Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8418c2c4760e065a955d70875a0990f488d092f7d92f80a261189cdb31edb0f6
+oid sha256:da7422b78c451f24bea372d10c59b604bc6463bbf5c7640c89898fc18f99a0af
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be6d80293c2e638226db52f7fdbff2a19af530cf0ff1a72b53ffd916e3766ecb
+oid sha256:ef76de28428e987acbf3f7a5b75e884ee6576b3419d46ba74ca1b7a7f0d6a3ef
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcaf77587bff5d8bb8c833deb34625f045202f9b85375b1b779c009d121b4300
+oid sha256:ef9b5633f8ea74d5940349e187435386c31aaae5593c1852f23bba36af65e9ae
 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": 2.3694231510162354,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.12232415902140673,
+  "best_metric": 2.3346669673919678,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.1834862385321101,
   "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": 18.485,
       "eval_steps_per_second": 4.688,
       "step": 20
+    },
+    {
+      "epoch": 0.12844036697247707,
+      "grad_norm": 1.500797986984253,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.2974,
+      "step": 21
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 1.67266047000885,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.361,
+      "step": 24
+    },
+    {
+      "epoch": 0.1529051987767584,
+      "eval_loss": 2.3453073501586914,
+      "eval_runtime": 7.4709,
+      "eval_samples_per_second": 18.472,
+      "eval_steps_per_second": 4.685,
+      "step": 25
+    },
+    {
+      "epoch": 0.1651376146788991,
+      "grad_norm": 1.972248911857605,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.2769,
+      "step": 27
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 1.8739374876022339,
+      "learning_rate": 0.0,
+      "loss": 2.4309,
+      "step": 30
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "eval_loss": 2.3346669673919678,
+      "eval_runtime": 7.4717,
+      "eval_samples_per_second": 18.47,
+      "eval_steps_per_second": 4.684,
+      "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": 1.483774567120896e+16,
+  "total_flos": 2.225661850681344e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null