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:edac6347e7d560bf2208780c130958f10555b1fdf628e0aa30fdd4ea42ea5620
+oid sha256:97d27a046cd1f76c07037efda2a39ae32786bd1c0794f45d1abd9f96e05db048
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59f38879a19f46f9e6365f4d9927e46f5a51cbe42d7c5d06318db3960bf40784
+oid sha256:c9411f8949036e4fa5932ff06da3f3a06aa2d852ebfaca7d640b174b3c86267f
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:502caeaace40245c3032f6b99cb5f08051c4da7ee8bc85ffdba98ad43c08c019
+oid sha256:3d2bc46b67022695e5b768ecf1db6e4358bac54da9b8fdd641a17844aaa193e6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.684432327747345,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.023249055507120024,
+  "best_metric": 0.6730473637580872,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.03487358326068003,
   "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": 12.776,
       "eval_steps_per_second": 6.405,
       "step": 20
+    },
+    {
+      "epoch": 0.024411508282476024,
+      "grad_norm": 1.189245343208313,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.6574,
+      "step": 21
+    },
+    {
+      "epoch": 0.02789886660854403,
+      "grad_norm": 2.2764976024627686,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.6139,
+      "step": 24
+    },
+    {
+      "epoch": 0.02906131938390003,
+      "eval_loss": 0.6749742031097412,
+      "eval_runtime": 28.4368,
+      "eval_samples_per_second": 12.765,
+      "eval_steps_per_second": 6.4,
+      "step": 25
+    },
+    {
+      "epoch": 0.03138622493461203,
+      "grad_norm": 1.5035099983215332,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.5178,
+      "step": 27
+    },
+    {
+      "epoch": 0.03487358326068003,
+      "grad_norm": 1.2478257417678833,
+      "learning_rate": 0.0,
+      "loss": 2.8392,
+      "step": 30
+    },
+    {
+      "epoch": 0.03487358326068003,
+      "eval_loss": 0.6730473637580872,
+      "eval_runtime": 28.4323,
+      "eval_samples_per_second": 12.767,
+      "eval_steps_per_second": 6.401,
+      "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": 6942993395220480.0,
+  "total_flos": 1.0210284404736e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null