Training in progress, step 800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a178873c1be01269d156281b0aeabae3412ade44249885d4be3caedf2ca7694c
+oid sha256:13da667a491abe7464dbf34da80e0981108c124fff443fa786ed05140577e929
 size 1006723888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd93542e536c46c0631602f64cf69999a452f2b21c5957c27aa0b97a512f027a
+oid sha256:04be8048b9fb741037825ccec0435f7f5efbd02b65626fe5c8d4888fb7ac72bb
 size 2013843826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4e5ec877d472e87615bbc7c6e1b30d1cb3386362c5acf9ae50a50a7d3fd67dc
+oid sha256:9053ba6a94b08cab2544f67605acae1101b562b8858b131eba5910ddfab4fc27
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47c7d347e630c2caaae2e183d7e607a96a479aa60cdcaafffb7f1f5065d10cae
+oid sha256:837ba1fa6e9c11dc854a2228688e74c482e56a8d1fff50b18304941ca46571f0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.859471321105957,
-  "best_model_checkpoint": "miner_id_24/checkpoint-700",
-  "epoch": 0.4094764551038315,
+  "best_metric": 0.836245059967041,
+  "best_model_checkpoint": "miner_id_24/checkpoint-800",
+  "epoch": 0.46797309154723604,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -169,6 +169,28 @@
       "eval_samples_per_second": 3.307,
       "eval_steps_per_second": 0.827,
       "step": 700
+    },
+    {
+      "epoch": 0.4387247733255338,
+      "grad_norm": 23.29357147216797,
+      "learning_rate": 2.707785484363049e-06,
+      "loss": 6.8282,
+      "step": 750
+    },
+    {
+      "epoch": 0.46797309154723604,
+      "grad_norm": 23.90059471130371,
+      "learning_rate": 0.0,
+      "loss": 6.7265,
+      "step": 800
+    },
+    {
+      "epoch": 0.46797309154723604,
+      "eval_loss": 0.836245059967041,
+      "eval_runtime": 855.5599,
+      "eval_samples_per_second": 3.366,
+      "eval_steps_per_second": 0.842,
+      "step": 800
     }
   ],
   "logging_steps": 50,
@@ -192,12 +214,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.974521423726379e+18,
+  "total_flos": 3.398843452341879e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null