Training in progress, step 110, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a79d6468f9a8226984a35f278d2afc4996fc80bf229f9e9f4696b88b0244d70
+oid sha256:aa396bc2eabb66ff27857a10437bfc7c558806c4a68ec1a75dacc99173908d82
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eed3ef08c89e9a07cd3218a687a41dd717cf80833936a581ab6db0cd1f2aabdf
+oid sha256:60c2f4152cf6b8df3c7f147c9866f5250416a16de45bd3c857da8ea2318ba659
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fa0933e237e365bbcbd10bdc7014a011ec526d46395768542a06f4bd5bcda7b
+oid sha256:7ee3a3829b510f41bd584ab9c5fe3e74aab24b4293509d98d00cb95ebef4b7e8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5c84ec0ff3c8c6aa13b25568668096db118f67ce80a9fa015a625446606f15d
+oid sha256:398198b060b9edcfe93ff59de4a929b40cbc42323ec0afb0426f8d7b821a61c1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.2894105911254883,
   "best_model_checkpoint": "miner_id_24/checkpoint-80",
-  "epoch": 0.028238616307800918,
+  "epoch": 0.03106247793858101,
   "eval_steps": 10,
-  "global_step": 100,
+  "global_step": 110,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -795,6 +795,84 @@
       "eval_samples_per_second": 1.771,
       "eval_steps_per_second": 1.771,
       "step": 100
+    },
+    {
+      "epoch": 0.028521002470878926,
+      "grad_norm": 0.8574671745300293,
+      "learning_rate": 0.00018345732537213027,
+      "loss": 1.9177,
+      "step": 101
+    },
+    {
+      "epoch": 0.028803388633956935,
+      "grad_norm": 0.9129525423049927,
+      "learning_rate": 0.00018310240965131041,
+      "loss": 2.4622,
+      "step": 102
+    },
+    {
+      "epoch": 0.029085774797034947,
+      "grad_norm": 0.8835414052009583,
+      "learning_rate": 0.00018274407791591966,
+      "loss": 1.051,
+      "step": 103
+    },
+    {
+      "epoch": 0.029368160960112955,
+      "grad_norm": 0.508120059967041,
+      "learning_rate": 0.00018238234489557215,
+      "loss": 0.4317,
+      "step": 104
+    },
+    {
+      "epoch": 0.029650547123190964,
+      "grad_norm": 1.259400725364685,
+      "learning_rate": 0.0001820172254596956,
+      "loss": 1.9737,
+      "step": 105
+    },
+    {
+      "epoch": 0.029932933286268972,
+      "grad_norm": 1.45259428024292,
+      "learning_rate": 0.00018164873461691986,
+      "loss": 0.6959,
+      "step": 106
+    },
+    {
+      "epoch": 0.03021531944934698,
+      "grad_norm": 0.8846643567085266,
+      "learning_rate": 0.00018127688751446027,
+      "loss": 1.3487,
+      "step": 107
+    },
+    {
+      "epoch": 0.030497705612424993,
+      "grad_norm": 0.7302697896957397,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.7445,
+      "step": 108
+    },
+    {
+      "epoch": 0.030780091775503,
+      "grad_norm": 1.3288211822509766,
+      "learning_rate": 0.0001805231858085356,
+      "loss": 1.2461,
+      "step": 109
+    },
+    {
+      "epoch": 0.03106247793858101,
+      "grad_norm": 0.4046940207481384,
+      "learning_rate": 0.00018014136218679567,
+      "loss": 1.9418,
+      "step": 110
+    },
+    {
+      "epoch": 0.03106247793858101,
+      "eval_loss": 1.3085497617721558,
+      "eval_runtime": 418.6203,
+      "eval_samples_per_second": 1.782,
+      "eval_steps_per_second": 1.782,
+      "step": 110
     }
   ],
   "logging_steps": 1,
@@ -809,7 +887,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -818,12 +896,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.46010452164608e+16,
+  "total_flos": 8.206114973810688e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null