Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02051dce60e318694307e019ba2a12d473be1baca7b7b87b16b49dc8ca9ac935
+oid sha256:ceff784f0bf45f4426fcc8231c76fdb24f415ccc8da4353d827fb7de96f6f071
 size 56660888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6f522bb6d2385326fbb21c4124daf59a29182ba48b22652e5b4203ff2a3a906
+oid sha256:46e5baa70b377d0e70ce2730d92b722cd2c6456cfd21043b7e4070fcbeb3e0c9
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b14767f69ea91d7c99f7825007a32154863c356a5bb1fc6e1dce0bf1776e4117
+oid sha256:f74c5c763155510b2b9ae353acee1a6a84cba1afd3e565190d8570e497033272
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6096174716949463,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.012338062924120914,
+  "best_metric": 0.5904346704483032,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.01850709438618137,
   "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": 45.83,
       "eval_steps_per_second": 11.483,
       "step": 20
+    },
+    {
+      "epoch": 0.012954966070326958,
+      "grad_norm": 0.19333085417747498,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.488,
+      "step": 21
+    },
+    {
+      "epoch": 0.014805675508945095,
+      "grad_norm": 0.21158280968666077,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.5433,
+      "step": 24
+    },
+    {
+      "epoch": 0.015422578655151141,
+      "eval_loss": 0.5933957695960999,
+      "eval_runtime": 30.015,
+      "eval_samples_per_second": 45.477,
+      "eval_steps_per_second": 11.394,
+      "step": 25
+    },
+    {
+      "epoch": 0.016656384947563233,
+      "grad_norm": 0.23070305585861206,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.5482,
+      "step": 27
+    },
+    {
+      "epoch": 0.01850709438618137,
+      "grad_norm": 0.2302953004837036,
+      "learning_rate": 0.0,
+      "loss": 0.5806,
+      "step": 30
+    },
+    {
+      "epoch": 0.01850709438618137,
+      "eval_loss": 0.5904346704483032,
+      "eval_runtime": 29.8967,
+      "eval_samples_per_second": 45.657,
+      "eval_steps_per_second": 11.439,
+      "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": 2642732988235776.0,
+  "total_flos": 3947786315759616.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null