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:facf61c6bc05191cd1de95f74ca10fe1793d49bbdf4b8af639baa6863ad2a574
+oid sha256:d304fab63eb613759fa21b511991fb472fe451122db3ecb57451a4de14d44553
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46cb0c9d4e26e7d42182c1cdaa6411d96436a691d88a53a04e084a7c45f5ba38
+oid sha256:d4f69de1fd80ce914315cccf479ee032a1136575e651c4e45e6a6b9ba8b9fcda
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
+oid sha256:83eb5cdc8dd621b9d3b7cf06b9b893f32eef10d148e5187947364f07998add5d
 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": 2.114116907119751,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.02041858090862685,
+  "best_metric": 2.087597370147705,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.030627871362940276,
   "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": 7.847,
       "eval_steps_per_second": 3.933,
       "step": 20
+    },
+    {
+      "epoch": 0.021439509954058193,
+      "grad_norm": 13.704133033752441,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 8.6983,
+      "step": 21
+    },
+    {
+      "epoch": 0.02450229709035222,
+      "grad_norm": 15.463887214660645,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 8.0824,
+      "step": 24
+    },
+    {
+      "epoch": 0.025523226135783564,
+      "eval_loss": 2.0934205055236816,
+      "eval_runtime": 52.6375,
+      "eval_samples_per_second": 7.846,
+      "eval_steps_per_second": 3.933,
+      "step": 25
+    },
+    {
+      "epoch": 0.027565084226646247,
+      "grad_norm": 12.577512741088867,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 7.9226,
+      "step": 27
+    },
+    {
+      "epoch": 0.030627871362940276,
+      "grad_norm": 13.241372108459473,
+      "learning_rate": 0.0,
+      "loss": 8.4831,
+      "step": 30
+    },
+    {
+      "epoch": 0.030627871362940276,
+      "eval_loss": 2.087597370147705,
+      "eval_runtime": 52.6034,
+      "eval_samples_per_second": 7.851,
+      "eval_steps_per_second": 3.935,
+      "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": 7031299013345280.0,
+  "total_flos": 1.054694852001792e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null