Training in progress, step 9500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dfabab5bf5157607fcc2602e95b9ce10a5b071f3b4fe4e130b9741ece0fba0a
+oid sha256:79d246435ab5b40ad2ea43d8f5100d2b86ff4b2b6856057a71c7e027ed54a525
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0adc8bbd6eae86e2c260d1fab52c374eee35d382f517b5c8cbd8551e8f7a77a3
+oid sha256:64f09f59006a636b77641a43b73bf147e4d36c6b5a2f33fb4d1638706ccc710a
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d89768c598d4fd9b0ed22710bf5b3c13eec14bfaad44bcf482c9b7c5838dd420
+oid sha256:9d34bc75d96aba8284db8d20e2294a4e554617b7623afa838e1b67103dc8d05a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:620c7bc458bafe9b83f6fadd9f5a5700bbd89b438e325546819b47236eeb8e3e
+oid sha256:6239f6e8ed7e2039649ceba0353d677c59a2e919a67e2025fa635742b0397798
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0838891863822937,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-9000",
-  "epoch": 0.72,
+  "best_metric": 0.08371420204639435,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-9500",
+  "epoch": 0.76,
   "eval_steps": 500,
-  "global_step": 9000,
+  "global_step": 9500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1411,6 +1411,84 @@
       "eval_samples_per_second": 22.706,
       "eval_steps_per_second": 5.676,
       "step": 9000
+    },
+    {
+      "epoch": 0.724,
+      "grad_norm": 0.152841717004776,
+      "learning_rate": 1.91424e-05,
+      "loss": 0.0611,
+      "step": 9050
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 0.16737787425518036,
+      "learning_rate": 1.90824e-05,
+      "loss": 0.0626,
+      "step": 9100
+    },
+    {
+      "epoch": 0.732,
+      "grad_norm": 0.1456371396780014,
+      "learning_rate": 1.90224e-05,
+      "loss": 0.0599,
+      "step": 9150
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 0.1772635579109192,
+      "learning_rate": 1.89624e-05,
+      "loss": 0.0577,
+      "step": 9200
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.11802179366350174,
+      "learning_rate": 1.89024e-05,
+      "loss": 0.0645,
+      "step": 9250
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 0.1235092505812645,
+      "learning_rate": 1.88424e-05,
+      "loss": 0.0584,
+      "step": 9300
+    },
+    {
+      "epoch": 0.748,
+      "grad_norm": 0.11901592463254929,
+      "learning_rate": 1.8782399999999998e-05,
+      "loss": 0.06,
+      "step": 9350
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 0.09477788209915161,
+      "learning_rate": 1.87224e-05,
+      "loss": 0.0637,
+      "step": 9400
+    },
+    {
+      "epoch": 0.756,
+      "grad_norm": 0.12917232513427734,
+      "learning_rate": 1.86624e-05,
+      "loss": 0.0648,
+      "step": 9450
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.17290474474430084,
+      "learning_rate": 1.86024e-05,
+      "loss": 0.0638,
+      "step": 9500
+    },
+    {
+      "epoch": 0.76,
+      "eval_loss": 0.08371420204639435,
+      "eval_runtime": 88.0684,
+      "eval_samples_per_second": 22.71,
+      "eval_steps_per_second": 5.677,
+      "step": 9500
     }
   ],
   "logging_steps": 50,
@@ -1430,7 +1508,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.192248406016e+16,
+  "total_flos": 2.314039984128e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null