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:d28e9a1fc5180c22315c9dbf34b3a03fe37a813184e30bd5127503dd3d2f9537
+oid sha256:918eb5726a03a076cbe1eb52acd564139a8bec55a19a4518d27de35ab83c74b5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfdd2c067dc09815bc732517090959a537db04874860c2706d239607f7bc6ec6
+oid sha256:f7d7afde126efe2fc0f0fc09fefa76fe7cf3703c5b920f1f88d4abe81757bc0d
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fa854d15c2384113f6d6357c09e94e127361d0e7a10ba3180761f3ddae8f800
+oid sha256:eec1013b2d4306eaaff15198a94dbae1b0f1c43bcdb42117e0ea1a38524b41a7
 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": 2.9677023887634277,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.06015037593984962,
+  "best_metric": 2.8565144538879395,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.09022556390977443,
   "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": 4.59,
       "eval_steps_per_second": 2.295,
       "step": 20
+    },
+    {
+      "epoch": 0.06315789473684211,
+      "grad_norm": 3.705134153366089,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.7218,
+      "step": 21
+    },
+    {
+      "epoch": 0.07218045112781955,
+      "grad_norm": 3.5439586639404297,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.5117,
+      "step": 24
+    },
+    {
+      "epoch": 0.07518796992481203,
+      "eval_loss": 2.8749964237213135,
+      "eval_runtime": 30.5809,
+      "eval_samples_per_second": 4.578,
+      "eval_steps_per_second": 2.289,
+      "step": 25
+    },
+    {
+      "epoch": 0.081203007518797,
+      "grad_norm": 3.6708028316497803,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.6444,
+      "step": 27
+    },
+    {
+      "epoch": 0.09022556390977443,
+      "grad_norm": 4.414663791656494,
+      "learning_rate": 0.0,
+      "loss": 2.4063,
+      "step": 30
+    },
+    {
+      "epoch": 0.09022556390977443,
+      "eval_loss": 2.8565144538879395,
+      "eval_runtime": 30.5715,
+      "eval_samples_per_second": 4.579,
+      "eval_steps_per_second": 2.29,
+      "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": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null