Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50106e395c737b9d71b9b0eaee9f3485cedac3368a9cb83379feb4ce5bb7cce7
+oid sha256:f0a0a7f8e4f0665341afaf3382e50b4c3a2a8ae74c63491fe95038c86faa0d3b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63f96557a699622105f66b5803917b907377a03465162104bf46bc60def075a5
+oid sha256:d0803b38a4198bd7a6d5f0b8e5f0a2bbc2c50075024ea44c76d3ed5e6cc9e8b9
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
+oid sha256:83eb5cdc8dd621b9d3b7cf06b9b893f32eef10d148e5187947364f07998add5d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.09213387966156,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.001218824748236513,
+  "best_metric": 1.0610778331756592,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0018282371223547695,
   "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": 6.798,
       "eval_steps_per_second": 3.399,
       "step": 20
+    },
+    {
+      "epoch": 0.0012797659856483385,
+      "grad_norm": 12.608725547790527,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 4.2671,
+      "step": 21
+    },
+    {
+      "epoch": 0.0014625896978838154,
+      "grad_norm": 11.816730499267578,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 4.0674,
+      "step": 24
+    },
+    {
+      "epoch": 0.0015235309352956412,
+      "eval_loss": 1.0658913850784302,
+      "eval_runtime": 1015.7997,
+      "eval_samples_per_second": 6.803,
+      "eval_steps_per_second": 3.401,
+      "step": 25
+    },
+    {
+      "epoch": 0.0016454134101192926,
+      "grad_norm": 12.555757522583008,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 4.0704,
+      "step": 27
+    },
+    {
+      "epoch": 0.0018282371223547695,
+      "grad_norm": 14.25430679321289,
+      "learning_rate": 0.0,
+      "loss": 4.4166,
+      "step": 30
+    },
+    {
+      "epoch": 0.0018282371223547695,
+      "eval_loss": 1.0610778331756592,
+      "eval_runtime": 1016.6239,
+      "eval_samples_per_second": 6.797,
+      "eval_steps_per_second": 3.399,
+      "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": 7031294986813440.0,
+  "total_flos": 1.054694248022016e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null