Training in progress, step 45600, checkpoint

last-checkpoint/README.md

@@ -1201,6 +1201,10 @@ You can finetune this model on your own dataset.
 | 0.8005 | 45300 | 0.34          |
 | 0.8014 | 45350 | 0.3249        |
 | 0.8022 | 45400 | 0.4092        |
+| 0.8031 | 45450 | 0.2601        |
+| 0.8040 | 45500 | 0.306         |
+| 0.8049 | 45550 | 0.2888        |
+| 0.8058 | 45600 | 0.3101        |
 
 
 ### Framework Versions

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c0a06246d378fd348d194b9107c71fc3364329ffb66f4f7a38a8b746879a0d6
+oid sha256:dafa20b9ee08adc30b1b45605dd3458876a74a9a04d0a242b2d07bff11ffcfd4
 size 90864192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d1617892fcac86335adbfa698c3e9768ddeb73254048f99d0d9d6c39374ede
+oid sha256:3e30656e2446cf01ec70d3edee1d105134bd862bca3236ab9a8c0b6f570bdcc1
 size 180609210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b29b46e66da0f87057694f5c54378f3edacf69ae5bc2fdbd8b89a7b5348aa80e
+oid sha256:3642579a8c93faba29891bb437590b2fc3296379ded34bad3a25d71b44ae26dc
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdf6bd37a0b6ce40122f150a97821e5e540ac2c58f691b7be91594627015644e
+oid sha256:803966f189174fdab2c5da9165b86bf3a54e44aa7c1402617aaf37d70a2c35b6
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f10606e492f72fdc0e1b33f5b8a22ab9b8d0af742b5c2aa76b87aee5ccfc338
+oid sha256:2db50723dd4d547a9dfd33b0f7da5dabf8169af1f05c3a349b52d1ff0ca949ad
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8022477072325989,
+  "epoch": 0.8057818381014649,
   "eval_steps": 500,
-  "global_step": 45400,
+  "global_step": 45600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6364,6 +6364,34 @@
       "learning_rate": 1.1004103591133103e-05,
       "loss": 0.4092,
       "step": 45400
+    },
+    {
+      "epoch": 0.8031312399498154,
+      "grad_norm": 1.7785700559616089,
+      "learning_rate": 1.0955017572794566e-05,
+      "loss": 0.2601,
+      "step": 45450
+    },
+    {
+      "epoch": 0.8040147726670318,
+      "grad_norm": 1.560614824295044,
+      "learning_rate": 1.0905931554456029e-05,
+      "loss": 0.306,
+      "step": 45500
+    },
+    {
+      "epoch": 0.8048983053842483,
+      "grad_norm": 1.2510974407196045,
+      "learning_rate": 1.0856845536117492e-05,
+      "loss": 0.2888,
+      "step": 45550
+    },
+    {
+      "epoch": 0.8057818381014649,
+      "grad_norm": 2.532653331756592,
+      "learning_rate": 1.0807759517778957e-05,
+      "loss": 0.3101,
+      "step": 45600
     }
   ],
   "logging_steps": 50,