Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:031ae2457f5bb2e3b6d27537b7e423b894efd6b20a5f8e77c62f19ad86be47d0
+oid sha256:0d43da8198c2c753b0355d59758c589b6a3228de855a162f9bf12abb52c7b016
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da4658f6e11513b47d2766fe13d182d2732609ed62018f254ea1169cbfad95fd
+oid sha256:3597d37552d94a18ab72349c8b6f00453ffac0bd1c34bffce335747f2c39eeb4
 size 111078

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
+oid sha256:4542ee77b862586921f712605c9da4a157f7c6fb74687d0b6cef8d69e7a87363
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.38062572479248,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0005646009330030418,
+  "best_metric": 10.380487442016602,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0008469013995045627,
   "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": 181.683,
       "eval_steps_per_second": 90.848,
       "step": 20
+    },
+    {
+      "epoch": 0.0005928309796531939,
+      "grad_norm": 0.027051709592342377,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 10.3791,
+      "step": 21
+    },
+    {
+      "epoch": 0.0006775211196036502,
+      "grad_norm": 0.03462803363800049,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.3784,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007057511662538022,
+      "eval_loss": 10.380508422851562,
+      "eval_runtime": 82.2704,
+      "eval_samples_per_second": 181.293,
+      "eval_steps_per_second": 90.652,
+      "step": 25
+    },
+    {
+      "epoch": 0.0007622112595541064,
+      "grad_norm": 0.020383477210998535,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 10.38,
+      "step": 27
+    },
+    {
+      "epoch": 0.0008469013995045627,
+      "grad_norm": 0.02623324654996395,
+      "learning_rate": 0.0,
+      "loss": 10.3798,
+      "step": 30
+    },
+    {
+      "epoch": 0.0008469013995045627,
+      "eval_loss": 10.380487442016602,
+      "eval_runtime": 82.2251,
+      "eval_samples_per_second": 181.392,
+      "eval_steps_per_second": 90.702,
+      "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": 523024465920.0,
+  "total_flos": 784536698880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null