Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fe2c2e1177e414fbdeb3bd6bdfcb4b353bc44e5938c06e345f469a890a82227
+oid sha256:a7794e90041109c3e511c9185e8ee46715db72eb3ee5eeb5b086d26524cc06fb
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c40bcb21f9edeaa1b725714414e9e9aed9b32f70f0e3a92be53f32923cd83ce
+oid sha256:4964d2b91728cc397af0204be935a6b00944ce7412e1055182836caed5493e81
 size 68874

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:e91b335f0cb5665f0f53210479eb36411f86b24a5aa5bf4b4c5d9cc95b29212d
+oid sha256:d1acf7518eaa83a30405413555139e93a2eb8b9085597afc9a51f69cd1ccf771
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.931843757629395,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.008506113769271665,
+  "best_metric": 11.931824684143066,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.012759170653907496,
   "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": 68.328,
       "eval_steps_per_second": 34.164,
       "step": 20
+    },
+    {
+      "epoch": 0.008931419457735247,
+      "grad_norm": 0.012297064065933228,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 11.9309,
+      "step": 21
+    },
+    {
+      "epoch": 0.010207336523125997,
+      "grad_norm": 0.016836898401379585,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 11.9325,
+      "step": 24
+    },
+    {
+      "epoch": 0.01063264221158958,
+      "eval_loss": 11.931828498840332,
+      "eval_runtime": 14.0894,
+      "eval_samples_per_second": 70.266,
+      "eval_steps_per_second": 35.133,
+      "step": 25
+    },
+    {
+      "epoch": 0.011483253588516746,
+      "grad_norm": 0.011750569567084312,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 11.9329,
+      "step": 27
+    },
+    {
+      "epoch": 0.012759170653907496,
+      "grad_norm": 0.015399892814457417,
+      "learning_rate": 0.0,
+      "loss": 11.9333,
+      "step": 30
+    },
+    {
+      "epoch": 0.012759170653907496,
+      "eval_loss": 11.931824684143066,
+      "eval_runtime": 14.4226,
+      "eval_samples_per_second": 68.642,
+      "eval_steps_per_second": 34.321,
+      "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": 7588380672.0,
+  "total_flos": 11335729152.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null