Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f69d5dfa3f789d9d0cbf4f26db614892e0a7c66d652669a73063ae4dbca8fa68
+oid sha256:4f23c0b8b57f59ffb8b415f957b211fa7b820ee0859db54feceff36e30a6f4d2
 size 838906392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10437a6cc0b94f9c418ffdae4fe846e6a33e69125c8c6668c953cd6bca3a2bfc
+oid sha256:e00bfa60385d0c75e3daf48603e2b8095cd4384e015f1133f6d7f0662e6ad9ed
 size 426360916

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:448adbe1c0216ce3ffc4e9b91893656657b7e2e86e93182d346c14307e64ee3d
+oid sha256:1d85688e1090f381bd7c33c28eb6cf2ec556b15a0cc721e368f11c06ca5feaa4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:259dc84c23e381fbb995c8c51d7b6bf45023b2b3ae0747622e30e21b211acefc
+oid sha256:2cb8558bc6d45d5a75fbf9d5c97c98ac097732c9c0fca052f9b523926f175692
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6618533730506897,
   "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 2.8391167192429023,
+  "epoch": 3.7854889589905363,
   "eval_steps": 150,
-  "global_step": 450,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 10.712,
       "eval_steps_per_second": 2.718,
       "step": 450
+    },
+    {
+      "epoch": 3.1545741324921135,
+      "grad_norm": 2.3724846839904785,
+      "learning_rate": 0.00016050337474956067,
+      "loss": 1.5111,
+      "step": 500
+    },
+    {
+      "epoch": 3.470031545741325,
+      "grad_norm": 3.490664482116699,
+      "learning_rate": 0.00015205340029146255,
+      "loss": 1.0948,
+      "step": 550
+    },
+    {
+      "epoch": 3.7854889589905363,
+      "grad_norm": 2.047959566116333,
+      "learning_rate": 0.00014305880647134847,
+      "loss": 1.179,
+      "step": 600
+    },
+    {
+      "epoch": 3.7854889589905363,
+      "eval_loss": 0.690345287322998,
+      "eval_runtime": 12.6156,
+      "eval_samples_per_second": 10.622,
+      "eval_steps_per_second": 2.695,
+      "step": 600
     }
   ],
   "logging_steps": 50,
@@ -116,7 +145,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -125,12 +154,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.9319589407883264e+17,
+  "total_flos": 6.548231660293325e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null