Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e3e7fdc85921297faceef406721a81413a556e9879445e055c4bd2e658ab4fe
+oid sha256:60c4924f96363ac1f33cf2784f5858a9730d25a1872c3a546c165694d8586928
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a16d77af8d92d8ed4468f1d1c4c113cca33181349c9999f3501618a562378dcc
+oid sha256:9cf5b4437de5a78b86a9e7946dded7aaa5f6606e4759dc196d556eacc490915f
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52e797e8201e9d20339e01a4e190837f065374f343ea33045e988dc36d3bcf11
+oid sha256:eb08d6cfeda2d7bd5d10f683efee0d67828d1397f45ed80f5b5f1e608b807956
 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": 0.49245163798332214,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.04008016032064128,
+  "best_metric": 0.48303693532943726,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.06012024048096192,
   "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": 3.231,
       "eval_steps_per_second": 0.814,
       "step": 20
+    },
+    {
+      "epoch": 0.04208416833667335,
+      "grad_norm": 1.6009563207626343,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.0628,
+      "step": 21
+    },
+    {
+      "epoch": 0.04809619238476954,
+      "grad_norm": 1.474389910697937,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.9829,
+      "step": 24
+    },
+    {
+      "epoch": 0.050100200400801605,
+      "eval_loss": 0.48446887731552124,
+      "eval_runtime": 130.4175,
+      "eval_samples_per_second": 3.228,
+      "eval_steps_per_second": 0.813,
+      "step": 25
+    },
+    {
+      "epoch": 0.05410821643286573,
+      "grad_norm": 1.4533580541610718,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.8224,
+      "step": 27
+    },
+    {
+      "epoch": 0.06012024048096192,
+      "grad_norm": 1.5185352563858032,
+      "learning_rate": 0.0,
+      "loss": 1.863,
+      "step": 30
+    },
+    {
+      "epoch": 0.06012024048096192,
+      "eval_loss": 0.48303693532943726,
+      "eval_runtime": 130.2143,
+      "eval_samples_per_second": 3.233,
+      "eval_steps_per_second": 0.814,
+      "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": 2.812517994725376e+16,
+  "total_flos": 4.218776992088064e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null