Training in progress, epoch 3
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 4976698672
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2084a59517cb4a70474be3c1e722ea545e8f68a67d7b68f875e27b733257236e
|
| 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:
|
| 3 |
size 4999802720
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ccfcccb6396c625846c0c26cc6783856f830de7e2d03dd11c3cddcdca1f0747
|
| 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:
|
| 3 |
size 4915916176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e646edcf28ad555b12788babef5e060b514ecbf4291f14d26309a86ac9138928
|
| 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:
|
| 3 |
size 1168138808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f663d9157f48970743403790b72c6614243dea49441a2a896c4e6bc9d2809708
|
| 3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
|
@@ -51,3 +51,29 @@
|
|
| 51 |
{"current_steps": 500, "total_steps": 771, "loss": 0.548, "lr": 5e-06, "epoch": 1.9455252918287937, "percentage": 64.85, "elapsed_time": "8:07:19", "remaining_time": "4:24:07"}
|
| 52 |
{"current_steps": 510, "total_steps": 771, "loss": 0.5559, "lr": 5e-06, "epoch": 1.9844357976653697, "percentage": 66.15, "elapsed_time": "8:16:57", "remaining_time": "4:14:19"}
|
| 53 |
{"current_steps": 514, "total_steps": 771, "eval_loss": 0.5962130427360535, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "8:25:21", "remaining_time": "4:12:40"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
{"current_steps": 500, "total_steps": 771, "loss": 0.548, "lr": 5e-06, "epoch": 1.9455252918287937, "percentage": 64.85, "elapsed_time": "8:07:19", "remaining_time": "4:24:07"}
|
| 52 |
{"current_steps": 510, "total_steps": 771, "loss": 0.5559, "lr": 5e-06, "epoch": 1.9844357976653697, "percentage": 66.15, "elapsed_time": "8:16:57", "remaining_time": "4:14:19"}
|
| 53 |
{"current_steps": 514, "total_steps": 771, "eval_loss": 0.5962130427360535, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "8:25:21", "remaining_time": "4:12:40"}
|
| 54 |
+
{"current_steps": 520, "total_steps": 771, "loss": 0.5269, "lr": 5e-06, "epoch": 2.0233463035019454, "percentage": 67.44, "elapsed_time": "8:32:21", "remaining_time": "4:07:18"}
|
| 55 |
+
{"current_steps": 530, "total_steps": 771, "loss": 0.4971, "lr": 5e-06, "epoch": 2.062256809338521, "percentage": 68.74, "elapsed_time": "8:41:59", "remaining_time": "3:57:21"}
|
| 56 |
+
{"current_steps": 540, "total_steps": 771, "loss": 0.4955, "lr": 5e-06, "epoch": 2.1011673151750974, "percentage": 70.04, "elapsed_time": "8:51:37", "remaining_time": "3:47:24"}
|
| 57 |
+
{"current_steps": 550, "total_steps": 771, "loss": 0.5002, "lr": 5e-06, "epoch": 2.140077821011673, "percentage": 71.34, "elapsed_time": "9:01:15", "remaining_time": "3:37:29"}
|
| 58 |
+
{"current_steps": 560, "total_steps": 771, "loss": 0.5012, "lr": 5e-06, "epoch": 2.178988326848249, "percentage": 72.63, "elapsed_time": "9:10:54", "remaining_time": "3:27:34"}
|
| 59 |
+
{"current_steps": 570, "total_steps": 771, "loss": 0.4955, "lr": 5e-06, "epoch": 2.217898832684825, "percentage": 73.93, "elapsed_time": "9:20:32", "remaining_time": "3:17:39"}
|
| 60 |
+
{"current_steps": 580, "total_steps": 771, "loss": 0.5055, "lr": 5e-06, "epoch": 2.2568093385214008, "percentage": 75.23, "elapsed_time": "9:30:08", "remaining_time": "3:07:45"}
|
| 61 |
+
{"current_steps": 590, "total_steps": 771, "loss": 0.503, "lr": 5e-06, "epoch": 2.2957198443579765, "percentage": 76.52, "elapsed_time": "9:39:48", "remaining_time": "2:57:52"}
