.9982905982905983, "percentage": 33.33, "elapsed_time": "6:31:31", "remaining_time": "13:03:02"}
|
45 |
{"current_steps": 440, "total_steps": 1314, "loss": 0.6472, "learning_rate": 5e-06, "epoch": 1.0034188034188034, "percentage": 33.49, "elapsed_time": "6:33:56", "remaining_time": "13:02:30"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
{"current_steps": 430, "total_steps": 1314, "loss": 0.6345, "learning_rate": 5e-06, "epoch": 0.98005698005698, "percentage": 32.72, "elapsed_time": "6:16:41", "remaining_time": "12:54:23"}
|
44 |
{"current_steps": 438, "total_steps": 1314, "eval_loss": 0.6251533031463623, "epoch": 0.9982905982905983, "percentage": 33.33, "elapsed_time": "6:31:31", "remaining_time": "13:03:02"}
|
45 |
{"current_steps": 440, "total_steps": 1314, "loss": 0.6472, "learning_rate": 5e-06, "epoch": 1.0034188034188034, "percentage": 33.49, "elapsed_time": "6:33:56", "remaining_time": "13:02:30"}
|
46 |
+
{"current_steps": 450, "total_steps": 1314, "loss": 0.6017, "learning_rate": 5e-06, "epoch": 1.0262108262108263, "percentage": 34.25, "elapsed_time": "6:42:41", "remaining_time": "12:53:10"}
|
47 |
+
{"current_steps": 460, "total_steps": 1314, "loss": 0.5955, "learning_rate": 5e-06, "epoch": 1.049002849002849, "percentage": 35.01, "elapsed_time": "6:51:28", "remaining_time": "12:43:54"}
|
48 |
+
{"current_steps": 470, "total_steps": 1314, "loss": 0.5964, "learning_rate": 5e-06, "epoch": 1.0717948717948718, "percentage": 35.77, "elapsed_time": "7:00:14", "remaining_time": "12:34:38"}
|
49 |
+
{"current_steps": 480, "total_steps": 1314, "loss": 0.6038, "learning_rate": 5e-06, "epoch": 1.0945868945868946, "percentage": 36.53, "elapsed_time": "7:09:00", "remaining_time": "12:25:24"}
|
50 |
+
{"current_steps": 490, "total_steps": 1314, "loss": 0.6089, "learning_rate": 5e-06, "epoch": 1.1173789173789175, "percentage": 37.29, "elapsed_time": "7:17:47", "remaining_time": "12:16:12"}
|
51 |
+
{"current_steps": 500, "total_steps": 1314, "loss": 0.5987, "learning_rate": 5e-06, "epoch": 1.1401709401709401, "percentage": 38.05, "elapsed_time": "7:26:34", "remaining_time": "12:07:01"}
|
52 |
+
{"current_steps": 510, "total_steps": 1314, "loss": 0.5966, "learning_rate": 5e-06, "epoch": 1.162962962962963, "percentage": 38.81, "elapsed_time": "7:35:22", "remaining_time": "11:57:52"}
|
53 |
+
{"current_steps": 520, "total_steps": 1314, "loss": 0.6023, "learning_rate": 5e-06, "epoch": 1.1857549857549858, "percentage": 39.57, "elapsed_time": "7:44:07", "remaining_time": "11:48:40"}
|
54 |
+
{"current_steps": 530, "total_steps": 1314, "loss": 0.5953, "learning_rate": 5e-06, "epoch": 1.2085470085470085, "percentage": 40.33, "elapsed_time": "7:52:52", "remaining_time": "11:39:30"}
|
55 |
+
{"current_steps": 540, "total_steps": 1314, "loss": 0.6056, "learning_rate": 5e-06, "epoch": 1.2313390313390313, "percentage": 41.1, "elapsed_time": "8:01:39", "remaining_time": "11:30:23"}
|
56 |
+
{"current_steps": 550, "total_steps": 1314, "loss": 0.6022, "learning_rate": 5e-06, "epoch": 1.2541310541310542, "percentage": 41.86, "elapsed_time": "8:10:26", "remaining_time": "11:21:16"}
|
57 |
+
{"current_steps": 560, "total_steps": 1314, "loss": 0.6037, "learning_rate": 5e-06, "epoch": 1.2769230769230768, "percentage": 42.62, "elapsed_time": "8:19:13", "remaining_time": "11:12:10"}
