Training in progress, step 43000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a9ad8913737016dba8650f3d7e7a145a4ce8913d458d7301634297efd00278c
+oid sha256:c0ecd85397c9873033c8fc72b8b958ac68dabe4479b23d12cd143f2bdaec2e49
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:674d8858e4474544083140dd69e34c045fc6b88c296cb2ac0d991075b6a9ebd1
+oid sha256:ba0de08f17477673f2db27ad78dc1cb0fb353da11bb179b4a06c1a9b0f4eb722
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07401c37c6a1bb4042ae60703b7c654f256d7be062ccd8d53ae2bf95d64aab34
+oid sha256:9125611692f04b4e4f7334517ac150a7a29269d10071636ff9110a9581f5f331
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03af6009394f4a2fb32c0cb40ddd5c5c4f50ce08dbb2d5a4f3d15eba8d0516e9
+oid sha256:f0ef3fe9ebcf9f8f4fee3c065efe25035b81435ae8780b056e116dcb1a8a428f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.8333333333333335,
+  "epoch": 2.8666666666666667,
   "eval_steps": 500,
-  "global_step": 42500,
+  "global_step": 43000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2998,6 +2998,41 @@
       "learning_rate": 1.1182222222222224e-06,
       "loss": 0.0549,
       "step": 42500
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 0.13869111239910126,
+      "learning_rate": 1.0737777777777778e-06,
+      "loss": 0.0543,
+      "step": 42600
+    },
+    {
+      "epoch": 2.8466666666666667,
+      "grad_norm": 0.12573951482772827,
+      "learning_rate": 1.0293333333333334e-06,
+      "loss": 0.0499,
+      "step": 42700
+    },
+    {
+      "epoch": 2.8533333333333335,
+      "grad_norm": 0.23486433923244476,
+      "learning_rate": 9.848888888888889e-07,
+      "loss": 0.0533,
+      "step": 42800
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 0.20186831057071686,
+      "learning_rate": 9.404444444444445e-07,
+      "loss": 0.0452,
+      "step": 42900
+    },
+    {
+      "epoch": 2.8666666666666667,
+      "grad_norm": 0.047486595809459686,
+      "learning_rate": 8.960000000000001e-07,
+      "loss": 0.0534,
+      "step": 43000
     }
   ],
   "logging_steps": 100,
@@ -3017,7 +3052,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.035228413952e+17,
+  "total_flos": 1.0474075717632e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null