Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ca46a7285b7d6cd9f065fd235faee562c73984959acb66acfd6a8d56a9de733
+oid sha256:c3ee152d2fd045ce3e1c3906d9a753d88c0f4783e1c5baa7ed8e4bece694883d
 size 2772512088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a11ef66d26dcefc414ce3395b10388d1721d4bf2020d24e9e98914f935cfaa8
+oid sha256:db10fce557d4a8e890862b5a7d901d8cfdd26c083720249106218c900eceb2d3
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff7e4b2abb90412df957a1fd7d426f03bbfd52b0886ad7eab985b908e83a985
+oid sha256:08311d6d02658da8fe2c633027d13383328a90f0d215b5393d40440b6b620f3c
 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": 1.3790680170059204,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.052395645339698434,
+  "best_metric": 1.3619989156723022,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.05821738371077604,
   "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": 10.589,
       "eval_steps_per_second": 2.649,
       "step": 450
+    },
+    {
+      "epoch": 0.053559993013913954,
+      "grad_norm": 0.9184896945953369,
+      "learning_rate": 4.125629382569038e-06,
+      "loss": 1.2853,
+      "step": 460
+    },
+    {
+      "epoch": 0.05472434068812947,
+      "grad_norm": 0.8102919459342957,
+      "learning_rate": 2.327280521849694e-06,
+      "loss": 1.3286,
+      "step": 470
+    },
+    {
+      "epoch": 0.05588868836234499,
+      "grad_norm": 1.2703608274459839,
+      "learning_rate": 1.0364506790227565e-06,
+      "loss": 1.3894,
+      "step": 480
+    },
+    {
+      "epoch": 0.05705303603656052,
+      "grad_norm": 2.265528678894043,
+      "learning_rate": 2.5942864732872295e-07,
+      "loss": 1.4614,
+      "step": 490
+    },
+    {
+      "epoch": 0.05821738371077604,
+      "grad_norm": 6.215338230133057,
+      "learning_rate": 0.0,
+      "loss": 1.4716,
+      "step": 500
+    },
+    {
+      "epoch": 0.05821738371077604,
+      "eval_loss": 1.3619989156723022,
+      "eval_runtime": 342.0703,
+      "eval_samples_per_second": 10.574,
+      "eval_steps_per_second": 2.646,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.2369817949228237e+17,
+  "total_flos": 1.3727480894875238e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null