Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cc1d163c2fc3a21f449bd5a992a2497f0783658696bc06514ad8ada654615f8
+oid sha256:14e55e875213d92682e84555aa6b33ea2bd487aa3e64808e8e018ff13e39def4
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28ac966a4de12ee90de7b518b6fd53f8a0eefca55f5177f9d8ff2999b1d4c552
+oid sha256:3f06185fe3645dcc7fe9ce829eede891f7480be5faf7d32fbc087ca425886173
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25cb807b51de3f4a8305842c1ca4aac11e27a7373ff29e3df6dc348caff5f32e
+oid sha256:089eaed71453cd0e3401835315e75796803c6c4fdbddff74a2269b34ba454a8b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed9587b68d28c9698d582d3d4dcbce0d8651715d3d136dd86a87f80621f5d638
+oid sha256:c911fb82d73d273c8bd13fe16df7396949ad9b406bf6a976c6d2d8dce418f3d4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08412499725818634,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-7500",
-  "epoch": 0.6,
+  "best_metric": 0.08401757478713989,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-8000",
+  "epoch": 0.64,
   "eval_steps": 500,
-  "global_step": 7500,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1177,6 +1177,84 @@
       "eval_samples_per_second": 22.765,
       "eval_steps_per_second": 5.691,
       "step": 7500
+    },
+    {
+      "epoch": 0.604,
+      "grad_norm": 0.14278633892536163,
+      "learning_rate": 2.09424e-05,
+      "loss": 0.0665,
+      "step": 7550
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.19127364456653595,
+      "learning_rate": 2.0882400000000002e-05,
+      "loss": 0.0652,
+      "step": 7600
+    },
+    {
+      "epoch": 0.612,
+      "grad_norm": 0.18026478588581085,
+      "learning_rate": 2.0822400000000002e-05,
+      "loss": 0.0673,
+      "step": 7650
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.1525663435459137,
+      "learning_rate": 2.0762400000000003e-05,
+      "loss": 0.0596,
+      "step": 7700
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.1647537797689438,
+      "learning_rate": 2.07024e-05,
+      "loss": 0.0638,
+      "step": 7750
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.14861586689949036,
+      "learning_rate": 2.06424e-05,
+      "loss": 0.0616,
+      "step": 7800
+    },
+    {
+      "epoch": 0.628,
+      "grad_norm": 0.13468614220619202,
+      "learning_rate": 2.05824e-05,
+      "loss": 0.0645,
+      "step": 7850
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.22103475034236908,
+      "learning_rate": 2.0522400000000002e-05,
+      "loss": 0.0618,
+      "step": 7900
+    },
+    {
+      "epoch": 0.636,
+      "grad_norm": 0.21467621624469757,
+      "learning_rate": 2.0462400000000002e-05,
+      "loss": 0.0609,
+      "step": 7950
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.09938893467187881,
+      "learning_rate": 2.04024e-05,
+      "loss": 0.0671,
+      "step": 8000
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 0.08401757478713989,
+      "eval_runtime": 88.0793,
+      "eval_samples_per_second": 22.707,
+      "eval_steps_per_second": 5.677,
+      "step": 8000
     }
   ],
   "logging_steps": 50,
@@ -1196,7 +1274,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.82687367168e+16,
+  "total_flos": 1.948665249792e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null