Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0af1b765e71bd846d26acd0c4fd2bdb0482cb61872789ba0e8a4be3e2dbd5cc1
+oid sha256:d6a0a5b55534350d56712884ba104a70662f3037e676f23fc4409aeb22caeccd
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c4ad1f6d0ec8f5d9a8bbb869e2e3fdacbcd9fc504fb25bbe145c502c33b3a5a
+oid sha256:fa8e96f4a50676171d1e42c954a30811a105697cca5914f838c82970b37e9b2f
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:716ce76fb7afaf5d474ae7ddddef1a9649af0a2191550281b695741b894128e4
+oid sha256:1e1dcbd4ca11878e182b2a443ac16eb53a385e713b9af55f8a27917cd0d74d93
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:303e83c678e93581d63a3650d04963a2cf914298a9658799e3e1f49cf7c8604f
+oid sha256:f03fffc232f1b8a6305d6fa9076c1e1bca28e4d7666df088caa1812431cf9135
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3000512421131134,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.350109409190372,
+  "best_metric": 0.29808175563812256,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.3938730853391685,
   "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": 10.029,
       "eval_steps_per_second": 2.523,
       "step": 400
+    },
+    {
+      "epoch": 0.3588621444201313,
+      "grad_norm": 0.36653754115104675,
+      "learning_rate": 1.9384775070942844e-05,
+      "loss": 0.7181,
+      "step": 410
+    },
+    {
+      "epoch": 0.3676148796498906,
+      "grad_norm": 0.229636549949646,
+      "learning_rate": 1.5423118240122765e-05,
+      "loss": 0.5265,
+      "step": 420
+    },
+    {
+      "epoch": 0.37636761487964987,
+      "grad_norm": 0.2803157567977905,
+      "learning_rate": 1.188081932481891e-05,
+      "loss": 0.1247,
+      "step": 430
+    },
+    {
+      "epoch": 0.3851203501094092,
+      "grad_norm": 0.01452224887907505,
+      "learning_rate": 8.775136049276001e-06,
+      "loss": 0.0002,
+      "step": 440
+    },
+    {
+      "epoch": 0.3938730853391685,
+      "grad_norm": 0.00235812459141016,
+      "learning_rate": 6.121198990230306e-06,
+      "loss": 0.0002,
+      "step": 450
+    },
+    {
+      "epoch": 0.3938730853391685,
+      "eval_loss": 0.29808175563812256,
+      "eval_runtime": 47.9228,
+      "eval_samples_per_second": 10.037,
+      "eval_steps_per_second": 2.525,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3090262709436416e+17,
+  "total_flos": 1.4734321501863936e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null