Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07a125f780b6e410ed18f70bab3d8d799f99c779c7f8b4cecf7b595efa6d28ad
+oid sha256:935fbf609b5733a76e093e62948836190b3272eb1d609cc7cbb419f072f1b250
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4d2fa2beff5f28395bc1ca3b34651cacffec9da6b05daf6d1f32c2fff34bf3d
+oid sha256:b3828ec5ba6617d39fc817940e3603c07c3ee70c3a437fb14272faa8a0800e71
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94eb3af0be59b8022e591483a56634de67b6ec709d4a7976205940027b927a1a
+oid sha256:5c6d05d84134bc054dc7899f24d2f88d3ea9e2a651e736719bc9e968bca1a100
 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": 0.8891144394874573,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.003604902667627974,
+  "best_metric": 0.8654800653457642,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.007209805335255948,
   "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": 4.345,
       "eval_steps_per_second": 2.174,
       "step": 10
+    },
+    {
+      "epoch": 0.003965392934390771,
+      "grad_norm": 0.7970941662788391,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 4.1142,
+      "step": 11
+    },
+    {
+      "epoch": 0.004325883201153569,
+      "grad_norm": 0.5384020805358887,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 3.7093,
+      "step": 12
+    },
+    {
+      "epoch": 0.004686373467916366,
+      "grad_norm": 0.6986257433891296,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 3.6642,
+      "step": 13
+    },
+    {
+      "epoch": 0.005046863734679163,
+      "grad_norm": 0.4670394957065582,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 3.3371,
+      "step": 14
+    },
+    {
+      "epoch": 0.005407354001441961,
+      "grad_norm": 0.5628902316093445,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.6892,
+      "step": 15
+    },
+    {
+      "epoch": 0.005407354001441961,
+      "eval_loss": 0.8725980520248413,
+      "eval_runtime": 268.9663,
+      "eval_samples_per_second": 4.346,
+      "eval_steps_per_second": 2.175,
+      "step": 15
+    },
+    {
+      "epoch": 0.005767844268204758,
+      "grad_norm": 0.4687001407146454,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.4787,
+      "step": 16
+    },
+    {
+      "epoch": 0.0061283345349675555,
+      "grad_norm": 0.6563277244567871,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 3.2084,
+      "step": 17
+    },
+    {
+      "epoch": 0.006488824801730353,
+      "grad_norm": 0.5968443155288696,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 4.0139,
+      "step": 18
+    },
+    {
+      "epoch": 0.00684931506849315,
+      "grad_norm": 0.5900570750236511,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 3.2689,
+      "step": 19
+    },
+    {
+      "epoch": 0.007209805335255948,
+      "grad_norm": 0.4784393310546875,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 4.1322,
+      "step": 20
+    },
+    {
+      "epoch": 0.007209805335255948,
+      "eval_loss": 0.8654800653457642,
+      "eval_runtime": 269.1247,
+      "eval_samples_per_second": 4.344,
+      "eval_steps_per_second": 2.174,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3257498484080640.0,
+  "total_flos": 6474278237110272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null