Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7c7f59d1d0bd853fc30c0d22c6711fa2f6d74d371705f1cc176c9d46f5a7151
+oid sha256:16ce0f3950097a05de1321ba301d5a23f9eacc5fbec098aebac6627662a8762f
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c2928577faf9f420c7fd6d3d74c9eec453042ab5c64f233e5f0e06f32b55256
+oid sha256:a607314405a10b96e29f8b209701f30f25525af2d21963c55f2e1953c08034a1
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16c26aca448a242d5bf2fabc2154114043b520f3da37396f4bb9075805b13b9b
+oid sha256:96783794f99c09a38f521ca1a51ff6944d75cc917b2669b46a6672f18b857f29
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6da36b358afefa2fe6fe8e3889efc77dfb89ac577ed7bb55c631123a9ebe149
+oid sha256:56e06160672e234a504b2a9f8fb3d80ed8c221e80fde36a5548d37e259bd5bc6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.005342242307960987,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.06067961165048544,
+  "epoch": 0.08090614886731391,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 18.042,
       "eval_steps_per_second": 4.528,
       "step": 150
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": 0.0019265917362645268,
+      "learning_rate": 2.2444444444444445e-06,
+      "loss": 0.0011,
+      "step": 160
+    },
+    {
+      "epoch": 0.06877022653721683,
+      "grad_norm": 0.004902382381260395,
+      "learning_rate": 1.6833333333333332e-06,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.07281553398058252,
+      "grad_norm": 0.012828897684812546,
+      "learning_rate": 1.1222222222222222e-06,
+      "loss": 0.0001,
+      "step": 180
+    },
+    {
+      "epoch": 0.07686084142394822,
+      "grad_norm": 0.03425660356879234,
+      "learning_rate": 5.611111111111111e-07,
+      "loss": 0.0035,
+      "step": 190
+    },
+    {
+      "epoch": 0.08090614886731391,
+      "grad_norm": 0.12202399224042892,
+      "learning_rate": 0.0,
+      "loss": 0.0148,
+      "step": 200
+    },
+    {
+      "epoch": 0.08090614886731391,
+      "eval_loss": 0.005512339062988758,
+      "eval_runtime": 43.2377,
+      "eval_samples_per_second": 18.063,
+      "eval_steps_per_second": 4.533,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.270979069824205e+16,
+  "total_flos": 5.685210549898445e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null