Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:349b92fc771467ba19f4a4375705b0be18ee0a70d66dd5e9a3218efead140655
+oid sha256:08cc70a8d9147b62aaa8d73b5fd034f0b9a37c003a019968738a858d8bfec586
 size 891333320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25b655e6762cc1be326580ea77e8423738abff3ab79f8450863570718360a4d6
+oid sha256:803c15a8df2aa86e5ee46fd8badb1ad4b87f235d80044cd7129490d7cd398912
 size 452984596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:100d6b5df23f5f5fd45227dfa104aadadc2938f6706932b75edbcb0c200c13d0
+oid sha256:8d7697df5d44ca894de45b6ad582a4eb3152cd85e0d2cf0de43bab26a0ef47e7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d0f57336dd58c2282a758b1873df2644647c71e8296b0dab58cb3a9f5f7c78
+oid sha256:7e45926e8bb4228c69b4b56f6b51f1445c0aeb3fb7bb09ed84764ec2b4c3a8ff
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.32411646842956543,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.08176614881439084,
+  "best_metric": 0.30879753828048706,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.12264922322158626,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 4.135,
       "eval_steps_per_second": 1.036,
       "step": 100
+    },
+    {
+      "epoch": 0.08994276369582993,
+      "grad_norm": 0.40755146741867065,
+      "learning_rate": 3.1076923076923076e-06,
+      "loss": 0.4638,
+      "step": 110
+    },
+    {
+      "epoch": 0.09811937857726902,
+      "grad_norm": 0.45769235491752625,
+      "learning_rate": 2.330769230769231e-06,
+      "loss": 0.388,
+      "step": 120
+    },
+    {
+      "epoch": 0.10629599345870809,
+      "grad_norm": 0.4743373692035675,
+      "learning_rate": 1.5538461538461538e-06,
+      "loss": 0.4562,
+      "step": 130
+    },
+    {
+      "epoch": 0.11447260834014718,
+      "grad_norm": 0.0975443497300148,
+      "learning_rate": 7.769230769230769e-07,
+      "loss": 0.2405,
+      "step": 140
+    },
+    {
+      "epoch": 0.12264922322158626,
+      "grad_norm": 0.1865679770708084,
+      "learning_rate": 0.0,
+      "loss": 0.0108,
+      "step": 150
+    },
+    {
+      "epoch": 0.12264922322158626,
+      "eval_loss": 0.30879753828048706,
+      "eval_runtime": 124.7845,
+      "eval_samples_per_second": 4.127,
+      "eval_steps_per_second": 1.034,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -124,12 +167,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.247192480219136e+17,
+  "total_flos": 1.874234003423232e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null