Training in progress, step 3500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ddbc523b79aaf9756951afaaf7b9b1bd6c6e25231ccc9851e69b239171dd53c
+oid sha256:e4c4d7f1004d07375088938a2c915adf18b5d2d761c11c84c756cd9be62677d5
 size 57029756

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc580a2c08cdc5e7ca83543b3c323f54249a857933da2e4c71cd3c5bd3da1786
+oid sha256:ac1785d9a6f3f9bf67b7c797da069a0600547111b633cf212059997cfa90fdfe
 size 114100410

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af9b7e49efa8bec2063dadfdfeab7409886026929b750eabf49749636c16bcc5
+oid sha256:74fc8a40aac27fc6e439c8bc1af8d0957585efb1611a745b3e0184b761cfcc2b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a1309f61c0d311eaceb7c90e770f4b3fcc4eb1a4147f8ffeac21539facfeab8
+oid sha256:470bd086a8fe9b0c7ccf7b8586cd470ddceac9947e167d5f90ab63505ad3ca75
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.416856492027335,
+  "epoch": 3.9863325740318905,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -85,6 +85,13 @@
       "learning_rate": 6.3325740318906616e-06,
       "loss": 0.1302,
       "step": 3000
+    },
+    {
+      "epoch": 3.9863325740318905,
+      "grad_norm": 5.151127338409424,
+      "learning_rate": 4.054669703872437e-06,
+      "loss": 0.116,
+      "step": 3500
     }
   ],
   "logging_steps": 500,
@@ -104,7 +111,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 62399928651750.0,
+  "total_flos": 72922812305958.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null