Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922c31af90c7350fc9c57bd6c29c79cb7f5f611bfdba472c8c76b3094dd67aa2
+oid sha256:2cda792a384931a10a183b64edc925bceb042ddfa01d654d05ee17cd9d79b950
 size 47235968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4718f953dfefb10400cc40a4acd6f24de02788a294f9a6dd8068c29515d20923
+oid sha256:8bbddee9d3d9714d89f0a57e61aeb77963cf8c71a3b1fcf9977d4a9acb0770f5
 size 24410836

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd25363458d3f51ae2460cffb1e73acc0b657d9ca64a41ba2022d45633554a46
+oid sha256:c7d5d48fcecd9394f8d62915f39f3e40d4f388910a340ed933c710b1001075f5
 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": 1.4638172388076782,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.012598425196850394,
+  "best_metric": 1.4445966482162476,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.025196850393700787,
   "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": 6.78,
       "eval_steps_per_second": 3.4,
       "step": 10
+    },
+    {
+      "epoch": 0.013858267716535434,
+      "grad_norm": 1.5400310754776,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.4818,
+      "step": 11
+    },
+    {
+      "epoch": 0.015118110236220473,
+      "grad_norm": 1.9725576639175415,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.5816,
+      "step": 12
+    },
+    {
+      "epoch": 0.016377952755905513,
+      "grad_norm": 1.9127973318099976,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.4193,
+      "step": 13
+    },
+    {
+      "epoch": 0.01763779527559055,
+      "grad_norm": 2.428370475769043,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.5406,
+      "step": 14
+    },
+    {
+      "epoch": 0.01889763779527559,
+      "grad_norm": 2.627856492996216,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.548,
+      "step": 15
+    },
+    {
+      "epoch": 0.01889763779527559,
+      "eval_loss": 1.4514150619506836,
+      "eval_runtime": 49.4496,
+      "eval_samples_per_second": 6.775,
+      "eval_steps_per_second": 3.397,
+      "step": 15
+    },
+    {
+      "epoch": 0.02015748031496063,
+      "grad_norm": 2.375114679336548,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.3945,
+      "step": 16
+    },
+    {
+      "epoch": 0.021417322834645668,
+      "grad_norm": 2.3865299224853516,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.4951,
+      "step": 17
+    },
+    {
+      "epoch": 0.02267716535433071,
+      "grad_norm": 2.61568546295166,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.6419,
+      "step": 18
+    },
+    {
+      "epoch": 0.02393700787401575,
+      "grad_norm": 2.4963173866271973,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.5219,
+      "step": 19
+    },
+    {
+      "epoch": 0.025196850393700787,
+      "grad_norm": 2.4020745754241943,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.5499,
+      "step": 20
+    },
+    {
+      "epoch": 0.025196850393700787,
+      "eval_loss": 1.4445966482162476,
+      "eval_runtime": 54.5616,
+      "eval_samples_per_second": 6.14,
+      "eval_steps_per_second": 3.079,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1307643897446400.0,
+  "total_flos": 2598942246174720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null