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:a349b12bc163a95b572b0c6f75077acdbdc2d9abb38e3396e59f85aa64aeaf5f
+oid sha256:f3b1c4631117a1f4d57a2b4d0bc47b06c03602236c4db1e2381462d141a2b807
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6213557f7c8c16724dac57d3be11eb4c987b1923f566b28b0674348d35d88183
+oid sha256:6d53ae0fadaaa2076408a8bb58126d1157f87f14aa75749d99c3083cf8cf4c16
 size 71878996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:555c517b5ec1b1f56c72674be5228517ec41b93bf562b6899969a8588f22db2b
+oid sha256:bc07869608f1dc652854831f1bf53bdb6d1c4bd180b591e20607fa38cf0da390
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23d0c4fcd75282d05c3ecf542229a263cdfdea966c314071913c5dc6faf85a25
+oid sha256:ddd16399db35d8a29f2ca6eadbdcd4462c58bf5886d5df4eb74f5a14652bb30c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.727031946182251,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.014038371548900327,
+  "best_metric": 2.7261009216308594,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.015598190609889253,
   "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": 40.24,
       "eval_steps_per_second": 10.062,
       "step": 450
+    },
+    {
+      "epoch": 0.014350335361098112,
+      "grad_norm": 0.999866247177124,
+      "learning_rate": 3.990045318353154e-06,
+      "loss": 2.7576,
+      "step": 460
+    },
+    {
+      "epoch": 0.014662299173295897,
+      "grad_norm": 0.8971395492553711,
+      "learning_rate": 2.250797124418014e-06,
+      "loss": 2.7613,
+      "step": 470
+    },
+    {
+      "epoch": 0.014974262985493684,
+      "grad_norm": 0.9451714754104614,
+      "learning_rate": 1.0023889196182526e-06,
+      "loss": 2.6846,
+      "step": 480
+    },
+    {
+      "epoch": 0.015286226797691468,
+      "grad_norm": 1.210644245147705,
+      "learning_rate": 2.5090282323810766e-07,
+      "loss": 2.6949,
+      "step": 490
+    },
+    {
+      "epoch": 0.015598190609889253,
+      "grad_norm": 2.4400453567504883,
+      "learning_rate": 0.0,
+      "loss": 2.7689,
+      "step": 500
+    },
+    {
+      "epoch": 0.015598190609889253,
+      "eval_loss": 2.7261009216308594,
+      "eval_runtime": 336.5767,
+      "eval_samples_per_second": 40.101,
+      "eval_steps_per_second": 10.027,
+      "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": 6767252429340672.0,
+  "total_flos": 7530440069480448.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null