Training in progress, epoch 2
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 sha256:138b613e7264cc31b51c9db306981c994d71fdcb0c835375724354b2d00f2d2e
|
| 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 sha256:87b102fe813e7b580f58c65faa8164fb7484b5fe515ace642b3b3f3ef6a0b334
|
| 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:f2ba5a65db813db2f6c4473d9dd7dea1e94db6b6a06064c861575a07ff88d633
|
| 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 sha256:3431e34015b3507a9f1f6676b9a2d091ae35026fa9878d555be541a18f4d7dda
|
| 3 |
size 1168138808
|
trainer_log.jsonl
CHANGED
|
@@ -54,3 +54,30 @@
|
|
| 54 |
{"current_steps": 530, "total_steps": 810, "loss": 0.6882, "lr": 5e-06, "epoch": 1.9611470860314524, "percentage": 65.43, "elapsed_time": "8:33:23", "remaining_time": "4:31:13"}
|
| 55 |
{"current_steps": 540, "total_steps": 810, "loss": 0.6816, "lr": 5e-06, "epoch": 1.998149861239593, "percentage": 66.67, "elapsed_time": "8:42:58", "remaining_time": "4:21:29"}
|
| 56 |
{"current_steps": 540, "total_steps": 810, "eval_loss": 0.7247459888458252, "epoch": 1.998149861239593, "percentage": 66.67, "elapsed_time": "8:48:10", "remaining_time": "4:24:05"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
{"current_steps": 530, "total_steps": 810, "loss": 0.6882, "lr": 5e-06, "epoch": 1.9611470860314524, "percentage": 65.43, "elapsed_time": "8:33:23", "remaining_time": "4:31:13"}
|
| 55 |
{"current_steps": 540, "total_steps": 810, "loss": 0.6816, "lr": 5e-06, "epoch": 1.998149861239593, "percentage": 66.67, "elapsed_time": "8:42:58", "remaining_time": "4:21:29"}
|
| 56 |
{"current_steps": 540, "total_steps": 810, "eval_loss": 0.7247459888458252, "epoch": 1.998149861239593, "percentage": 66.67, "elapsed_time": "8:48:10", "remaining_time": "4:24:05"}
|
| 57 |
+
{"current_steps": 550, "total_steps": 810, "loss": 0.6817, "lr": 5e-06, "epoch": 2.0351526364477337, "percentage": 67.9, "elapsed_time": "8:58:34", "remaining_time": "4:14:35"}
|
| 58 |
+
{"current_steps": 560, "total_steps": 810, "loss": 0.6302, "lr": 5e-06, "epoch": 2.0721554116558742, "percentage": 69.14, "elapsed_time": "9:08:09", "remaining_time": "4:04:42"}
|
| 59 |
+
{"current_steps": 570, "total_steps": 810, "loss": 0.6333, "lr": 5e-06, "epoch": 2.109158186864015, "percentage": 70.37, "elapsed_time": "9:17:44", "remaining_time": "3:54:50"}
|
| 60 |
+
{"current_steps": 580, "total_steps": 810, "loss": 0.631, "lr": 5e-06, "epoch": 2.1461609620721553, "percentage": 71.6, "elapsed_time": "9:27:19", "remaining_time": "3:44:58"}
|
| 61 |
+
{"current_steps": 590, "total_steps": 810, "loss": 0.6331, "lr": 5e-06, "epoch": 2.183163737280296, "percentage": 72.84, "elapsed_time": "9:36:53", "remaining_time": "3:35:06"}
|
| 62 |
+
{"current_steps": 600, "total_steps": 810, "loss": 0.6352, "lr": 5e-06, "epoch": 2.2201665124884364, "percentage": 74.07, "elapsed_time": "9:46:28", "remaining_time": "3:25:16"}
|
| 63 |
+
{"current_steps": 610, "total_steps": 810, "loss": 0.6324, "lr": 5e-06, "epoch": 2.2571692876965774, "percentage": 75.31, "elapsed_time": "9:56:02", "remaining_time": "3:15:25"}
|
| 64 |
+
{"current_steps": 620, "total_steps": 810, "loss": 0.6373, "lr": 5e-06, "epoch": 2.294172062904718, "percentage": 76.54, "elapsed_time": "10:05:38", "remaining_time": "3:05:35"}
|
| 65 |
+
{"current_steps": 630, "total_steps": 810, "loss": 0.6357, "lr": 5e-06, "epoch": 2.3311748381128585, "percentage": 77.78, "elapsed_time": "10:15:12", "remaining_time": "2:55:46"}
