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:f4db288e5c8832d87f051d5549ad12eed0f673d0aaedd5044a939cc66a3545af
+oid sha256:615578988577e62a1cb4092695d8731fb479d4409219aed6069f2a09d2f48ea5
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42cb890b571d792e3cd4f8b039a5e9d468cb72ffb151f2fb4a69cc2b25643ac0
+oid sha256:a3a711e722f140dd4e24e38b0b07c139b70940dc1c95259455dba80ec38ed0ff
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5965194b68ddd55e77ac2ec5342fe35c8e9dd3df55c7164694232ba89c3ef48f
+oid sha256:0038f9c4cc916603d95a744848cb9dbe6901f5564389c4acdeed724e7671d314
 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": 1.5002901554107666,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0007082403767838804,
+  "best_metric": 1.3844151496887207,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0014164807535677608,
   "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": 16.907,
       "eval_steps_per_second": 8.453,
       "step": 10
+    },
+    {
+      "epoch": 0.0008498884521406565,
+      "grad_norm": 0.5659921169281006,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.5074,
+      "step": 12
+    },
+    {
+      "epoch": 0.0010623605651758207,
+      "grad_norm": 0.5782586336135864,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.4052,
+      "step": 15
+    },
+    {
+      "epoch": 0.0010623605651758207,
+      "eval_loss": 1.426486611366272,
+      "eval_runtime": 351.68,
+      "eval_samples_per_second": 16.907,
+      "eval_steps_per_second": 8.454,
+      "step": 15
+    },
+    {
+      "epoch": 0.0012748326782109848,
+      "grad_norm": 0.4913944602012634,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.4415,
+      "step": 18
+    },
+    {
+      "epoch": 0.0014164807535677608,
+      "eval_loss": 1.3844151496887207,
+      "eval_runtime": 351.1479,
+      "eval_samples_per_second": 16.933,
+      "eval_steps_per_second": 8.467,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3470744113643520.0,
+  "total_flos": 6941488227287040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null