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:e709d5c3e5eb47b32f7b7082d79d5f753e8feeb4655476da7163f9ddf022b5ff
+oid sha256:291a8ef77cf9ab774fa2201e9d80ae096ad36365fde91583e38bd5e2324a360b
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a255a07a947da136f3f73886a60e43999ec9518db79d3f5962c0e1373f37e72
+oid sha256:3deb85445192dd0dfd516b073476ff223e571fbf44eb67966c581f52bfd6fcb0
 size 71078228

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c422b89769c0b6f7d1f077f50efdb452b79d83f301219ab544192746d2ee505
+oid sha256:72b98c16bcfc363d94109d990348efc95f59975a05ac72014c342ea7fae181bb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4edd2cafd3d507df56f5f20b4a96c47a9d3caf3610b7118aaa38eea9544bff7
+oid sha256:4210d0f4c79be19a1b0c8a85facc89fa1bc09497d44c3c3383a1a0c00e4709d7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.5193032026290894,
   "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.5892255892255892,
+  "epoch": 0.6734006734006734,
   "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": 46.2,
       "eval_steps_per_second": 11.642,
       "step": 350
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 0.23477864265441895,
+      "learning_rate": 4.6945955780365475e-05,
+      "loss": 1.5487,
+      "step": 360
+    },
+    {
+      "epoch": 0.622895622895623,
+      "grad_norm": 0.28491002321243286,
+      "learning_rate": 4.0932052877817393e-05,
+      "loss": 1.5135,
+      "step": 370
+    },
+    {
+      "epoch": 0.6397306397306397,
+      "grad_norm": 0.4891034662723541,
+      "learning_rate": 3.523759042278163e-05,
+      "loss": 1.4778,
+      "step": 380
+    },
+    {
+      "epoch": 0.6565656565656566,
+      "grad_norm": 0.8539410829544067,
+      "learning_rate": 2.989031126393367e-05,
+      "loss": 1.2319,
+      "step": 390
+    },
+    {
+      "epoch": 0.6734006734006734,
+      "grad_norm": 2.4153780937194824,
+      "learning_rate": 2.4916266807828855e-05,
+      "loss": 1.4218,
+      "step": 400
+    },
+    {
+      "epoch": 0.6734006734006734,
+      "eval_loss": 1.5206342935562134,
+      "eval_runtime": 5.5387,
+      "eval_samples_per_second": 45.137,
+      "eval_steps_per_second": 11.375,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -330,7 +373,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3013720898273280.0,
+  "total_flos": 3443025869537280.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null