Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c0fe74f9686d2e5df16ba0094186f1bda0b310be5a50a0d3d3d34aa458b5a29
+oid sha256:b0b6c37a1ab1c628e5723cced9d20cb75e1ce00c7d1d35c93c3f93f8ebd92062
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16a774cc9625373d6b0bf0e4207fb87f122827c5607e1303332f232f408e4ce0
+oid sha256:ca5ba0609f9b8e4b679644c1ac00747fc598fcf1fe399419cefd8db6c4fc6a65
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:641ccbea056a1efd23f98e262e590ac8fcc4ad1b6b9ff16c4024e39e19c73f47
+oid sha256:c03b57fce19476462d13e0d7cc32cd4ec24586678f59ff5533dc6754e7878d95
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de68da4a411755dd89261d95dc85b46978ce68b71b6b640a5e732fce38d3ca1d
+oid sha256:673699a33c258fc5668f5919a0c3d2b61b77874f7dbb4fb806a02e77a15f3cef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.14272888004779816,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.3991130820399113,
+  "epoch": 0.4434589800443459,
   "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": 12.387,
       "eval_steps_per_second": 3.103,
       "step": 450
+    },
+    {
+      "epoch": 0.4079822616407982,
+      "grad_norm": 0.6553061604499817,
+      "learning_rate": 3.893199558198952e-06,
+      "loss": 0.1552,
+      "step": 460
+    },
+    {
+      "epoch": 0.41685144124168516,
+      "grad_norm": 1.4326709508895874,
+      "learning_rate": 2.1961661262525285e-06,
+      "loss": 0.1773,
+      "step": 470
+    },
+    {
+      "epoch": 0.42572062084257206,
+      "grad_norm": 0.36754101514816284,
+      "learning_rate": 9.780590914721787e-07,
+      "loss": 0.1508,
+      "step": 480
+    },
+    {
+      "epoch": 0.43458980044345896,
+      "grad_norm": 0.2781977355480194,
+      "learning_rate": 2.4481294888766817e-07,
+      "loss": 0.1077,
+      "step": 490
+    },
+    {
+      "epoch": 0.4434589800443459,
+      "grad_norm": 1.0655410289764404,
+      "learning_rate": 0.0,
+      "loss": 0.104,
+      "step": 500
+    },
+    {
+      "epoch": 0.4434589800443459,
+      "eval_loss": 0.14348678290843964,
+      "eval_runtime": 38.233,
+      "eval_samples_per_second": 12.424,
+      "eval_steps_per_second": 3.112,
+      "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": 1.1231202659165798e+17,
+  "total_flos": 1.2480978011081933e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null