Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68072f9c7ecbda1585e913ce9205e078aca9c7c76c2ecd2cf94a7ba1da3d2676
+oid sha256:857d53b0f8466551de813fc49060e15d23e205154add09689f901748b1fdfa0a
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef8839db52c30b8a3a43196bb7f12b80666a01fd6917be9848203588c4b0fe56
+oid sha256:90e31f91e9abb2da49e90b46fc5ea51860121c817128ddfa2820e7dc5e8346bb
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb4aa45ce48d129cd19ca79e9875a72794280171d73dfd391533a430f237a529
+oid sha256:929439017dd5958fb30f41ac33cf00333dbaa333b4c84a2525c1811de7da0a66
 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": 1.1814048290252686,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.006811409110259685,
+  "best_metric": 1.1645457744598389,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.010217113665389528,
   "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": 7.457,
       "eval_steps_per_second": 3.731,
       "step": 20
+    },
+    {
+      "epoch": 0.007151979565772669,
+      "grad_norm": 0.46628570556640625,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.0381,
+      "step": 21
+    },
+    {
+      "epoch": 0.008173690932311623,
+      "grad_norm": 0.3525000810623169,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.003,
+      "step": 24
+    },
+    {
+      "epoch": 0.008514261387824606,
+      "eval_loss": 1.1674165725708008,
+      "eval_runtime": 165.9767,
+      "eval_samples_per_second": 7.453,
+      "eval_steps_per_second": 3.729,
+      "step": 25
+    },
+    {
+      "epoch": 0.009195402298850575,
+      "grad_norm": 0.39437252283096313,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.1823,
+      "step": 27
+    },
+    {
+      "epoch": 0.010217113665389528,
+      "grad_norm": 0.30337342619895935,
+      "learning_rate": 0.0,
+      "loss": 0.9293,
+      "step": 30
+    },
+    {
+      "epoch": 0.010217113665389528,
+      "eval_loss": 1.1645457744598389,
+      "eval_runtime": 165.9841,
+      "eval_samples_per_second": 7.453,
+      "eval_steps_per_second": 3.729,
+      "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": 7354672050339840.0,
+  "total_flos": 1.123859998703616e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null