Training in progress, step 2200
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:aba14bfcf9a401dcd470a154e03dc6a7df0ded3c81ec8bbb4f669e7e6b6a567d
|
| 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 sha256:23cd2966042952c89f25954d1c169dbc1386173a29b23e3d05bffeb791138f89
|
| 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:e42a87a9990917973718e30b8ea8b2e7faf43a91c23fbbf466a5ba700c1dd169
|
| 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:c0ab5bb2dc227dcf18de8cf09d4d35f3bcc8d623f712a5bf6cce9b9b490490fd
|
| 3 |
size 1580230264
|
trainer_log.jsonl
CHANGED
|
@@ -398,3 +398,43 @@
|
|
| 398 |
{"current_steps": 1990, "total_steps": 4340, "loss": 0.4959, "lr": 2.629343998348155e-05, "epoch": 3.2096774193548385, "percentage": 45.85, "elapsed_time": "9:47:52", "remaining_time": "11:34:13"}
|
| 399 |
{"current_steps": 1995, "total_steps": 4340, "loss": 0.4909, "lr": 2.6217045181849906e-05, "epoch": 3.217741935483871, "percentage": 45.97, "elapsed_time": "9:49:27", "remaining_time": "11:32:52"}
|
| 400 |
{"current_steps": 2000, "total_steps": 4340, "loss": 0.509, "lr": 2.6140549835626645e-05, "epoch": 3.225806451612903, "percentage": 46.08, "elapsed_time": "9:50:51", "remaining_time": "11:31:18"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 398 |
{"current_steps": 1990, "total_steps": 4340, "loss": 0.4959, "lr": 2.629343998348155e-05, "epoch": 3.2096774193548385, "percentage": 45.85, "elapsed_time": "9:47:52", "remaining_time": "11:34:13"}
|
| 399 |
{"current_steps": 1995, "total_steps": 4340, "loss": 0.4909, "lr": 2.6217045181849906e-05, "epoch": 3.217741935483871, "percentage": 45.97, "elapsed_time": "9:49:27", "remaining_time": "11:32:52"}
|
| 400 |
{"current_steps": 2000, "total_steps": 4340, "loss": 0.509, "lr": 2.6140549835626645e-05, "epoch": 3.225806451612903, "percentage": 46.08, "elapsed_time": "9:50:51", "remaining_time": "11:31:18"}
|
| 401 |
+
{"current_steps": 2005, "total_steps": 4340, "loss": 0.5251, "lr": 2.6063955181925736e-05, "epoch": 3.2338709677419355, "percentage": 46.2, "elapsed_time": "9:53:47", "remaining_time": "11:31:31"}
|
| 402 |
+
{"current_steps": 2010, "total_steps": 4340, "loss": 0.5031, "lr": 2.5987262459467168e-05, "epoch": 3.241935483870968, "percentage": 46.31, "elapsed_time": "9:55:12", "remaining_time": "11:29:57"}
|
| 403 |
+
{"current_steps": 2015, "total_steps": 4340, "loss": 0.4763, "lr": 2.5910472908556933e-05, "epoch": 3.25, "percentage": 46.43, "elapsed_time": "9:56:45", "remaining_time": "11:28:34"}
|
| 404 |
+
{"current_steps": 2020, "total_steps": 4340, "loss": 0.4974, "lr": 2.5833587771067e-05, "epoch": 3.258064516129032, "percentage": 46.54, "elapsed_time": "9:58:12", "remaining_time": "11:27:02"}
|
| 405 |
+
{"current_steps": 2025, "total_steps": 4340, "loss": 0.501, "lr": 2.5756608290415185e-05, "epoch": 3.2661290322580645, "percentage": 46.66, "elapsed_time": "9:59:44", "remaining_time": "11:25:37"}
|
| 406 |
+
{"current_steps": 2030, "total_steps": 4340, "loss": 0.5079, "lr": 2.5679535711545053e-05, "epoch": 3.274193548387097, "percentage": 46.77, "elapsed_time": "10:01:07", "remaining_time": "11:24:02"}
|
| 407 |
+
