Training in progress, step 2600
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 4902257696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a375fe86d663ca4e5e17fcfc38cae241b677039228f4d00a63b2a53800fb68ad
|
| 3 |
size 4902257696
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915960368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa6ab39e372275385dcff9f8a0f79be2922242203fe5bf9a444dcbcbf564863d
|
| 3 |
size 4915960368
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4983068496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d64dc3d8afa7e6b0a9ee99b5a6d0248ec3d5a10a8f9dd7bdc20a3ddec0990939
|
| 3 |
size 4983068496
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1580230264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9453cf53d89d8caaefabc9cafbee19e9d8b9420c3675b179fd429a000882092
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -478,3 +478,43 @@
|
|
| 478 |
{"current_steps": 2390, "total_steps": 4340, "loss": 0.4846, "lr": 1.9967828046095945e-05, "epoch": 3.8548387096774195, "percentage": 55.07, "elapsed_time": "11:47:14", "remaining_time": "9:37:02"}
|
| 479 |
{"current_steps": 2395, "total_steps": 4340, "loss": 0.491, "lr": 1.988739870764869e-05, "epoch": 3.8629032258064515, "percentage": 55.18, "elapsed_time": "11:48:47", "remaining_time": "9:35:36"}
|
| 480 |
{"current_steps": 2400, "total_steps": 4340, "loss": 0.5053, "lr": 1.9806971190235485e-05, "epoch": 3.870967741935484, "percentage": 55.3, "elapsed_time": "11:50:20", "remaining_time": "9:34:11"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 478 |
{"current_steps": 2390, "total_steps": 4340, "loss": 0.4846, "lr": 1.9967828046095945e-05, "epoch": 3.8548387096774195, "percentage": 55.07, "elapsed_time": "11:47:14", "remaining_time": "9:37:02"}
|
| 479 |
{"current_steps": 2395, "total_steps": 4340, "loss": 0.491, "lr": 1.988739870764869e-05, "epoch": 3.8629032258064515, "percentage": 55.18, "elapsed_time": "11:48:47", "remaining_time": "9:35:36"}
|
| 480 |
{"current_steps": 2400, "total_steps": 4340, "loss": 0.5053, "lr": 1.9806971190235485e-05, "epoch": 3.870967741935484, "percentage": 55.3, "elapsed_time": "11:50:20", "remaining_time": "9:34:11"}
|
| 481 |
+
{"current_steps": 2405, "total_steps": 4340, "loss": 0.4951, "lr": 1.972654679456295e-05, "epoch": 3.879032258064516, "percentage": 55.41, "elapsed_time": "11:53:27", "remaining_time": "9:34:01"}
|
| 482 |
+
{"current_steps": 2410, "total_steps": 4340, "loss": 0.491, "lr": 1.9646126821287245e-05, "epoch": 3.8870967741935485, "percentage": 55.53, "elapsed_time": "11:54:59", "remaining_time": "9:32:34"}
|
| 483 |
+
{"current_steps": 2415, "total_steps": 4340, "loss": 0.5023, "lr": 1.9565712570992988e-05, "epoch": 3.8951612903225805, "percentage": 55.65, "elapsed_time": "11:56:29", "remaining_time": "9:31:07"}
|
| 484 |
+
{"current_steps": 2420, "total_steps": 4340, "loss": 0.4887, "lr": 1.948530534417225e-05, "epoch": 3.903225806451613, "percentage": 55.76, "elapsed_time": "11:57:58", "remaining_time": "9:29:37"}
|
| 485 |
+
{"current_steps": 2425, "total_steps": 4340, "loss": 0.5006, "lr": 1.9404906441203512e-05, "epoch": 3.911290322580645, "percentage": 55.88, "elapsed_time": "11:59:23", "remaining_time": "9:28:05"}
|
| 486 |
+
{"current_steps": 2430, "total_steps": 4340, "loss": 0.5004, "lr": 1.932451716233064e-05, "epoch": 3.9193548387096775, "percentage": 55.99, "elapsed_time": "12:00:53", "remaining_time": "9:26:37"}
|
| 487 |
+
