Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7df5bb680c1d2e698ee4f9c3fc3af4431d27b247f9092b6064871e5ecf0baf27
+oid sha256:cf6f5f3dbea8b8176bcc9852bb0bf1beaee40807ac5bed55df3c1b775e91b6d1
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ab2cbe1bbe91c7eabeea5be2e9656cfdf98c4e2bb7ecf022c81c11215f4255f
+oid sha256:12cdec3a0e616afbfd6eb1c8e1597029f22292b3a9ba4679df6ec6eef9c6b379
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fddb71a9a3d250332f98e562706fe25ec1ff4e66f7c9c4eb0af41236fd2dde1a
+oid sha256:89699f0b3577d72b5b6de2d71d0ef276004d62fe3404dae5160b3a000e6359ef
 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": 3.066793203353882,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.012511729746637473,
+  "best_metric": 2.2870724201202393,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.025023459493274947,
   "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": 19.009,
       "eval_steps_per_second": 9.533,
       "step": 10
+    },
+    {
+      "epoch": 0.015014075695964968,
+      "grad_norm": 1.6633483171463013,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 2.9406,
+      "step": 12
+    },
+    {
+      "epoch": 0.01876759461995621,
+      "grad_norm": 1.8299262523651123,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 2.6414,
+      "step": 15
+    },
+    {
+      "epoch": 0.01876759461995621,
+      "eval_loss": 2.5201518535614014,
+      "eval_runtime": 17.8514,
+      "eval_samples_per_second": 18.878,
+      "eval_steps_per_second": 9.467,
+      "step": 15
+    },
+    {
+      "epoch": 0.022521113543947452,
+      "grad_norm": 1.523863434791565,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.4272,
+      "step": 18
+    },
+    {
+      "epoch": 0.025023459493274947,
+      "eval_loss": 2.2870724201202393,
+      "eval_runtime": 17.7315,
+      "eval_samples_per_second": 19.006,
+      "eval_steps_per_second": 9.531,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3495193466634240.0,
+  "total_flos": 6990386933268480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null