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:bd6a91dde1f16050d5709de9b869f02e4ccdd6c86a314771d7bba99a91ad2232
+oid sha256:1aa640c79ea38138eea6e4636f1240a4b94542c421ef1a7436dc0964a3a28d8c
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccbe7f82eaf9c77b1b6aafff47d237dfaeb04a9dcb944a6fa4e677b1d99d790b
+oid sha256:30f5a4b66375ca7f2781d92ef704396263f42917900111db40b93ac4260e8021
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bcfa19231d15070493ee31c334b85fdd1d4dc308828e4bb1e8f323a2d24cb81
+oid sha256:b7cf0947a2981ff86ac0cca24c8c0539156c29e5189c8266ec5381a02fca596a
 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": 0.8469862937927246,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.02201430930104568,
+  "best_metric": 0.8162607550621033,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.03302146395156852,
   "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": 5.579,
       "eval_steps_per_second": 2.797,
       "step": 20
+    },
+    {
+      "epoch": 0.023115024766097964,
+      "grad_norm": 0.3673122227191925,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.8913,
+      "step": 21
+    },
+    {
+      "epoch": 0.026417171161254815,
+      "grad_norm": 0.47454002499580383,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.8332,
+      "step": 24
+    },
+    {
+      "epoch": 0.0275178866263071,
+      "eval_loss": 0.8205612897872925,
+      "eval_runtime": 68.4569,
+      "eval_samples_per_second": 5.595,
+      "eval_steps_per_second": 2.805,
+      "step": 25
+    },
+    {
+      "epoch": 0.02971931755641167,
+      "grad_norm": 0.45923295617103577,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.7341,
+      "step": 27
+    },
+    {
+      "epoch": 0.03302146395156852,
+      "grad_norm": 0.8842540979385376,
+      "learning_rate": 0.0,
+      "loss": 0.8529,
+      "step": 30
+    },
+    {
+      "epoch": 0.03302146395156852,
+      "eval_loss": 0.8162607550621033,
+      "eval_runtime": 68.5224,
+      "eval_samples_per_second": 5.589,
+      "eval_steps_per_second": 2.802,
+      "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": 6779628844744704.0,
+  "total_flos": 1.0046919854260224e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null