Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b29bd7c8570e8d4fa6ab41c839f6272e53370d0ec347fe7fdf8d3f06f46517c
+oid sha256:d0257b23fd26924f7f3ea312f9d2de034cde95238082b69bb6f05217e4c7b5e3
 size 389074464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8e9e9e02e9eac66c654a5a2ec9e44a14ddca54b4ca6180874ea09f207a9212a
+oid sha256:89c5eba26c4b0db142d3d9e8592a0e6c2627424cdb049217f20c6213dd6abfae
 size 198011700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2fbabb02420f33b29ea23843c91d8ed69ded55901170cb0052b61945a50e386
+oid sha256:afb9b9d218527abb770051c858236e6767f3c8b4fed914f52f8b1f32b8a7be16
 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": 0.524067223072052,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.0846262341325811,
+  "best_metric": 0.5226322412490845,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.09402914903620123,
   "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": 20.185,
       "eval_steps_per_second": 5.049,
       "step": 450
+    },
+    {
+      "epoch": 0.08650681711330513,
+      "grad_norm": 0.9640802145004272,
+      "learning_rate": 4.106260230538197e-06,
+      "loss": 0.6474,
+      "step": 460
+    },
+    {
+      "epoch": 0.08838740009402915,
+      "grad_norm": 0.6373594403266907,
+      "learning_rate": 2.316354322216597e-06,
+      "loss": 0.5344,
+      "step": 470
+    },
+    {
+      "epoch": 0.09026798307475317,
+      "grad_norm": 0.6497265696525574,
+      "learning_rate": 1.0315847133935416e-06,
+      "loss": 0.5107,
+      "step": 480
+    },
+    {
+      "epoch": 0.0921485660554772,
+      "grad_norm": 0.7859962582588196,
+      "learning_rate": 2.582106724586351e-07,
+      "loss": 0.4527,
+      "step": 490
+    },
+    {
+      "epoch": 0.09402914903620123,
+      "grad_norm": 0.8895713090896606,
+      "learning_rate": 0.0,
+      "loss": 0.4403,
+      "step": 500
+    },
+    {
+      "epoch": 0.09402914903620123,
+      "eval_loss": 0.5226322412490845,
+      "eval_runtime": 110.6062,
+      "eval_samples_per_second": 20.243,
+      "eval_steps_per_second": 5.063,
+      "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": 4.891046515310592e+16,
+  "total_flos": 5.442856891396915e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null