Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:291a8ef77cf9ab774fa2201e9d80ae096ad36365fde91583e38bd5e2324a360b
+oid sha256:abb26bbd49a7842002542fd7f4458494690a26e4dc18d8f9d5e3d27614d4ce08
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3deb85445192dd0dfd516b073476ff223e571fbf44eb67966c581f52bfd6fcb0
+oid sha256:b5deacecd4d12176e7fb2b3541352e417ffe813790a44346a2e64e26d7d97b17
 size 71078228

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72b98c16bcfc363d94109d990348efc95f59975a05ac72014c342ea7fae181bb
+oid sha256:758bc4b8235cc4432f485c7beea8d8ec58f8fdd33fd71ececbfb2e91ae45d9aa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4210d0f4c79be19a1b0c8a85facc89fa1bc09497d44c3c3383a1a0c00e4709d7
+oid sha256:8c579f5f648f371ddcf6d84448bace40e1d46168d2f7b5fae9b6105a9c79d201
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.5193032026290894,
   "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.6734006734006734,
+  "epoch": 0.7575757575757576,
   "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": 45.137,
       "eval_steps_per_second": 11.375,
       "step": 400
+    },
+    {
+      "epoch": 0.6902356902356902,
+      "grad_norm": 0.2167581021785736,
+      "learning_rate": 2.033969009906811e-05,
+      "loss": 1.6139,
+      "step": 410
+    },
+    {
+      "epoch": 0.7070707070707071,
+      "grad_norm": 0.3121006190776825,
+      "learning_rate": 1.6182877759340637e-05,
+      "loss": 1.5518,
+      "step": 420
+    },
+    {
+      "epoch": 0.7239057239057239,
+      "grad_norm": 0.49474164843559265,
+      "learning_rate": 1.2466081360524275e-05,
+      "loss": 1.48,
+      "step": 430
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.6177422404289246,
+      "learning_rate": 9.207408761062996e-06,
+      "loss": 1.2871,
+      "step": 440
+    },
+    {
+      "epoch": 0.7575757575757576,
+      "grad_norm": 1.8054125308990479,
+      "learning_rate": 6.422735886300764e-06,
+      "loss": 1.5863,
+      "step": 450
+    },
+    {
+      "epoch": 0.7575757575757576,
+      "eval_loss": 1.519939661026001,
+      "eval_runtime": 5.4146,
+      "eval_samples_per_second": 46.172,
+      "eval_steps_per_second": 11.635,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -373,7 +416,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -382,12 +425,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3443025869537280.0,
+  "total_flos": 3872330840801280.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null