Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6299c096c457b19d9812c1e685cede9c583e7f2a5f430edaf8bdc21bcfe53cd6
+oid sha256:3c6064ff840555e968b22c9c2efac44cc5b00e7bee182ea6191988ae21a7599c
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e94ec0b8a747d9361542961b40411170e3ed75970cb858ea641809a36c2e0c
+oid sha256:44c91e97686bd1398dabc0d74d12f54df502915bfa066e902827f3cb0c3c30df
 size 21354682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1252d792e41bb665fe1605a92d938aec774e3f7f662e20fc53dbfeaa1c4d6a22
+oid sha256:12a571fbd35dd1d237c083d1ae676e59340903405be5b1c371f5816d7d483485
 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": 3.2530300617218018,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.05555555555555555,
+  "best_metric": 3.2455074787139893,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.08333333333333333,
   "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": 170.063,
       "eval_steps_per_second": 42.516,
       "step": 20
+    },
+    {
+      "epoch": 0.058333333333333334,
+      "grad_norm": 4.678488254547119,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 13.2836,
+      "step": 21
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 4.627444744110107,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 13.3123,
+      "step": 24
+    },
+    {
+      "epoch": 0.06944444444444445,
+      "eval_loss": 3.247187852859497,
+      "eval_runtime": 1.7611,
+      "eval_samples_per_second": 172.619,
+      "eval_steps_per_second": 43.155,
+      "step": 25
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 4.9202470779418945,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 12.9437,
+      "step": 27
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 4.927825927734375,
+      "learning_rate": 0.0,
+      "loss": 12.9429,
+      "step": 30
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "eval_loss": 3.2455074787139893,
+      "eval_runtime": 1.759,
+      "eval_samples_per_second": 172.826,
+      "eval_steps_per_second": 43.207,
+      "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": 172445285744640.0,
+  "total_flos": 258667928616960.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null