Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b171e11cf1f06b390942cd5db703ed9b47273c7612b41e4993a30dbad949cdd
+oid sha256:136fa05d4822b585e93ffebb7f6e290435b41a950ca4ec0870515b9da5c83243
 size 1340623936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13798f6e5591b7f07db647f3489a166d6156b5472962733618f77a107016972a
+oid sha256:91a6833a7fe2adbcb1959181cf2a161bed8da2ab70461adce0419862c0a89a53
 size 2681480830

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f8256de738109b958aaf2e3557bae2f85d4052ebbc24cf2866e264ba390a20e
+oid sha256:a99c6b534c3c4da04d2699dfbe806811bb55edcbda8669fe77a5c48de7405792
 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:f2ce5645288f483e7a9daa2c7a16180a6531e36418232835ffee5a4fecb21062
+oid sha256:38a85adeb1e28a9f8d2b9e5eda88bb40a25fff60709bb465ee86ac35b1f82adc
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 1000,
-  "best_metric": 0.16814623773097992,
-  "best_model_checkpoint": "./training_output/checkpoint-1000",
-  "epoch": 0.125,
+  "best_global_step": 2000,
+  "best_metric": 0.07912886142730713,
+  "best_model_checkpoint": "./training_output/checkpoint-2000",
+  "epoch": 0.25,
   "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": 15.374,
       "eval_steps_per_second": 0.961,
       "step": 1000
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 0.07351929694414139,
+      "learning_rate": 1.62525e-05,
+      "loss": 0.0782,
+      "step": 1500
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.13799075782299042,
+      "learning_rate": 1.5002500000000002e-05,
+      "loss": 0.0618,
+      "step": 2000
+    },
+    {
+      "epoch": 0.25,
+      "eval_accuracy": 0.923125,
+      "eval_loss": 0.07912886142730713,
+      "eval_runtime": 529.7101,
+      "eval_samples_per_second": 15.103,
+      "eval_steps_per_second": 0.944,
+      "step": 2000
     }
   ],
   "logging_steps": 500,
@@ -50,7 +73,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3727725453312000.0,
+  "total_flos": 7455450906624000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null