Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fdd24f3861ce94f899d4c744f87c1ba5303846af51e47fa6a8ce1542e3d97cf
+oid sha256:d82982e473b93166acf2ae06b2b8c81358abb0b3d2d6660fad62051a987ccad6
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aebc17480e68ed96cf09af44e6b230e34a5c00f55aee81b2935ecf1c825551e7
+oid sha256:87de0d8f27304dba8f31f4e473702edb767180fca758e624df50af2eb49e0176
 size 85723732

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f232d75a176f683907640adb1af366d8fd10500788f26a4a1e367ec1cb90111
+oid sha256:b145b0652a322d3e6987222fd70dacda9095b67e4935291c7667ea58af2bf360
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa0f7e2faaa98aa485e5dc42922e1b1819381507fa6961c3be50a0b49af04c0
+oid sha256:b617d9f149fb11f5d9825dc6193f0b55aa7bf4899d1811982c0c93a389d7300b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4198478162288666,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.33382789317507416,
+  "best_metric": 0.4194607138633728,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.37091988130563797,
   "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": 8.996,
       "eval_steps_per_second": 2.249,
       "step": 450
+    },
+    {
+      "epoch": 0.34124629080118696,
+      "grad_norm": 0.37923330068588257,
+      "learning_rate": 4.106260230538197e-06,
+      "loss": 0.4221,
+      "step": 460
+    },
+    {
+      "epoch": 0.3486646884272997,
+      "grad_norm": 0.3553723990917206,
+      "learning_rate": 2.316354322216597e-06,
+      "loss": 0.4364,
+      "step": 470
+    },
+    {
+      "epoch": 0.3560830860534125,
+      "grad_norm": 0.38167324662208557,
+      "learning_rate": 1.0315847133935416e-06,
+      "loss": 0.4317,
+      "step": 480
+    },
+    {
+      "epoch": 0.36350148367952523,
+      "grad_norm": 0.36284124851226807,
+      "learning_rate": 2.582106724586351e-07,
+      "loss": 0.4302,
+      "step": 490
+    },
+    {
+      "epoch": 0.37091988130563797,
+      "grad_norm": 0.3405497074127197,
+      "learning_rate": 0.0,
+      "loss": 0.3725,
+      "step": 500
+    },
+    {
+      "epoch": 0.37091988130563797,
+      "eval_loss": 0.4194607138633728,
+      "eval_runtime": 63.1755,
+      "eval_samples_per_second": 8.991,
+      "eval_steps_per_second": 2.248,
+      "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": 1.669246388011008e+17,
+  "total_flos": 1.85471820890112e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null