{"current_steps": 2035, "total_steps": 4340, "loss": 0.4851, "lr": 2.56023712809058e-05, "epoch": 3.282258064516129, "percentage": 46.89, "elapsed_time": "10:02:35", "remaining_time": "11:22:32"}
|
| 408 |
+
{"current_steps": 2040, "total_steps": 4340, "loss": 0.4942, "lr": 2.552511624643209e-05, "epoch": 3.2903225806451615, "percentage": 47.0, "elapsed_time": "10:04:15", "remaining_time": "11:21:16"}
|
| 409 |
+
{"current_steps": 2045, "total_steps": 4340, "loss": 0.5059, "lr": 2.5447771857523868e-05, "epoch": 3.2983870967741935, "percentage": 47.12, "elapsed_time": "10:05:34", "remaining_time": "11:19:36"}
|
| 410 |
+
{"current_steps": 2050, "total_steps": 4340, "loss": 0.5034, "lr": 2.5370339365026145e-05, "epoch": 3.306451612903226, "percentage": 47.24, "elapsed_time": "10:07:06", "remaining_time": "11:18:11"}
|
| 411 |
+
{"current_steps": 2055, "total_steps": 4340, "loss": 0.5133, "lr": 2.5292820021208794e-05, "epoch": 3.314516129032258, "percentage": 47.35, "elapsed_time": "10:08:23", "remaining_time": "11:16:28"}
|
| 412 |
+
{"current_steps": 2060, "total_steps": 4340, "loss": 0.511, "lr": 2.5215215079746268e-05, "epoch": 3.3225806451612905, "percentage": 47.47, "elapsed_time": "10:09:41", "remaining_time": "11:14:48"}
|
| 413 |
+
{"current_steps": 2065, "total_steps": 4340, "loss": 0.4799, "lr": 2.5137525795697356e-05, "epoch": 3.3306451612903225, "percentage": 47.58, "elapsed_time": "10:11:10", "remaining_time": "11:13:19"}
|
| 414 |
+
{"current_steps": 2070, "total_steps": 4340, "loss": 0.4928, "lr": 2.5059753425484858e-05, "epoch": 3.338709677419355, "percentage": 47.7, "elapsed_time": "10:12:42", "remaining_time": "11:11:54"}
|
| 415 |
+
{"current_steps": 2075, "total_steps": 4340, "loss": 0.5225, "lr": 2.4981899226875274e-05, "epoch": 3.346774193548387, "percentage": 47.81, "elapsed_time": "10:13:54", "remaining_time": "11:10:07"}
|
| 416 |
+
{"current_steps": 2080, "total_steps": 4340, "loss": 0.5256, "lr": 2.490396445895849e-05, "epoch": 3.3548387096774195, "percentage": 47.93, "elapsed_time": "10:15:23", "remaining_time": "11:08:38"}
|
| 417 |
+
{"current_steps": 2085, "total_steps": 4340, "loss": 0.5107, "lr": 2.4825950382127356e-05, "epoch": 3.3629032258064515, "percentage": 48.04, "elapsed_time": "10:16:50", "remaining_time": "11:07:08"}
|
| 418 |
+
{"current_steps": 2090, "total_steps": 4340, "loss": 0.4841, "lr": 2.4747858258057365e-05, "epoch": 3.370967741935484, "percentage": 48.16, "elapsed_time": "10:18:24", "remaining_time": "11:05:44"}
|
| 419 |
+
{"current_steps": 2095, "total_steps": 4340, "loss": 0.4819, "lr": 2.4669689349686224e-05, "epoch": 3.379032258064516, "percentage": 48.27, "elapsed_time": "10:19:54", "remaining_time": "11:04:17"}
|
| 420 |
+
{"current_steps": 2100, "total_steps": 4340, "loss": 0.4952, "lr": 2.4591444921193396e-05, "epoch": 3.3870967741935485, "percentage": 48.39, "elapsed_time": "10:21:26", "remaining_time": "11:02:51"}
|
| 421 |
+
{"current_steps": 2105, "total_steps": 4340, "loss": 0.4911, "lr": 2.4513126237979723e-05, "epoch": 3.3951612903225805, "percentage": 48.5, "elapsed_time": "10:22:55", "remaining_time": "11:01:24"}
|
| 422 |
+
{"current_steps": 2110, "total_steps": 4340, "loss": 0.4911, "lr": 2.4434734566646903e-05, "epoch": 3.403225806451613, "percentage": 48.62, "elapsed_time": "10:24:21", "remaining_time": "10:59:51"}