|
58 |
+
{"current_steps": 570, "total_steps": 1314, "loss": 0.5977, "learning_rate": 5e-06, "epoch": 1.2997150997150997, "percentage": 43.38, "elapsed_time": "8:28:00", "remaining_time": "11:03:04"}
|
59 |
+
{"current_steps": 580, "total_steps": 1314, "loss": 0.5962, "learning_rate": 5e-06, "epoch": 1.3225071225071225, "percentage": 44.14, "elapsed_time": "8:36:46", "remaining_time": "10:53:59"}
|
60 |
+
{"current_steps": 590, "total_steps": 1314, "loss": 0.5959, "learning_rate": 5e-06, "epoch": 1.3452991452991454, "percentage": 44.9, "elapsed_time": "8:45:33", "remaining_time": "10:44:54"}
|
61 |
+
{"current_steps": 600, "total_steps": 1314, "loss": 0.6016, "learning_rate": 5e-06, "epoch": 1.368091168091168, "percentage": 45.66, "elapsed_time": "8:54:19", "remaining_time": "10:35:50"}
|
62 |
+
{"current_steps": 610, "total_steps": 1314, "loss": 0.6016, "learning_rate": 5e-06, "epoch": 1.390883190883191, "percentage": 46.42, "elapsed_time": "9:03:05", "remaining_time": "10:26:47"}
|
63 |
+
{"current_steps": 620, "total_steps": 1314, "loss": 0.6041, "learning_rate": 5e-06, "epoch": 1.4136752136752135, "percentage": 47.18, "elapsed_time": "9:11:51", "remaining_time": "10:17:43"}
|
64 |
+
{"current_steps": 630, "total_steps": 1314, "loss": 0.6022, "learning_rate": 5e-06, "epoch": 1.4364672364672364, "percentage": 47.95, "elapsed_time": "9:20:38", "remaining_time": "10:08:41"}
|
65 |
+
{"current_steps": 640, "total_steps": 1314, "loss": 0.597, "learning_rate": 5e-06, "epoch": 1.4592592592592593, "percentage": 48.71, "elapsed_time": "9:29:25", "remaining_time": "9:59:40"}
|
66 |
+
{"current_steps": 650, "total_steps": 1314, "loss": 0.5949, "learning_rate": 5e-06, "epoch": 1.4820512820512821, "percentage": 49.47, "elapsed_time": "9:38:11", "remaining_time": "9:50:38"}
|
67 |
+
{"current_steps": 660, "total_steps": 1314, "loss": 0.5946, "learning_rate": 5e-06, "epoch": 1.504843304843305, "percentage": 50.23, "elapsed_time": "9:46:58", "remaining_time": "9:41:38"}
|
68 |
+
{"current_steps": 670, "total_steps": 1314, "loss": 0.6023, "learning_rate": 5e-06, "epoch": 1.5276353276353276, "percentage": 50.99, "elapsed_time": "9:55:44", "remaining_time": "9:32:37"}
|
69 |
+
{"current_steps": 680, "total_steps": 1314, "loss": 0.5908, "learning_rate": 5e-06, "epoch": 1.5504273504273505, "percentage": 51.75, "elapsed_time": "10:04:30", "remaining_time": "9:23:36"}
|
70 |
+
{"current_steps": 690, "total_steps": 1314, "loss": 0.5948, "learning_rate": 5e-06, "epoch": 1.573219373219373, "percentage": 52.51, "elapsed_time": "10:13:15", "remaining_time": "9:14:35"}
|
71 |
+
{"current_steps": 700, "total_steps": 1314, "loss": 0.6103, "learning_rate": 5e-06, "epoch": 1.596011396011396, "percentage": 53.27, "elapsed_time": "10:22:02", "remaining_time": "9:05:36"}
|
72 |
+
{"current_steps": 710, "total_steps": 1314, "loss": 0.5973, "learning_rate": 5e-06, "epoch": 1.6188034188034188, "percentage": 54.03, "elapsed_time": "10:30:48", "remaining_time": "8:56:38"}
|
73 |
+
{"current_steps": 720, "total_steps": 1314, "loss": 0.602, "learning_rate": 5e-06, "epoch": 1.6415954415954417, "percentage": 54.79, "elapsed_time": "10:39:34", "remaining_time": "8:47:38"}
