Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:700122bc692e4da06a1d9d93d5854ab80b79263ce39b5faa747e2ac7fcb1604f
+oid sha256:209651481e545a8628b2d44e8b2a9f1059f530b93915aa608c55eb27d489f681
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e5a4521641f5d5715c4c043f2e0eff579870ce668872590aaebe492d44b0b7b
+oid sha256:8ce8b3ef2b743f5b7c6ab536c343bc8cab9a6ccbda07384f97037797f575e3b2
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2d7c61922050288084f0dea9ba69f104273c3d5ef07fbed6077de3c816be22a
+oid sha256:3ebc07ea3cab779586e4adccc201b202913ae9dfa88e91955d8fdd45bde14274
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5220d0af0ff98b2d6e04334f1c29842da7230747bf3383cf1f883a4d2eb6d4f2
+oid sha256:90c455b2a7603e9003556345290fd0185bd6c6017de2b595e3f9c6216f721e5e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.7216787338256836,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.02140716426430712,
+  "best_metric": 2.712040901184082,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.028542885685742828,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 13.69,
       "eval_steps_per_second": 3.427,
       "step": 150
+    },
+    {
+      "epoch": 0.02283430854859426,
+      "grad_norm": 7.011553764343262,
+      "learning_rate": 2.2644444444444443e-06,
+      "loss": 2.8096,
+      "step": 160
+    },
+    {
+      "epoch": 0.024261452832881406,
+      "grad_norm": 9.93742847442627,
+      "learning_rate": 1.6983333333333333e-06,
+      "loss": 2.7749,
+      "step": 170
+    },
+    {
+      "epoch": 0.025688597117168546,
+      "grad_norm": 8.066086769104004,
+      "learning_rate": 1.1322222222222221e-06,
+      "loss": 2.7175,
+      "step": 180
+    },
+    {
+      "epoch": 0.027115741401455687,
+      "grad_norm": 10.917490005493164,
+      "learning_rate": 5.661111111111111e-07,
+      "loss": 2.7104,
+      "step": 190
+    },
+    {
+      "epoch": 0.028542885685742828,
+      "grad_norm": 14.808945655822754,
+      "learning_rate": 0.0,
+      "loss": 2.4751,
+      "step": 200
+    },
+    {
+      "epoch": 0.028542885685742828,
+      "eval_loss": 2.712040901184082,
+      "eval_runtime": 161.5317,
+      "eval_samples_per_second": 13.7,
+      "eval_steps_per_second": 3.43,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.006569286670746e+16,
+  "total_flos": 5.333247858416026e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null