Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d685bc1ae1f9d4a4b0170716f4160b7dcdd0ce5327bc813c2c8c8513515f3ee
+oid sha256:7b9a60183d6357e9d76e7fb5ed62331597023349752d24d2d06f10ef425f6c61
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4268c37857fb09285f8a02da91d24795870ec69b44cd634353f4c2f2bda3d3ee
+oid sha256:d9fb69bbe4ff728742c2fac869caae052a239319e5d8e879e1361b6801760d33
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95fb1d9d58cf0df5459c57ad8557e8625668cb4fe8c20af1f15ebb287d603c67
+oid sha256:266ab93c9e14590f1e60d99c86b6237155e03af842fdc723952273962820feed
 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": 0.30446988344192505,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.010961907371882707,
+  "best_metric": 0.1798376888036728,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.021923814743765414,
   "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": 3.253,
       "eval_steps_per_second": 1.631,
       "step": 10
+    },
+    {
+      "epoch": 0.012058098109070978,
+      "grad_norm": 0.9388976693153381,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.1843,
+      "step": 11
+    },
+    {
+      "epoch": 0.013154288846259249,
+      "grad_norm": 1.1695252656936646,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.1949,
+      "step": 12
+    },
+    {
+      "epoch": 0.01425047958344752,
+      "grad_norm": 1.5253500938415527,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.2296,
+      "step": 13
+    },
+    {
+      "epoch": 0.01534667032063579,
+      "grad_norm": 0.8718650937080383,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.1098,
+      "step": 14
+    },
+    {
+      "epoch": 0.01644286105782406,
+      "grad_norm": 0.8161805272102356,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.1306,
+      "step": 15
+    },
+    {
+      "epoch": 0.01644286105782406,
+      "eval_loss": 0.20339640974998474,
+      "eval_runtime": 117.3158,
+      "eval_samples_per_second": 3.282,
+      "eval_steps_per_second": 1.645,
+      "step": 15
+    },
+    {
+      "epoch": 0.017539051795012334,
+      "grad_norm": 0.4280713200569153,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0685,
+      "step": 16
+    },
+    {
+      "epoch": 0.018635242532200603,
+      "grad_norm": 0.41537296772003174,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.0388,
+      "step": 17
+    },
+    {
+      "epoch": 0.019731433269388872,
+      "grad_norm": 4.0038371086120605,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.7503,
+      "step": 18
+    },
+    {
+      "epoch": 0.020827624006577145,
+      "grad_norm": 0.3152463138103485,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0241,
+      "step": 19
+    },
+    {
+      "epoch": 0.021923814743765414,
+      "grad_norm": 0.960701048374176,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.1267,
+      "step": 20
+    },
+    {
+      "epoch": 0.021923814743765414,
+      "eval_loss": 0.1798376888036728,
+      "eval_runtime": 118.1391,
+      "eval_samples_per_second": 3.259,
+      "eval_steps_per_second": 1.634,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2589389947404288.0,
+  "total_flos": 5363736319623168.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null