Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:250fc3759fff61e84e146d6c3bd16c94c6f944952dafb2f9205a70c473c962e2
+oid sha256:839dd62ebc7426c13c76076ca3f6271c6d518c0bb603a47a98788a0e311f7d7c
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:471d93129bcd02d6c6af00d36c8fb9d70329418b8a9d5723c4d6265ab7fe222a
+oid sha256:f1fa5ed4af004ba67bc1a57af9c8ffd6b90eb55aad5aea945cfd95293388d1bd
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9795c5ae678d05e9e1d200c8c48172e717b8b0016868766324e0e229567119a2
+oid sha256:86ca8b505a33949ce5b55718626a47836e8e857e3d8daa8042fb9300dca48630
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7601059079170227,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.09950248756218906,
+  "best_metric": 0.7514960765838623,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.14925373134328357,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 8.581,
       "eval_steps_per_second": 2.171,
       "step": 20
+    },
+    {
+      "epoch": 0.1044776119402985,
+      "grad_norm": 0.2184319645166397,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.7278,
+      "step": 21
+    },
+    {
+      "epoch": 0.11940298507462686,
+      "grad_norm": 0.21364577114582062,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.7362,
+      "step": 24
+    },
+    {
+      "epoch": 0.12437810945273632,
+      "eval_loss": 0.7529632449150085,
+      "eval_runtime": 19.7853,
+      "eval_samples_per_second": 8.592,
+      "eval_steps_per_second": 2.173,
+      "step": 25
+    },
+    {
+      "epoch": 0.13432835820895522,
+      "grad_norm": 0.20248772203922272,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.7408,
+      "step": 27
+    },
+    {
+      "epoch": 0.14925373134328357,
+      "grad_norm": 0.21757778525352478,
+      "learning_rate": 0.0,
+      "loss": 0.7231,
+      "step": 30
+    },
+    {
+      "epoch": 0.14925373134328357,
+      "eval_loss": 0.7514960765838623,
+      "eval_runtime": 19.7906,
+      "eval_samples_per_second": 8.59,
+      "eval_steps_per_second": 2.173,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.4155533539868672e+16,
+  "total_flos": 2.114592047313715e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null