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:b6107c5c400f75b990ac5126e61f5f27b5e01376c728ce48909382cbc8e0a73e
+oid sha256:78c440d8e8c1d38ca27fc6fafceef55c4421afc76b44ddf713612eba064ab028
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c456b4ed3203dea79b940867cbc0faea4e0576ffa104fec3e6ae2a037ae6ecb7
+oid sha256:ca6610dee21657d44af3a59d9f69a81237f5b7f8ca4a0fe3f986774562eb13c1
 size 1324282

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f72921554647509a84f489eea356191fc911a431b3330b3dcf7603de92d4c473
+oid sha256:e14296ca838f734a1caaacbbf6377518d2d15994a97b3b60292ab29c4da0ae79
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30565d7b1986ad1c3966f0f9b850f0ae7d4cfe76be60a78deb1442c25c9c950e
+oid sha256:693af3889e4633c932ce337b10348752049de987b4153b6619512b489850fe7b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.683765411376953,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.08982932428386066,
+  "best_metric": 11.683656692504883,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.09981036031540073,
   "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": 67.077,
       "eval_steps_per_second": 16.785,
       "step": 450
+    },
+    {
+      "epoch": 0.09182553149016869,
+      "grad_norm": 0.09349461644887924,
+      "learning_rate": 4.028783622414835e-06,
+      "loss": 11.7391,
+      "step": 460
+    },
+    {
+      "epoch": 0.0938217386964767,
+      "grad_norm": 0.10472937673330307,
+      "learning_rate": 2.272649523684208e-06,
+      "loss": 11.7317,
+      "step": 470
+    },
+    {
+      "epoch": 0.09581794590278471,
+      "grad_norm": 0.09036318957805634,
+      "learning_rate": 1.0121208508766823e-06,
+      "loss": 11.7292,
+      "step": 480
+    },
+    {
+      "epoch": 0.09781415310909272,
+      "grad_norm": 0.11662813276052475,
+      "learning_rate": 2.533387729782834e-07,
+      "loss": 11.7119,
+      "step": 490
+    },
+    {
+      "epoch": 0.09981036031540073,
+      "grad_norm": 0.38686299324035645,
+      "learning_rate": 0.0,
+      "loss": 11.5104,
+      "step": 500
+    },
+    {
+      "epoch": 0.09981036031540073,
+      "eval_loss": 11.683656692504883,
+      "eval_runtime": 31.6964,
+      "eval_samples_per_second": 66.569,
+      "eval_steps_per_second": 16.658,
+      "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": 63793057628160.0,
+  "total_flos": 70838858022912.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null