Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79e8fedd947d21c1b068dc7570fae027d636f21be8675dd6fd8005c44d498fd4
+oid sha256:ba0cfcfae75cac3b1e3a9de6399eb42004558382974cabded94c595bf6d208de
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bff0a2b02dc8212ed9dbee7dadf3298e1df1329d89c3361a3c00a420080fcdb
+oid sha256:6a3eba2787f787ff71a4d66f9dac89222b1befcd50b4672cfd05ee43b86019bb
 size 997345931

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3106ce26d8876d17e74b10716d47cadecb00ff3a2233d08bdb01a7952809d554
+oid sha256:ba7e7aeb52209ad5d8132c35dc5dea4045b9348ce56da3f145b30c0fd7a0758b
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00b4eb0c27b559cfd649f7c80a6d3394a55880d92b3ee2ca98f71b67e7b2333a
+oid sha256:1e6fd97f105f8edb4cfe7d5753c1c5716920ac3feb07414e58ddd6a461f2d28f
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe28f7d29e7f98f2600c3c6c7c0177a5ef0e8009ada6a2b943e31e01e5a4324e
+oid sha256:3eb90156edd50a6f5a58999d9f241525ea76a46a3dd6243488805187f9dab05f
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 9000,
   "best_metric": 0.04935265704989433,
   "best_model_checkpoint": "./training_output/checkpoint-9000",
-  "epoch": 0.45,
+  "epoch": 0.5,
   "eval_steps": 1000,
-  "global_step": 9000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -215,6 +215,29 @@
       "eval_samples_per_second": 52.55,
       "eval_steps_per_second": 3.284,
       "step": 9000
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 0.08418703079223633,
+      "learning_rate": 1.0501000000000002e-05,
+      "loss": 0.0262,
+      "step": 9500
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.19593098759651184,
+      "learning_rate": 1.0001000000000001e-05,
+      "loss": 0.0301,
+      "step": 10000
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.9689,
+      "eval_loss": 0.05831901729106903,
+      "eval_runtime": 380.4459,
+      "eval_samples_per_second": 52.57,
+      "eval_steps_per_second": 3.286,
+      "step": 10000
     }
   ],
   "logging_steps": 500,
@@ -234,7 +257,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9471997992960000.0,
+  "total_flos": 1.05244422144e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null