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:ce11877e4e553b7dc4a5a65cdabc39ec8d921d058f2c9d82614d79393797ab0e
+oid sha256:770c5ef10e164b978041217efa00995725baee1a96e1bcab08e7c0f08a1a1142
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7688bd49ceef3c0f870a5ae30078b923ab31b7827a8c4524911c4cd30208fa02
+oid sha256:15b57d57833f094609f80c37c5bd1f6d794f57eed1b2568d8bd0fe6960af82d5
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23a6eee3875a9902a549f4bad55856201b51958acc44fbbb2102e758981da379
+oid sha256:e6cb22d889af96bc5968098482fe54159da994b406807fec9cba907cd974afc0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9270801a091d1fd46d6e273e2ff0ed3fb1f5321828110607b5eb48295bb7f4c
+oid sha256:59836f5c73dcbc1cd9e839a79f50d96177860a3d03c4212fba8b4249bf77b097
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9600940942764282,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.3007518796992481,
+  "best_metric": 1.6451599597930908,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.45112781954887216,
   "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": 16.307,
       "eval_steps_per_second": 4.077,
       "step": 100
+    },
+    {
+      "epoch": 0.3308270676691729,
+      "grad_norm": 5.71964168548584,
+      "learning_rate": 0.00019470244854643905,
+      "loss": 1.7275,
+      "step": 110
+    },
+    {
+      "epoch": 0.3609022556390977,
+      "grad_norm": 5.346231460571289,
+      "learning_rate": 0.0001867136665491626,
+      "loss": 1.1856,
+      "step": 120
+    },
+    {
+      "epoch": 0.39097744360902253,
+      "grad_norm": 4.990022659301758,
+      "learning_rate": 0.0001777681791345876,
+      "loss": 1.1762,
+      "step": 130
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 8.322728157043457,
+      "learning_rate": 0.0001679761110291609,
+      "loss": 1.6037,
+      "step": 140
+    },
+    {
+      "epoch": 0.45112781954887216,
+      "grad_norm": 17.498231887817383,
+      "learning_rate": 0.0001574580089142965,
+      "loss": 1.6452,
+      "step": 150
+    },
+    {
+      "epoch": 0.45112781954887216,
+      "eval_loss": 1.6451599597930908,
+      "eval_runtime": 8.5559,
+      "eval_samples_per_second": 16.363,
+      "eval_steps_per_second": 4.091,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -115,7 +158,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.88564197343232e+16,
+  "total_flos": 2.82846296014848e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null