Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c8f97d3c49eb5278493c5690687bf5cf3c89e0813e240df71f0c48c52aef6e9
+oid sha256:f88abc840265b6458ad3208291fb58870887e585b588baba60b101a6edf40d38
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af14fe404107fbaf815af4abbffc79c0b0ed95f4a9ab46a2595b7efd9734842d
+oid sha256:9cfd2c862c80c139d8748c656989aa1e052ccbf9cd5092cf41d835d8fe5bc4ba
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8f788b1d02f736f3bc30cc38883afa61050c2c4554dce865e59dcd88c3d7b7a
+oid sha256:b6467d52a7066a8d54356dfc76b5ae6c1c350c73b9c7b70c65a389c4c6a5a9fc
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae0a5f636e3b7efad4ad765d67a451cd40f8f2e24e01c5d42929e454a337257
+oid sha256:4f23fa0ef01cbb776456cad40209cd1c0c6a02d9fdf8c0632982552f2f542168
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4987999498844147,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.08480165834354093,
+  "best_metric": 0.4941071569919586,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.0942240648261566,
   "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": 16.821,
       "eval_steps_per_second": 4.207,
       "step": 450
+    },
+    {
+      "epoch": 0.08668613964006407,
+      "grad_norm": 1.5833096504211426,
+      "learning_rate": 4.067521926476516e-06,
+      "loss": 1.0851,
+      "step": 460
+    },
+    {
+      "epoch": 0.0885706209365872,
+      "grad_norm": 1.6312237977981567,
+      "learning_rate": 2.294501922950403e-06,
+      "loss": 0.9651,
+      "step": 470
+    },
+    {
+      "epoch": 0.09045510223311033,
+      "grad_norm": 1.7241089344024658,
+      "learning_rate": 1.021852782135112e-06,
+      "loss": 0.9172,
+      "step": 480
+    },
+    {
+      "epoch": 0.09233958352963346,
+      "grad_norm": 1.8601709604263306,
+      "learning_rate": 2.5577472271845927e-07,
+      "loss": 0.9021,
+      "step": 490
+    },
+    {
+      "epoch": 0.0942240648261566,
+      "grad_norm": 3.0098185539245605,
+      "learning_rate": 0.0,
+      "loss": 1.042,
+      "step": 500
+    },
+    {
+      "epoch": 0.0942240648261566,
+      "eval_loss": 0.4941071569919586,
+      "eval_runtime": 132.4872,
+      "eval_samples_per_second": 16.87,
+      "eval_steps_per_second": 4.219,
+      "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": 8.094082488336384e+16,
+  "total_flos": 8.988456243953664e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null