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:daddbf1845dcf994d260fafc02debf9f157cea7b2a248511ca0952571d12ee80
+oid sha256:f9f2f5fd965c9a23e4e37ed886df91402edd9c8068438c5eb6902fbd06bf0143
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e616c66552151b8d0f3625a96b585d82ab9d0c96847db63919038d5c7a32e742
+oid sha256:3d09b2a5d957ac933651ceb09d517f8dc509f9b41f0799dbc712ad4ddb5d982c
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b0959b5e9e0e795488fd06c14f6a3e9380afd1a45a8f81e87894a28f39b0bf3
+oid sha256:eebcfb1ae254997c92616d83af93e361bb5b009b301f11af138466c07c45b3e1
 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": 3.2637407779693604,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0026481297583581596,
+  "best_metric": 0.5812541246414185,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.005296259516716319,
   "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": 6.04,
       "eval_steps_per_second": 3.02,
       "step": 10
+    },
+    {
+      "epoch": 0.0029129427341939755,
+      "grad_norm": 6.349696159362793,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 3.0975,
+      "step": 11
+    },
+    {
+      "epoch": 0.0031777557100297915,
+      "grad_norm": 5.839406967163086,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 3.0467,
+      "step": 12
+    },
+    {
+      "epoch": 0.0034425686858656074,
+      "grad_norm": 6.869053840637207,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.1539,
+      "step": 13
+    },
+    {
+      "epoch": 0.0037073816617014233,
+      "grad_norm": 6.232503414154053,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.1858,
+      "step": 14
+    },
+    {
+      "epoch": 0.003972194637537239,
+      "grad_norm": 4.319960117340088,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8805,
+      "step": 15
+    },
+    {
+      "epoch": 0.003972194637537239,
+      "eval_loss": 0.738400936126709,
+      "eval_runtime": 259.7504,
+      "eval_samples_per_second": 6.121,
+      "eval_steps_per_second": 3.061,
+      "step": 15
+    },
+    {
+      "epoch": 0.004237007613373056,
+      "grad_norm": 3.7483651638031006,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6488,
+      "step": 16
+    },
+    {
+      "epoch": 0.004501820589208871,
+      "grad_norm": 2.9983370304107666,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.7815,
+      "step": 17
+    },
+    {
+      "epoch": 0.004766633565044687,
+      "grad_norm": 2.427694320678711,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.5643,
+      "step": 18
+    },
+    {
+      "epoch": 0.005031446540880503,
+      "grad_norm": 3.6419785022735596,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.8709,
+      "step": 19
+    },
+    {
+      "epoch": 0.005296259516716319,
+      "grad_norm": 2.5277099609375,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.3725,
+      "step": 20
+    },
+    {
+      "epoch": 0.005296259516716319,
+      "eval_loss": 0.5812541246414185,
+      "eval_runtime": 261.3371,
+      "eval_samples_per_second": 6.084,
+      "eval_steps_per_second": 3.042,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 685606636093440.0,
+  "total_flos": 1371213272186880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null