Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:991d42f874d11dd7f685f12c44d997ee37d1294b9c1942a2ef1c866f4b0be971
+oid sha256:66d80efb87d11f17ebb283d9dda9995dc999263fba8711a9d0a320ca84e036d5
 size 9864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ad4c67cbd52d97c89f217975ad88698b15efeae1065f62a8d511a29d891ddb8
+oid sha256:f7098ed589633ebe6e61bc1384f918a181b738c3931be5979b3d1e878db0b017
 size 24006

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ccc884acd19b8a23e74071ab1c8930e4c49c6a544ce2691cea49c49a59e71c5
+oid sha256:e781d4de74a376f62b3dab9fbfdd6f349e5485013db3f9a7a8b5c0c58f822a02
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:268aeb7b294c90cd83aa86854c13d1f13a76d08ba75be276a0b5b8f8a3905924
+oid sha256:fdcafde4de54854e715c6bd59aa06fddefbf193f4a0d1cabc2a35c45a0b6a364
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.058343057176196034,
+  "epoch": 0.08751458576429405,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 178.75,
       "eval_steps_per_second": 44.811,
       "step": 100
+    },
+    {
+      "epoch": 0.06417736289381563,
+      "grad_norm": 7.025956438155845e-05,
+      "learning_rate": 0.00020283581851011567,
+      "loss": 23.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.07001166861143523,
+      "grad_norm": 0.00010229845065623522,
+      "learning_rate": 0.00019959244484304625,
+      "loss": 23.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.07584597432905485,
+      "grad_norm": 0.0003530419198796153,
+      "learning_rate": 0.00019589309819258114,
+      "loss": 23.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.08168028004667445,
+      "grad_norm": 0.00015672302106395364,
+      "learning_rate": 0.00019175580140374444,
+      "loss": 23.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.08751458576429405,
+      "grad_norm": 0.00022062881907913834,
+      "learning_rate": 0.00018720071097061167,
+      "loss": 23.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.08751458576429405,
+      "eval_loss": 11.5,
+      "eval_runtime": 3.966,
+      "eval_samples_per_second": 182.046,
+      "eval_steps_per_second": 45.638,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -115,7 +158,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2004778450944.0,
+  "total_flos": 3002180665344.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null