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:d465fe60f8c75dc2d124033966fd6716745dd6efdaa252dff7cdece61a0fed07
+oid sha256:d84df58efe0520c6661c6a763e35fa7229d387aba914ac735bca30c19800a803
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:809d328d5c0d10c9c3be9b230eeeb1826217c2f798e7f8634daae4e2f0c9cb6d
+oid sha256:41cc4a87be80059a6bf8a7c8a2bf4c73173af028e64d5dc6253369cdb1c8c6bc
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e031ffae7060cc93e58b995a2451307eeb9000994a1aff5ea99507c2815cbbde
+oid sha256:ff79bed600d5057e1b5481364c429a52fea800fd5fbbcabc1511d61c30149c77
 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": 2.021346092224121,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.029250457038391225,
+  "best_metric": 1.9288491010665894,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.043875685557586835,
   "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": 19.888,
       "eval_steps_per_second": 4.972,
       "step": 20
+    },
+    {
+      "epoch": 0.030712979890310785,
+      "grad_norm": 2.345966100692749,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.1036,
+      "step": 21
+    },
+    {
+      "epoch": 0.03510054844606947,
+      "grad_norm": 2.4038145542144775,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.0068,
+      "step": 24
+    },
+    {
+      "epoch": 0.03656307129798903,
+      "eval_loss": 1.946331262588501,
+      "eval_runtime": 28.9445,
+      "eval_samples_per_second": 19.9,
+      "eval_steps_per_second": 4.975,
+      "step": 25
+    },
+    {
+      "epoch": 0.03948811700182815,
+      "grad_norm": 2.389855146408081,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.8486,
+      "step": 27
+    },
+    {
+      "epoch": 0.043875685557586835,
+      "grad_norm": 2.1546502113342285,
+      "learning_rate": 0.0,
+      "loss": 1.8765,
+      "step": 30
+    },
+    {
+      "epoch": 0.043875685557586835,
+      "eval_loss": 1.9288491010665894,
+      "eval_runtime": 28.9156,
+      "eval_samples_per_second": 19.92,
+      "eval_steps_per_second": 4.98,
+      "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