Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23726fab36d4f6c1887a4d7742a04971b2d75c15de272e78045cb4698eafa766
+oid sha256:b358ffcf3ed6bb637f45a9da15f70b04289a07504fb8f4bc787a851fd5af2e92
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dec4d9c3a088bb0a97d010ec76c0faf022dae164d55beba0999647258efd8bc0
+oid sha256:fad666f4da76f08cc79a0f9e109b91e437fc8505e3a1e5f45d64ce3604e9f9d5
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8f8ef9c1dadf94d7117ddba77731b4254fea788745478fd3be237ddfcceab2f
+oid sha256:ca192d730f97ce1d51c982d60c335de46cf9589c25afad87957845efa012b532
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2965959310531616,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0034057045551298426,
+  "best_metric": 1.1818900108337402,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.006811409110259685,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 16.108,
       "eval_steps_per_second": 8.061,
       "step": 10
+    },
+    {
+      "epoch": 0.004086845466155811,
+      "grad_norm": 0.5418891310691833,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.2131,
+      "step": 12
+    },
+    {
+      "epoch": 0.005108556832694764,
+      "grad_norm": 0.5988765358924866,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.3546,
+      "step": 15
+    },
+    {
+      "epoch": 0.005108556832694764,
+      "eval_loss": 1.225139856338501,
+      "eval_runtime": 76.1545,
+      "eval_samples_per_second": 16.243,
+      "eval_steps_per_second": 8.128,
+      "step": 15
+    },
+    {
+      "epoch": 0.006130268199233717,
+      "grad_norm": 0.36577218770980835,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.1357,
+      "step": 18
+    },
+    {
+      "epoch": 0.006811409110259685,
+      "eval_loss": 1.1818900108337402,
+      "eval_runtime": 75.864,
+      "eval_samples_per_second": 16.305,
+      "eval_steps_per_second": 8.159,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3718654407475200.0,
+  "total_flos": 7354672050339840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null