Training in progress, step 45400, checkpoint

last-checkpoint/README.md

@@ -1197,6 +1197,10 @@ You can finetune this model on your own dataset.
 | 0.7969 | 45100 | 0.311         |
 | 0.7978 | 45150 | 0.2368        |
 | 0.7987 | 45200 | 0.3147        |
+| 0.7996 | 45250 | 0.2964        |
+| 0.8005 | 45300 | 0.34          |
+| 0.8014 | 45350 | 0.3249        |
+| 0.8022 | 45400 | 0.4092        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7bc1279cf26374bbe94542da62a9c0d4afab0f4ba7ae70859bbcb9c9a68dd05
+oid sha256:8c0a06246d378fd348d194b9107c71fc3364329ffb66f4f7a38a8b746879a0d6
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c01262363633d3d77ce1db0dfb29f97a979fcb51db6af60308b261c77050d227
+oid sha256:02d1617892fcac86335adbfa698c3e9768ddeb73254048f99d0d9d6c39374ede
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b37a75ff2cf38c26a23d005c931008fab38bb3848944732097424886cc09ed5
+oid sha256:b29b46e66da0f87057694f5c54378f3edacf69ae5bc2fdbd8b89a7b5348aa80e
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7508f8a8b4fb4d80e6e1cbe138ce75da05ff3779ab0aeb5d7b1f2c4f9795a0eb
+oid sha256:fdf6bd37a0b6ce40122f150a97821e5e540ac2c58f691b7be91594627015644e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:229878378d7cc80eb5eb56eb236e5a16279538f082126201a0410ceb9d7b9c95
+oid sha256:6f10606e492f72fdc0e1b33f5b8a22ab9b8d0af742b5c2aa76b87aee5ccfc338
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7987135763637327,
+  "epoch": 0.8022477072325989,
   "eval_steps": 500,
-  "global_step": 45200,
+  "global_step": 45400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6336,6 +6336,34 @@
       "learning_rate": 1.120044766448725e-05,
       "loss": 0.3147,
       "step": 45200
+    },
+    {
+      "epoch": 0.7995971090809493,
+      "grad_norm": 1.4544724225997925,
+      "learning_rate": 1.115136164614871e-05,
+      "loss": 0.2964,
+      "step": 45250
+    },
+    {
+      "epoch": 0.8004806417981658,
+      "grad_norm": 1.5149188041687012,
+      "learning_rate": 1.1102275627810175e-05,
+      "loss": 0.34,
+      "step": 45300
+    },
+    {
+      "epoch": 0.8013641745153823,
+      "grad_norm": 1.4456932544708252,
+      "learning_rate": 1.1053189609471638e-05,
+      "loss": 0.3249,
+      "step": 45350
+    },
+    {
+      "epoch": 0.8022477072325989,
+      "grad_norm": 4.4482574462890625,
+      "learning_rate": 1.1004103591133103e-05,
+      "loss": 0.4092,
+      "step": 45400
     }
   ],
   "logging_steps": 50,