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:c810a13be971e8ec283ffafd28f13aaf7c37f9737a3702a2465f5329db957e55
+oid sha256:82f8ba1a7566d953e4f6bd8b51a55d60246f663a8fd2f0c6bb0d3b05ec2fc7e4
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af22c08c32acc5f4c0f5c263493158db886812b610b5bb2dfcaec2b33f2ba875
+oid sha256:3b0952a742e4621ae6007042d08b7f283dee4449f95a5a8fc212ccfc6ba71797
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0261b527139ee9676e8e320675e34598ff7498b3449469d955868455e9d6849a
+oid sha256:4769c32ac7a0b50b6a84655d674cc7d766891952a2a2a7f72f55a20a4c8f319d
 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": 1.0281891822814941,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.004227882887644013,
+  "best_metric": 0.98299241065979,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.008455765775288025,
   "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": 7.277,
       "eval_steps_per_second": 3.638,
       "step": 10
+    },
+    {
+      "epoch": 0.005073459465172815,
+      "grad_norm": 8.697997093200684,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 3.8483,
+      "step": 12
+    },
+    {
+      "epoch": 0.006341824331466018,
+      "grad_norm": 9.351025581359863,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 3.9851,
+      "step": 15
+    },
+    {
+      "epoch": 0.006341824331466018,
+      "eval_loss": 0.9977760910987854,
+      "eval_runtime": 136.7759,
+      "eval_samples_per_second": 7.282,
+      "eval_steps_per_second": 3.641,
+      "step": 15
+    },
+    {
+      "epoch": 0.007610189197759222,
+      "grad_norm": 8.28114128112793,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.7435,
+      "step": 18
+    },
+    {
+      "epoch": 0.008455765775288025,
+      "eval_loss": 0.98299241065979,
+      "eval_runtime": 136.7944,
+      "eval_samples_per_second": 7.281,
+      "eval_steps_per_second": 3.64,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3867216671932416.0,
+  "total_flos": 7646542055866368.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null