Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c964c3f4b97d7f8dc4937b7c150596ecbb65d5d84d558e394e6a057183fb47
+oid sha256:aeadd452fcb4d211b4578fc9c096270755a1340d533c5a4798145c5eae3d9fbb
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83900e9a8bdb0c720e521696bb18379616e869bec8f8663a743841c3065209fd
+oid sha256:5b26df5634a4b1f9f8651c6c2b8d9176684eff4a4e43e0bcf729c553d5b6548f
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa9f4dcad0ce36d89bf1cf0db0ae4de33b1f8cf39473433de3f6d40fbc2ea74a
+oid sha256:670a21c48e7af636310774afe9303e33287af3995a6a4ab6ff30a820851c6f79
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0051c53bcb92b7c913136d782f625b409707ede35cdcc9bbc83a63d788098e04
+oid sha256:596785cc644037bdf9b1374ba5340995054de5f4bde563878d8bc4f03a7aa10e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3073418140411377,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.0652954619653934,
+  "best_metric": 1.267966389656067,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.0979431929480901,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 61.28,
       "eval_steps_per_second": 15.326,
       "step": 100
+    },
+    {
+      "epoch": 0.07182500816193274,
+      "grad_norm": 0.15941736102104187,
+      "learning_rate": 0.0001861554081393806,
+      "loss": 1.2118,
+      "step": 110
+    },
+    {
+      "epoch": 0.07835455435847209,
+      "grad_norm": 0.07974281907081604,
+      "learning_rate": 0.0001833313919082515,
+      "loss": 1.2545,
+      "step": 120
+    },
+    {
+      "epoch": 0.08488410055501143,
+      "grad_norm": 0.14130432903766632,
+      "learning_rate": 0.00018027116379309638,
+      "loss": 1.3471,
+      "step": 130
+    },
+    {
+      "epoch": 0.09141364675155077,
+      "grad_norm": 0.31553900241851807,
+      "learning_rate": 0.00017698339834299061,
+      "loss": 1.3692,
+      "step": 140
+    },
+    {
+      "epoch": 0.0979431929480901,
+      "grad_norm": 0.9388893246650696,
+      "learning_rate": 0.00017347741508630672,
+      "loss": 1.4355,
+      "step": 150
+    },
+    {
+      "epoch": 0.0979431929480901,
+      "eval_loss": 1.267966389656067,
+      "eval_runtime": 42.2941,
+      "eval_samples_per_second": 60.978,
+      "eval_steps_per_second": 15.25,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6291971484090368e+16,
+  "total_flos": 2.4377913105186816e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null