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:baeb7b0af2e0f1adc50527ed15e70e16db821ed91041cfe3aa3c126d71b78f70
+oid sha256:4d947e666abb7539248b621ca6668974d0a8ae64200c4bb22fecc7d568bc7c9b
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:525a1aa1ac209279c690ddbf2ab0ae66f8f74f79f0c46bb37fe0e886cdccaaff
+oid sha256:b490d6fb6adb43c58e1f0c3340aff0b859a501061d0444f1bcc656e0b68d435a
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f50382a7b74721780781f51be66dff804a86521a06c2e4edc45eb8b3dd006cd
+oid sha256:40f8404ec89e14b2dc4ab049922c5f3582f32fceb6aae141af4d39f03d2cd1c4
 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": 2.035742998123169,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.16236694930543027,
+  "epoch": 0.1804077214504781,
   "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": 15.878,
       "eval_steps_per_second": 3.973,
       "step": 450
+    },
+    {
+      "epoch": 0.16597510373443983,
+      "grad_norm": 1.0669924020767212,
+      "learning_rate": 4.22247514272324e-06,
+      "loss": 2.0513,
+      "step": 460
+    },
+    {
+      "epoch": 0.1695832581634494,
+      "grad_norm": 1.5129503011703491,
+      "learning_rate": 2.38191152001518e-06,
+      "loss": 2.0959,
+      "step": 470
+    },
+    {
+      "epoch": 0.17319141259245896,
+      "grad_norm": 1.5468735694885254,
+      "learning_rate": 1.0607805071688306e-06,
+      "loss": 2.1127,
+      "step": 480
+    },
+    {
+      "epoch": 0.1767995670214685,
+      "grad_norm": 1.8866146802902222,
+      "learning_rate": 2.655185216791625e-07,
+      "loss": 2.0466,
+      "step": 490
+    },
+    {
+      "epoch": 0.1804077214504781,
+      "grad_norm": 4.180663108825684,
+      "learning_rate": 0.0,
+      "loss": 1.813,
+      "step": 500
+    },
+    {
+      "epoch": 0.1804077214504781,
+      "eval_loss": 2.0386555194854736,
+      "eval_runtime": 73.3404,
+      "eval_samples_per_second": 15.912,
+      "eval_steps_per_second": 3.981,
+      "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": 8.758806966593126e+16,
+  "total_flos": 9.72048437304361e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null