Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb68774a30d5a3fcd24884d4b170eb257b3711373d06049c931cbe2074b8d637
+oid sha256:58fae9c47d7e2ec4977bc485a2f0058cf87c757ea972fc32f6c61d6c2c78a187
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:669371e9dbd9c99d7c04c02f87836a853411b99e3871b905beb1ac17d3e51356
+oid sha256:544f048ef4b0bcc6f18bf4479f9da8b74d37999805fee4cad3d8ca04ab735624
 size 1656122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6d452ad494028e3ac82b12f56f879b71199291123b500e8417c5868671ffef
+oid sha256:a2cc23769bd6635ba1949e2088b47629acd228d28e621016c671af30e94aa51d
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5af47dd9c5e9b44c4716c2346f73b0786fc7e3f54a83c79e7160e9fd20c0002
+oid sha256:eee6af1247b0c3edba481f71529e1869926553e17a2f84fc94836be1e54d922b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 4.150573253631592,
   "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.36304961678096004,
+  "epoch": 0.40338846308995563,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 167.236,
       "eval_steps_per_second": 41.969,
       "step": 450
+    },
+    {
+      "epoch": 0.3711173860427592,
+      "grad_norm": 748.3049926757812,
+      "learning_rate": 4.183736838661559e-06,
+      "loss": 7.7169,
+      "step": 460
+    },
+    {
+      "epoch": 0.37918515530455826,
+      "grad_norm": 1504.5245361328125,
+      "learning_rate": 2.3600591207489855e-06,
+      "loss": 7.7157,
+      "step": 470
+    },
+    {
+      "epoch": 0.3872529245663574,
+      "grad_norm": 909.215087890625,
+      "learning_rate": 1.0510485759104009e-06,
+      "loss": 7.8045,
+      "step": 480
+    },
+    {
+      "epoch": 0.3953206938281565,
+      "grad_norm": 1973.363525390625,
+      "learning_rate": 2.6308257193898664e-07,
+      "loss": 8.7159,
+      "step": 490
+    },
+    {
+      "epoch": 0.40338846308995563,
+      "grad_norm": 6883.01171875,
+      "learning_rate": 0.0,
+      "loss": 10.4879,
+      "step": 500
+    },
+    {
+      "epoch": 0.40338846308995563,
+      "eval_loss": 4.240499973297119,
+      "eval_runtime": 3.0961,
+      "eval_samples_per_second": 168.598,
+      "eval_steps_per_second": 42.311,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 807707590262784.0,
+  "total_flos": 898756232871936.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null