Training in progress, step 3000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d1c9680990467f4f5b27c801ce52e3a2c3ff1262d1f29cd4c622c56aa687fd3
+oid sha256:d7a9a940508f9f6c79c40565b60b743aee8833c200ddf8325493c276db8fdc78
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeaf49429c405b64027193334814d1c268a2931bbf62a168037a701bdf250011
+oid sha256:dec974729977bfed9dd55f8e2bb2116a9c4d8d6b04fd9061e20bd9a9bcf3ea1f
 size 147360212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:844d9922fee038233ae22054458295a183977341fb28c224c56fc9e2c4e3ef11
+oid sha256:d71d19f7e56bb076c92fbd2570dc9b4e01a59dacb70d9a3c8d5f5dc629ed65ac
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f76a102ac755d5bd19e6f0e55ad50e49a03a307409b32eeac7fb5a2a13752ba
+oid sha256:4b5b8ae682ae9c51a247d395336eab40b1fa2d190384873d8421e390f09af11a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.44117751717567444,
-  "best_model_checkpoint": "miner_id_24/checkpoint-2700",
-  "epoch": 0.2881844380403458,
+  "best_metric": 0.4388670027256012,
+  "best_model_checkpoint": "miner_id_24/checkpoint-3000",
+  "epoch": 0.3033520400424693,
   "eval_steps": 150,
-  "global_step": 2850,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -566,6 +566,35 @@
       "eval_samples_per_second": 38.383,
       "eval_steps_per_second": 9.596,
       "step": 2850
+    },
+    {
+      "epoch": 0.293240305374387,
+      "grad_norm": 0.2669506371021271,
+      "learning_rate": 5.665199789862907e-07,
+      "loss": 0.431,
+      "step": 2900
+    },
+    {
+      "epoch": 0.2982961727084281,
+      "grad_norm": 0.09382705390453339,
+      "learning_rate": 1.4173043232380557e-07,
+      "loss": 0.4565,
+      "step": 2950
+    },
+    {
+      "epoch": 0.3033520400424693,
+      "grad_norm": 0.16964586079120636,
+      "learning_rate": 0.0,
+      "loss": 0.4481,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3033520400424693,
+      "eval_loss": 0.4388670027256012,
+      "eval_runtime": 217.1959,
+      "eval_samples_per_second": 38.343,
+      "eval_steps_per_second": 9.586,
+      "step": 3000
     }
   ],
   "logging_steps": 50,
@@ -580,7 +609,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -589,12 +618,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.192760627913032e+17,
+  "total_flos": 4.4136390549150106e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null