Training in progress, step 2400
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:e943f2ec5c0b3c8f04bbdc6faad7ae424102d4a5aa351318e0d67e12d33ee62f
|
| 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:ecb4d42698662ac5a728181930928e290f59b74617f356d535578b17ddfc6481
|
| 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 sha256:88b9f16e82085876ee3d43dc05fe696480e7cbb09d2932c3d6728f0f5048ba15
|
| 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 sha256:14cf05a9ea20c4ce12ca8a995313b42594aadca7a69e39e7507a5f3580d64828
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -438,3 +438,43 @@
|
|
| 438 |
{"current_steps": 2190, "total_steps": 4340, "loss": 0.4942, "lr": 2.317157932441167e-05, "epoch": 3.532258064516129, "percentage": 50.46, "elapsed_time": "10:47:38", "remaining_time": "10:35:49"}
|
| 439 |
{"current_steps": 2195, "total_steps": 4340, "loss": 0.4843, "lr": 2.3092141709236388e-05, "epoch": 3.540322580645161, "percentage": 50.58, "elapsed_time": "10:49:11", "remaining_time": "10:34:24"}
|
| 440 |
{"current_steps": 2200, "total_steps": 4340, "loss": 0.4941, "lr": 2.3012654086683605e-05, "epoch": 3.5483870967741935, "percentage": 50.69, "elapsed_time": "10:50:36", "remaining_time": "10:32:51"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 438 |
{"current_steps": 2190, "total_steps": 4340, "loss": 0.4942, "lr": 2.317157932441167e-05, "epoch": 3.532258064516129, "percentage": 50.46, "elapsed_time": "10:47:38", "remaining_time": "10:35:49"}
|
| 439 |
{"current_steps": 2195, "total_steps": 4340, "loss": 0.4843, "lr": 2.3092141709236388e-05, "epoch": 3.540322580645161, "percentage": 50.58, "elapsed_time": "10:49:11", "remaining_time": "10:34:24"}
|
| 440 |
{"current_steps": 2200, "total_steps": 4340, "loss": 0.4941, "lr": 2.3012654086683605e-05, "epoch": 3.5483870967741935, "percentage": 50.69, "elapsed_time": "10:50:36", "remaining_time": "10:32:51"}
|
| 441 |
+
{"current_steps": 2205, "total_steps": 4340, "loss": 0.5032, "lr": 2.293311774225958e-05, "epoch": 3.556451612903226, "percentage": 50.81, "elapsed_time": "10:53:36", "remaining_time": "10:32:51"}
|
| 442 |
+
{"current_steps": 2210, "total_steps": 4340, "loss": 0.5081, "lr": 2.2853533962258547e-05, "epoch": 3.564516129032258, "percentage": 50.92, "elapsed_time": "10:55:06", "remaining_time": "10:31:23"}
|
| 443 |
+
{"current_steps": 2215, "total_steps": 4340, "loss": 0.4797, "lr": 2.277390403374186e-05, "epoch": 3.5725806451612905, "percentage": 51.04, "elapsed_time": "10:56:39", "remaining_time": "10:29:58"}
|
| 444 |
+
{"current_steps": 2220, "total_steps": 4340, "loss": 0.49, "lr": 2.2694229244517226e-05, "epoch": 3.5806451612903225, "percentage": 51.15, "elapsed_time": "10:58:03", "remaining_time": "10:28:25"}
|
| 445 |
+
{"current_steps": 2225, "total_steps": 4340, "loss": 0.5068, "lr": 2.2614510883117834e-05, "epoch": 3.588709677419355, "percentage": 51.27, "elapsed_time": "10:59:29", "remaining_time": "10:26:52"}
|
| 446 |
+
{"current_steps": 2230, "total_steps": 4340, "loss": 0.4995, "lr": 2.2534750238781566e-05, "epoch": 3.596774193548387, "percentage": 51.38, "elapsed_time": "11:00:54", "remaining_time": "10:25:20"}
|
| 447 |
+
