Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5675512a0f4a0690adb6856c62f98e6c7a91c16adfec78eb7b5c6873212c9b16
+oid sha256:be519ae45756ec217f5d0c5b96ac40d5101be37250be4d2b97a8ebed3aca8363
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e971049b33d8baa5fd33a0f4ec20729c0f4b6803ca663ed3694eeb510f3b0849
+oid sha256:c6ff571968aa08b2bea08cc93fa04e6ef9e9322e3f2a21402710a3ecf7a55e71
 size 82461044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a14570f9e7677b9c2cd15afab549c8871548f9b1c9a9a9381b998248d253daa
+oid sha256:9d69f2dd55cfb42ebd70ddb251e18d065478cd12816bcd9452185cfcd5ccab8d
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:275a3f467a10238121d3751994e96dac39b01caeff52940c5c443f8040986af4
+oid sha256:2b9e64598e5491bb996b411334acd2cefa3c30b5e20788d80cc38bcc4e5e5001
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.2717281579971313,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.25929127052722556,
+  "epoch": 0.28810141169691733,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 16.348,
       "eval_steps_per_second": 4.093,
       "step": 450
+    },
+    {
+      "epoch": 0.2650532987611639,
+      "grad_norm": 0.5627772808074951,
+      "learning_rate": 4.164367686630719e-06,
+      "loss": 1.6535,
+      "step": 460
+    },
+    {
+      "epoch": 0.2708153269951023,
+      "grad_norm": 0.6691345572471619,
+      "learning_rate": 2.3491329211158885e-06,
+      "loss": 1.3014,
+      "step": 470
+    },
+    {
+      "epoch": 0.27657735522904064,
+      "grad_norm": 0.8095937371253967,
+      "learning_rate": 1.046182610281186e-06,
+      "loss": 1.2333,
+      "step": 480
+    },
+    {
+      "epoch": 0.282339383462979,
+      "grad_norm": 1.0728657245635986,
+      "learning_rate": 2.6186459706889876e-07,
+      "loss": 1.0591,
+      "step": 490
+    },
+    {
+      "epoch": 0.28810141169691733,
+      "grad_norm": 2.1311142444610596,
+      "learning_rate": 0.0,
+      "loss": 0.7293,
+      "step": 500
+    },
+    {
+      "epoch": 0.28810141169691733,
+      "eval_loss": 1.2725006341934204,
+      "eval_runtime": 45.1255,
+      "eval_samples_per_second": 16.199,
+      "eval_steps_per_second": 4.055,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.16127674459095e+16,
+  "total_flos": 9.070027045915853e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null