Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:064b91dc92e5659a8c6afd38112adfbef7fe22a920c463ae75326e928ffab030
+oid sha256:b151c332b7e64084fa3cb9ff7541f9e9b96048de8adc321807092a8187785439
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:162b67149bb754fa35d67e9bfb3f37daf8bea70dfeaad6fcb5b958378f8777ec
+oid sha256:bf282d2bbe0cc76fd1be03e0053272667a815943fba557f2871639640dbbc28d
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:693f2ba868c0f92675730d61461971a22b5f30ceaf6e2e1865bc16d007ddfbd8
+oid sha256:d10cb6967c268919dfd4a5f35da79aa6e60d991b3515055573321cc9d7a28efa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8342094421386719,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00015743073047858942,
+  "best_metric": 1.4616883993148804,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00031486146095717883,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 9.27,
       "eval_steps_per_second": 4.635,
       "step": 10
+    },
+    {
+      "epoch": 0.00017317380352644836,
+      "grad_norm": 7.459911823272705,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 5.8751,
+      "step": 11
+    },
+    {
+      "epoch": 0.0001889168765743073,
+      "grad_norm": 6.928237438201904,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 5.749,
+      "step": 12
+    },
+    {
+      "epoch": 0.00020465994962216624,
+      "grad_norm": 7.434017181396484,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 6.5052,
+      "step": 13
+    },
+    {
+      "epoch": 0.00022040302267002518,
+      "grad_norm": 10.980093002319336,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 8.7775,
+      "step": 14
+    },
+    {
+      "epoch": 0.00023614609571788412,
+      "grad_norm": 5.352643966674805,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.7138,
+      "step": 15
+    },
+    {
+      "epoch": 0.00023614609571788412,
+      "eval_loss": 1.5234931707382202,
+      "eval_runtime": 2884.8217,
+      "eval_samples_per_second": 9.271,
+      "eval_steps_per_second": 4.636,
+      "step": 15
+    },
+    {
+      "epoch": 0.00025188916876574307,
+      "grad_norm": 7.328005313873291,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.5667,
+      "step": 16
+    },
+    {
+      "epoch": 0.00026763224181360204,
+      "grad_norm": 7.550777912139893,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 5.6812,
+      "step": 17
+    },
+    {
+      "epoch": 0.00028337531486146095,
+      "grad_norm": 6.579277038574219,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 5.7069,
+      "step": 18
+    },
+    {
+      "epoch": 0.0002991183879093199,
+      "grad_norm": 7.71389102935791,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 7.9642,
+      "step": 19
+    },
+    {
+      "epoch": 0.00031486146095717883,
+      "grad_norm": 4.719141483306885,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 5.1321,
+      "step": 20
+    },
+    {
+      "epoch": 0.00031486146095717883,
+      "eval_loss": 1.4616883993148804,
+      "eval_runtime": 2912.6548,
+      "eval_samples_per_second": 9.183,
+      "eval_steps_per_second": 4.591,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1193339391049728.0,
+  "total_flos": 2409627616542720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null