Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d92451ae8471118d0f4ff3201506d5a90f2bd77bc4421e8d24fa92669e67129e
+oid sha256:e1e91e1bdef8cc188ea4d189cd5523f60cddadc3613fe79933294461a702e8a8
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1139382effd26c75058f4fa1f776505299c54924e4b6db23f70ae7f64e41724
+oid sha256:89290f193b6b7457d80f97bce6f0ec93a64c4a9bc3d593d8d12aeb4cde9c3c6d
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a72f59ef3242e6b962c12852e52500422626ceac4df8fb1a56d6379db9b8a98
+oid sha256:0ea7477084e9e4ebf5f677e60167e6c2deee97d19a5a21299c6eb4ed40d31928
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94a107a53df948b9265998ab0f5b874dabd9db8a133cddea9279d7b4c6c999e9
+oid sha256:69f50b15ae17c7257c9fed364b38e68d62581d1ae697e8e4bb273e2e41cb49e9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08653330057859421,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-4500",
-  "epoch": 0.36,
+  "best_metric": 0.0860014408826828,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-5000",
+  "epoch": 0.4,
   "eval_steps": 500,
-  "global_step": 4500,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -709,6 +709,84 @@
       "eval_samples_per_second": 22.784,
       "eval_steps_per_second": 5.696,
       "step": 4500
+    },
+    {
+      "epoch": 0.364,
+      "grad_norm": 0.09011202305555344,
+      "learning_rate": 2.45424e-05,
+      "loss": 0.0699,
+      "step": 4550
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 0.1441943347454071,
+      "learning_rate": 2.44824e-05,
+      "loss": 0.0634,
+      "step": 4600
+    },
+    {
+      "epoch": 0.372,
+      "grad_norm": 0.17736917734146118,
+      "learning_rate": 2.4422400000000002e-05,
+      "loss": 0.0688,
+      "step": 4650
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 0.16143649816513062,
+      "learning_rate": 2.4362400000000002e-05,
+      "loss": 0.0575,
+      "step": 4700
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.1789257675409317,
+      "learning_rate": 2.43024e-05,
+      "loss": 0.067,
+      "step": 4750
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.13589045405387878,
+      "learning_rate": 2.42424e-05,
+      "loss": 0.0713,
+      "step": 4800
+    },
+    {
+      "epoch": 0.388,
+      "grad_norm": 0.12760789692401886,
+      "learning_rate": 2.41824e-05,
+      "loss": 0.0644,
+      "step": 4850
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 0.17507490515708923,
+      "learning_rate": 2.41224e-05,
+      "loss": 0.0634,
+      "step": 4900
+    },
+    {
+      "epoch": 0.396,
+      "grad_norm": 0.15503354370594025,
+      "learning_rate": 2.4062400000000002e-05,
+      "loss": 0.0654,
+      "step": 4950
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.12309867143630981,
+      "learning_rate": 2.4002400000000002e-05,
+      "loss": 0.0698,
+      "step": 5000
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.0860014408826828,
+      "eval_runtime": 87.7287,
+      "eval_samples_per_second": 22.798,
+      "eval_steps_per_second": 5.699,
+      "step": 5000
     }
   ],
   "logging_steps": 50,
@@ -728,7 +806,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.096124203008e+16,
+  "total_flos": 1.21791578112e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null