Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8210a0b50da7fd33208abfb412fac5049c16b6f63ced0bcdbf53909d1d5daca1
+oid sha256:a4d21725a061163326cf340ea0ed7893a52a247551926912476731be249b8009
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1e944da48fb616f6b095af7675b849cdc14a65623c7b346efe86e4780e183c1
+oid sha256:26759449ef6ad9e5841f39110e62b26e22a072f3ff3f2fbf0be154658507d048
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8911b5f46997fa9f12867e8137d6f3c05ab465feed07980c8e04741b612f58c8
+oid sha256:7e098a7d8700c380d125ce9fd50258bcd139f75b52adb8f4f3101bba5734d49a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3012fb121cd84e6e41f718fd33de9e34ed33145ada7b055f7e25e49408431d
+oid sha256:71a96715f430c2eb0d6104363f54769b2c1bdb005671dc81f0d67833a84ba743
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.864070475101471,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.042500944465432566,
+  "epoch": 0.04722327162825841,
   "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": 17.326,
       "eval_steps_per_second": 4.334,
       "step": 450
+    },
+    {
+      "epoch": 0.043445409897997736,
+      "grad_norm": 0.5827313661575317,
+      "learning_rate": 4.22247514272324e-06,
+      "loss": 0.9635,
+      "step": 460
+    },
+    {
+      "epoch": 0.0443898753305629,
+      "grad_norm": 0.8031895756721497,
+      "learning_rate": 2.38191152001518e-06,
+      "loss": 0.9467,
+      "step": 470
+    },
+    {
+      "epoch": 0.04533434076312807,
+      "grad_norm": 0.6544033288955688,
+      "learning_rate": 1.0607805071688306e-06,
+      "loss": 0.8662,
+      "step": 480
+    },
+    {
+      "epoch": 0.04627880619569324,
+      "grad_norm": 1.268267273902893,
+      "learning_rate": 2.655185216791625e-07,
+      "loss": 0.8408,
+      "step": 490
+    },
+    {
+      "epoch": 0.04722327162825841,
+      "grad_norm": 2.5217607021331787,
+      "learning_rate": 0.0,
+      "loss": 0.7067,
+      "step": 500
+    },
+    {
+      "epoch": 0.04722327162825841,
+      "eval_loss": 0.8645666837692261,
+      "eval_runtime": 256.669,
+      "eval_samples_per_second": 17.369,
+      "eval_steps_per_second": 4.344,
+      "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": 7.5783538212864e+16,
+  "total_flos": 8.4194585739264e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null