Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:136fa05d4822b585e93ffebb7f6e290435b41a950ca4ec0870515b9da5c83243
+oid sha256:6d7421efb0f77cd2ad05e257eaaa7cf70bc46b98f46b55a33fcb605105540605
 size 1340623936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91a6833a7fe2adbcb1959181cf2a161bed8da2ab70461adce0419862c0a89a53
+oid sha256:97cd9487290e93a4cf8df97c810828fa6608cfd8679b75d5176a1b829226af00
 size 2681480830

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a99c6b534c3c4da04d2699dfbe806811bb55edcbda8669fe77a5c48de7405792
+oid sha256:e484b91022d49823d8d81e38c9d2aecc8d11dd67a5a779bad4167814a1359c3d
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
+oid sha256:5ac1c46a2776d12775d23d0f587efc112188137ce2140da35bc15d301c9f620e
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38a85adeb1e28a9f8d2b9e5eda88bb40a25fff60709bb465ee86ac35b1f82adc
+oid sha256:4d3f655ea9c5a4a9f86c577483cce348f86f4499f93b7851c6926bdee4b92c1f
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 2000,
   "best_metric": 0.07912886142730713,
   "best_model_checkpoint": "./training_output/checkpoint-2000",
-  "epoch": 0.25,
+  "epoch": 0.375,
   "eval_steps": 1000,
-  "global_step": 2000,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -54,6 +54,29 @@
       "eval_samples_per_second": 15.103,
       "eval_steps_per_second": 0.944,
       "step": 2000
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 1.579990029335022,
+      "learning_rate": 1.3752500000000003e-05,
+      "loss": 0.056,
+      "step": 2500
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.19930818676948547,
+      "learning_rate": 1.2502500000000003e-05,
+      "loss": 0.0598,
+      "step": 3000
+    },
+    {
+      "epoch": 0.375,
+      "eval_accuracy": 0.9135,
+      "eval_loss": 0.08944346010684967,
+      "eval_runtime": 526.2119,
+      "eval_samples_per_second": 15.203,
+      "eval_steps_per_second": 0.95,
+      "step": 3000
     }
   ],
   "logging_steps": 500,
@@ -73,7 +96,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7455450906624000.0,
+  "total_flos": 1.1183176359936e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null