Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3833cd0ac15cb58e965e1fe964f2d730c9bc22aa3217feb7a43c6f35fab45e95
+oid sha256:c63a78f795107dd71dbb2d54be8713dbd86b613f378c5fac490f8c01575cb6d9
 size 389074464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0f75600a1bc88c0be9a59ff8d846b84467168078c722d628c0784b0ef7ca05c
+oid sha256:d452638b2294c2930ecef78001d8ae163b22480714297ee9377297e4d378ee03
 size 198011700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9abda639c2cfa293d536cf66b24d39666c85f8fe12c5ec6b2e6c3f2d17980cd8
+oid sha256:f9771a5e723821a32e63d9d270ebfc9dbe650a0189f3bf6a00990cbbff71218c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4be7b38aa7a01f117ebb95bff4f596a12bcbebf1c53b704b1e44c42b56276682
+oid sha256:fe3012fb121cd84e6e41f718fd33de9e34ed33145ada7b055f7e25e49408431d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5289891362190247,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.07522331922896097,
+  "best_metric": 0.5236806869506836,
+  "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": 20.45,
       "eval_steps_per_second": 5.115,
       "step": 400
+    },
+    {
+      "epoch": 0.07710390220968501,
+      "grad_norm": 0.6698129773139954,
+      "learning_rate": 2.081714761313074e-05,
+      "loss": 0.7042,
+      "step": 410
+    },
+    {
+      "epoch": 0.07898448519040903,
+      "grad_norm": 0.6338317394256592,
+      "learning_rate": 1.656275751894957e-05,
+      "loss": 0.5512,
+      "step": 420
+    },
+    {
+      "epoch": 0.08086506817113305,
+      "grad_norm": 0.6592607498168945,
+      "learning_rate": 1.275871237837696e-05,
+      "loss": 0.4842,
+      "step": 430
+    },
+    {
+      "epoch": 0.08274565115185707,
+      "grad_norm": 0.6793785095214844,
+      "learning_rate": 9.423545116956494e-06,
+      "loss": 0.4469,
+      "step": 440
+    },
+    {
+      "epoch": 0.0846262341325811,
+      "grad_norm": 0.8718426823616028,
+      "learning_rate": 6.573504334335994e-06,
+      "loss": 0.4685,
+      "step": 450
+    },
+    {
+      "epoch": 0.0846262341325811,
+      "eval_loss": 0.5236806869506836,
+      "eval_runtime": 109.5695,
+      "eval_samples_per_second": 20.435,
+      "eval_steps_per_second": 5.111,
+      "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