Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0669de46788b385d1864d042e3012a50eaabc302959603caa7a4a8b508fed047
+oid sha256:28606bc0b1fc5290c1ff02cdcaddb93039c19cc52dbc6d97e6195bb54fa9aa7f
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7562f117f208e3e39c614f3fc7ef59117312c519779862e3c4127c737276a251
+oid sha256:4af63342d7cf9b729fb78f4cd100e075d8be3a312906cc59b5f2efcd7b878d35
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56b0b736ba7e794c6825c083ee09502612769b2781725f4f635dfce7d52cb0f1
+oid sha256:3d9519b100db2f6a65aee6286df43d61993dfe8421c42e05a6af7fa912f083f0
 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": 0.5977821946144104,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.04239533651298357,
+  "best_metric": 0.5702555179595947,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.06359300476947535,
   "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": 6.886,
       "eval_steps_per_second": 1.73,
       "step": 20
+    },
+    {
+      "epoch": 0.04451510333863275,
+      "grad_norm": 0.5103761553764343,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.2397,
+      "step": 21
+    },
+    {
+      "epoch": 0.05087440381558029,
+      "grad_norm": 0.573857307434082,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.169,
+      "step": 24
+    },
+    {
+      "epoch": 0.052994170641229466,
+      "eval_loss": 0.5750617384910583,
+      "eval_runtime": 57.4007,
+      "eval_samples_per_second": 6.934,
+      "eval_steps_per_second": 1.742,
+      "step": 25
+    },
+    {
+      "epoch": 0.057233704292527825,
+      "grad_norm": 0.5762279629707336,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.1634,
+      "step": 27
+    },
+    {
+      "epoch": 0.06359300476947535,
+      "grad_norm": 0.566165566444397,
+      "learning_rate": 0.0,
+      "loss": 2.1161,
+      "step": 30
+    },
+    {
+      "epoch": 0.06359300476947535,
+      "eval_loss": 0.5702555179595947,
+      "eval_runtime": 57.4317,
+      "eval_samples_per_second": 6.93,
+      "eval_steps_per_second": 1.741,
+      "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": 2.613858577416192e+16,
+  "total_flos": 3.920787866124288e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null