Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24ec3600840daa40cc3bf0f024806ab93d9b5e45cbc16c1ebfdf26e49d0cc9d4
+oid sha256:f3704a02e69d43bbf24ccf73d008dc8ac74320a182ff2012db5aaed0458f9185
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1abba53e8342947c5f4862bd2c4f321bf0c02360df56a8905f0124763a8d5e7b
+oid sha256:4669655a34d119afe92d5514a4d4687c7a5b5a384ee18931d7f90e91379f2c1c
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a6f493f122dc24fd8aa4852b1b6691b338460b3dd171aed4a858da508e00e20
+oid sha256:5bfe8b3574114a4b78e34aef09eb36bffde8eb10418fac748c2c7b754105548f
 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": 1.555640697479248,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.011841326228537596,
+  "best_metric": 1.4427205324172974,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.023682652457075192,
   "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": 4.344,
       "eval_steps_per_second": 2.172,
       "step": 10
+    },
+    {
+      "epoch": 0.013025458851391355,
+      "grad_norm": 0.9944465160369873,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.9366,
+      "step": 11
+    },
+    {
+      "epoch": 0.014209591474245116,
+      "grad_norm": 1.5967128276824951,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.2509,
+      "step": 12
+    },
+    {
+      "epoch": 0.015393724097098875,
+      "grad_norm": 0.6631534099578857,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.1633,
+      "step": 13
+    },
+    {
+      "epoch": 0.016577856719952634,
+      "grad_norm": 0.5836420655250549,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.0428,
+      "step": 14
+    },
+    {
+      "epoch": 0.017761989342806393,
+      "grad_norm": 0.8438186645507812,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.6668,
+      "step": 15
+    },
+    {
+      "epoch": 0.017761989342806393,
+      "eval_loss": 1.4639616012573242,
+      "eval_runtime": 87.2922,
+      "eval_samples_per_second": 4.078,
+      "eval_steps_per_second": 2.039,
+      "step": 15
+    },
+    {
+      "epoch": 0.018946121965660152,
+      "grad_norm": 1.0537880659103394,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.756,
+      "step": 16
+    },
+    {
+      "epoch": 0.020130254588513915,
+      "grad_norm": 1.179638147354126,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.8299,
+      "step": 17
+    },
+    {
+      "epoch": 0.021314387211367674,
+      "grad_norm": 0.7309013605117798,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.1362,
+      "step": 18
+    },
+    {
+      "epoch": 0.022498519834221433,
+      "grad_norm": 0.7479605674743652,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.7835,
+      "step": 19
+    },
+    {
+      "epoch": 0.023682652457075192,
+      "grad_norm": 0.629127025604248,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.9961,
+      "step": 20
+    },
+    {
+      "epoch": 0.023682652457075192,
+      "eval_loss": 1.4427205324172974,
+      "eval_runtime": 82.6509,
+      "eval_samples_per_second": 4.307,
+      "eval_steps_per_second": 2.154,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 133557245706240.0,
+  "total_flos": 276018307792896.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null