Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80b9847510fba97356841de685ac84b6accf281efdb38e046d4bcc201e9c7aa3
+oid sha256:d10d9938017d223b78cba7fab64f11e1e93ce841ccbb27bff073d7b72d9419cd
 size 159712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bd0044c13a5e02b73220dfb979b96f95a137439e8f2daf793a26e1fb1cf7ce5
+oid sha256:9aa6c74dbce6dd1a992d606edc3d6cc9b1a98510fb66c5704eeb445b8b2a1c21
 size 336202

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 sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.780200004577637,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.026729034413631808,
+  "best_metric": 10.775128364562988,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.04009355162044771,
   "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": 149.925,
       "eval_steps_per_second": 75.201,
       "step": 20
+    },
+    {
+      "epoch": 0.028065486134313398,
+      "grad_norm": 0.23427802324295044,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 10.7809,
+      "step": 21
+    },
+    {
+      "epoch": 0.03207484129635817,
+      "grad_norm": 0.21550685167312622,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 10.7798,
+      "step": 24
+    },
+    {
+      "epoch": 0.03341129301703976,
+      "eval_loss": 10.775887489318848,
+      "eval_runtime": 2.0682,
+      "eval_samples_per_second": 152.305,
+      "eval_steps_per_second": 76.394,
+      "step": 25
+    },
+    {
+      "epoch": 0.03608419645840294,
+      "grad_norm": 0.21427230536937714,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 10.7783,
+      "step": 27
+    },
+    {
+      "epoch": 0.04009355162044771,
+      "grad_norm": 0.2252117246389389,
+      "learning_rate": 0.0,
+      "loss": 10.7767,
+      "step": 30
+    },
+    {
+      "epoch": 0.04009355162044771,
+      "eval_loss": 10.775128364562988,
+      "eval_runtime": 2.0808,
+      "eval_samples_per_second": 151.384,
+      "eval_steps_per_second": 75.932,
+      "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": 6559489327104.0,
+  "total_flos": 9859861315584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null