Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d09049aae0d00e64379f908af2bc4c73dedba59722e405a7094f4a414209ec7
+oid sha256:83a2948544e45cfd5b7c8624734f0f5d93a992844e3e438b9bba8131e82c611e
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d1b387894ada6c7e7773a0f35db603a07853edc292cf130dd8b545f69940a1b
+oid sha256:a6953dd1595a7586362631d514a2f891f63202f6ed2354cb40a734ba9131756d
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54084b4e5347aa66384acf631cd10655127aa584d5035af527f6405c0212fdfb
+oid sha256:2e684c1ad226077703afde09b83b95f3a8175c286a931e3d446a3b86d76af18a
 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": 3.346342086791992,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 3.192807243841075e-05,
+  "best_metric": 3.055253505706787,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 6.38561448768215e-05,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 34.636,
       "eval_steps_per_second": 17.319,
       "step": 10
+    },
+    {
+      "epoch": 3.8313686926092896e-05,
+      "grad_norm": 1.2107754945755005,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 3.2029,
+      "step": 12
+    },
+    {
+      "epoch": 4.789210865761612e-05,
+      "grad_norm": 1.50534188747406,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 3.1148,
+      "step": 15
+    },
+    {
+      "epoch": 4.789210865761612e-05,
+      "eval_loss": 3.137223243713379,
+      "eval_runtime": 933.6085,
+      "eval_samples_per_second": 35.314,
+      "eval_steps_per_second": 17.657,
+      "step": 15
+    },
+    {
+      "epoch": 5.747053038913935e-05,
+      "grad_norm": 1.7882508039474487,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 3.3444,
+      "step": 18
+    },
+    {
+      "epoch": 6.38561448768215e-05,
+      "eval_loss": 3.055253505706787,
+      "eval_runtime": 940.5098,
+      "eval_samples_per_second": 35.054,
+      "eval_steps_per_second": 17.528,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 17354698260480.0,
+  "total_flos": 34709396520960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null