Training in progress, step 5000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b8b2e9b70bd50a6107cf935c4ee7553fe4d165acbb631aebb19fdd2952bd8c6
+oid sha256:7ffcd8b545710d2deb1452b4a64b7bc1dad2673f31e03dcb3b1797de89cc7950
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49089f5da9e62f3703191358d317a32f5e301aae4b5d381f3dd7b7771cd0e4e5
+oid sha256:331d061a629d7e43ed6f87056cf8b7a5c9d87ad133577087062ab4d83f230875
 size 671472978

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8802196682461502be670175c89363a21ec3127850a663775a099368fb8766e
+oid sha256:e7648dde45e1b2b06d70c9f35ad9adedc1a2d1a3b142ab4448f8c383a8e1910e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f6d93467eee9f7eb66e857b295a064a9a7b557fc916f9b5131020a127e4f67a
+oid sha256:016e25fda59c3776a60450c0d95b5f609ee100d53eaff927c1f903b335520ed3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.4104703664779663,
   "best_model_checkpoint": "miner_id_24/checkpoint-4500",
-  "epoch": 1.6285171446666062,
+  "epoch": 1.809463494074007,
   "eval_steps": 500,
-  "global_step": 4500,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -717,6 +717,84 @@
       "eval_samples_per_second": 21.162,
       "eval_steps_per_second": 10.581,
       "step": 4500
+    },
+    {
+      "epoch": 1.6466117796073463,
+      "grad_norm": 11.539615631103516,
+      "learning_rate": 4.050702638550275e-06,
+      "loss": 3.8056,
+      "step": 4550
+    },
+    {
+      "epoch": 1.6647064145480865,
+      "grad_norm": 14.798728942871094,
+      "learning_rate": 3.2051298603643753e-06,
+      "loss": 3.6837,
+      "step": 4600
+    },
+    {
+      "epoch": 1.6828010494888266,
+      "grad_norm": 14.411064147949219,
+      "learning_rate": 2.4570213114592954e-06,
+      "loss": 3.7863,
+      "step": 4650
+    },
+    {
+      "epoch": 1.7008956844295666,
+      "grad_norm": 13.782867431640625,
+      "learning_rate": 1.8071302737293295e-06,
+      "loss": 3.6069,
+      "step": 4700
+    },
+    {
+      "epoch": 1.7189903193703067,
+      "grad_norm": 24.582422256469727,
+      "learning_rate": 1.2561111323605712e-06,
+      "loss": 3.6882,
+      "step": 4750
+    },
+    {
+      "epoch": 1.737084954311047,
+      "grad_norm": 20.012916564941406,
+      "learning_rate": 8.04518716920466e-07,
+      "loss": 3.8095,
+      "step": 4800
+    },
+    {
+      "epoch": 1.755179589251787,
+      "grad_norm": 18.923974990844727,
+      "learning_rate": 4.5280774269154115e-07,
+      "loss": 3.7323,
+      "step": 4850
+    },
+    {
+      "epoch": 1.773274224192527,
+      "grad_norm": 17.673463821411133,
+      "learning_rate": 2.0133235281156736e-07,
+      "loss": 3.7895,
+      "step": 4900
+    },
+    {
+      "epoch": 1.791368859133267,
+      "grad_norm": 12.837079048156738,
+      "learning_rate": 5.0345761681491746e-08,
+      "loss": 3.683,
+      "step": 4950
+    },
+    {
+      "epoch": 1.809463494074007,
+      "grad_norm": 15.028837203979492,
+      "learning_rate": 0.0,
+      "loss": 3.6422,
+      "step": 5000
+    },
+    {
+      "epoch": 1.809463494074007,
+      "eval_loss": 1.4128326177597046,
+      "eval_runtime": 55.1436,
+      "eval_samples_per_second": 21.109,
+      "eval_steps_per_second": 10.554,
+      "step": 5000
     }
   ],
   "logging_steps": 50,
@@ -731,7 +809,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -740,12 +818,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.248564640812892e+17,
+  "total_flos": 9.167552121761956e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null