Training in progress, epoch 16, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9b902eb3b4443e9e6ca1c49076b09284849a2ffb4ecdc3e8c3bf1fbe514bbc7
+oid sha256:2d3a577e65845eb010e1c16ec7fa32ad36897f7e449c26ac8dfb9529a0f69423
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7e6a95af0728eac99d0191b1cec4690c95dfc879ed16d9bb13979700895bffa
+oid sha256:de2450c6993e9a56e7dc9145137de8e225a8a9120841cbf3c0dfa256a5593dcc
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dc3166b9e11cb23782075549599a0e8c4e8aab9089933e217d2e070c0e8f21d
+oid sha256:dacd9ceced445683b429d8048de3408ac5db4d13805bc178931c8c7bec632745
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfa3e083a3e79a06e9eae173f2709cb78a344ee7abc2df0517cdf8c00499b006
+oid sha256:32c36238a16299a3ca7723d304d049d1e0393d69d7c985f0021c667d4adf33a6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.988075315952301,
-  "best_model_checkpoint": "./opt_trained/checkpoint-2814",
-  "epoch": 15.0,
+  "best_metric": 0.9877104163169861,
+  "best_model_checkpoint": "./opt_trained/checkpoint-3216",
+  "epoch": 16.0,
   "eval_steps": 500,
-  "global_step": 3015,
+  "global_step": 3216,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -169,6 +169,14 @@
       "eval_samples_per_second": 37.049,
       "eval_steps_per_second": 9.262,
       "step": 3015
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 0.9877104163169861,
+      "eval_runtime": 77.0222,
+      "eval_samples_per_second": 37.08,
+      "eval_steps_per_second": 9.27,
+      "step": 3216
     }
   ],
   "logging_steps": 500,
@@ -188,7 +196,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.014952664448e+17,
+  "total_flos": 1.0826161754112e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null