Training in progress, step 7500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b6beb99d53dc85acda2f8ace3d229350875cf63a734ef325761a0e457e7f612
+oid sha256:3d943046e9cee201d90914fe8b465ff2a60ed77f63734520ab719ff090af0b77
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2701e97535a87882ab713841abd901bf0568af17cf0a339a8c12431670adb4b
+oid sha256:78ae5dc18c5c42b1ab70202f0fb9bb247ed17fda7375648f017acb36f68f1f78
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f110c3c4fe22448ff8783649fbef7b54b070a7c45b4469624f986b9a7cd74b3
+oid sha256:9e6d24d84d7824f21eaa5899dfd03019f712068506f4aab4dbb4d9b68c233cb1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ccfed333de7ee72e49042ff43701fa36052369ab2407e1f957a0a822d1a798f
+oid sha256:551dce9770f5878295b9620e9ba43823a7a814027d76d3160674655baa064b21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08321517705917358,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-6000",
-  "epoch": 1.12,
+  "best_metric": 0.08285799622535706,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-7500",
+  "epoch": 1.2,
   "eval_steps": 500,
-  "global_step": 7000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1099,6 +1099,84 @@
       "eval_samples_per_second": 17.139,
       "eval_steps_per_second": 2.142,
       "step": 7000
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 5663.18603515625,
+      "learning_rate": 1.872e-05,
+      "loss": 0.0537,
+      "step": 7050
+    },
+    {
+      "epoch": 1.1360000000000001,
+      "grad_norm": 9569.765625,
+      "learning_rate": 1.8639999999999998e-05,
+      "loss": 0.0607,
+      "step": 7100
+    },
+    {
+      "epoch": 1.144,
+      "grad_norm": 7370.98046875,
+      "learning_rate": 1.8560000000000002e-05,
+      "loss": 0.0607,
+      "step": 7150
+    },
+    {
+      "epoch": 1.152,
+      "grad_norm": 5951.6533203125,
+      "learning_rate": 1.848e-05,
+      "loss": 0.0547,
+      "step": 7200
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 8285.0830078125,
+      "learning_rate": 1.84e-05,
+      "loss": 0.0589,
+      "step": 7250
+    },
+    {
+      "epoch": 1.168,
+      "grad_norm": 7549.8271484375,
+      "learning_rate": 1.832e-05,
+      "loss": 0.0587,
+      "step": 7300
+    },
+    {
+      "epoch": 1.176,
+      "grad_norm": 7480.25927734375,
+      "learning_rate": 1.824e-05,
+      "loss": 0.058,
+      "step": 7350
+    },
+    {
+      "epoch": 1.184,
+      "grad_norm": 35994.15234375,
+      "learning_rate": 1.816e-05,
+      "loss": 0.0585,
+      "step": 7400
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 7489.05859375,
+      "learning_rate": 1.808e-05,
+      "loss": 0.0616,
+      "step": 7450
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 6134.80126953125,
+      "learning_rate": 1.8e-05,
+      "loss": 0.0572,
+      "step": 7500
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.08285799622535706,
+      "eval_runtime": 116.9169,
+      "eval_samples_per_second": 17.106,
+      "eval_steps_per_second": 2.138,
+      "step": 7500
     }
   ],
   "logging_steps": 50,
@@ -1118,7 +1196,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.410164187136e+16,
+  "total_flos": 3.65374734336e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null