|
| 66 |
+
{"current_steps": 640, "total_steps": 810, "loss": 0.6351, "lr": 5e-06, "epoch": 2.368177613320999, "percentage": 79.01, "elapsed_time": "10:24:46", "remaining_time": "2:45:57"}
|
| 67 |
+
{"current_steps": 650, "total_steps": 810, "loss": 0.6349, "lr": 5e-06, "epoch": 2.4051803885291396, "percentage": 80.25, "elapsed_time": "10:34:23", "remaining_time": "2:36:09"}
|
| 68 |
+
{"current_steps": 660, "total_steps": 810, "loss": 0.632, "lr": 5e-06, "epoch": 2.44218316373728, "percentage": 81.48, "elapsed_time": "10:43:58", "remaining_time": "2:26:21"}
|
| 69 |
+
{"current_steps": 670, "total_steps": 810, "loss": 0.6303, "lr": 5e-06, "epoch": 2.4791859389454207, "percentage": 82.72, "elapsed_time": "10:53:32", "remaining_time": "2:16:33"}
|
| 70 |
+
{"current_steps": 680, "total_steps": 810, "loss": 0.6319, "lr": 5e-06, "epoch": 2.5161887141535617, "percentage": 83.95, "elapsed_time": "11:03:08", "remaining_time": "2:06:46"}
|
| 71 |
+
{"current_steps": 690, "total_steps": 810, "loss": 0.6383, "lr": 5e-06, "epoch": 2.5531914893617023, "percentage": 85.19, "elapsed_time": "11:12:44", "remaining_time": "1:56:59"}
|
| 72 |
+
{"current_steps": 700, "total_steps": 810, "loss": 0.6371, "lr": 5e-06, "epoch": 2.590194264569843, "percentage": 86.42, "elapsed_time": "11:22:21", "remaining_time": "1:47:13"}
|
| 73 |
+
{"current_steps": 710, "total_steps": 810, "loss": 0.6382, "lr": 5e-06, "epoch": 2.6271970397779834, "percentage": 87.65, "elapsed_time": "11:31:58", "remaining_time": "1:37:27"}
|
| 74 |
+
{"current_steps": 720, "total_steps": 810, "loss": 0.6411, "lr": 5e-06, "epoch": 2.664199814986124, "percentage": 88.89, "elapsed_time": "11:41:33", "remaining_time": "1:27:41"}
|
| 75 |
+
{"current_steps": 730, "total_steps": 810, "loss": 0.6369, "lr": 5e-06, "epoch": 2.7012025901942645, "percentage": 90.12, "elapsed_time": "11:51:07", "remaining_time": "1:17:55"}
|
| 76 |
+
{"current_steps": 740, "total_steps": 810, "loss": 0.6348, "lr": 5e-06, "epoch": 2.738205365402405, "percentage": 91.36, "elapsed_time": "12:00:41", "remaining_time": "1:08:10"}
|
| 77 |
+
{"current_steps": 750, "total_steps": 810, "loss": 0.636, "lr": 5e-06, "epoch": 2.7752081406105455, "percentage": 92.59, "elapsed_time": "12:10:16", "remaining_time": "0:58:25"}
|
| 78 |
+
{"current_steps": 760, "total_steps": 810, "loss": 0.6396, "lr": 5e-06, "epoch": 2.8122109158186865, "percentage": 93.83, "elapsed_time": "12:19:51", "remaining_time": "0:48:40"}
|
| 79 |
+
{"current_steps": 770, "total_steps": 810, "loss": 0.639, "lr": 5e-06, "epoch": 2.849213691026827, "percentage": 95.06, "elapsed_time": "12:29:26", "remaining_time": "0:38:55"}
|
| 80 |
+
{"current_steps": 780, "total_steps": 810, "loss": 0.6352, "lr": 5e-06, "epoch": 2.8862164662349676, "percentage": 96.3, "elapsed_time": "12:39:01", "remaining_time": "0:29:11"}
|
| 81 |
+
{"current_steps": 790, "total_steps": 810, "loss": 0.6387, "lr": 5e-06, "epoch": 2.923219241443108, "percentage": 97.53, "elapsed_time": "12:48:35", "remaining_time": "0:19:27"}
|
| 82 |
+
{"current_steps": 800, "total_steps": 810, "loss": 0.6346, "lr": 5e-06, "epoch": 2.9602220166512487, "percentage": 98.77, "elapsed_time": "12:58:10", "remaining_time": "0:09:43"}
|
| 83 |
+
{"current_steps": 810, "total_steps": 810, "loss": 0.6406, "lr": 5e-06, "epoch": 2.9972247918593897, "percentage": 100.0, "elapsed_time": "13:07:44", "remaining_time": "0:00:00"}
|