Training in progress, step 43500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0ecd85397c9873033c8fc72b8b958ac68dabe4479b23d12cd143f2bdaec2e49
+oid sha256:e3f3f60f837bc2d6b892b2d0546640ca46d3f194d47c20345c8767c8ccaa5c07
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba0de08f17477673f2db27ad78dc1cb0fb353da11bb179b4a06c1a9b0f4eb722
+oid sha256:6211545bbfeb1c43922e986aa4087c1ebccc0eedc2e220fb0dba4944f73f39c0
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9125611692f04b4e4f7334517ac150a7a29269d10071636ff9110a9581f5f331
+oid sha256:85869ac30f3cee5a03da0dea6f3e99cba1ee27fffe68afedef7c1dce40526f4d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0ef3fe9ebcf9f8f4fee3c065efe25035b81435ae8780b056e116dcb1a8a428f
+oid sha256:7d6701719fda370188bcff5587df70fa5f1ce20ee16a7c8ee75ec8b4d555e1ea
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.8666666666666667,
+  "epoch": 2.9,
   "eval_steps": 500,
-  "global_step": 43000,
+  "global_step": 43500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3033,6 +3033,41 @@
       "learning_rate": 8.960000000000001e-07,
       "loss": 0.0534,
       "step": 43000
+    },
+    {
+      "epoch": 2.873333333333333,
+      "grad_norm": 0.22133620083332062,
+      "learning_rate": 8.515555555555556e-07,
+      "loss": 0.0489,
+      "step": 43100
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.23495450615882874,
+      "learning_rate": 8.071111111111112e-07,
+      "loss": 0.0524,
+      "step": 43200
+    },
+    {
+      "epoch": 2.8866666666666667,
+      "grad_norm": 0.22712914645671844,
+      "learning_rate": 7.626666666666667e-07,
+      "loss": 0.0471,
+      "step": 43300
+    },
+    {
+      "epoch": 2.8933333333333335,
+      "grad_norm": 0.3228939175605774,
+      "learning_rate": 7.182222222222223e-07,
+      "loss": 0.0495,
+      "step": 43400
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.20631560683250427,
+      "learning_rate": 6.737777777777778e-07,
+      "loss": 0.0521,
+      "step": 43500
     }
   ],
   "logging_steps": 100,
@@ -3052,7 +3087,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0474075717632e+17,
+  "total_flos": 1.0595867295744e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null