Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89998e9136aa086519bd51602fba1f4658c0a72d430a3653cbd524e23b54cec4
+oid sha256:32808af77b7a8d903e812412f6cf38b63bfdc246c635bec72412a92a3d637e3d
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f191dde72c78ffeb18a830b912bf47179bb6a3889b8858ed8f82b504ca77b29
+oid sha256:9f69d561851d5d891d5d712006d9ae8015e3c729015b6cdf646b80141378ed7b
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1602f4b9e7c9bf339373e2c887608333f686af18bd19f710db43367937f27367
+oid sha256:f21817f11d5487005de742e9d4bcd3ada581b65221b66cdd367ec2cd636b3b5d
 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": 2.5562493801116943,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0007838526357044876,
+  "best_metric": 2.5440361499786377,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0011757789535567313,
   "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": 22.59,
       "eval_steps_per_second": 11.295,
       "step": 20
+    },
+    {
+      "epoch": 0.0008230452674897119,
+      "grad_norm": 1.0085471868515015,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.5653,
+      "step": 21
+    },
+    {
+      "epoch": 0.0009406231628453851,
+      "grad_norm": 0.9731463193893433,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.467,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009798157946306093,
+      "eval_loss": 2.5461301803588867,
+      "eval_runtime": 476.3553,
+      "eval_samples_per_second": 22.555,
+      "eval_steps_per_second": 11.277,
+      "step": 25
+    },
+    {
+      "epoch": 0.0010582010582010583,
+      "grad_norm": 0.9443745613098145,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.494,
+      "step": 27
+    },
+    {
+      "epoch": 0.0011757789535567313,
+      "grad_norm": 0.7436442971229553,
+      "learning_rate": 0.0,
+      "loss": 2.4049,
+      "step": 30
+    },
+    {
+      "epoch": 0.0011757789535567313,
+      "eval_loss": 2.5440361499786377,
+      "eval_runtime": 476.3288,
+      "eval_samples_per_second": 22.556,
+      "eval_steps_per_second": 11.278,
+      "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": 1306268836823040.0,
+  "total_flos": 1959403255234560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null