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:be9d443b12f0875cd5ab182915aac45ab6949f5b08cd6d37cfb5079bf908d75f
+oid sha256:b84093c2b5aa39e792700f9b8b11f8177647592398ebd2cffdd16f8e13eee488
 size 28351000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5dd5acadcb66f7da3b27579ce7d80e7cff4b58f49b93a48c9553f02b35345a6
+oid sha256:6cd46e02854f56a637a1a1baaee92e68a5942bc67e7fc2da88a00b1fe9323695
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8952570c97dded1c892fe6f5f802bfa6149e5695b69d61b9a8887de9d3cefa2
+oid sha256:dfe9202856d3a1a0d133765053790d64eb621b1ab384d57fef2e4af852ded9e9
 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": 1.4742869138717651,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0008227067050596463,
+  "best_metric": 1.45272696018219,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0016454134101192926,
   "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": 5.255,
       "eval_steps_per_second": 2.627,
       "step": 10
+    },
+    {
+      "epoch": 0.0009049773755656109,
+      "grad_norm": 3.754530668258667,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 6.7109,
+      "step": 11
+    },
+    {
+      "epoch": 0.0009872480460715754,
+      "grad_norm": 2.7262985706329346,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 6.0774,
+      "step": 12
+    },
+    {
+      "epoch": 0.0010695187165775401,
+      "grad_norm": 2.529963254928589,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 5.9247,
+      "step": 13
+    },
+    {
+      "epoch": 0.0011517893870835046,
+      "grad_norm": 3.371697425842285,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 6.4366,
+      "step": 14
+    },
+    {
+      "epoch": 0.0012340600575894694,
+      "grad_norm": 3.3902432918548584,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 5.9649,
+      "step": 15
+    },
+    {
+      "epoch": 0.0012340600575894694,
+      "eval_loss": 1.4562937021255493,
+      "eval_runtime": 946.1588,
+      "eval_samples_per_second": 5.409,
+      "eval_steps_per_second": 2.705,
+      "step": 15
+    },
+    {
+      "epoch": 0.0013163307280954339,
+      "grad_norm": 2.6186981201171875,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 5.7222,
+      "step": 16
+    },
+    {
+      "epoch": 0.0013986013986013986,
+      "grad_norm": 2.9605960845947266,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 5.6037,
+      "step": 17
+    },
+    {
+      "epoch": 0.0014808720691073633,
+      "grad_norm": 2.3991353511810303,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 5.9318,
+      "step": 18
+    },
+    {
+      "epoch": 0.0015631427396133278,
+      "grad_norm": 1.7448457479476929,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 5.5354,
+      "step": 19
+    },
+    {
+      "epoch": 0.0016454134101192926,
+      "grad_norm": 3.0942559242248535,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 5.8968,
+      "step": 20
+    },
+    {
+      "epoch": 0.0016454134101192926,
+      "eval_loss": 1.45272696018219,
+      "eval_runtime": 953.2521,
+      "eval_samples_per_second": 5.369,
+      "eval_steps_per_second": 2.684,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 410802758615040.0,
+  "total_flos": 791728952967168.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null