Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78fc44db87fd38938ab8a804c005d347f325a22c345096f4a29a8e5661dbad04
+oid sha256:eba98368d984a617f0eb4bb797e1823e5f9e480c835ec20db03acb2898f3b422
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8dc1b9518659e007860727d6967069e94e53a70b51df9b27a219a9e32f30e0e
+oid sha256:1407bbe143352efed3f55efd04901daaf6a9f64a58877a41228595cc6591d363
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f74ca324355024b1bc3cdaf5e61e07df907426038a98bb548eac48bb9e6efbb5
+oid sha256:5f4d209ccbecc5bd3caf9d9c74b5b27fe41dce8950349a94de61ae5a5cffd459
 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": 0.839118242263794,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0006499573465491328,
+  "best_metric": 0.8021699786186218,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.000974936019823699,
   "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": 5.522,
       "eval_steps_per_second": 2.761,
       "step": 20
+    },
+    {
+      "epoch": 0.0006824552138765894,
+      "grad_norm": 8.269264221191406,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 3.1608,
+      "step": 21
+    },
+    {
+      "epoch": 0.0007799488158589592,
+      "grad_norm": 9.56568431854248,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.5208,
+      "step": 24
+    },
+    {
+      "epoch": 0.0008124466831864158,
+      "eval_loss": 0.8103323578834534,
+      "eval_runtime": 2346.7098,
+      "eval_samples_per_second": 5.521,
+      "eval_steps_per_second": 2.761,
+      "step": 25
+    },
+    {
+      "epoch": 0.0008774424178413291,
+      "grad_norm": 9.634747505187988,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.0911,
+      "step": 27
+    },
+    {
+      "epoch": 0.000974936019823699,
+      "grad_norm": 4.219669342041016,
+      "learning_rate": 0.0,
+      "loss": 2.71,
+      "step": 30
+    },
+    {
+      "epoch": 0.000974936019823699,
+      "eval_loss": 0.8021699786186218,
+      "eval_runtime": 2347.5701,
+      "eval_samples_per_second": 5.519,
+      "eval_steps_per_second": 2.76,
+      "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": 8525445171511296.0,
+  "total_flos": 1.2656330976264192e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null