Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a37da1bec04a539e9083a0690c020dd6b5a85ca6ba96130597ced0a592b992f
+oid sha256:5c001192b49ac33ee8f47a5309a370cfdfa4c3a70dda715a94b188da6ca70162
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b600d17da29b382922c79850abe38cc3a0b9b7af51d7d358a1ba2bfc872d80d7
+oid sha256:7637d351cab3d505a7c81380e8e251c1b0641e2bf3a5583d4012a983c8e533e9
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d49a79be8c359f422cb59c77ee0154f081dfd7e588f93c61b503afdc15d8e88d
+oid sha256:0233e0c60d0eeda67a49aa9719818a64279caead7bb9a9439f543fe78e64a894
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d33bcf6e84bd960ce66a36a7bd45e4c58615ca69233e24115c69f6a6b57693ba
+oid sha256:e79009f389b4fe7467240d87a72862340c60d6549edf4f6a20e75882e0962455
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08841572701931,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-2500",
-  "epoch": 0.2,
+  "best_metric": 0.08755213767290115,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-3000",
+  "epoch": 0.24,
   "eval_steps": 500,
-  "global_step": 2500,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -397,6 +397,84 @@
       "eval_samples_per_second": 22.791,
       "eval_steps_per_second": 5.698,
       "step": 2500
+    },
+    {
+      "epoch": 0.204,
+      "grad_norm": 0.14937053620815277,
+      "learning_rate": 2.69412e-05,
+      "loss": 0.0727,
+      "step": 2550
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 0.15660254657268524,
+      "learning_rate": 2.68812e-05,
+      "loss": 0.0656,
+      "step": 2600
+    },
+    {
+      "epoch": 0.212,
+      "grad_norm": 0.09593763947486877,
+      "learning_rate": 2.68212e-05,
+      "loss": 0.0726,
+      "step": 2650
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 0.25192323327064514,
+      "learning_rate": 2.67624e-05,
+      "loss": 0.0753,
+      "step": 2700
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.1267642378807068,
+      "learning_rate": 2.67024e-05,
+      "loss": 0.0707,
+      "step": 2750
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 0.13844658434391022,
+      "learning_rate": 2.66424e-05,
+      "loss": 0.0711,
+      "step": 2800
+    },
+    {
+      "epoch": 0.228,
+      "grad_norm": 0.15095186233520508,
+      "learning_rate": 2.65824e-05,
+      "loss": 0.0696,
+      "step": 2850
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 0.09553442895412445,
+      "learning_rate": 2.65224e-05,
+      "loss": 0.0709,
+      "step": 2900
+    },
+    {
+      "epoch": 0.236,
+      "grad_norm": 0.21425922214984894,
+      "learning_rate": 2.64624e-05,
+      "loss": 0.0662,
+      "step": 2950
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.10706017166376114,
+      "learning_rate": 2.64024e-05,
+      "loss": 0.0721,
+      "step": 3000
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 0.08755213767290115,
+      "eval_runtime": 87.7619,
+      "eval_samples_per_second": 22.789,
+      "eval_steps_per_second": 5.697,
+      "step": 3000
     }
   ],
   "logging_steps": 50,
@@ -416,7 +494,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6089578905600000.0,
+  "total_flos": 7307494686720000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null