{"current_steps": 2435, "total_steps": 4340, "loss": 0.4937, "lr": 1.9244138807641858e-05, "epoch": 3.9274193548387095, "percentage": 56.11, "elapsed_time": "12:02:07", "remaining_time": "9:24:57"}
|
| 488 |
+
{"current_steps": 2440, "total_steps": 4340, "loss": 0.5052, "lr": 1.9163772677048716e-05, "epoch": 3.935483870967742, "percentage": 56.22, "elapsed_time": "12:03:32", "remaining_time": "9:23:24"}
|
| 489 |
+
{"current_steps": 2445, "total_steps": 4340, "loss": 0.4966, "lr": 1.9083420070265065e-05, "epoch": 3.943548387096774, "percentage": 56.34, "elapsed_time": "12:05:06", "remaining_time": "9:21:59"}
|
| 490 |
+
{"current_steps": 2450, "total_steps": 4340, "loss": 0.4944, "lr": 1.9003082286786056e-05, "epoch": 3.9516129032258065, "percentage": 56.45, "elapsed_time": "12:06:24", "remaining_time": "9:20:22"}
|
| 491 |
+
{"current_steps": 2455, "total_steps": 4340, "loss": 0.5076, "lr": 1.8922760625867114e-05, "epoch": 3.959677419354839, "percentage": 56.57, "elapsed_time": "12:07:43", "remaining_time": "9:18:45"}
|
| 492 |
+
{"current_steps": 2460, "total_steps": 4340, "loss": 0.4927, "lr": 1.8842456386502907e-05, "epoch": 3.967741935483871, "percentage": 56.68, "elapsed_time": "12:09:03", "remaining_time": "9:17:09"}
|
| 493 |
+
{"current_steps": 2465, "total_steps": 4340, "loss": 0.4904, "lr": 1.8762170867406366e-05, "epoch": 3.975806451612903, "percentage": 56.8, "elapsed_time": "12:10:22", "remaining_time": "9:15:33"}
|
| 494 |
+
{"current_steps": 2470, "total_steps": 4340, "loss": 0.4977, "lr": 1.868190536698766e-05, "epoch": 3.9838709677419355, "percentage": 56.91, "elapsed_time": "12:11:50", "remaining_time": "9:14:03"}
|
| 495 |
+
{"current_steps": 2475, "total_steps": 4340, "loss": 0.4853, "lr": 1.860166118333323e-05, "epoch": 3.991935483870968, "percentage": 57.03, "elapsed_time": "12:13:10", "remaining_time": "9:12:28"}
|
| 496 |
+
{"current_steps": 2480, "total_steps": 4340, "loss": 0.4871, "lr": 1.852143961418474e-05, "epoch": 4.0, "percentage": 57.14, "elapsed_time": "12:14:46", "remaining_time": "9:11:05"}
|
| 497 |
+
{"current_steps": 2485, "total_steps": 4340, "loss": 0.4516, "lr": 1.844124195691816e-05, "epoch": 4.008064516129032, "percentage": 57.26, "elapsed_time": "12:15:57", "remaining_time": "9:09:22"}
|
| 498 |
+
{"current_steps": 2490, "total_steps": 4340, "loss": 0.4398, "lr": 1.8361069508522716e-05, "epoch": 4.016129032258065, "percentage": 57.37, "elapsed_time": "12:17:29", "remaining_time": "9:07:56"}
|
| 499 |
+
{"current_steps": 2495, "total_steps": 4340, "loss": 0.4605, "lr": 1.828092356557996e-05, "epoch": 4.024193548387097, "percentage": 57.49, "elapsed_time": "12:18:45", "remaining_time": "9:06:17"}
|
| 500 |
+
{"current_steps": 2500, "total_steps": 4340, "loss": 0.4388, "lr": 1.820080542424278e-05, "epoch": 4.032258064516129, "percentage": 57.6, "elapsed_time": "12:20:16", "remaining_time": "9:04:50"}
|
| 501 |
+
{"current_steps": 2505, "total_steps": 4340, "loss": 0.4353, "lr": 1.812071638021447e-05, "epoch": 4.040322580645161, "percentage": 57.72, "elapsed_time": "12:21:57", "remaining_time": "9:03:30"}
|
| 502 |
+
{"current_steps": 2510, "total_steps": 4340, "loss": 0.4497, "lr": 1.8040657728727714e-05, "epoch": 4.048387096774194, "percentage": 57.83, "elapsed_time": "12:23:41", "remaining_time": "9:02:12"}
|
| 503 |
+
{"current_steps": 2515, "total_steps": 4340, "loss": 0.4674, "lr": 1.7960630764523703e-05, "epoch": 4.056451612903226, "percentage": 57.95, "elapsed_time": "12:24:58", "remaining_time": "9:00:35"}
|
| 504 |
+
