Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d47800fd7b2372b988dc3c344a939b92ccc7537aa031f947529baf509a4f155
+oid sha256:679f9b6abfcc50d19f008546c86d77bf96e6f778a47d113ab2ac191e0f6e2192
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1420074370493ac7568e8d8aa56e07cabe5d75adcb9b56d4d4be1129b9fcb090
+oid sha256:01374c17f55aa2226a21eeebc985f4e9cf97dca21d859b155bafa4b0791beb40
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ac9ef8a8d750dd06f1b2f32aa7dc4ccd0792acf7e63e2006163d178a7597fee
+oid sha256:0a2ba38d61cd6275d77c5204447109dd9eddc38992e480ed671e0d925609356b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.6078875064849854,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003429355281207133,
+  "best_metric": 3.5863263607025146,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0051440329218107,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 77.572,
       "eval_steps_per_second": 38.786,
       "step": 20
+    },
+    {
+      "epoch": 0.00360082304526749,
+      "grad_norm": 75.07467651367188,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 14.2807,
+      "step": 21
+    },
+    {
+      "epoch": 0.00411522633744856,
+      "grad_norm": 96.82402038574219,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 14.0723,
+      "step": 24
+    },
+    {
+      "epoch": 0.0042866941015089165,
+      "eval_loss": 3.58929705619812,
+      "eval_runtime": 31.6823,
+      "eval_samples_per_second": 77.52,
+      "eval_steps_per_second": 38.76,
+      "step": 25
+    },
+    {
+      "epoch": 0.004629629629629629,
+      "grad_norm": 67.07957458496094,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 13.2909,
+      "step": 27
+    },
+    {
+      "epoch": 0.0051440329218107,
+      "grad_norm": 66.56720733642578,
+      "learning_rate": 0.0,
+      "loss": 14.2312,
+      "step": 30
+    },
+    {
+      "epoch": 0.0051440329218107,
+      "eval_loss": 3.5863263607025146,
+      "eval_runtime": 31.6317,
+      "eval_samples_per_second": 77.644,
+      "eval_steps_per_second": 38.822,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 354006639575040.0,
+  "total_flos": 531009959362560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null