Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aaba68f647fee22cb77c49e43ee4dae23f37655bbe213f31570b1357661f142
+oid sha256:aaaf6dccd7e53556b9896536674a6f93b1b87303cdb3e4d1780fdc8def332fd8
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da62823cfb64872a84bfec0d0de4fd70895ee1c907d36e2f7614b9373e1597f5
+oid sha256:50853924a5b6418f51f14b5b682b6250ac64083fa21dcda2a1212748a75b41a3
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c9a75f108334a418a7a60fec99e44fa186e26e0cb2561fc9cb4a7566e3c595c
+oid sha256:c8195f5f8ab0a2152863fee8331a14f0c6fd922ebfbe0783423b8278beeaadd3
 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": 3.971724510192871,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0017146776406035665,
+  "best_metric": 3.6764440536499023,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.003429355281207133,
   "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": 11.895,
       "eval_steps_per_second": 5.948,
       "step": 10
+    },
+    {
+      "epoch": 0.0018861454046639231,
+      "grad_norm": 74.35279083251953,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 13.9742,
+      "step": 11
+    },
+    {
+      "epoch": 0.00205761316872428,
+      "grad_norm": 71.51895141601562,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 15.6666,
+      "step": 12
+    },
+    {
+      "epoch": 0.0022290809327846365,
+      "grad_norm": 65.90678405761719,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 15.632,
+      "step": 13
+    },
+    {
+      "epoch": 0.0024005486968449933,
+      "grad_norm": 68.94075775146484,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 18.9844,
+      "step": 14
+    },
+    {
+      "epoch": 0.00257201646090535,
+      "grad_norm": 67.19559478759766,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 14.3089,
+      "step": 15
+    },
+    {
+      "epoch": 0.00257201646090535,
+      "eval_loss": 3.7722387313842773,
+      "eval_runtime": 206.3715,
+      "eval_samples_per_second": 11.901,
+      "eval_steps_per_second": 5.95,
+      "step": 15
+    },
+    {
+      "epoch": 0.0027434842249657062,
+      "grad_norm": 87.80136108398438,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 17.8558,
+      "step": 16
+    },
+    {
+      "epoch": 0.002914951989026063,
+      "grad_norm": 63.244606018066406,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 16.5816,
+      "step": 17
+    },
+    {
+      "epoch": 0.0030864197530864196,
+      "grad_norm": 66.2993392944336,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 15.0449,
+      "step": 18
+    },
+    {
+      "epoch": 0.0032578875171467765,
+      "grad_norm": 80.09910583496094,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 14.8124,
+      "step": 19
+    },
+    {
+      "epoch": 0.003429355281207133,
+      "grad_norm": 53.13572311401367,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 15.4691,
+      "step": 20
+    },
+    {
+      "epoch": 0.003429355281207133,
+      "eval_loss": 3.6764440536499023,
+      "eval_runtime": 206.3223,
+      "eval_samples_per_second": 11.904,
+      "eval_steps_per_second": 5.952,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 87728565780480.0,
+  "total_flos": 175457131560960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null