Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c1147a90e06aa7bfe8e4662bd4a7e9c542eb62571389d08ca0de1309dee33d
+oid sha256:8b29bd7c8570e8d4fa6ab41c839f6272e53370d0ec347fe7fdf8d3f06f46517c
 size 389074464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26fb9f25f2cc06bd5ccf4fc8af12925b0024dda1f2df8bb8e1d73e7fdc16a321
+oid sha256:b8e9e9e02e9eac66c654a5a2ec9e44a14ddca54b4ca6180874ea09f207a9212a
 size 198011700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4ca152b7762ba8b2cf1d5f4750c99b0533a7b9469d79bbb11556eeb21ae3bd0
+oid sha256:a2fbabb02420f33b29ea23843c91d8ed69ded55901170cb0052b61945a50e386
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93f83d259563f490ff1ff7e4916ac178dc618734e66d8ea8288665df23ceab41
+oid sha256:5fa0f7e2faaa98aa485e5dc42922e1b1819381507fa6961c3be50a0b49af04c0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.528462827205658,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.07522331922896097,
+  "best_metric": 0.524067223072052,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.0846262341325811,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 20.219,
       "eval_steps_per_second": 5.057,
       "step": 400
+    },
+    {
+      "epoch": 0.07710390220968501,
+      "grad_norm": 1.0959731340408325,
+      "learning_rate": 2.024419859625558e-05,
+      "loss": 0.7066,
+      "step": 410
+    },
+    {
+      "epoch": 0.07898448519040903,
+      "grad_norm": 0.6210688948631287,
+      "learning_rate": 1.610690180741885e-05,
+      "loss": 0.5475,
+      "step": 420
+    },
+    {
+      "epoch": 0.08086506817113305,
+      "grad_norm": 0.6310533881187439,
+      "learning_rate": 1.240755515695374e-05,
+      "loss": 0.4826,
+      "step": 430
+    },
+    {
+      "epoch": 0.08274565115185707,
+      "grad_norm": 0.6733012199401855,
+      "learning_rate": 9.164181489884296e-06,
+      "loss": 0.4465,
+      "step": 440
+    },
+    {
+      "epoch": 0.0846262341325811,
+      "grad_norm": 0.8576263785362244,
+      "learning_rate": 6.392582196693718e-06,
+      "loss": 0.47,
+      "step": 450
+    },
+    {
+      "epoch": 0.0846262341325811,
+      "eval_loss": 0.524067223072052,
+      "eval_runtime": 110.922,
+      "eval_samples_per_second": 20.185,
+      "eval_steps_per_second": 5.049,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.339236139224269e+16,
+  "total_flos": 4.891046515310592e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null