Training in progress, step 3500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c001192b49ac33ee8f47a5309a370cfdfa4c3a70dda715a94b188da6ca70162
+oid sha256:d826c309b9f9492a58d67f6f2eecf7cdd6615d329adca02ac882e7b2d1de12cb
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7637d351cab3d505a7c81380e8e251c1b0641e2bf3a5583d4012a983c8e533e9
+oid sha256:c3a553addc7ddb7e0af58a94d7cce4e00b2edf20465e6287f926268d68186099
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0233e0c60d0eeda67a49aa9719818a64279caead7bb9a9439f543fe78e64a894
+oid sha256:4a7290491808e872bdfba856354703f0501eed54b9da7aaa39843c9c248c6159
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e79009f389b4fe7467240d87a72862340c60d6549edf4f6a20e75882e0962455
+oid sha256:5c790c63fb7345bfd79d855efc8355667eb23eb3bcba2a26737d1f0ffb0ba07b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08755213767290115,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-3000",
-  "epoch": 0.24,
+  "best_metric": 0.0869474709033966,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-3500",
+  "epoch": 0.28,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -475,6 +475,84 @@
       "eval_samples_per_second": 22.789,
       "eval_steps_per_second": 5.697,
       "step": 3000
+    },
+    {
+      "epoch": 0.244,
+      "grad_norm": 0.18366344273090363,
+      "learning_rate": 2.63424e-05,
+      "loss": 0.0781,
+      "step": 3050
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.15975314378738403,
+      "learning_rate": 2.62824e-05,
+      "loss": 0.0771,
+      "step": 3100
+    },
+    {
+      "epoch": 0.252,
+      "grad_norm": 0.14510446786880493,
+      "learning_rate": 2.6222399999999998e-05,
+      "loss": 0.0734,
+      "step": 3150
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.10040156543254852,
+      "learning_rate": 2.61624e-05,
+      "loss": 0.0624,
+      "step": 3200
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.1453912854194641,
+      "learning_rate": 2.61024e-05,
+      "loss": 0.0661,
+      "step": 3250
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.13999666273593903,
+      "learning_rate": 2.60424e-05,
+      "loss": 0.0694,
+      "step": 3300
+    },
+    {
+      "epoch": 0.268,
+      "grad_norm": 0.13396582007408142,
+      "learning_rate": 2.59824e-05,
+      "loss": 0.0692,
+      "step": 3350
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.1334969699382782,
+      "learning_rate": 2.59224e-05,
+      "loss": 0.0629,
+      "step": 3400
+    },
+    {
+      "epoch": 0.276,
+      "grad_norm": 0.16296976804733276,
+      "learning_rate": 2.5862399999999998e-05,
+      "loss": 0.0679,
+      "step": 3450
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.1321544647216797,
+      "learning_rate": 2.58024e-05,
+      "loss": 0.0764,
+      "step": 3500
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 0.0869474709033966,
+      "eval_runtime": 87.6679,
+      "eval_samples_per_second": 22.813,
+      "eval_steps_per_second": 5.703,
+      "step": 3500
     }
   ],
   "logging_steps": 50,
@@ -494,7 +572,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7307494686720000.0,
+  "total_flos": 8525410467840000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null