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:ab05263b78754b3fd28b0c6444b69cf45c54fa84717db2f7cffc7f7608a48d51
+oid sha256:68072f9c7ecbda1585e913ce9205e078aca9c7c76c2ecd2cf94a7ba1da3d2676
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8038d9f0f38b88202eb72506d5b13c4d137a1c55d4f341b10e5541c26a49888
+oid sha256:ef8839db52c30b8a3a43196bb7f12b80666a01fd6917be9848203588c4b0fe56
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0f6aab0ede0461cd9d0c82c37b11b02e4e50ddf39f260cc74be0fadde97ea0e
+oid sha256:fb4aa45ce48d129cd19ca79e9875a72794280171d73dfd391533a430f237a529
 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": 1.2941644191741943,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0034057045551298426,
+  "best_metric": 1.1814048290252686,
+  "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": 7.458,
       "eval_steps_per_second": 3.732,
       "step": 10
+    },
+    {
+      "epoch": 0.004086845466155811,
+      "grad_norm": 0.5516128540039062,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.2105,
+      "step": 12
+    },
+    {
+      "epoch": 0.005108556832694764,
+      "grad_norm": 0.6083524227142334,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.3534,
+      "step": 15
+    },
+    {
+      "epoch": 0.005108556832694764,
+      "eval_loss": 1.2232894897460938,
+      "eval_runtime": 165.8974,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.731,
+      "step": 15
+    },
+    {
+      "epoch": 0.006130268199233717,
+      "grad_norm": 0.38056692481040955,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.1349,
+      "step": 18
+    },
+    {
+      "epoch": 0.006811409110259685,
+      "eval_loss": 1.1814048290252686,
+      "eval_runtime": 165.895,
+      "eval_samples_per_second": 7.457,
+      "eval_steps_per_second": 3.731,
+      "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