Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40a904456440ca292d0da61bd0fbd0cd8ae32113b811c1e4e9eef4ae96b8a2e2
+oid sha256:8d3a80806a563a9e8decbbcba13c4dfef6743516d003ae87ee1fb55ab4ca7037
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97c9b47dcfa098fd0d6e9ea46b504eaec37730bba7513017ced1a9bd55598ecd
+oid sha256:a0c12b4e07d1f0aa4a58f09f73747e4e80f37b3d945241a5bd270008977415f1
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1f0e1a56d3eb745a492fafbf5c632734ab8d943c2e3780ce159f6153a3e78f5
+oid sha256:baf28eade6cb6d7d7731158c0de04222d71e1eb7eda652ae1faf10ca8fe267a2
 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": 1.32414972782135,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.006146281499692686,
+  "best_metric": 1.0627840757369995,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.012292562999385371,
   "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": 5.819,
       "eval_steps_per_second": 2.914,
       "step": 10
+    },
+    {
+      "epoch": 0.006760909649661954,
+      "grad_norm": 0.6576057076454163,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.1595,
+      "step": 11
+    },
+    {
+      "epoch": 0.007375537799631223,
+      "grad_norm": 0.6442687511444092,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.8054,
+      "step": 12
+    },
+    {
+      "epoch": 0.007990165949600492,
+      "grad_norm": 1.0020877122879028,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.0942,
+      "step": 13
+    },
+    {
+      "epoch": 0.008604794099569761,
+      "grad_norm": 0.729012668132782,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.9238,
+      "step": 14
+    },
+    {
+      "epoch": 0.00921942224953903,
+      "grad_norm": 0.7299153804779053,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.7567,
+      "step": 15
+    },
+    {
+      "epoch": 0.00921942224953903,
+      "eval_loss": 1.1356873512268066,
+      "eval_runtime": 118.267,
+      "eval_samples_per_second": 5.792,
+      "eval_steps_per_second": 2.9,
+      "step": 15
+    },
+    {
+      "epoch": 0.009834050399508297,
+      "grad_norm": 1.3167082071304321,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.908,
+      "step": 16
+    },
+    {
+      "epoch": 0.010448678549477565,
+      "grad_norm": 0.6335702538490295,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.6436,
+      "step": 17
+    },
+    {
+      "epoch": 0.011063306699446834,
+      "grad_norm": 0.6994488835334778,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.7299,
+      "step": 18
+    },
+    {
+      "epoch": 0.011677934849416103,
+      "grad_norm": 0.6342307329177856,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.9354,
+      "step": 19
+    },
+    {
+      "epoch": 0.012292562999385371,
+      "grad_norm": 0.5913541316986084,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.9592,
+      "step": 20
+    },
+    {
+      "epoch": 0.012292562999385371,
+      "eval_loss": 1.0627840757369995,
+      "eval_runtime": 118.1209,
+      "eval_samples_per_second": 5.799,
+      "eval_steps_per_second": 2.904,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2866824584626176.0,
+  "total_flos": 5733649169252352.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null