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:b358ffcf3ed6bb637f45a9da15f70b04289a07504fb8f4bc787a851fd5af2e92
+oid sha256:d5176535121e8d16b215534d9aa301cecac96aa4814ec95d903b8cfb069b6966
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fad666f4da76f08cc79a0f9e109b91e437fc8505e3a1e5f45d64ce3604e9f9d5
+oid sha256:aa7311bb90d4f3a9b3a796cf87a03ca51cb478fc327963aff5f1bf3f49a31866
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca192d730f97ce1d51c982d60c335de46cf9589c25afad87957845efa012b532
+oid sha256:a2e200774c8839a5950df0d4f0c3de0bc2a9694a6ffea48eb98cd3bc1d225da4
 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": 1.1818900108337402,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.006811409110259685,
+  "best_metric": 1.1647752523422241,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.010217113665389528,
   "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": 16.305,
       "eval_steps_per_second": 8.159,
       "step": 20
+    },
+    {
+      "epoch": 0.007151979565772669,
+      "grad_norm": 0.46006566286087036,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.038,
+      "step": 21
+    },
+    {
+      "epoch": 0.008173690932311623,
+      "grad_norm": 0.3569260239601135,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.0024,
+      "step": 24
+    },
+    {
+      "epoch": 0.008514261387824606,
+      "eval_loss": 1.16751229763031,
+      "eval_runtime": 76.089,
+      "eval_samples_per_second": 16.257,
+      "eval_steps_per_second": 8.135,
+      "step": 25
+    },
+    {
+      "epoch": 0.009195402298850575,
+      "grad_norm": 0.39700376987457275,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.1828,
+      "step": 27
+    },
+    {
+      "epoch": 0.010217113665389528,
+      "grad_norm": 0.3018814027309418,
+      "learning_rate": 0.0,
+      "loss": 0.9282,
+      "step": 30
+    },
+    {
+      "epoch": 0.010217113665389528,
+      "eval_loss": 1.1647752523422241,
+      "eval_runtime": 76.0133,
+      "eval_samples_per_second": 16.273,
+      "eval_steps_per_second": 8.143,
+      "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": 7354672050339840.0,
+  "total_flos": 1.123859998703616e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null