Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:234b1d5c01d29c1839967d8b18af236339a3d667efeb276feb222738d4348424
+oid sha256:0af1b765e71bd846d26acd0c4fd2bdb0482cb61872789ba0e8a4be3e2dbd5cc1
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5475096bc4406baf8f948f663a50d0793d2d5ade166f537d50ac7b7161329ba6
+oid sha256:3c4ad1f6d0ec8f5d9a8bbb869e2e3fdacbcd9fc504fb25bbe145c502c33b3a5a
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c56088c033bb948005186a85403f9f53a67e87ceb9bf29f30351f95a6f5bc69f
+oid sha256:716ce76fb7afaf5d474ae7ddddef1a9649af0a2191550281b695741b894128e4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6230a4f38a0ea478447f5ea0afea90b5855d705f677280e45e7e6abb464194a3
+oid sha256:303e83c678e93581d63a3650d04963a2cf914298a9658799e3e1f49cf7c8604f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.31218644976615906,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.3063457330415755,
+  "best_metric": 0.3000512421131134,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.350109409190372,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 10.03,
       "eval_steps_per_second": 2.523,
       "step": 350
+    },
+    {
+      "epoch": 0.3150984682713348,
+      "grad_norm": 0.3766857385635376,
+      "learning_rate": 4.4741920297719214e-05,
+      "loss": 0.6989,
+      "step": 360
+    },
+    {
+      "epoch": 0.3238512035010941,
+      "grad_norm": 0.45434561371803284,
+      "learning_rate": 3.901036025444568e-05,
+      "loss": 0.6038,
+      "step": 370
+    },
+    {
+      "epoch": 0.33260393873085337,
+      "grad_norm": 0.002181870862841606,
+      "learning_rate": 3.358324345457592e-05,
+      "loss": 0.1711,
+      "step": 380
+    },
+    {
+      "epoch": 0.3413566739606127,
+      "grad_norm": 0.0015434159431606531,
+      "learning_rate": 2.8487010265626928e-05,
+      "loss": 0.0022,
+      "step": 390
+    },
+    {
+      "epoch": 0.350109409190372,
+      "grad_norm": 0.07286681234836578,
+      "learning_rate": 2.3746489023423744e-05,
+      "loss": 0.0005,
+      "step": 400
+    },
+    {
+      "epoch": 0.350109409190372,
+      "eval_loss": 0.3000512421131134,
+      "eval_runtime": 47.9614,
+      "eval_samples_per_second": 10.029,
+      "eval_steps_per_second": 2.523,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1455090721292288e+17,
+  "total_flos": 1.3090262709436416e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null