Training in progress, step 3500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15ce635d318a1039b9c276644e773f2d7ad3637d56b6c50a4005c33d2b5e386d
+oid sha256:b6740cbf07f2409e7cdacf7f21dbc25ceef3f58d12ba3d99c422a2aa929ff4a7
 size 57029756

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8af70d3e3b4d7a8fbd0595c3e26dd49c01fb81313a5582b18d591031e5f00893
+oid sha256:8bb19959c962abb746dad87f4337a2f0080c11e990d8a64a61c42fb552d90fc8
 size 114100410

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da8eecb9924546ad8bb4a529eedddeb04a0d0ddded5717f5bbcd35d294eccc01
+oid sha256:c9a039e79155fe722a6f689a73713003d3aa2d14a08d309b89d24e3a83a694cc
 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": 0.0841,
       "step": 3000
+    },
+    {
+      "epoch": 3.9863325740318905,
+      "grad_norm": 7.105097770690918,
+      "learning_rate": 4.054669703872437e-06,
+      "loss": 0.076,
+      "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