Training in progress, step 4500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:164eb6a81614e9f1939013796bd9b48e2712186901dcd74df1d6b04dce844484
+oid sha256:d92451ae8471118d0f4ff3201506d5a90f2bd77bc4421e8d24fa92669e67129e
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1b12fd71694fa1ec35a8b9d6e65e079baa75b27e5b9f063a99bdafa82fe1e09
+oid sha256:a1139382effd26c75058f4fa1f776505299c54924e4b6db23f70ae7f64e41724
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66d55cead2e68dd96646c1b6f8fd0e4361ef538e5be0ae590c27b3898e8c95df
+oid sha256:4a72f59ef3242e6b962c12852e52500422626ceac4df8fb1a56d6379db9b8a98
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53ae3cfedd2dd31595a079dd5baf168ac1b0849191aed860395ad88084b14144
+oid sha256:94a107a53df948b9265998ab0f5b874dabd9db8a133cddea9279d7b4c6c999e9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0867869183421135,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-4000",
-  "epoch": 0.32,
+  "best_metric": 0.08653330057859421,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-4500",
+  "epoch": 0.36,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -631,6 +631,84 @@
       "eval_samples_per_second": 22.784,
       "eval_steps_per_second": 5.696,
       "step": 4000
+    },
+    {
+      "epoch": 0.324,
+      "grad_norm": 0.07968447357416153,
+      "learning_rate": 2.5142400000000002e-05,
+      "loss": 0.0635,
+      "step": 4050
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.1641731858253479,
+      "learning_rate": 2.5082400000000002e-05,
+      "loss": 0.0667,
+      "step": 4100
+    },
+    {
+      "epoch": 0.332,
+      "grad_norm": 0.15083415806293488,
+      "learning_rate": 2.5022400000000003e-05,
+      "loss": 0.071,
+      "step": 4150
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.16534006595611572,
+      "learning_rate": 2.4962400000000003e-05,
+      "loss": 0.0735,
+      "step": 4200
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.1629945933818817,
+      "learning_rate": 2.49024e-05,
+      "loss": 0.0641,
+      "step": 4250
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.11393357813358307,
+      "learning_rate": 2.48424e-05,
+      "loss": 0.0679,
+      "step": 4300
+    },
+    {
+      "epoch": 0.348,
+      "grad_norm": 0.10581399500370026,
+      "learning_rate": 2.4782400000000002e-05,
+      "loss": 0.0666,
+      "step": 4350
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.1571837067604065,
+      "learning_rate": 2.4722400000000002e-05,
+      "loss": 0.0619,
+      "step": 4400
+    },
+    {
+      "epoch": 0.356,
+      "grad_norm": 0.11944606155157089,
+      "learning_rate": 2.4662400000000003e-05,
+      "loss": 0.0666,
+      "step": 4450
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.17318391799926758,
+      "learning_rate": 2.46024e-05,
+      "loss": 0.0684,
+      "step": 4500
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 0.08653330057859421,
+      "eval_runtime": 87.7823,
+      "eval_samples_per_second": 22.784,
+      "eval_steps_per_second": 5.696,
+      "step": 4500
     }
   ],
   "logging_steps": 50,
@@ -650,7 +728,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9743326248960000.0,
+  "total_flos": 1.096124203008e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null