Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1670e911a1234ed4c6618aaf36bdcb9f06ff9d48046a2ce0d996455294fab1bb
+oid sha256:ba0c01b603bb89deac23332e23e06b630d6b4629d6d28309d7047756c29252ab
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bd7ab3378c9533c951275172eab0ca065c950b0ed4f748c701ddf791f40abfd
+oid sha256:0b48031f6809643a96741c90fe90cd3b52e2499436456dd13fdec4c022bf910d
 size 509177556

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29bf655f04ba4d6f431f8857e6a5cac3c70198350a5d4bf9bc32053533fddbb0
+oid sha256:9819e84c128b7f2dbde0598a7e15d059f219247e1626d2aeb816ff5e8484789b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30565d7b1986ad1c3966f0f9b850f0ae7d4cfe76be60a78deb1442c25c9c950e
+oid sha256:693af3889e4633c932ce337b10348752049de987b4153b6619512b489850fe7b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.2485902309417725,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.37735849056603776,
+  "epoch": 0.4192872117400419,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 7.645,
       "eval_steps_per_second": 1.919,
       "step": 450
+    },
+    {
+      "epoch": 0.3857442348008386,
+      "grad_norm": 0.3485514223575592,
+      "learning_rate": 4.028783622414835e-06,
+      "loss": 2.1634,
+      "step": 460
+    },
+    {
+      "epoch": 0.3941299790356394,
+      "grad_norm": 0.3629409968852997,
+      "learning_rate": 2.272649523684208e-06,
+      "loss": 2.1506,
+      "step": 470
+    },
+    {
+      "epoch": 0.4025157232704403,
+      "grad_norm": 0.5289710760116577,
+      "learning_rate": 1.0121208508766823e-06,
+      "loss": 2.2475,
+      "step": 480
+    },
+    {
+      "epoch": 0.4109014675052411,
+      "grad_norm": 1.0514436960220337,
+      "learning_rate": 2.533387729782834e-07,
+      "loss": 2.2678,
+      "step": 490
+    },
+    {
+      "epoch": 0.4192872117400419,
+      "grad_norm": 2.3110058307647705,
+      "learning_rate": 0.0,
+      "loss": 2.5459,
+      "step": 500
+    },
+    {
+      "epoch": 0.4192872117400419,
+      "eval_loss": 2.2513039112091064,
+      "eval_runtime": 65.9436,
+      "eval_samples_per_second": 7.613,
+      "eval_steps_per_second": 1.911,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.076925904289792e+17,
+  "total_flos": 2.3071587758505984e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null