Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f0a92132b5abeabd49eac72628f48c00c1999ab5e41b8e1ff6449dec85073ac
+oid sha256:06f916592837ed8ad40e3321d5c4c3e81a2e504a86b5042fdb6f632624a9830e
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c8526ceea7abd5173465e95ac37d172c021c98cffec5036a0c8d76c78dbd3a3
+oid sha256:bf5668503f6c23e8e5257b2a942c6056145d37c81c9ac579c553def4c609932b
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e697cf9cc36b0a13279730091b4c6c6515c529d84fc9e847eeae1ffe72fe4ddf
+oid sha256:a037268637beae4b6a91d109f6186872b922d25363229788706f6cecdef8d957
 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": 1.92122220993042,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.05970149253731343,
+  "best_metric": 1.9168668985366821,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.08955223880597014,
   "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": 13.493,
       "eval_steps_per_second": 6.794,
       "step": 20
+    },
+    {
+      "epoch": 0.0626865671641791,
+      "grad_norm": 0.3020223379135132,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.9412,
+      "step": 21
+    },
+    {
+      "epoch": 0.07164179104477612,
+      "grad_norm": 0.3058167099952698,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.9293,
+      "step": 24
+    },
+    {
+      "epoch": 0.07462686567164178,
+      "eval_loss": 1.9176359176635742,
+      "eval_runtime": 10.5315,
+      "eval_samples_per_second": 13.388,
+      "eval_steps_per_second": 6.742,
+      "step": 25
+    },
+    {
+      "epoch": 0.08059701492537313,
+      "grad_norm": 0.3004499077796936,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.8636,
+      "step": 27
+    },
+    {
+      "epoch": 0.08955223880597014,
+      "grad_norm": 0.2995579242706299,
+      "learning_rate": 0.0,
+      "loss": 1.9513,
+      "step": 30
+    },
+    {
+      "epoch": 0.08955223880597014,
+      "eval_loss": 1.9168668985366821,
+      "eval_runtime": 10.5857,
+      "eval_samples_per_second": 13.32,
+      "eval_steps_per_second": 6.707,
+      "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": 2058737544069120.0,
+  "total_flos": 3088106316103680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null