Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54ccfc3986b143a4a2f96f549d098aa614f7f7aafd2890657bfdccb267a85f59
+oid sha256:27c8a2b6e97b08b7904c57aad3e862d6ca0f2fd623099c6777958c9a01df4990
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b567591f8cd8ea2446a2ceaf481a78303768763a4b7e2bb9a16792754e0908b8
+oid sha256:3949051628f355e4a79783f058d384ae02aa5e967c67fffb273e2500562305e7
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:222b56b9f8df0f0e53f193b41fb7b31d9e4883bc8c3809d0e1455a3588234cfb
+oid sha256:d2f8d836fc74ab1dcd19c00e141e586a98256bb27f2b43f2fea9ac75779943de
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf1a6f89c4ccfeb423775f70e378195af348273ade7a1d504b8ad665994fa62
+oid sha256:0585a94ca770852d904d0a057ee7d0f13731dc026d439d9add35f155aff77fb2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.3372433185577393,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.14513788098693758,
+  "best_metric": 2.194847345352173,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.21770682148040638,
   "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": 11.884,
       "eval_steps_per_second": 2.991,
       "step": 100
+    },
+    {
+      "epoch": 0.15965166908563136,
+      "grad_norm": 1.1661285161972046,
+      "learning_rate": 0.000203792591238937,
+      "loss": 2.1987,
+      "step": 110
+    },
+    {
+      "epoch": 0.1741654571843251,
+      "grad_norm": 1.179563045501709,
+      "learning_rate": 0.0002005339186394757,
+      "loss": 2.1252,
+      "step": 120
+    },
+    {
+      "epoch": 0.18867924528301888,
+      "grad_norm": 1.3845571279525757,
+      "learning_rate": 0.00019681712224065936,
+      "loss": 2.1114,
+      "step": 130
+    },
+    {
+      "epoch": 0.20319303338171263,
+      "grad_norm": 1.61588454246521,
+      "learning_rate": 0.0001926603099009319,
+      "loss": 2.1507,
+      "step": 140
+    },
+    {
+      "epoch": 0.21770682148040638,
+      "grad_norm": 3.884338140487671,
+      "learning_rate": 0.00018808373319217114,
+      "loss": 2.0528,
+      "step": 150
+    },
+    {
+      "epoch": 0.21770682148040638,
+      "eval_loss": 2.194847345352173,
+      "eval_runtime": 24.5982,
+      "eval_samples_per_second": 11.789,
+      "eval_steps_per_second": 2.968,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.611614133203763e+16,
+  "total_flos": 3.874994255403418e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null