Training in progress, step 333, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4ed40840d313f8b2bc02bbe93f473a44a8ddfbb609a1d6ba51ab3b59a7c7c06
+oid sha256:a50a56d448a32e46b2848b0462cc8353ef5a589be6f245319c4f2a36128b4f4e
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fe30416035663be14c01526fb642e21e0724255646d9e1749d8f86484136405
+oid sha256:f4ec84e8bd327506bceeb7096227e3096bd636419e8915e1e9e452ee06531302
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7d5cf676d8fda0c44ed176ed4d50b1b1325744e81de8669d54f997792603643
+oid sha256:006a6cecce092db230fd771b6410c427a7535ec6aa2f50099d6c28ff00e54292
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c60c381bac9e8799c60aa8a777b39a5a5a50e40ffdd2eef1f8ffb61c67f3a087
+oid sha256:7bb8ec8add3b88c5563729db509453ece9c4c0821e8789a637378889f06fe3ca
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.0833128690719604,
   "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.9022556390977443,
+  "epoch": 1.0015037593984963,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 333,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,27 @@
       "eval_samples_per_second": 16.375,
       "eval_steps_per_second": 4.094,
       "step": 300
+    },
+    {
+      "epoch": 0.9323308270676691,
+      "grad_norm": 3.119682550430298,
+      "learning_rate": 3.5336086742025136e-06,
+      "loss": 1.0088,
+      "step": 310
+    },
+    {
+      "epoch": 0.9624060150375939,
+      "grad_norm": 4.465202331542969,
+      "learning_rate": 1.1330686378846785e-06,
+      "loss": 0.9312,
+      "step": 320
+    },
+    {
+      "epoch": 0.9924812030075187,
+      "grad_norm": 7.782965183258057,
+      "learning_rate": 6.044017959302761e-08,
+      "loss": 1.1944,
+      "step": 330
     }
   ],
   "logging_steps": 10,
@@ -296,12 +317,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.65692592029696e+16,
+  "total_flos": 6.279187771529626e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null