Training in progress, epoch 15, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e4bafc2b77710795cdff82135d33b98d3e03624530d1e4f26289dbd3fd3de22
+oid sha256:f9b902eb3b4443e9e6ca1c49076b09284849a2ffb4ecdc3e8c3bf1fbe514bbc7
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f8a18366996dfb79e76aa61f98956ea2819f13009f48dcd12034b4ebc915c40
+oid sha256:d7e6a95af0728eac99d0191b1cec4690c95dfc879ed16d9bb13979700895bffa
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8966283890d5dc8ebbfea9d3f7bdea0c6e04a5d3e7ba30691c56d6df18154ed1
+oid sha256:7dc3166b9e11cb23782075549599a0e8c4e8aab9089933e217d2e070c0e8f21d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2205ee6bf1fa4b47a57261bcc175ce8e1c6681af606be42f521e4e63f5f43338
+oid sha256:dfa3e083a3e79a06e9eae173f2709cb78a344ee7abc2df0517cdf8c00499b006
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.988075315952301,
   "best_model_checkpoint": "./opt_trained/checkpoint-2814",
-  "epoch": 14.0,
+  "epoch": 15.0,
   "eval_steps": 500,
-  "global_step": 2814,
+  "global_step": 3015,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -154,6 +154,21 @@
       "eval_samples_per_second": 37.083,
       "eval_steps_per_second": 9.271,
       "step": 2814
+    },
+    {
+      "epoch": 14.926525529265255,
+      "grad_norm": 1.8893911838531494,
+      "learning_rate": 0.0001001,
+      "loss": 0.9428,
+      "step": 3000
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 0.9882552027702332,
+      "eval_runtime": 77.0864,
+      "eval_samples_per_second": 37.049,
+      "eval_steps_per_second": 9.262,
+      "step": 3015
     }
   ],
   "logging_steps": 500,
@@ -173,7 +188,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.472891534848e+16,
+  "total_flos": 1.014952664448e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null