Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e865908f709316176feee7b94d6472fab01ab159a18575443026979cab1e424
+oid sha256:825975d9faf4d7b3c9be6e34e2a815053ef62de61f74416ddc6fb420a1ffb2f2
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cc1c2eebf235dc06b3eff514c22b49c3d7c0f31c874fee34a4e1f8de12140f4
+oid sha256:b9e56d1765e49b2451c7154ff9794aaf9b5c5839875c60a8dd84017a354fe0c4
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beb07234a3b2450909dbdd8c935ebb33cae5d683491846c7af37296213d8d53e
+oid sha256:d76530992a3adae00800f571246c5225ee013628cfbba9fa5d38d06c5a758f0a
 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": 2.099807024002075,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.006860475087899837,
+  "best_metric": 2.0782320499420166,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.010290712631849755,
   "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": 4.151,
       "eval_steps_per_second": 2.075,
       "step": 20
+    },
+    {
+      "epoch": 0.0072034988422948285,
+      "grad_norm": 0.24353356659412384,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.1351,
+      "step": 21
+    },
+    {
+      "epoch": 0.008232570105479805,
+      "grad_norm": 0.22688663005828857,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.1239,
+      "step": 24
+    },
+    {
+      "epoch": 0.008575593859874796,
+      "eval_loss": 2.081972599029541,
+      "eval_runtime": 295.2455,
+      "eval_samples_per_second": 4.159,
+      "eval_steps_per_second": 2.08,
+      "step": 25
+    },
+    {
+      "epoch": 0.00926164136866478,
+      "grad_norm": 0.2258845567703247,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.0864,
+      "step": 27
+    },
+    {
+      "epoch": 0.010290712631849755,
+      "grad_norm": 0.22580111026763916,
+      "learning_rate": 0.0,
+      "loss": 2.0962,
+      "step": 30
+    },
+    {
+      "epoch": 0.010290712631849755,
+      "eval_loss": 2.0782320499420166,
+      "eval_runtime": 295.3833,
+      "eval_samples_per_second": 4.157,
+      "eval_steps_per_second": 2.079,
+      "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": 8658321175216128.0,
+  "total_flos": 1.2824117212348416e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null