Training in progress, step 22500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b24490e1afd177c9d7aa64e2bc93a14c723f2b07f34c096656faca30a819b31
+oid sha256:596c1e3afdd59a5f888e2e097f32bc12312812a5874bc9ba56a6a84a477bb16a
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cb51a493e883d2bba3783d9a9c610f4b7ed8a2fdbc2ae094434c3938af33f10
+oid sha256:5db73359845187641317b27e1b4060f1552fef0e348ea1b12216d2d2fe327502
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75610a62f0c2e3c2144553b21cd56625818792160128bd8489e6566f2e9cc991
+oid sha256:59a02c4a661b5f9af67ada735fa8a7871859bbc9bec13b24943a443d89f55f00
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16420615b82a27af4c6aa0fff49c44fb5eed4e6ef5c3ebd2f44a0387c672c1ca
+oid sha256:5024d85f7d5741e2ee48baa326700e94d49b2910a8865857cf6ad58106fa2d05
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08166228979825974,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-22000",
-  "epoch": 1.76,
+  "best_metric": 0.0815029963850975,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-22500",
+  "epoch": 1.8,
   "eval_steps": 500,
-  "global_step": 22000,
+  "global_step": 22500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3439,6 +3439,84 @@
       "eval_samples_per_second": 22.704,
       "eval_steps_per_second": 5.676,
       "step": 22000
+    },
+    {
+      "epoch": 1.764,
+      "grad_norm": 0.18784619867801666,
+      "learning_rate": 3.5483999999999998e-06,
+      "loss": 0.0559,
+      "step": 22050
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.1378210335969925,
+      "learning_rate": 3.4884e-06,
+      "loss": 0.0528,
+      "step": 22100
+    },
+    {
+      "epoch": 1.772,
+      "grad_norm": 0.1482810080051422,
+      "learning_rate": 3.4284e-06,
+      "loss": 0.0535,
+      "step": 22150
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 0.2096211314201355,
+      "learning_rate": 3.3684000000000002e-06,
+      "loss": 0.0455,
+      "step": 22200
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.16895908117294312,
+      "learning_rate": 3.3084000000000004e-06,
+      "loss": 0.0527,
+      "step": 22250
+    },
+    {
+      "epoch": 1.784,
+      "grad_norm": 0.11279798299074173,
+      "learning_rate": 3.2484e-06,
+      "loss": 0.0524,
+      "step": 22300
+    },
+    {
+      "epoch": 1.788,
+      "grad_norm": 0.1444096565246582,
+      "learning_rate": 3.1884000000000003e-06,
+      "loss": 0.0539,
+      "step": 22350
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.16793648898601532,
+      "learning_rate": 3.1284e-06,
+      "loss": 0.0578,
+      "step": 22400
+    },
+    {
+      "epoch": 1.796,
+      "grad_norm": 0.1865730732679367,
+      "learning_rate": 3.0684e-06,
+      "loss": 0.0538,
+      "step": 22450
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.11493191868066788,
+      "learning_rate": 3.0084e-06,
+      "loss": 0.0515,
+      "step": 22500
+    },
+    {
+      "epoch": 1.8,
+      "eval_loss": 0.0815029963850975,
+      "eval_runtime": 88.0709,
+      "eval_samples_per_second": 22.709,
+      "eval_steps_per_second": 5.677,
+      "step": 22500
     }
   ],
   "logging_steps": 50,
@@ -3458,7 +3536,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.358829436928e+16,
+  "total_flos": 5.48062101504e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null