Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:545a04e9df3284fbdb667405b41943b312504d3dbee9cbcfd0e52fe0a66f2c9b
+oid sha256:ced59d2768734b516ce36f32954d7a73063e6d047760110969809eee13f3d755
 size 188784440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6aca25c636dd48dd894e38f353ade9a31f62907a721efb9ea69241bda3a7ed5
+oid sha256:285bb2208af5c6f4bf1aa03b21f9a3de323d71f706391974e0d94d78c5d95baf
 size 377730170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88089b75d6b623f34c98becff8927336b43ddcda017bf8dd6cdbc2ddbbe5dcbc
+oid sha256:9428953a082ef7fb8f13d1f4889d09763e06b75a7c250785d2590da27fb48013
 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": 0.8677180409431458,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.049782202862476664,
+  "best_metric": 0.8590857982635498,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.07467330429371499,
   "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": 6.302,
       "eval_steps_per_second": 3.151,
       "step": 20
+    },
+    {
+      "epoch": 0.0522713130056005,
+      "grad_norm": 1.252132534980774,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 3.5534,
+      "step": 21
+    },
+    {
+      "epoch": 0.059738643434972,
+      "grad_norm": 1.1756926774978638,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 3.4548,
+      "step": 24
+    },
+    {
+      "epoch": 0.06222775357809583,
+      "eval_loss": 0.860339343547821,
+      "eval_runtime": 27.0432,
+      "eval_samples_per_second": 6.286,
+      "eval_steps_per_second": 3.143,
+      "step": 25
+    },
+    {
+      "epoch": 0.0672059738643435,
+      "grad_norm": 1.9984924793243408,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 3.43,
+      "step": 27
+    },
+    {
+      "epoch": 0.07467330429371499,
+      "grad_norm": 1.1472349166870117,
+      "learning_rate": 0.0,
+      "loss": 3.3337,
+      "step": 30
+    },
+    {
+      "epoch": 0.07467330429371499,
+      "eval_loss": 0.8590857982635498,
+      "eval_runtime": 26.9854,
+      "eval_samples_per_second": 6.3,
+      "eval_steps_per_second": 3.15,
+      "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": 1.14344142569472e+16,
+  "total_flos": 1.71516213854208e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null