Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:688bd2ad49cc6deff38d08ed9658f63d9dd729c3174f808d5388fa345994760d
+oid sha256:7276c6c6b1c82e9ac9adcb8071efabe9d6403ea71bce9e614de2ddfa8e9da999
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60dfb739f017a67b1b8c3df5ec24aae094073ef27b02ab8fbc6a7ebc561691d4
+oid sha256:8223c38a3bd9512aab359703cdeea80e50f0deab87444d44c511a35aa25a9a3b
 size 91850362

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a92b8bdf2dc3465881c067fa2bc3b3cd0525382ae14db7cdbc434fbf6e324148
+oid sha256:1b202187c87a83cf67b64ba9fe2bfec485327f87ec105c2cc9fd2354d68fe406
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:697eb5c311706d748c20f07b0521bb9d1f71aee638eb745112aecf80a82e51da
+oid sha256:d4ffe1cc6011db9bcd26d2a5ee9a2f60bf90f43b3c6aed165ee32997fe344b31
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.7512803077697754,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.016526194017517766,
+  "best_metric": 2.7373805046081543,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.02478929102627665,
   "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": 58.476,
       "eval_steps_per_second": 14.619,
       "step": 100
+    },
+    {
+      "epoch": 0.01817881341926954,
+      "grad_norm": 2.182637929916382,
+      "learning_rate": 0.0002085764548830435,
+      "loss": 2.4546,
+      "step": 110
+    },
+    {
+      "epoch": 0.01983143282102132,
+      "grad_norm": 2.9767863750457764,
+      "learning_rate": 0.00020524128762162305,
+      "loss": 2.252,
+      "step": 120
+    },
+    {
+      "epoch": 0.021484052222773095,
+      "grad_norm": 4.451344966888428,
+      "learning_rate": 0.00020143724248105043,
+      "loss": 2.1921,
+      "step": 130
+    },
+    {
+      "epoch": 0.02313667162452487,
+      "grad_norm": 5.990928649902344,
+      "learning_rate": 0.0001971828523868693,
+      "loss": 2.0887,
+      "step": 140
+    },
+    {
+      "epoch": 0.02478929102627665,
+      "grad_norm": 19.66733741760254,
+      "learning_rate": 0.0001924988442999686,
+      "loss": 2.5636,
+      "step": 150
+    },
+    {
+      "epoch": 0.02478929102627665,
+      "eval_loss": 2.7373805046081543,
+      "eval_runtime": 43.5877,
+      "eval_samples_per_second": 58.457,
+      "eval_steps_per_second": 14.614,
+      "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": 2527438181498880.0,
+  "total_flos": 3791157272248320.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null