Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:294ecbda74d2df68685f36ebfeebca6c986c81b2849874d837cb02f2aff91928
+oid sha256:b4decf62e2186d1e7f80fc13575fec02bad7e07bfd05f7a8861fb7d2eca46114
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:443fc093d3e51479cccc220a32c8fee5f6880bf4863678a768ce8a11bd148931
+oid sha256:72d385f7b81f2f06360950bfeec7841f5529e9368a0a5db9131784c40545a46a
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea30508b2168921b3e75386a046978772f5cbc66bbd566c5d99dd61ea40c26f1
+oid sha256:4cf355fd48ca7fbf33eb7fc35115a0613a7bff5e1759da5fa0cb1ec53729b7e7
 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": 1.5573710203170776,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.008592910848549946,
+  "best_metric": 1.4633499383926392,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.017185821697099892,
   "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": 11.287,
       "eval_steps_per_second": 5.644,
       "step": 10
+    },
+    {
+      "epoch": 0.00945220193340494,
+      "grad_norm": 0.17970110476016998,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.5495,
+      "step": 11
+    },
+    {
+      "epoch": 0.010311493018259935,
+      "grad_norm": 0.17453698813915253,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.5553,
+      "step": 12
+    },
+    {
+      "epoch": 0.01117078410311493,
+      "grad_norm": 0.18503691256046295,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.5771,
+      "step": 13
+    },
+    {
+      "epoch": 0.012030075187969926,
+      "grad_norm": 0.16835591197013855,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.3748,
+      "step": 14
+    },
+    {
+      "epoch": 0.01288936627282492,
+      "grad_norm": 0.1760474592447281,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.5093,
+      "step": 15
+    },
+    {
+      "epoch": 0.01288936627282492,
+      "eval_loss": 1.4957950115203857,
+      "eval_runtime": 43.272,
+      "eval_samples_per_second": 11.324,
+      "eval_steps_per_second": 5.662,
+      "step": 15
+    },
+    {
+      "epoch": 0.013748657357679914,
+      "grad_norm": 0.1684129536151886,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.4227,
+      "step": 16
+    },
+    {
+      "epoch": 0.014607948442534909,
+      "grad_norm": 0.18524901568889618,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.6153,
+      "step": 17
+    },
+    {
+      "epoch": 0.015467239527389903,
+      "grad_norm": 0.1905449479818344,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.4586,
+      "step": 18
+    },
+    {
+      "epoch": 0.0163265306122449,
+      "grad_norm": 0.19282594323158264,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.4929,
+      "step": 19
+    },
+    {
+      "epoch": 0.017185821697099892,
+      "grad_norm": 0.20464837551116943,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.4875,
+      "step": 20
+    },
+    {
+      "epoch": 0.017185821697099892,
+      "eval_loss": 1.4633499383926392,
+      "eval_runtime": 43.3147,
+      "eval_samples_per_second": 11.313,
+      "eval_steps_per_second": 5.656,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 511583956500480.0,
+  "total_flos": 1023167913000960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null