{"current_steps": 2235, "total_steps": 4340, "loss": 0.4936, "lr": 2.2454948601430112e-05, "epoch": 3.6048387096774195, "percentage": 51.5, "elapsed_time": "11:02:09", "remaining_time": "10:23:38"}
|
| 448 |
+
{"current_steps": 2240, "total_steps": 4340, "loss": 0.5061, "lr": 2.2375107261648102e-05, "epoch": 3.6129032258064515, "percentage": 51.61, "elapsed_time": "11:03:31", "remaining_time": "10:22:02"}
|
| 449 |
+
{"current_steps": 2245, "total_steps": 4340, "loss": 0.4996, "lr": 2.229522751066228e-05, "epoch": 3.620967741935484, "percentage": 51.73, "elapsed_time": "11:04:46", "remaining_time": "10:20:21"}
|
| 450 |
+
{"current_steps": 2250, "total_steps": 4340, "loss": 0.5057, "lr": 2.2215310640320555e-05, "epoch": 3.629032258064516, "percentage": 51.84, "elapsed_time": "11:06:19", "remaining_time": "10:18:56"}
|
| 451 |
+
{"current_steps": 2255, "total_steps": 4340, "loss": 0.4881, "lr": 2.213535794307118e-05, "epoch": 3.6370967741935485, "percentage": 51.96, "elapsed_time": "11:07:37", "remaining_time": "10:17:17"}
|
| 452 |
+
{"current_steps": 2260, "total_steps": 4340, "loss": 0.5186, "lr": 2.2055370711941797e-05, "epoch": 3.6451612903225805, "percentage": 52.07, "elapsed_time": "11:09:05", "remaining_time": "10:15:48"}
|
| 453 |
+
{"current_steps": 2265, "total_steps": 4340, "loss": 0.5184, "lr": 2.1975350240518542e-05, "epoch": 3.653225806451613, "percentage": 52.19, "elapsed_time": "11:10:27", "remaining_time": "10:14:13"}
|
| 454 |
+
{"current_steps": 2270, "total_steps": 4340, "loss": 0.4777, "lr": 2.1895297822925138e-05, "epoch": 3.661290322580645, "percentage": 52.3, "elapsed_time": "11:12:14", "remaining_time": "10:13:00"}
|
| 455 |
+
{"current_steps": 2275, "total_steps": 4340, "loss": 0.4792, "lr": 2.1815214753801944e-05, "epoch": 3.6693548387096775, "percentage": 52.42, "elapsed_time": "11:13:32", "remaining_time": "10:11:22"}
|
| 456 |
+
{"current_steps": 2280, "total_steps": 4340, "loss": 0.4875, "lr": 2.173510232828504e-05, "epoch": 3.6774193548387095, "percentage": 52.53, "elapsed_time": "11:14:46", "remaining_time": "10:09:39"}
|
| 457 |
+
{"current_steps": 2285, "total_steps": 4340, "loss": 0.4953, "lr": 2.1654961841985256e-05, "epoch": 3.685483870967742, "percentage": 52.65, "elapsed_time": "11:16:11", "remaining_time": "10:08:07"}
|
| 458 |
+
{"current_steps": 2290, "total_steps": 4340, "loss": 0.5057, "lr": 2.157479459096724e-05, "epoch": 3.693548387096774, "percentage": 52.76, "elapsed_time": "11:17:34", "remaining_time": "10:06:33"}
|
| 459 |
+
{"current_steps": 2295, "total_steps": 4340, "loss": 0.4928, "lr": 2.149460187172849e-05, "epoch": 3.7016129032258065, "percentage": 52.88, "elapsed_time": "11:18:56", "remaining_time": "10:04:58"}
|
| 460 |
+
{"current_steps": 2300, "total_steps": 4340, "loss": 0.4967, "lr": 2.1414384981178377e-05, "epoch": 3.709677419354839, "percentage": 53.0, "elapsed_time": "11:20:32", "remaining_time": "10:03:36"}
|
| 461 |
+
{"current_steps": 2305, "total_steps": 4340, "loss": 0.4876, "lr": 2.13341452166172e-05, "epoch": 3.717741935483871, "percentage": 53.11, "elapsed_time": "11:22:05", "remaining_time": "10:02:11"}
|
| 462 |
+
{"current_steps": 2310, "total_steps": 4340, "loss": 0.4481, "lr": 2.125388387571517e-05, "epoch": 3.725806451612903, "percentage": 53.23, "elapsed_time": "11:23:36", "remaining_time": "10:00:44"}
