Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04e7bf6a6e81f562dcf6e207e3e05bd3643c8998509abbcb7be63eee7a52fa93
+oid sha256:58d1afc50d5ba455cb5d673fdc6b9cd0d1ba845c2104b32f99bd58013ef68865
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa417c8b5f2d9fa0c8c1a27deaa96e03e26dace1b14b911e2fe8466c7956d549
+oid sha256:9e20d46a9918fc988a447e1053ea5d496b3044b157baebaad83b883a16e18240
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7332cedcc7b3b36b7974e070bd9fa7171e6a96e191919b27b6014d872048e1e
+oid sha256:83fdd6955092c161405108c24aff329154c04f5feb7c98b00794794c0262bcda
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.768876075744629,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.09313154831199069,
+  "best_metric": 2.727842330932617,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.13969732246798602,
   "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": 5.114,
       "eval_steps_per_second": 2.585,
       "step": 20
+    },
+    {
+      "epoch": 0.09778812572759023,
+      "grad_norm": 2.3748066425323486,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.9547,
+      "step": 21
+    },
+    {
+      "epoch": 0.11175785797438882,
+      "grad_norm": 1.8192694187164307,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.8456,
+      "step": 24
+    },
+    {
+      "epoch": 0.11641443538998836,
+      "eval_loss": 2.73561429977417,
+      "eval_runtime": 17.7904,
+      "eval_samples_per_second": 5.115,
+      "eval_steps_per_second": 2.586,
+      "step": 25
+    },
+    {
+      "epoch": 0.12572759022118743,
+      "grad_norm": 2.1935503482818604,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.8691,
+      "step": 27
+    },
+    {
+      "epoch": 0.13969732246798602,
+      "grad_norm": 1.8655444383621216,
+      "learning_rate": 0.0,
+      "loss": 2.7834,
+      "step": 30
+    },
+    {
+      "epoch": 0.13969732246798602,
+      "eval_loss": 2.727842330932617,
+      "eval_runtime": 17.8081,
+      "eval_samples_per_second": 5.11,
+      "eval_steps_per_second": 2.583,
+      "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": 1.2695579394048e+16,
+  "total_flos": 1.9043369091072e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null