Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78ea6d1631d1f50812215903ae5b19bc39715b4e974f3dd49febf719f7765492
+oid sha256:adadf44f1e459344e83749883329a7a42d9cd526e045515d581288a614c95052
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffb8bda5cb9358367d950ad17ee53a7a3adfeae35d2ac832321c872a30fc3212
+oid sha256:ca0939f144f4a3fab18378090a7055b038e279c6b9e2ff8a9a2a8ff2a99c8b8c
 size 997345931

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41afff64258c100464839a9401c63f65038ccc9dbd2dd2c5f61f68f3b93f2b79
+oid sha256:8cbb9d20ae0e060525bcac1b70551f336242a3392c3ba0392910b81075e6dc33
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
+oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed290419ddbbaf4c4f46d92ab98980c1b33e3e9b93e34d7bc94d8d13097423b4
+oid sha256:f8cac132f6cb7e26c16168d7dd2d5889b5966954ea1f2f629ae0cf0022b48d02
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1000,
   "best_metric": 0.12729284167289734,
   "best_model_checkpoint": "./training_output/checkpoint-1000",
-  "epoch": 0.05,
+  "epoch": 0.1,
   "eval_steps": 1000,
-  "global_step": 1000,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -31,6 +31,29 @@
       "eval_samples_per_second": 55.001,
       "eval_steps_per_second": 3.438,
       "step": 1000
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 0.017511729151010513,
+      "learning_rate": 1.8501e-05,
+      "loss": 0.0956,
+      "step": 1500
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.022739391773939133,
+      "learning_rate": 1.8001000000000003e-05,
+      "loss": 0.0721,
+      "step": 2000
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.88555,
+      "eval_loss": 0.21215863525867462,
+      "eval_runtime": 363.0614,
+      "eval_samples_per_second": 55.087,
+      "eval_steps_per_second": 3.443,
+      "step": 2000
     }
   ],
   "logging_steps": 500,
@@ -50,7 +73,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1052444221440000.0,
+  "total_flos": 2104888442880000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null