Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:821802ca26bbc646a97bcaa96f1c124e7ca7124c77b92edf91b9ec5873e07b4c
+oid sha256:8675af280dd6f91c521bca73ccb114c2cebdeaf71cf0d2824137ff5488c35d66
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:014d0673bd206043331a4f95ae7eb7fa9146704c70791f9621974fde4f6957e9
-size 328468404
+oid sha256:fae6c96eac3f06cf99d9e1b034482059c7af9a17032ab7fe09b5e366c77b4c72
+size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76dd3cb3e9c75811bddd59e490c3bb8cc4de2a51ae2bf711a3bd7b427cd669ef
+oid sha256:3783299537239442fbf2d6aafce550907932af8feb54b4212623fce71ccc4e09
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9b2510d4f3300d86de2c5b705a4b3113b18ea2234bf5e3432bd4dee5175a4db
+oid sha256:e79d8c81c28cccecf62c97d7dd656ff3c70055cc3d5608fb5051fff0516dc264
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.0026957893278449774,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.028682882055988984,
+  "epoch": 0.03441945846718678,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 37.11,
       "eval_steps_per_second": 9.283,
       "step": 250
+    },
+    {
+      "epoch": 0.029830197338228545,
+      "grad_norm": 0.011473994702100754,
+      "learning_rate": 0.00011210963902166683,
+      "loss": 0.0347,
+      "step": 260
+    },
+    {
+      "epoch": 0.030977512620468106,
+      "grad_norm": 0.013728223741054535,
+      "learning_rate": 0.00010504229891530386,
+      "loss": 0.0007,
+      "step": 270
+    },
+    {
+      "epoch": 0.03212482790270767,
+      "grad_norm": 0.0017318534664809704,
+      "learning_rate": 9.795770108469618e-05,
+      "loss": 0.0008,
+      "step": 280
+    },
+    {
+      "epoch": 0.03327214318494722,
+      "grad_norm": 0.0025633713230490685,
+      "learning_rate": 9.08903609783332e-05,
+      "loss": 0.0009,
+      "step": 290
+    },
+    {
+      "epoch": 0.03441945846718678,
+      "grad_norm": 0.22336512804031372,
+      "learning_rate": 8.387470996680658e-05,
+      "loss": 0.0027,
+      "step": 300
+    },
+    {
+      "epoch": 0.03441945846718678,
+      "eval_loss": 0.002929302165284753,
+      "eval_runtime": 99.9465,
+      "eval_samples_per_second": 36.72,
+      "eval_steps_per_second": 9.185,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -244,7 +287,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -253,12 +296,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.701119465914368e+16,
+  "total_flos": 5.64312071995392e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null