Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2860207cb5aaf9deb7826e18aaf1d627f08058063a2ed9706ba706abfddf386d
+oid sha256:fb276611db3566ffa0598c8e3202ab83d93fa2fff87da8519eb01f727c43f6e0
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01448a6a8c02fe5911d5ad65fbecc548c2f1403301c26fd83c18128afbb3a962
+oid sha256:482d7ca14eb907ce0cdf19560648226144f7f69b63a8b8ee17775b96b896e5d9
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94eb3af0be59b8022e591483a56634de67b6ec709d4a7976205940027b927a1a
+oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
 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": 0.9063844680786133,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0059907143926913285,
+  "best_metric": 0.8007434606552124,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.011981428785382657,
   "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": 5.419,
       "eval_steps_per_second": 2.713,
       "step": 10
+    },
+    {
+      "epoch": 0.006589785831960461,
+      "grad_norm": 0.31022465229034424,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.8604,
+      "step": 11
+    },
+    {
+      "epoch": 0.007188857271229594,
+      "grad_norm": 0.4046589732170105,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.9009,
+      "step": 12
+    },
+    {
+      "epoch": 0.007787928710498727,
+      "grad_norm": 0.5031927824020386,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.876,
+      "step": 13
+    },
+    {
+      "epoch": 0.00838700014976786,
+      "grad_norm": 0.4806121289730072,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.9419,
+      "step": 14
+    },
+    {
+      "epoch": 0.008986071589036993,
+      "grad_norm": 0.35671281814575195,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.8153,
+      "step": 15
+    },
+    {
+      "epoch": 0.008986071589036993,
+      "eval_loss": 0.8290239572525024,
+      "eval_runtime": 130.5907,
+      "eval_samples_per_second": 5.383,
+      "eval_steps_per_second": 2.695,
+      "step": 15
+    },
+    {
+      "epoch": 0.009585143028306126,
+      "grad_norm": 0.3003746569156647,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.8158,
+      "step": 16
+    },
+    {
+      "epoch": 0.010184214467575258,
+      "grad_norm": 0.2912845015525818,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.804,
+      "step": 17
+    },
+    {
+      "epoch": 0.010783285906844391,
+      "grad_norm": 0.31682682037353516,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.8039,
+      "step": 18
+    },
+    {
+      "epoch": 0.011382357346113524,
+      "grad_norm": 0.3057119846343994,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.8771,
+      "step": 19
+    },
+    {
+      "epoch": 0.011981428785382657,
+      "grad_norm": 0.28653478622436523,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.8927,
+      "step": 20
+    },
+    {
+      "epoch": 0.011981428785382657,
+      "eval_loss": 0.8007434606552124,
+      "eval_runtime": 135.9653,
+      "eval_samples_per_second": 5.17,
+      "eval_steps_per_second": 2.589,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3295645846732800.0,
+  "total_flos": 6591291693465600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null