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:ed29e9adef70fe772cd08c83a62acfefb3235dfd9c81ae854e541ddad68c84fd
+oid sha256:bdd92950e563088e0d1c1c3cd65c763601b59dfc8f69774287aa0146ee6352b6
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c7de3be56f9b60d3519f3ff1e5fdee53b641252b60d963ec575a5bed7e3b5cf
+oid sha256:a6b5a1be8a552ddbce66a9c6a6c78d45f415b68bba454702e2c73404fd4bc906
 size 118090

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:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.379389762878418,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0005646009330030418,
+  "best_metric": 10.378952026367188,
+  "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": 182.923,
       "eval_steps_per_second": 91.467,
       "step": 20
+    },
+    {
+      "epoch": 0.0005928309796531939,
+      "grad_norm": 0.03818906843662262,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.3778,
+      "step": 21
+    },
+    {
+      "epoch": 0.0006775211196036502,
+      "grad_norm": 0.05160631984472275,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.377,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007057511662538022,
+      "eval_loss": 10.379020690917969,
+      "eval_runtime": 81.2289,
+      "eval_samples_per_second": 183.617,
+      "eval_steps_per_second": 91.815,
+      "step": 25
+    },
+    {
+      "epoch": 0.0007622112595541064,
+      "grad_norm": 0.02562943659722805,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.3788,
+      "step": 27
+    },
+    {
+      "epoch": 0.0008469013995045627,
+      "grad_norm": 0.042826201766729355,
+      "learning_rate": 0.0,
+      "loss": 10.3782,
+      "step": 30
+    },
+    {
+      "epoch": 0.0008469013995045627,
+      "eval_loss": 10.378952026367188,
+      "eval_runtime": 81.8344,
+      "eval_samples_per_second": 182.258,
+      "eval_steps_per_second": 91.135,
+      "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