Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a1ae36715fd97b6921b6abafa0171471bf081db3ea6389b12aa602ff621ea33
+oid sha256:974e4c9c8df8170574cc7c4ed3a1c0b3505848be9a647f4e23ec4cc2e0319401
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d44da03e4347eee589aa4832642ced40166ca12d3c3a67801a4ae826bde8cd
+oid sha256:4cd9a333b53a46b11f32096ccd797545b35bc45602eb79fd3bcdd5525ba57d3e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3539375d5c34a24a1a4a0bf5eba2cb9a6eedf0a8a26ee67de8a1de1edb9ded6b
+oid sha256:23f538a2e00a790186d8cd9b02e1d05e40cc3e7a18fef6baad39acb9077438c7
 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": 1.431047797203064,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0016858786588835268,
+  "best_metric": 1.4155030250549316,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.00252881798832529,
   "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": 7.549,
       "eval_steps_per_second": 1.888,
       "step": 20
+    },
+    {
+      "epoch": 0.0017701725918277031,
+      "grad_norm": 0.3949830234050751,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.3766,
+      "step": 21
+    },
+    {
+      "epoch": 0.0020230543906602323,
+      "grad_norm": 0.47331270575523376,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.4327,
+      "step": 24
+    },
+    {
+      "epoch": 0.0021073483236044087,
+      "eval_loss": 1.418473720550537,
+      "eval_runtime": 1321.3789,
+      "eval_samples_per_second": 7.56,
+      "eval_steps_per_second": 1.89,
+      "step": 25
+    },
+    {
+      "epoch": 0.0022759361894927614,
+      "grad_norm": 0.40120798349380493,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.3449,
+      "step": 27
+    },
+    {
+      "epoch": 0.00252881798832529,
+      "grad_norm": 0.4255647659301758,
+      "learning_rate": 0.0,
+      "loss": 1.3517,
+      "step": 30
+    },
+    {
+      "epoch": 0.00252881798832529,
+      "eval_loss": 1.4155030250549316,
+      "eval_runtime": 1321.4996,
+      "eval_samples_per_second": 7.56,
+      "eval_steps_per_second": 1.89,
+      "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": 1.7248879342780416e+16,
+  "total_flos": 2.4667752178384896e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null