Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b94119a569fd4e73635adbadf4a908812696655be08abac20484594c5f5a09e
+oid sha256:3e884818e3fcbf63d15984f0e5b7ff5fff7872bb43adbba18ab3637fc060f6dd
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8beff5a1e0c6a1d48e4969a3b799ad3ca7354fe92ba8d84593078de4dfd1a5cd
+oid sha256:018ca782f96006e255da38f7f81eaf12d0561735bfb6c21d74b9cb417fb20cb0
 size 1389562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d28e5f5aa78cef16e62cc6537d3b81b1ea74dc330b0053f2dd2ab2d360377f3
+oid sha256:ab5f6a013153d6987532a0d60eee1ff2d339487feb3395f01a3a00d204323569
 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": 11.918572425842285,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0018958244466562397,
+  "best_metric": 11.916055679321289,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0028437366699843596,
   "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": 51.178,
       "eval_steps_per_second": 25.589,
       "step": 20
+    },
+    {
+      "epoch": 0.0019906156689890515,
+      "grad_norm": 0.2178204357624054,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 11.9194,
+      "step": 21
+    },
+    {
+      "epoch": 0.0022749893359874877,
+      "grad_norm": 0.25847911834716797,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 11.9182,
+      "step": 24
+    },
+    {
+      "epoch": 0.0023697805583202994,
+      "eval_loss": 11.916461944580078,
+      "eval_runtime": 88.043,
+      "eval_samples_per_second": 50.453,
+      "eval_steps_per_second": 25.226,
+      "step": 25
+    },
+    {
+      "epoch": 0.0025593630029859234,
+      "grad_norm": 0.2141972929239273,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 11.9164,
+      "step": 27
+    },
+    {
+      "epoch": 0.0028437366699843596,
+      "grad_norm": 0.24047067761421204,
+      "learning_rate": 0.0,
+      "loss": 11.9166,
+      "step": 30
+    },
+    {
+      "epoch": 0.0028437366699843596,
+      "eval_loss": 11.916055679321289,
+      "eval_runtime": 87.1535,
+      "eval_samples_per_second": 50.968,
+      "eval_steps_per_second": 25.484,
+      "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": 5458908413952.0,
+  "total_flos": 7997935583232.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null