Training in progress, step 16500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d7224364f596ebfca3a99c1d3b9d449fb04ce1b01252f00b468ebb7f2583738
+oid sha256:08df383ddf8539b1c156d553a75182fefc1bd9cb8d1be80a3bb2d48549c72268
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c146dfaf517426e21001d58ecb591e013237c1f0457fc2b2e18c8128376dd232
+oid sha256:4942b168045dd01e1507ab88999a6fa88c39bef7244ce53f7c7f5c00a6c5e0d5
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e2dd927672719d15b56be948c4d341bf0d4717fdddd441106e1853c80a9c881
+oid sha256:ac7de248f1039c222833b4241b4257bf2afda51b5d7ba778b660b2c2050b7e97
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc65b1cc8bef515a746903c5c0ceccfd01df11517dd7fe9004c63360d9c9a98b
+oid sha256:c923446f6a9040a7fff312fb9744a6058c7cd7ec45e59a8a878177b2e96073c7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.08243728429079056,
   "best_model_checkpoint": "./fine-tuned/checkpoint-15000",
-  "epoch": 1.28,
+  "epoch": 1.32,
   "eval_steps": 500,
-  "global_step": 16000,
+  "global_step": 16500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2503,6 +2503,84 @@
       "eval_samples_per_second": 22.708,
       "eval_steps_per_second": 5.677,
       "step": 16000
+    },
+    {
+      "epoch": 1.284,
+      "grad_norm": 0.14214898645877838,
+      "learning_rate": 1.07448e-05,
+      "loss": 0.056,
+      "step": 16050
+    },
+    {
+      "epoch": 1.288,
+      "grad_norm": 0.13236215710639954,
+      "learning_rate": 1.06848e-05,
+      "loss": 0.0566,
+      "step": 16100
+    },
+    {
+      "epoch": 1.292,
+      "grad_norm": 0.1475580334663391,
+      "learning_rate": 1.06248e-05,
+      "loss": 0.0507,
+      "step": 16150
+    },
+    {
+      "epoch": 1.296,
+      "grad_norm": 0.13150113821029663,
+      "learning_rate": 1.05648e-05,
+      "loss": 0.0488,
+      "step": 16200
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.0869784876704216,
+      "learning_rate": 1.0504800000000001e-05,
+      "loss": 0.0498,
+      "step": 16250
+    },
+    {
+      "epoch": 1.304,
+      "grad_norm": 0.15695451200008392,
+      "learning_rate": 1.04448e-05,
+      "loss": 0.0517,
+      "step": 16300
+    },
+    {
+      "epoch": 1.308,
+      "grad_norm": 0.1383635401725769,
+      "learning_rate": 1.0384800000000001e-05,
+      "loss": 0.0509,
+      "step": 16350
+    },
+    {
+      "epoch": 1.312,
+      "grad_norm": 0.17300955951213837,
+      "learning_rate": 1.0324800000000002e-05,
+      "loss": 0.0587,
+      "step": 16400
+    },
+    {
+      "epoch": 1.316,
+      "grad_norm": 0.1608356237411499,
+      "learning_rate": 1.02648e-05,
+      "loss": 0.0523,
+      "step": 16450
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.1598045974969864,
+      "learning_rate": 1.0204800000000001e-05,
+      "loss": 0.0524,
+      "step": 16500
+    },
+    {
+      "epoch": 1.32,
+      "eval_loss": 0.08258219808340073,
+      "eval_runtime": 88.0858,
+      "eval_samples_per_second": 22.705,
+      "eval_steps_per_second": 5.676,
+      "step": 16500
     }
   ],
   "logging_steps": 50,
@@ -2522,7 +2600,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.897330499584e+16,
+  "total_flos": 4.019122077696e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null