Training in progress, epoch 13, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7fc909fdc3f1ae4015f0d4750a4a63b89ee5f2effb1be178a4a372ea6822ec
+oid sha256:d015ef15509cfb9f762fd3d2b34b40d57c6c7112878cb58801881b168f1f6703
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e57e13a2fd122f2acccb2788d69aba473e357b7997bcdc0b72c1738b5c9421f2
+oid sha256:6cc0453603d99f5a3a85b0355d23697527cfdd0bc2953c24b342dcfd04a3589f
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee46d463575e74c9a732147771eadee45646a33c68ec6df02d9e322d868ddf4c
+oid sha256:1a449f7255706dff15a0d555917ab0822fa831c22ce55482da38c2abcdd8543a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a653363dc6a007bb7991143643fc45ea80be1e2dd1763a9221017fc9c83922
+oid sha256:0c1fed43e073c0325f316aa96bff1d9a1c3b9720a79c3191e87924a2e78e00a0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.9905564785003662,
   "best_model_checkpoint": "./opt_trained/checkpoint-2412",
-  "epoch": 12.0,
+  "epoch": 13.0,
   "eval_steps": 500,
-  "global_step": 2412,
+  "global_step": 2613,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,21 @@
       "eval_samples_per_second": 36.932,
       "eval_steps_per_second": 9.233,
       "step": 2412
+    },
+    {
+      "epoch": 12.438356164383562,
+      "grad_norm": 1.4806139469146729,
+      "learning_rate": 0.0001501,
+      "loss": 0.9638,
+      "step": 2500
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 0.990676999092102,
+      "eval_runtime": 77.0729,
+      "eval_samples_per_second": 37.056,
+      "eval_steps_per_second": 9.264,
+      "step": 2613
     }
   ],
   "logging_steps": 500,
@@ -150,7 +165,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.119621315584e+16,
+  "total_flos": 8.796256425216e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null