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:c4b07f1690cd7484bac2a5d44f37f0490be0f9178aaa8772a1ab302ebf6c556b
+oid sha256:982c294eed45b411a0e191d5585e16f0372bf92a2431711f935171d8b24267f5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a044fec3932a98b2ed133b50e8e251bdf218cf337c691d4efd8843cf8eb45da1
+oid sha256:9b222c29a53e079ed88ec411da50382d90227f6ca86af2adbfe949f572c044a6
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:719783700eff0b0359f760319e8f58a38ea509869b51a6224836e8a9bd8a3920
+oid sha256:8304c876eb57d571aaaf9a0913a650c7296ed5543e000640481eff1d2f78ec43
 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": 1.4814709424972534,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0007979413114165454,
+  "best_metric": 1.4709290266036987,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0011969119671248179,
   "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": 4.63,
       "eval_steps_per_second": 2.315,
       "step": 20
+    },
+    {
+      "epoch": 0.0008378383769873726,
+      "grad_norm": 0.5599179863929749,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.4394,
+      "step": 21
+    },
+    {
+      "epoch": 0.0009575295736998544,
+      "grad_norm": 0.5533298254013062,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.3392,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009974266392706816,
+      "eval_loss": 1.47230863571167,
+      "eval_runtime": 2280.0193,
+      "eval_samples_per_second": 4.629,
+      "eval_steps_per_second": 2.314,
+      "step": 25
+    },
+    {
+      "epoch": 0.0010772207704123362,
+      "grad_norm": 0.5216392874717712,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.4882,
+      "step": 27
+    },
+    {
+      "epoch": 0.0011969119671248179,
+      "grad_norm": 0.5612313747406006,
+      "learning_rate": 0.0,
+      "loss": 1.4671,
+      "step": 30
+    },
+    {
+      "epoch": 0.0011969119671248179,
+      "eval_loss": 1.4709290266036987,
+      "eval_runtime": 2282.1443,
+      "eval_samples_per_second": 4.625,
+      "eval_steps_per_second": 2.312,
+      "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": 7511608746049536.0,
+  "total_flos": 1.1221045163851776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null