Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ccc2da199ee823cffaa2accad8ef19f18db2b9a54d653c335804acf6db3843d
+oid sha256:67c1c47b6346ea4506c1844f84c204b3eea23d6b962162616b87d50f12ab507e
 size 56662456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d03bd464edb7d5072a2e685bacb2e2b2f0926a8769f10334442de2fa64fdf18
+oid sha256:db7bc101c312f4e6f0b9e9c798119aff0c662801282102cd14532082e1050f6f
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb3488d1166a4e2425300cbf1fdf31a2531b509a517ac0709564154699174f83
+oid sha256:c0ea9bafbae92c292a727a27db257a44824d6a0c0d074f3197011ffcc671c7be
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2363591194152832,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.03148366784730421,
+  "best_metric": 1.2269476652145386,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.047225501770956316,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 10.051,
       "eval_steps_per_second": 2.517,
       "step": 20
+    },
+    {
+      "epoch": 0.03305785123966942,
+      "grad_norm": 0.36420589685440063,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 3.8621,
+      "step": 21
+    },
+    {
+      "epoch": 0.03778040141676505,
+      "grad_norm": 0.3829841911792755,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 3.889,
+      "step": 24
+    },
+    {
+      "epoch": 0.03935458480913026,
+      "eval_loss": 1.2311996221542358,
+      "eval_runtime": 53.7481,
+      "eval_samples_per_second": 9.954,
+      "eval_steps_per_second": 2.493,
+      "step": 25
+    },
+    {
+      "epoch": 0.04250295159386069,
+      "grad_norm": 0.6779709458351135,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 5.2738,
+      "step": 27
+    },
+    {
+      "epoch": 0.047225501770956316,
+      "grad_norm": 0.4863479435443878,
+      "learning_rate": 0.0,
+      "loss": 4.2184,
+      "step": 30
+    },
+    {
+      "epoch": 0.047225501770956316,
+      "eval_loss": 1.2269476652145386,
+      "eval_runtime": 53.1339,
+      "eval_samples_per_second": 10.069,
+      "eval_steps_per_second": 2.522,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4807501849559040.0,
+  "total_flos": 7000924568420352.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null