|
| 463 |
+
{"current_steps": 2315, "total_steps": 4340, "loss": 0.4912, "lr": 2.1173602256491438e-05, "epoch": 3.7338709677419355, "percentage": 53.34, "elapsed_time": "11:24:59", "remaining_time": "9:59:10"}
|
| 464 |
+
{"current_steps": 2320, "total_steps": 4340, "loss": 0.5043, "lr": 2.109330165729311e-05, "epoch": 3.741935483870968, "percentage": 53.46, "elapsed_time": "11:26:23", "remaining_time": "9:57:38"}
|
| 465 |
+
{"current_steps": 2325, "total_steps": 4340, "loss": 0.4934, "lr": 2.1012983376774255e-05, "epoch": 3.75, "percentage": 53.57, "elapsed_time": "11:28:00", "remaining_time": "9:56:16"}
|
| 466 |
+
{"current_steps": 2330, "total_steps": 4340, "loss": 0.523, "lr": 2.0932648713874873e-05, "epoch": 3.758064516129032, "percentage": 53.69, "elapsed_time": "11:29:25", "remaining_time": "9:54:44"}
|
| 467 |
+
{"current_steps": 2335, "total_steps": 4340, "loss": 0.4818, "lr": 2.0852298967799915e-05, "epoch": 3.7661290322580645, "percentage": 53.8, "elapsed_time": "11:30:53", "remaining_time": "9:53:14"}
|
| 468 |
+
{"current_steps": 2340, "total_steps": 4340, "loss": 0.4856, "lr": 2.0771935437998256e-05, "epoch": 3.774193548387097, "percentage": 53.92, "elapsed_time": "11:32:15", "remaining_time": "9:51:40"}
|
| 469 |
+
{"current_steps": 2345, "total_steps": 4340, "loss": 0.5123, "lr": 2.0691559424141694e-05, "epoch": 3.782258064516129, "percentage": 54.03, "elapsed_time": "11:33:29", "remaining_time": "9:49:59"}
|
| 470 |
+
{"current_steps": 2350, "total_steps": 4340, "loss": 0.4881, "lr": 2.0611172226103936e-05, "epoch": 3.790322580645161, "percentage": 54.15, "elapsed_time": "11:35:07", "remaining_time": "9:48:38"}
|
| 471 |
+
{"current_steps": 2355, "total_steps": 4340, "loss": 0.4809, "lr": 2.0530775143939536e-05, "epoch": 3.7983870967741935, "percentage": 54.26, "elapsed_time": "11:36:35", "remaining_time": "9:47:08"}
|
| 472 |
+
{"current_steps": 2360, "total_steps": 4340, "loss": 0.488, "lr": 2.0450369477862922e-05, "epoch": 3.806451612903226, "percentage": 54.38, "elapsed_time": "11:37:58", "remaining_time": "9:45:35"}
|
| 473 |
+
{"current_steps": 2365, "total_steps": 4340, "loss": 0.5134, "lr": 2.036995652822734e-05, "epoch": 3.814516129032258, "percentage": 54.49, "elapsed_time": "11:39:31", "remaining_time": "9:44:09"}
|
| 474 |
+
{"current_steps": 2370, "total_steps": 4340, "loss": 0.4928, "lr": 2.028953759550381e-05, "epoch": 3.8225806451612905, "percentage": 54.61, "elapsed_time": "11:40:59", "remaining_time": "9:42:41"}
|
| 475 |
+
{"current_steps": 2375, "total_steps": 4340, "loss": 0.4996, "lr": 2.0209113980260146e-05, "epoch": 3.8306451612903225, "percentage": 54.72, "elapsed_time": "11:42:24", "remaining_time": "9:41:08"}
|
| 476 |
+
{"current_steps": 2380, "total_steps": 4340, "loss": 0.4864, "lr": 2.012868698313985e-05, "epoch": 3.838709677419355, "percentage": 54.84, "elapsed_time": "11:44:01", "remaining_time": "9:39:46"}
|
| 477 |
+
{"current_steps": 2385, "total_steps": 4340, "loss": 0.5012, "lr": 2.0048257904841165e-05, "epoch": 3.846774193548387, "percentage": 54.95, "elapsed_time": "11:45:40", "remaining_time": "9:38:26"}
|
| 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"}
|