Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:733197a61ea376aac61a951bb50d1ca3020638327455f8dec4a0ff679cecc0b1
+oid sha256:0f6aef3a65b706883648a40261c469821b28ad715e937813acd70959ef272f12
 size 272123144

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:684dc2452fd203426d3639b34576b775f954fd7cb3c2337d837769d9331de7b5
+oid sha256:754050cd8531a1ec4be7c92439fadfa8bb9b0a1187abc0ab8979a2df096fbe8a
 size 544259743

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:147289ff04041b1e9043e727828828c698ed512128acb68e5fd4bf30ee75b6c5
+oid sha256:74ace5f16e09466618cf956d695538d60bba6bf21c0003f9e08e546fc6acbe93
 size 1000

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5288207297726071,
+  "epoch": 0.7932310946589106,
   "eval_steps": 1000,
-  "global_step": 2000,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -53,6 +53,29 @@
       "eval_samples_per_second": 25.237,
       "eval_steps_per_second": 0.535,
       "step": 2000
+    },
+    {
+      "epoch": 0.6610259122157589,
+      "grad_norm": 1.4154396057128906,
+      "learning_rate": 8.206313191070773e-05,
+      "loss": 2.686,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7932310946589106,
+      "grad_norm": 1.821349024772644,
+      "learning_rate": 7.742312671390191e-05,
+      "loss": 2.607,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7932310946589106,
+      "eval_accuracy": 0.5497897240925214,
+      "eval_loss": 2.657219886779785,
+      "eval_runtime": 73.4297,
+      "eval_samples_per_second": 25.058,
+      "eval_steps_per_second": 0.531,
+      "step": 3000
     }
   ],
   "logging_steps": 500,
@@ -72,7 +95,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5630334779392e+16,
+  "total_flos": 3.8445502169088e+16,
   "train_batch_size": 24,
   "trial_name": null,
   "trial_params": null