Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d7652a9232339d6e1ccab695f9ba6075718fdf1dba2b8c3ef19b0f3a6ee730a
+oid sha256:b4976591835d5aca83e7b5f41a00cb52acee5cb572e72a643fb9be051e9f83d1
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:985478ebfc1a47c88f3e1ac69469cffbbf30686a65738f52bcb40a45462289c1
+oid sha256:61279ee4a931a5ad88cec6cf2852e6f43ed00d1fcc1a243cbc084b1c64b079ad
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67614312c1d6bdffeb060b44c3dda6a1d76fa4797cd7f644d2f81b287adb0cdc
+oid sha256:7889ea0c99419f757623bd536c886c76ec1b2bc48f8905f0fbdab85178a3efa4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c11535f68e6db49da07158fe11fecce1c2974b2e1c50f93ec69532ea7b0bd8a
+oid sha256:7840dd1a31d2cba594152573000c19a8714961f30a02991b54083675256ff19f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6234413965087282,
+  "epoch": 0.8312551953449709,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -28,6 +28,13 @@
       "learning_rate": 1.7509559434746467e-05,
       "loss": 0.4473,
       "step": 1500
+    },
+    {
+      "epoch": 0.8312551953449709,
+      "grad_norm": 0.5443118214607239,
+      "learning_rate": 1.6678304239401496e-05,
+      "loss": 0.4326,
+      "step": 2000
     }
   ],
   "logging_steps": 500,
@@ -47,7 +54,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3653747343360000.0,
+  "total_flos": 4871663124480000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null