Training in progress, step 86, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d64d51d5572cf0d3de72c7fe2dcd5cf32886a8cb4b9c9bee7149c8911d24ae5d
+oid sha256:0c0095234fdf3d3d5b1ae019436515d2ee56c3adf5d290330b7245a0a2755609
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d139a41f32489738a1726451c6512d18d85cf3aad76cf8f5cbe421c2a96dba4
+oid sha256:3b87b43afc1024ec753affd264082d8c3309fddad2cdc97ec89745700d9c0aa6
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6790ebcbcdc3b161187f1c009affc1d514617eea28ccc5a1522b9e5ec92474d9
+oid sha256:eff02c9f4f2cdc4f23b8aa1bc1b9cb59470cd4053b68b8a9a7e57d8d3a3e1fd1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd3f7fe94e41de9162d2be9069d2abe07a8724ed4cf3fe8f5b9587b8ba67952
+oid sha256:8af9f1d83a7a9ce351ac79fbea75e478171c07c97bc6ce60eba0960af66c7e25
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5098581314086914,
-  "best_model_checkpoint": "miner_id_24/checkpoint-43",
-  "epoch": 0.1328698339127076,
+  "best_metric": 0.47387948632240295,
+  "best_model_checkpoint": "miner_id_24/checkpoint-86",
+  "epoch": 0.2657396678254152,
   "eval_steps": 43,
-  "global_step": 43,
+  "global_step": 86,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 21.64,
       "eval_steps_per_second": 1.364,
       "step": 43
+    },
+    {
+      "epoch": 0.2657396678254152,
+      "grad_norm": 3.0645856857299805,
+      "learning_rate": 0.000344,
+      "loss": 3.7852,
+      "step": 86
+    },
+    {
+      "epoch": 0.2657396678254152,
+      "eval_loss": 0.47387948632240295,
+      "eval_runtime": 70.3748,
+      "eval_samples_per_second": 21.641,
+      "eval_steps_per_second": 1.364,
+      "step": 86
     }
   ],
   "logging_steps": 43,
@@ -58,7 +73,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.2854840261751603e+17,
+  "total_flos": 4.5464306471613235e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null