Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f6aef3a65b706883648a40261c469821b28ad715e937813acd70959ef272f12
+oid sha256:baf7620b0c51ef17a030b63cfe26c514df5d88602a1b8140fb12c4968dfa6ff4
 size 272123144

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:754050cd8531a1ec4be7c92439fadfa8bb9b0a1187abc0ab8979a2df096fbe8a
+oid sha256:908d9d7ed41d479f7f47a9fd0646de3f7800df94e052115c9815ea463d99e70d
 size 544259743

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
+oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74ace5f16e09466618cf956d695538d60bba6bf21c0003f9e08e546fc6acbe93
+oid sha256:394be853393fcf0db07e5bdfe4c0d7e15ce8f5fac5bdbb2ad1b413385499af51
 size 1000

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7932310946589106,
+  "epoch": 1.0576414595452142,
   "eval_steps": 1000,
-  "global_step": 3000,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -76,6 +76,29 @@
       "eval_samples_per_second": 25.058,
       "eval_steps_per_second": 0.531,
       "step": 3000
+    },
+    {
+      "epoch": 0.9254362771020624,
+      "grad_norm": 2.0297396183013916,
+      "learning_rate": 7.278312151709609e-05,
+      "loss": 2.5642,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0576414595452142,
+      "grad_norm": 2.8318285942077637,
+      "learning_rate": 6.814311632029027e-05,
+      "loss": 2.4734,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0576414595452142,
+      "eval_accuracy": 0.5582058048894458,
+      "eval_loss": 2.5735702514648438,
+      "eval_runtime": 73.4679,
+      "eval_samples_per_second": 25.045,
+      "eval_steps_per_second": 0.531,
+      "step": 4000
     }
   ],
   "logging_steps": 500,
@@ -95,7 +118,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.8445502169088e+16,
+  "total_flos": 5.124838835670221e+16,
   "train_batch_size": 24,
   "trial_name": null,
   "trial_params": null