Training in progress, epoch 14, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d015ef15509cfb9f762fd3d2b34b40d57c6c7112878cb58801881b168f1f6703
+oid sha256:4e4bafc2b77710795cdff82135d33b98d3e03624530d1e4f26289dbd3fd3de22
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cc0453603d99f5a3a85b0355d23697527cfdd0bc2953c24b342dcfd04a3589f
+oid sha256:0f8a18366996dfb79e76aa61f98956ea2819f13009f48dcd12034b4ebc915c40
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a449f7255706dff15a0d555917ab0822fa831c22ce55482da38c2abcdd8543a
+oid sha256:8966283890d5dc8ebbfea9d3f7bdea0c6e04a5d3e7ba30691c56d6df18154ed1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c1fed43e073c0325f316aa96bff1d9a1c3b9720a79c3191e87924a2e78e00a0
+oid sha256:2205ee6bf1fa4b47a57261bcc175ce8e1c6681af606be42f521e4e63f5f43338
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9905564785003662,
-  "best_model_checkpoint": "./opt_trained/checkpoint-2412",
-  "epoch": 13.0,
+  "best_metric": 0.988075315952301,
+  "best_model_checkpoint": "./opt_trained/checkpoint-2814",
+  "epoch": 14.0,
   "eval_steps": 500,
-  "global_step": 2613,
+  "global_step": 2814,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -146,6 +146,14 @@
       "eval_samples_per_second": 37.056,
       "eval_steps_per_second": 9.264,
       "step": 2613
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 0.988075315952301,
+      "eval_runtime": 77.0166,
+      "eval_samples_per_second": 37.083,
+      "eval_steps_per_second": 9.271,
+      "step": 2814
     }
   ],
   "logging_steps": 500,
@@ -165,7 +173,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.796256425216e+16,
+  "total_flos": 9.472891534848e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null