Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deb88f38f2e4b0c442c99f8c21c66551c7ed25ab6f9e77f31b0a4b20306776a4
+oid sha256:1ed1a959d8007b175b9b4889ab51e78dece828b975ea7fb2460344a95f49b0c6
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c85280c74b1faf098dac11caa7e8941c058fa6f1d9e4be9591ce4a33e475455
+oid sha256:04fc597453c99acc9d62a6a458584722b3fdd5dc4ed7cb9e7e61c01df9e5caf0
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6db0c5052b354e79639ce104f44910d59ab0a2975aea3f8bfe7e14b036dc270
+oid sha256:5ab520cc199ab160eef65d5d172aedd6d2987741847f79baf9be3bae2ba3fe17
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:321052ad5e93c8a107bd6c10f372f50285d863120fc0088befc39ec2733238fb
+oid sha256:530505d607699f384741067a5f9139d72f043713adb680898a3f1b5714170c97
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6013292670249939,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.011977362784337602,
+  "best_metric": 0.5775735974311829,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.015969817045783468,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,28 @@
       "eval_samples_per_second": 14.986,
       "eval_steps_per_second": 7.494,
       "step": 150
+    },
+    {
+      "epoch": 0.012775853636626776,
+      "grad_norm": 19.138328552246094,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 4.5843,
+      "step": 160
+    },
+    {
+      "epoch": 0.015969817045783468,
+      "grad_norm": 44.18806838989258,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 4.4517,
+      "step": 200
+    },
+    {
+      "epoch": 0.015969817045783468,
+      "eval_loss": 0.5775735974311829,
+      "eval_runtime": 704.1932,
+      "eval_samples_per_second": 14.977,
+      "eval_steps_per_second": 7.489,
+      "step": 200
     }
   ],
   "logging_steps": 40,
@@ -88,7 +110,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.308815333811814e+16,
+  "total_flos": 7.076947002025574e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null