|
74 |
+
{"current_steps": 730, "total_steps": 1314, "loss": 0.5951, "learning_rate": 5e-06, "epoch": 1.6643874643874645, "percentage": 55.56, "elapsed_time": "10:48:20", "remaining_time": "8:38:40"}
|
75 |
+
{"current_steps": 740, "total_steps": 1314, "loss": 0.5962, "learning_rate": 5e-06, "epoch": 1.6871794871794872, "percentage": 56.32, "elapsed_time": "10:57:06", "remaining_time": "8:29:42"}
|
76 |
+
{"current_steps": 750, "total_steps": 1314, "loss": 0.5935, "learning_rate": 5e-06, "epoch": 1.7099715099715098, "percentage": 57.08, "elapsed_time": "11:05:52", "remaining_time": "8:20:44"}
|
77 |
+
{"current_steps": 760, "total_steps": 1314, "loss": 0.5975, "learning_rate": 5e-06, "epoch": 1.7327635327635327, "percentage": 57.84, "elapsed_time": "11:14:38", "remaining_time": "8:11:46"}
|
78 |
+
{"current_steps": 770, "total_steps": 1314, "loss": 0.5939, "learning_rate": 5e-06, "epoch": 1.7555555555555555, "percentage": 58.6, "elapsed_time": "11:23:23", "remaining_time": "8:02:48"}
|
79 |
+
{"current_steps": 780, "total_steps": 1314, "loss": 0.601, "learning_rate": 5e-06, "epoch": 1.7783475783475784, "percentage": 59.36, "elapsed_time": "11:32:10", "remaining_time": "7:53:52"}
|
80 |
+
{"current_steps": 790, "total_steps": 1314, "loss": 0.5985, "learning_rate": 5e-06, "epoch": 1.8011396011396013, "percentage": 60.12, "elapsed_time": "11:40:54", "remaining_time": "7:44:54"}
|
81 |
+
{"current_steps": 800, "total_steps": 1314, "loss": 0.5854, "learning_rate": 5e-06, "epoch": 1.823931623931624, "percentage": 60.88, "elapsed_time": "11:49:40", "remaining_time": "7:35:58"}
|
82 |
+
{"current_steps": 810, "total_steps": 1314, "loss": 0.5932, "learning_rate": 5e-06, "epoch": 1.8467236467236468, "percentage": 61.64, "elapsed_time": "11:58:25", "remaining_time": "7:27:01"}
|
83 |
+
{"current_steps": 820, "total_steps": 1314, "loss": 0.591, "learning_rate": 5e-06, "epoch": 1.8695156695156694, "percentage": 62.4, "elapsed_time": "12:07:11", "remaining_time": "7:18:05"}
|
84 |
+
{"current_steps": 830, "total_steps": 1314, "loss": 0.5948, "learning_rate": 5e-06, "epoch": 1.8923076923076922, "percentage": 63.17, "elapsed_time": "12:15:57", "remaining_time": "7:09:09"}
|
85 |
+
{"current_steps": 840, "total_steps": 1314, "loss": 0.5992, "learning_rate": 5e-06, "epoch": 1.915099715099715, "percentage": 63.93, "elapsed_time": "12:24:45", "remaining_time": "7:00:15"}
|
86 |
+
{"current_steps": 850, "total_steps": 1314, "loss": 0.5974, "learning_rate": 5e-06, "epoch": 1.937891737891738, "percentage": 64.69, "elapsed_time": "12:33:32", "remaining_time": "6:51:20"}
|
87 |
+
{"current_steps": 860, "total_steps": 1314, "loss": 0.5987, "learning_rate": 5e-06, "epoch": 1.9606837606837608, "percentage": 65.45, "elapsed_time": "12:42:19", "remaining_time": "6:42:26"}
|
88 |
+
{"current_steps": 870, "total_steps": 1314, "loss": 0.5961, "learning_rate": 5e-06, "epoch": 1.9834757834757835, "percentage": 66.21, "elapsed_time": "12:51:05", "remaining_time": "6:33:31"}
|
89 |
+
{"current_steps": 877, "total_steps": 1314, "eval_loss": 0.6187062859535217, "epoch": 1.9994301994301993, "percentage": 66.74, "elapsed_time": "13:04:31", "remaining_time": "6:30:55"}
|