Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e6dd61b556050da5648a35d5e7d8f93275589f55704611f74356dbefa276cce
+oid sha256:37c89d8a8534f1e865d129124bb0637ff877e1be53a765f1c556b1daf9a92616
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408237144217d6bf1b0f11dcef515cc4b5f6fd04a345f52f7125d9e7f52880d1
+oid sha256:609a0c88368f8b08b2cc0455a190ddc2ee5140fc31bfa17bf9fa9287bddbbb31
 size 101107578

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d616c21e6738d673051c3b1bfe81804ed383456ad1f17d9fac066ae6f18c0ad
+oid sha256:395c0ab44e92085537132c8c1f035a64e3b4ecb27fecef250c06d7831da2ae5a
 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": 1.5292763710021973,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.017185821697099892,
+  "best_metric": 1.4968665838241577,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.02577873254564984,
   "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": 14.299,
       "eval_steps_per_second": 7.149,
       "step": 20
+    },
+    {
+      "epoch": 0.01804511278195489,
+      "grad_norm": 0.14562292397022247,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.5016,
+      "step": 21
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "grad_norm": 0.15869614481925964,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.4865,
+      "step": 24
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "eval_loss": 1.5023248195648193,
+      "eval_runtime": 34.5684,
+      "eval_samples_per_second": 14.175,
+      "eval_steps_per_second": 7.087,
+      "step": 25
+    },
+    {
+      "epoch": 0.023200859291084855,
+      "grad_norm": 0.15873423218727112,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.5036,
+      "step": 27
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "grad_norm": 0.142244353890419,
+      "learning_rate": 0.0,
+      "loss": 1.52,
+      "step": 30
+    },
+    {
+      "epoch": 0.02577873254564984,
+      "eval_loss": 1.4968665838241577,
+      "eval_runtime": 34.2982,
+      "eval_samples_per_second": 14.286,
+      "eval_steps_per_second": 7.143,
+      "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": 2058737544069120.0,
+  "total_flos": 3088106316103680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null