Training in progress, step 160, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b47bdf9d9dbb19daa258c7cfd7d4a464d9687724469943937b1352b2831b75
+oid sha256:8425d507f0f36ee1eef998c15601287109913addc9b4d411f74a29a0e727069f
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f606363e00340c98ba428dd4f93d560320af0ff1c69f0c2cd00396f45ea7f0db
+oid sha256:e437285ca548e6751dac63fe81fa1d7d7c5390e739df7e4059dbd16f1e1d20af
 size 46057082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:320193f57a9c9ab92eeb8e7b288aa137ef49a372e28016d95c7f7930d933ca5d
+oid sha256:3583a844a2ebe7f88f14edfae8eae81e5f1252d9e214fd1adf0c1db5eb1b93a5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8fa6a7a6709edeb55cdf23229934c07be2d8aae0e4056fbdb6ff2482d0eb3d3
+oid sha256:ac2f052986474c47aa92ee09f81c986cf5cd3c01bde827e5d887e85b2bbda4c2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.5968632698059082,
   "best_model_checkpoint": "miner_id_24/checkpoint-130",
-  "epoch": 0.04235792446170138,
+  "epoch": 0.04518178609248147,
   "eval_steps": 10,
-  "global_step": 150,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1185,6 +1185,84 @@
       "eval_samples_per_second": 5.593,
       "eval_steps_per_second": 5.593,
       "step": 150
+    },
+    {
+      "epoch": 0.04264031062477939,
+      "grad_norm": 1.4214565753936768,
+      "learning_rate": 0.00016184643766056317,
+      "loss": 1.9267,
+      "step": 151
+    },
+    {
+      "epoch": 0.042922696787857394,
+      "grad_norm": 1.2661665678024292,
+      "learning_rate": 0.00016134135287043669,
+      "loss": 1.8779,
+      "step": 152
+    },
+    {
+      "epoch": 0.043205082950935406,
+      "grad_norm": 2.253584384918213,
+      "learning_rate": 0.00016083374657755134,
+      "loss": 1.2,
+      "step": 153
+    },
+    {
+      "epoch": 0.04348746911401341,
+      "grad_norm": 2.3451638221740723,
+      "learning_rate": 0.00016032363964761363,
+      "loss": 2.1057,
+      "step": 154
+    },
+    {
+      "epoch": 0.04376985527709142,
+      "grad_norm": 2.77101731300354,
+      "learning_rate": 0.00015981105304912162,
+      "loss": 1.8791,
+      "step": 155
+    },
+    {
+      "epoch": 0.044052241440169435,
+      "grad_norm": 1.678722620010376,
+      "learning_rate": 0.00015929600785250257,
+      "loss": 2.4479,
+      "step": 156
+    },
+    {
+      "epoch": 0.04433462760324744,
+      "grad_norm": 1.2198508977890015,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 2.3366,
+      "step": 157
+    },
+    {
+      "epoch": 0.04461701376632545,
+      "grad_norm": 5.628009796142578,
+      "learning_rate": 0.0001582586264510396,
+      "loss": 1.3177,
+      "step": 158
+    },
+    {
+      "epoch": 0.04489939992940346,
+      "grad_norm": 2.065458297729492,
+      "learning_rate": 0.00015773633288888197,
+      "loss": 2.0971,
+      "step": 159
+    },
+    {
+      "epoch": 0.04518178609248147,
+      "grad_norm": 0.9564564824104309,
+      "learning_rate": 0.00015721166601221698,
+      "loss": 1.3886,
+      "step": 160
+    },
+    {
+      "epoch": 0.04518178609248147,
+      "eval_loss": 1.6064260005950928,
+      "eval_runtime": 133.4242,
+      "eval_samples_per_second": 5.591,
+      "eval_steps_per_second": 5.591,
+      "step": 160
     }
   ],
   "logging_steps": 1,
@@ -1199,7 +1277,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -1208,12 +1286,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.46820537778176e+16,
+  "total_flos": 1.566085736300544e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null