{"current_steps": 2520, "total_steps": 4340, "loss": 0.466, "lr": 1.7880636781831148e-05, "epoch": 4.064516129032258, "percentage": 58.06, "elapsed_time": "12:26:17", "remaining_time": "8:58:59"}
|
| 505 |
+
{"current_steps": 2525, "total_steps": 4340, "loss": 0.4521, "lr": 1.7800677074345387e-05, "epoch": 4.07258064516129, "percentage": 58.18, "elapsed_time": "12:28:03", "remaining_time": "8:57:43"}
|
| 506 |
+
{"current_steps": 2530, "total_steps": 4340, "loss": 0.4581, "lr": 1.7720752935207437e-05, "epoch": 4.080645161290323, "percentage": 58.29, "elapsed_time": "12:29:23", "remaining_time": "8:56:07"}
|
| 507 |
+
{"current_steps": 2535, "total_steps": 4340, "loss": 0.4479, "lr": 1.7640865656983084e-05, "epoch": 4.088709677419355, "percentage": 58.41, "elapsed_time": "12:30:43", "remaining_time": "8:54:32"}
|
| 508 |
+
{"current_steps": 2540, "total_steps": 4340, "loss": 0.454, "lr": 1.7561016531642e-05, "epoch": 4.096774193548387, "percentage": 58.53, "elapsed_time": "12:32:10", "remaining_time": "8:53:02"}
|
| 509 |
+
{"current_steps": 2545, "total_steps": 4340, "loss": 0.4412, "lr": 1.748120685053681e-05, "epoch": 4.104838709677419, "percentage": 58.64, "elapsed_time": "12:33:38", "remaining_time": "8:51:33"}
|
| 510 |
+
{"current_steps": 2550, "total_steps": 4340, "loss": 0.4518, "lr": 1.7401437904382252e-05, "epoch": 4.112903225806452, "percentage": 58.76, "elapsed_time": "12:34:58", "remaining_time": "8:49:57"}
|
| 511 |
+
{"current_steps": 2555, "total_steps": 4340, "loss": 0.4592, "lr": 1.7321710983234278e-05, "epoch": 4.120967741935484, "percentage": 58.87, "elapsed_time": "12:36:19", "remaining_time": "8:48:23"}
|
| 512 |
+
{"current_steps": 2560, "total_steps": 4340, "loss": 0.4556, "lr": 1.7242027376469183e-05, "epoch": 4.129032258064516, "percentage": 58.99, "elapsed_time": "12:37:48", "remaining_time": "8:46:55"}
|
| 513 |
+
{"current_steps": 2565, "total_steps": 4340, "loss": 0.444, "lr": 1.7162388372762775e-05, "epoch": 4.137096774193548, "percentage": 59.1, "elapsed_time": "12:39:18", "remaining_time": "8:45:26"}
|
| 514 |
+
{"current_steps": 2570, "total_steps": 4340, "loss": 0.4585, "lr": 1.7082795260069515e-05, "epoch": 4.145161290322581, "percentage": 59.22, "elapsed_time": "12:40:33", "remaining_time": "8:43:48"}
|
| 515 |
+
{"current_steps": 2575, "total_steps": 4340, "loss": 0.422, "lr": 1.7003249325601712e-05, "epoch": 4.153225806451613, "percentage": 59.33, "elapsed_time": "12:42:20", "remaining_time": "8:42:32"}
|
| 516 |
+
{"current_steps": 2580, "total_steps": 4340, "loss": 0.4279, "lr": 1.6923751855808664e-05, "epoch": 4.161290322580645, "percentage": 59.45, "elapsed_time": "12:43:58", "remaining_time": "8:41:09"}
|
| 517 |
+
{"current_steps": 2585, "total_steps": 4340, "loss": 0.4436, "lr": 1.6844304136355894e-05, "epoch": 4.169354838709677, "percentage": 59.56, "elapsed_time": "12:45:29", "remaining_time": "8:39:42"}
|
| 518 |
+
{"current_steps": 2590, "total_steps": 4340, "loss": 0.4384, "lr": 1.6764907452104352e-05, "epoch": 4.17741935483871, "percentage": 59.68, "elapsed_time": "12:46:52", "remaining_time": "8:38:09"}
|
| 519 |
+
{"current_steps": 2595, "total_steps": 4340, "loss": 0.4482, "lr": 1.6685563087089597e-05, "epoch": 4.185483870967742, "percentage": 59.79, "elapsed_time": "12:48:13", "remaining_time": "8:36:35"}
|
| 520 |
+
{"current_steps": 2600, "total_steps": 4340, "loss": 0.4447, "lr": 1.6606272324501087e-05, "epoch": 4.193548387096774, "percentage": 59.91, "elapsed_time": "12:49:51", "remaining_time": "8:35:12"}
|