|
| 62 |
+
{"current_steps": 600, "total_steps": 771, "loss": 0.5027, "lr": 5e-06, "epoch": 2.3346303501945527, "percentage": 77.82, "elapsed_time": "9:49:27", "remaining_time": "2:47:59"}
|
| 63 |
+
{"current_steps": 610, "total_steps": 771, "loss": 0.497, "lr": 5e-06, "epoch": 2.3735408560311284, "percentage": 79.12, "elapsed_time": "9:59:05", "remaining_time": "2:38:07"}
|
| 64 |
+
{"current_steps": 620, "total_steps": 771, "loss": 0.4932, "lr": 5e-06, "epoch": 2.412451361867704, "percentage": 80.42, "elapsed_time": "10:08:44", "remaining_time": "2:28:15"}
|
| 65 |
+
{"current_steps": 630, "total_steps": 771, "loss": 0.5024, "lr": 5e-06, "epoch": 2.4513618677042803, "percentage": 81.71, "elapsed_time": "10:18:22", "remaining_time": "2:18:23"}
|
| 66 |
+
{"current_steps": 640, "total_steps": 771, "loss": 0.4985, "lr": 5e-06, "epoch": 2.490272373540856, "percentage": 83.01, "elapsed_time": "10:28:00", "remaining_time": "2:08:32"}
|
| 67 |
+
{"current_steps": 650, "total_steps": 771, "loss": 0.5107, "lr": 5e-06, "epoch": 2.529182879377432, "percentage": 84.31, "elapsed_time": "10:37:38", "remaining_time": "1:58:42"}
|
| 68 |
+
{"current_steps": 660, "total_steps": 771, "loss": 0.4941, "lr": 5e-06, "epoch": 2.5680933852140075, "percentage": 85.6, "elapsed_time": "10:47:18", "remaining_time": "1:48:51"}
|
| 69 |
+
{"current_steps": 670, "total_steps": 771, "loss": 0.5018, "lr": 5e-06, "epoch": 2.6070038910505837, "percentage": 86.9, "elapsed_time": "10:56:57", "remaining_time": "1:39:01"}
|
| 70 |
+
{"current_steps": 680, "total_steps": 771, "loss": 0.5104, "lr": 5e-06, "epoch": 2.6459143968871595, "percentage": 88.2, "elapsed_time": "11:06:35", "remaining_time": "1:29:12"}
|
| 71 |
+
{"current_steps": 690, "total_steps": 771, "loss": 0.4999, "lr": 5e-06, "epoch": 2.6848249027237356, "percentage": 89.49, "elapsed_time": "11:16:14", "remaining_time": "1:19:23"}
|
| 72 |
+
{"current_steps": 700, "total_steps": 771, "loss": 0.5009, "lr": 5e-06, "epoch": 2.7237354085603114, "percentage": 90.79, "elapsed_time": "11:25:53", "remaining_time": "1:09:34"}
|
| 73 |
+
{"current_steps": 710, "total_steps": 771, "loss": 0.5055, "lr": 5e-06, "epoch": 2.762645914396887, "percentage": 92.09, "elapsed_time": "11:35:32", "remaining_time": "0:59:45"}
|
| 74 |
+
{"current_steps": 720, "total_steps": 771, "loss": 0.5075, "lr": 5e-06, "epoch": 2.801556420233463, "percentage": 93.39, "elapsed_time": "11:45:11", "remaining_time": "0:49:57"}
|
| 75 |
+
{"current_steps": 730, "total_steps": 771, "loss": 0.4927, "lr": 5e-06, "epoch": 2.840466926070039, "percentage": 94.68, "elapsed_time": "11:54:50", "remaining_time": "0:40:08"}
|
| 76 |
+
{"current_steps": 740, "total_steps": 771, "loss": 0.51, "lr": 5e-06, "epoch": 2.8793774319066148, "percentage": 95.98, "elapsed_time": "12:04:28", "remaining_time": "0:30:20"}
|
| 77 |
+
{"current_steps": 750, "total_steps": 771, "loss": 0.4998, "lr": 5e-06, "epoch": 2.9182879377431905, "percentage": 97.28, "elapsed_time": "12:14:08", "remaining_time": "0:20:33"}
|
| 78 |
+
{"current_steps": 760, "total_steps": 771, "loss": 0.5119, "lr": 5e-06, "epoch": 2.9571984435797667, "percentage": 98.57, "elapsed_time": "12:23:48", "remaining_time": "0:10:45"}
|
| 79 |
+
{"current_steps": 770, "total_steps": 771, "loss": 0.5053, "lr": 5e-06, "epoch": 2.9961089494163424, "percentage": 99.87, "elapsed_time": "12:33:28", "remaining_time": "0:00:58"}
|