Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c74d134d28f061850e15df366d4863896ced4faaa17cb01a54c3f1db5808342
+oid sha256:ddba15324ccc0e9b883e810a416ea55793f38fa3ee21cd043b5b0b858b58f861
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5547bb8a1009116af126a33ad249e4c698fde0dc1adc5b88d6689324b936c08f
+oid sha256:7f57c5489d9226ea40ccdb8ef3fb83b8aa848d2c7720f43c3500fdb895e188a3
 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": 0.889240562915802,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.003604902667627974,
+  "best_metric": 0.8657696843147278,
+  "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": 4.992,
       "eval_steps_per_second": 2.498,
       "step": 10
+    },
+    {
+      "epoch": 0.003965392934390771,
+      "grad_norm": 0.9040248990058899,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 4.1139,
+      "step": 11
+    },
+    {
+      "epoch": 0.004325883201153569,
+      "grad_norm": 0.5644927024841309,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 3.7057,
+      "step": 12
+    },
+    {
+      "epoch": 0.004686373467916366,
+      "grad_norm": 1.0138068199157715,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 3.6704,
+      "step": 13
+    },
+    {
+      "epoch": 0.005046863734679163,
+      "grad_norm": 0.4622229337692261,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 3.3469,
+      "step": 14
+    },
+    {
+      "epoch": 0.005407354001441961,
+      "grad_norm": 0.5623894929885864,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.6863,
+      "step": 15
+    },
+    {
+      "epoch": 0.005407354001441961,
+      "eval_loss": 0.8727303743362427,
+      "eval_runtime": 231.1288,
+      "eval_samples_per_second": 5.058,
+      "eval_steps_per_second": 2.531,
+      "step": 15
+    },
+    {
+      "epoch": 0.005767844268204758,
+      "grad_norm": 0.486777663230896,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.4783,
+      "step": 16
+    },
+    {
+      "epoch": 0.0061283345349675555,
+      "grad_norm": 0.6631057858467102,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 3.2112,
+      "step": 17
+    },
+    {
+      "epoch": 0.006488824801730353,
+      "grad_norm": 0.6003482341766357,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 4.0095,
+      "step": 18
+    },
+    {
+      "epoch": 0.00684931506849315,
+      "grad_norm": 0.5666629672050476,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 3.2599,
+      "step": 19
+    },
+    {
+      "epoch": 0.007209805335255948,
+      "grad_norm": 0.7612733244895935,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 4.1332,
+      "step": 20
+    },
+    {
+      "epoch": 0.007209805335255948,
+      "eval_loss": 0.8657696843147278,
+      "eval_runtime": 231.5309,
+      "eval_samples_per_second": 5.049,
+      "eval_steps_per_second": 2.527,
+      "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