Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:384bae3bcb1814d7caa79d8aa1145aa3d99cc75cad819e5e8a43ec06a62260a5
+oid sha256:6e7331cb846d469a18351621969328ecbe72d0f166efebf4458cdbee541d5347
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a72013cfa5c4b60b1e46834d8a68e01afb64c3ea3622b4af391ffbee64cec013
+oid sha256:c2d261bf8148e82402f88fbcfb71e41653f0518d7247961b66ff097fe4c7d4cd
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87186703aed64a28f7aa092aa66ac4cff9ccd6f164d6515ce692fb3a15c4760e
+oid sha256:f7a008e4416221a92675c1aa1d6ef4a2ecef81cd840382268d055b69f64f070b
 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": 1.5705841779708862,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0003312629399585921,
+  "best_metric": 1.5604957342147827,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0004968944099378882,
   "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": 8.386,
       "eval_steps_per_second": 4.193,
       "step": 20
+    },
+    {
+      "epoch": 0.00034782608695652176,
+      "grad_norm": 0.34454429149627686,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.5959,
+      "step": 21
+    },
+    {
+      "epoch": 0.00039751552795031056,
+      "grad_norm": 0.30111217498779297,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.5235,
+      "step": 24
+    },
+    {
+      "epoch": 0.00041407867494824016,
+      "eval_loss": 1.5620274543762207,
+      "eval_runtime": 3033.885,
+      "eval_samples_per_second": 8.379,
+      "eval_steps_per_second": 4.19,
+      "step": 25
+    },
+    {
+      "epoch": 0.00044720496894409936,
+      "grad_norm": 0.2756118178367615,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.5289,
+      "step": 27
+    },
+    {
+      "epoch": 0.0004968944099378882,
+      "grad_norm": 0.2829815149307251,
+      "learning_rate": 0.0,
+      "loss": 1.5688,
+      "step": 30
+    },
+    {
+      "epoch": 0.0004968944099378882,
+      "eval_loss": 1.5604957342147827,
+      "eval_runtime": 3033.3725,
+      "eval_samples_per_second": 8.38,
+      "eval_steps_per_second": 4.19,
+      "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": 3292692008140800.0,
+  "total_flos": 4939038012211200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null