Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c47fea650ec741b07e6a187541e4217459975b8d59c02f835544382c220ca692
+oid sha256:733197a61ea376aac61a951bb50d1ca3020638327455f8dec4a0ff679cecc0b1
 size 272123144

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a8aed857e58fca9787217eea0e79ed566fc87283905d5129d8c7a662387e4a5
+oid sha256:684dc2452fd203426d3639b34576b775f954fd7cb3c2337d837769d9331de7b5
 size 544259743

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dac398be5f56dbc72468a9a99f3dccd46ef72a345b45f80d1e818b6cd90b1bef
+oid sha256:147289ff04041b1e9043e727828828c698ed512128acb68e5fd4bf30ee75b6c5
 size 1000

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.26441036488630354,
+  "epoch": 0.5288207297726071,
   "eval_steps": 1000,
-  "global_step": 1000,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,29 @@
       "eval_samples_per_second": 24.909,
       "eval_steps_per_second": 0.528,
       "step": 1000
+    },
+    {
+      "epoch": 0.3966155473294553,
+      "grad_norm": 0.9617258906364441,
+      "learning_rate": 9.134314230431938e-05,
+      "loss": 3.0005,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5288207297726071,
+      "grad_norm": 0.8953185677528381,
+      "learning_rate": 8.670313710751356e-05,
+      "loss": 2.8119,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5288207297726071,
+      "eval_accuracy": 0.5365118094348038,
+      "eval_loss": 2.821384906768799,
+      "eval_runtime": 72.909,
+      "eval_samples_per_second": 25.237,
+      "eval_steps_per_second": 0.535,
+      "step": 2000
     }
   ],
   "logging_steps": 500,
@@ -49,7 +72,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2815167389696e+16,
+  "total_flos": 2.5630334779392e+16,
   "train_batch_size": 24,
   "trial_name": null,
   "trial_params": null