|
| 423 |
+
{"current_steps": 2115, "total_steps": 4340, "loss": 0.5073, "lr": 2.435627117497703e-05, "epoch": 3.411290322580645, "percentage": 48.73, "elapsed_time": "10:25:57", "remaining_time": "10:58:30"}
|
| 424 |
+
{"current_steps": 2120, "total_steps": 4340, "loss": 0.5062, "lr": 2.4277737331912104e-05, "epoch": 3.4193548387096775, "percentage": 48.85, "elapsed_time": "10:27:30", "remaining_time": "10:57:06"}
|
| 425 |
+
{"current_steps": 2125, "total_steps": 4340, "loss": 0.5083, "lr": 2.419913430753347e-05, "epoch": 3.4274193548387095, "percentage": 48.96, "elapsed_time": "10:28:52", "remaining_time": "10:55:30"}
|
| 426 |
+
{"current_steps": 2130, "total_steps": 4340, "loss": 0.4816, "lr": 2.412046337304131e-05, "epoch": 3.435483870967742, "percentage": 49.08, "elapsed_time": "10:30:28", "remaining_time": "10:54:08"}
|
| 427 |
+
{"current_steps": 2135, "total_steps": 4340, "loss": 0.5192, "lr": 2.404172580073409e-05, "epoch": 3.443548387096774, "percentage": 49.19, "elapsed_time": "10:31:45", "remaining_time": "10:52:28"}
|
| 428 |
+
{"current_steps": 2140, "total_steps": 4340, "loss": 0.478, "lr": 2.3962922863987956e-05, "epoch": 3.4516129032258065, "percentage": 49.31, "elapsed_time": "10:33:11", "remaining_time": "10:50:57"}
|
| 429 |
+
{"current_steps": 2145, "total_steps": 4340, "loss": 0.4953, "lr": 2.388405583723615e-05, "epoch": 3.4596774193548385, "percentage": 49.42, "elapsed_time": "10:34:35", "remaining_time": "10:49:23"}
|
| 430 |
+
{"current_steps": 2150, "total_steps": 4340, "loss": 0.5114, "lr": 2.3805125995948422e-05, "epoch": 3.467741935483871, "percentage": 49.54, "elapsed_time": "10:36:02", "remaining_time": "10:47:52"}
|
| 431 |
+
{"current_steps": 2155, "total_steps": 4340, "loss": 0.5, "lr": 2.3726134616610366e-05, "epoch": 3.475806451612903, "percentage": 49.65, "elapsed_time": "10:37:34", "remaining_time": "10:46:26"}
|
| 432 |
+
{"current_steps": 2160, "total_steps": 4340, "loss": 0.5074, "lr": 2.3647082976702805e-05, "epoch": 3.4838709677419355, "percentage": 49.77, "elapsed_time": "10:39:02", "remaining_time": "10:44:57"}
|
| 433 |
+
{"current_steps": 2165, "total_steps": 4340, "loss": 0.5054, "lr": 2.3567972354681113e-05, "epoch": 3.491935483870968, "percentage": 49.88, "elapsed_time": "10:40:24", "remaining_time": "10:43:21"}
|
| 434 |
+
{"current_steps": 2170, "total_steps": 4340, "loss": 0.5144, "lr": 2.348880402995456e-05, "epoch": 3.5, "percentage": 50.0, "elapsed_time": "10:41:40", "remaining_time": "10:41:40"}
|
| 435 |
+
{"current_steps": 2175, "total_steps": 4340, "loss": 0.5037, "lr": 2.3409579282865592e-05, "epoch": 3.508064516129032, "percentage": 50.12, "elapsed_time": "10:43:01", "remaining_time": "10:40:03"}
|
| 436 |
+
{"current_steps": 2180, "total_steps": 4340, "loss": 0.4963, "lr": 2.3330299394669144e-05, "epoch": 3.5161290322580645, "percentage": 50.23, "elapsed_time": "10:44:17", "remaining_time": "10:38:23"}
|
| 437 |
+
{"current_steps": 2185, "total_steps": 4340, "loss": 0.4777, "lr": 2.325096564751193e-05, "epoch": 3.524193548387097, "percentage": 50.35, "elapsed_time": "10:46:20", "remaining_time": "10:37:27"}
|
| 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"}
|