Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:344e158bb76ca64786ce26a7b19e0fe27bb99e46f0c0860483f79c113326886a
+oid sha256:3c5e315eae7aadf57c4f69ad5d89a929539a6a7a764790e832b11f884d5760ec
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80d9256def4ddbecd133ffaf91a3beb43b27b05754727833c953c41932a0e8ae
+oid sha256:c7be2edbad2004afeeb2dd039b906c1a51fd5f0c22fa1436ebc804433337479d
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea04cc3ac22ce1d0030ee2ec4c6a340f77b0c8932fd68c5cc068a1a0638110d6
+oid sha256:dac6304c3d282c68b3b54b02e10f7ccb87b4af7f30bf7c763231322312d8a778
 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": 1.5659117698669434,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0021369804466289132,
+  "best_metric": 1.3795337677001953,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0042739608932578265,
   "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": 7.167,
       "eval_steps_per_second": 3.585,
       "step": 10
+    },
+    {
+      "epoch": 0.0023506784912918047,
+      "grad_norm": 0.842316746711731,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.4946,
+      "step": 11
+    },
+    {
+      "epoch": 0.002564376535954696,
+      "grad_norm": 0.9651074409484863,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.5619,
+      "step": 12
+    },
+    {
+      "epoch": 0.002778074580617587,
+      "grad_norm": 0.9838403463363647,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.6461,
+      "step": 13
+    },
+    {
+      "epoch": 0.0029917726252804786,
+      "grad_norm": 0.9522503614425659,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.3381,
+      "step": 14
+    },
+    {
+      "epoch": 0.00320547066994337,
+      "grad_norm": 1.0169678926467896,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.321,
+      "step": 15
+    },
+    {
+      "epoch": 0.00320547066994337,
+      "eval_loss": 1.4373729228973389,
+      "eval_runtime": 275.0162,
+      "eval_samples_per_second": 7.167,
+      "eval_steps_per_second": 3.585,
+      "step": 15
+    },
+    {
+      "epoch": 0.0034191687146062615,
+      "grad_norm": 1.0345380306243896,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.3766,
+      "step": 16
+    },
+    {
+      "epoch": 0.0036328667592691525,
+      "grad_norm": 0.920183002948761,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.5197,
+      "step": 17
+    },
+    {
+      "epoch": 0.003846564803932044,
+      "grad_norm": 1.0014177560806274,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.5562,
+      "step": 18
+    },
+    {
+      "epoch": 0.004060262848594935,
+      "grad_norm": 0.8492229580879211,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.2455,
+      "step": 19
+    },
+    {
+      "epoch": 0.0042739608932578265,
+      "grad_norm": 0.8897610902786255,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.369,
+      "step": 20
+    },
+    {
+      "epoch": 0.0042739608932578265,
+      "eval_loss": 1.3795337677001953,
+      "eval_runtime": 277.9232,
+      "eval_samples_per_second": 7.092,
+      "eval_steps_per_second": 3.548,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1628733135912960.0,
+  "total_flos": 3257466271825920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null