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:d1b32496f47a95a6c3ecfe24090e553840124fbd8c8b5be1c218a92a91c41afe
+oid sha256:2842e0ca5b05fbae9e56fec8ef21d4e3e563b7ee2954d10e51702e8ebac4a844
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fae3d3ea4cae28e5b362a01261b7d8f6ac861dc003432dba3f679362123282ab
+oid sha256:50942a7726eb1111b22c2979cdecc1af938f2d653b2db67bff8200a3dd9283a8
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aa91133351808aacad3e45f05aebdf1a2981ac4aa08431c95904a973b1b12d5
+oid sha256:b90cec581bf01b7b4ecfb930623a750a1d6c081eb2553ed745e3e8de8e41bc7c
 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": 3.1660454273223877,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.10075566750629723,
+  "best_metric": 3.132758378982544,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.15113350125944586,
   "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": 17.28,
       "eval_steps_per_second": 8.64,
       "step": 20
+    },
+    {
+      "epoch": 0.10579345088161209,
+      "grad_norm": 2.862460136413574,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 3.1378,
+      "step": 21
+    },
+    {
+      "epoch": 0.12090680100755667,
+      "grad_norm": 2.4443368911743164,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 3.1421,
+      "step": 24
+    },
+    {
+      "epoch": 0.12594458438287154,
+      "eval_loss": 3.138329267501831,
+      "eval_runtime": 4.8644,
+      "eval_samples_per_second": 17.268,
+      "eval_steps_per_second": 8.634,
+      "step": 25
+    },
+    {
+      "epoch": 0.13602015113350127,
+      "grad_norm": 1.9224209785461426,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 3.1215,
+      "step": 27
+    },
+    {
+      "epoch": 0.15113350125944586,
+      "grad_norm": 4.030033588409424,
+      "learning_rate": 0.0,
+      "loss": 3.1646,
+      "step": 30
+    },
+    {
+      "epoch": 0.15113350125944586,
+      "eval_loss": 3.132758378982544,
+      "eval_runtime": 4.8523,
+      "eval_samples_per_second": 17.311,
+      "eval_steps_per_second": 8.656,
+      "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": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null