Training in progress, step 11400, checkpoint

last-checkpoint/README.md

@@ -1249,6 +1249,10 @@ You can finetune this model on your own dataset.
 | 0.1961 | 11100 | 0.4334        |
 | 0.1970 | 11150 | 0.4479        |
 | 0.1979 | 11200 | 0.3545        |
+| 0.1988 | 11250 | 0.3192        |
+| 0.1997 | 11300 | 0.3883        |
+| 0.2006 | 11350 | 0.3312        |
+| 0.2014 | 11400 | 0.4888        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e44300f1a7eda978b714254f7642e5fa8e46c4465149d151fb36c7a22d09887
+oid sha256:0251d55d19012022b3471da785a65a2bc6f56faf0f41cb8aec5fee968199572e
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:283034d540cc735bf4188ad3d17ee98d86aa7e8c24e656d2a4ff17d9e61dfb8e
+oid sha256:528621d7ef01154800460a8cccb1fb80bff45f808fc6990cc94b2503052d3ae3
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f802fc7d6b08b3448bdbc5653ab5c831b50c834ee5d8105b5d34c4dfeaebf61e
+oid sha256:c7ccafbbd3f23088187d3f39081089feeb9cb03fb0fae7e1ed1996a1e0cdc7f7
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16f0df52c717c2e3e1dfb7c95b1b78d2bff8956a86b6980e2bde6913f11a1016
+oid sha256:b3a99e201ecedb03053afb6fbd1f38ffbe8b22238d6484e117d413c9c1ea3a69
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5330400d6885c6b9af0b1821a1e49b220dac708c65a515f28b9197806d03f3ed
+oid sha256:18eafe3970ca850979514a20be184f0f34883513f106b08256d4a503712c8ab0
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.19791132865650016,
+  "epoch": 0.20144545952536622,
   "eval_steps": 500,
-  "global_step": 11200,
+  "global_step": 11400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1576,6 +1576,34 @@
       "learning_rate": 4.456323260882371e-05,
       "loss": 0.3545,
       "step": 11200
+    },
+    {
+      "epoch": 0.19879486137371666,
+      "grad_norm": 2.1903252601623535,
+      "learning_rate": 4.451414659048517e-05,
+      "loss": 0.3192,
+      "step": 11250
+    },
+    {
+      "epoch": 0.1996783940909332,
+      "grad_norm": 1.9699974060058594,
+      "learning_rate": 4.446506057214663e-05,
+      "loss": 0.3883,
+      "step": 11300
+    },
+    {
+      "epoch": 0.20056192680814972,
+      "grad_norm": 1.7133831977844238,
+      "learning_rate": 4.441597455380809e-05,
+      "loss": 0.3312,
+      "step": 11350
+    },
+    {
+      "epoch": 0.20144545952536622,
+      "grad_norm": 3.0174543857574463,
+      "learning_rate": 4.436688853546956e-05,
+      "loss": 0.4888,
+      "step": 11400
     }
   ],
   "logging_steps": 50,