Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a959d3e2c734772605e5230b07eb049bc75a9d337c43e4c12b920095a80d02b
+oid sha256:c3a56350d0049cf817fffee4065dc73b9da4f6a91dbf4f2f94ea75cb8f461654
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a27ee3419a245578a2277005c188d6d5258bb8341f12348499f11e663fad5476
+oid sha256:b46eb5d2fd6348206567179c75e97f6ca3741ef517d5dd88437365c93cab98c2
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24795ebfcca9e4abb0f4bd3458750424e888df4066034ea7fa5c8e1351dd64a8
+oid sha256:598475c58a7436696980643ce0b72129a627aa03cb4cec759dc20419448d4988
 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": 0.06836262345314026,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.20143240823634737,
+  "best_metric": 0.06628672778606415,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.22381378692927484,
   "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": 16.596,
       "eval_steps_per_second": 4.162,
       "step": 450
+    },
+    {
+      "epoch": 0.20590868397493287,
+      "grad_norm": 0.6762747168540955,
+      "learning_rate": 4.106260230538197e-06,
+      "loss": 0.1374,
+      "step": 460
+    },
+    {
+      "epoch": 0.21038495971351837,
+      "grad_norm": 0.873978853225708,
+      "learning_rate": 2.316354322216597e-06,
+      "loss": 0.1061,
+      "step": 470
+    },
+    {
+      "epoch": 0.21486123545210384,
+      "grad_norm": 0.9010151028633118,
+      "learning_rate": 1.0315847133935416e-06,
+      "loss": 0.1034,
+      "step": 480
+    },
+    {
+      "epoch": 0.21933751119068934,
+      "grad_norm": 0.5987867712974548,
+      "learning_rate": 2.582106724586351e-07,
+      "loss": 0.1206,
+      "step": 490
+    },
+    {
+      "epoch": 0.22381378692927484,
+      "grad_norm": 1.7397042512893677,
+      "learning_rate": 0.0,
+      "loss": 0.1681,
+      "step": 500
+    },
+    {
+      "epoch": 0.22381378692927484,
+      "eval_loss": 0.06628672778606415,
+      "eval_runtime": 56.633,
+      "eval_samples_per_second": 16.616,
+      "eval_steps_per_second": 4.167,
+      "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": 8.129866588854682e+16,
+  "total_flos": 9.033185098727424e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null