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:a0fcb5f29ea2814dcf23a6b9742012173d85c8ba12f6050c74ead684571989d9
+oid sha256:efede148730bf4781165fbeca79b6fb2d67c40f709f5388a430cab6c653b00d6
 size 1006723888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91a86e165119f43a87eaf3a5eb649fa86b1369b3c93a106587a95289addf02ce
+oid sha256:e5d95620492b0300469ca81922da357520d5ee3c3b43d51bbcb87f31fbdc58f8
 size 2013843826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34349ec0c3e558ab25e7e80fb79b0a58097dd48353982087681d852250ffe1e2
+oid sha256:77302e068b407fc05ff84e12986ed11ac753f89c85e7d469586073c866681536
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d84f1d22d1dbd789e1697ea3e7c73bcf7d3096d0797e7591ebf3f736315f60cc
+oid sha256:59414e4d4970b56c3194c746b96a59c7bb7799d9be3d150123d1bd9b4ba0c19f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.797318696975708,
-  "best_model_checkpoint": "miner_id_24/checkpoint-700",
-  "epoch": 0.34073623364770306,
+  "best_metric": 0.7953770160675049,
+  "best_model_checkpoint": "miner_id_24/checkpoint-800",
+  "epoch": 0.3894128384545178,
   "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": 5.444,
       "eval_steps_per_second": 1.361,
       "step": 700
+    },
+    {
+      "epoch": 0.36507453605111045,
+      "grad_norm": 24.764808654785156,
+      "learning_rate": 2.569889001363079e-06,
+      "loss": 6.2853,
+      "step": 750
+    },
+    {
+      "epoch": 0.3894128384545178,
+      "grad_norm": 23.11544418334961,
+      "learning_rate": 0.0,
+      "loss": 6.4544,
+      "step": 800
+    },
+    {
+      "epoch": 0.3894128384545178,
+      "eval_loss": 0.7953770160675049,
+      "eval_runtime": 634.496,
+      "eval_samples_per_second": 5.453,
+      "eval_steps_per_second": 1.363,
+      "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": 1.774364837447467e+18,
+  "total_flos": 2.026664422029656e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null