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:f7f1911ec010b41aabf49e37cdece65c512c34ab5c85ea3add6c9891742f6ba5
+oid sha256:10725999e83420e46ad5732ba9fe6e8344cd83d336ac2b2cc516584e0e3155a4
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ad451adbe79d7073ff16839115625badfcfc03f7532c228e5918b4d9eb3532c
+oid sha256:5ee5b9f343f187ede450567ea3f92226ab8ee97d0ac98fe9f3f2fcd1b3933c9f
 size 18810356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cb5ce401cf12131a99389fa65789cdf2fc26192986a95a0b15362c0157abb95
+oid sha256:8ce81bff3eb8484485387cf28e7673dacfc603871d944b7d6d91bbcbeac1c67a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c579f5f648f371ddcf6d84448bace40e1d46168d2f7b5fae9b6105a9c79d201
+oid sha256:2c9718e38efb2d48aaa61791c4fc8b4a7f9cfd08f355dda43ae7de9f2cb195d8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.8709187507629395,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.2234359483614697,
+  "best_metric": 2.8699963092803955,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.24826216484607747,
   "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": 48.038,
       "eval_steps_per_second": 12.01,
       "step": 450
+    },
+    {
+      "epoch": 0.22840119165839126,
+      "grad_norm": 0.6205804944038391,
+      "learning_rate": 4.125629382569038e-06,
+      "loss": 2.7751,
+      "step": 460
+    },
+    {
+      "epoch": 0.2333664349553128,
+      "grad_norm": 0.6956404447555542,
+      "learning_rate": 2.327280521849694e-06,
+      "loss": 2.8201,
+      "step": 470
+    },
+    {
+      "epoch": 0.23833167825223436,
+      "grad_norm": 1.010880470275879,
+      "learning_rate": 1.0364506790227565e-06,
+      "loss": 2.8927,
+      "step": 480
+    },
+    {
+      "epoch": 0.24329692154915591,
+      "grad_norm": 1.3041315078735352,
+      "learning_rate": 2.5942864732872295e-07,
+      "loss": 3.034,
+      "step": 490
+    },
+    {
+      "epoch": 0.24826216484607747,
+      "grad_norm": 3.136924982070923,
+      "learning_rate": 0.0,
+      "loss": 3.0295,
+      "step": 500
+    },
+    {
+      "epoch": 0.24826216484607747,
+      "eval_loss": 2.8699963092803955,
+      "eval_runtime": 17.7309,
+      "eval_samples_per_second": 47.826,
+      "eval_steps_per_second": 11.957,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "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": 4451892807598080.0,
+  "total_flos": 4938536960655360.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null