Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0512adf5e2d704951a2119467df3b023e91752180a2584792dac97f45a6d51d2
+oid sha256:6e7ec7a5cefd65b7298b3dd29d969d7733b469965aa96b86800ee245f9fbc838
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:090a15778b5358a36e826a4b0f0647896b115d7c92a6d4fca84f94715f21a62a
-size 71077780
+oid sha256:17b2bddc66eb120b7a6ea5c26aa7058ac92187a758cd04d9162edc03849f2926
+size 71078228

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1547f7a46a4025a2e8f1050349fae922a592afd828add8bd99bed2de0e91df91
+oid sha256:ab5ec668da2c84fab883766cc1fae7ca32155c821bbec7edcd09197050c5f1ed
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:110c23ba7ac9436ac98f0e4bb88f393b7c16138e63fbbb47259fe31aa44af728
+oid sha256:735a1b0cd55f79037943936c337afc90625099f161e9c9087d89d1e07502d69f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5298550128936768,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.4208754208754209,
+  "best_metric": 1.5193032026290894,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.5050505050505051,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 46.18,
       "eval_steps_per_second": 11.637,
       "step": 250
+    },
+    {
+      "epoch": 0.4377104377104377,
+      "grad_norm": 0.22314110398292542,
+      "learning_rate": 0.0001176322813380051,
+      "loss": 1.5448,
+      "step": 260
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.3010413348674774,
+      "learning_rate": 0.00011021679639881638,
+      "loss": 1.5598,
+      "step": 270
+    },
+    {
+      "epoch": 0.4713804713804714,
+      "grad_norm": 0.6368963718414307,
+      "learning_rate": 0.00010278320360118368,
+      "loss": 1.3521,
+      "step": 280
+    },
+    {
+      "epoch": 0.4882154882154882,
+      "grad_norm": 0.9707889556884766,
+      "learning_rate": 9.536771866199493e-05,
+      "loss": 1.38,
+      "step": 290
+    },
+    {
+      "epoch": 0.5050505050505051,
+      "grad_norm": 2.023444175720215,
+      "learning_rate": 8.800646907847192e-05,
+      "loss": 1.8022,
+      "step": 300
+    },
+    {
+      "epoch": 0.5050505050505051,
+      "eval_loss": 1.5193032026290894,
+      "eval_runtime": 5.5005,
+      "eval_samples_per_second": 45.45,
+      "eval_steps_per_second": 11.453,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2155110955745280.0,
+  "total_flos": 2584415927009280.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null