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:c92c9d7fdbaf596c36f37462e1c013d740b5f8a8c67b3ba9f4a0a72207b55232
+oid sha256:9666fa0167af0b4dacd93d6ec50b1e2661e15a210118dabfa04c733a80e3befa
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f4d2e642016b3a9abb73e04a89eb0836085362c376908a5f1869ad19c28197b
+oid sha256:10dcb2d16c910bf109b0dfb2fb28b1fb3103d8c19ace3cdff78cb974c46128fe
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e38a2828e0b38a28392e23e3b506b789fb5850cc0a215f4236a6b47921f3efd9
+oid sha256:2e650560bc75043cf17158e230003191fed97937001ae4cc5db3912e912c82c7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e883b7b3f89fde3f0f981a15cfeb8504571510ffa0b99f735bed98a1fe00478
+oid sha256:d5ad005f18ad2c3c460e78d824d33373300bb1b0c9741a994c687b284a694890
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.739017486572266,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.1749271137026239,
+  "best_metric": 11.735800743103027,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.23323615160349853,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 221.96,
       "eval_steps_per_second": 55.951,
       "step": 150
+    },
+    {
+      "epoch": 0.18658892128279883,
+      "grad_norm": 0.24353830516338348,
+      "learning_rate": 0.00017451298973437308,
+      "loss": 11.7474,
+      "step": 160
+    },
+    {
+      "epoch": 0.19825072886297376,
+      "grad_norm": 0.2174033671617508,
+      "learning_rate": 0.0001694167565454241,
+      "loss": 11.742,
+      "step": 170
+    },
+    {
+      "epoch": 0.2099125364431487,
+      "grad_norm": 0.1835821270942688,
+      "learning_rate": 0.0001639896397455543,
+      "loss": 11.739,
+      "step": 180
+    },
+    {
+      "epoch": 0.22157434402332363,
+      "grad_norm": 0.18794667720794678,
+      "learning_rate": 0.0001582580797022808,
+      "loss": 11.7329,
+      "step": 190
+    },
+    {
+      "epoch": 0.23323615160349853,
+      "grad_norm": 0.3341284394264221,
+      "learning_rate": 0.00015225,
+      "loss": 11.7255,
+      "step": 200
+    },
+    {
+      "epoch": 0.23323615160349853,
+      "eval_loss": 11.735800743103027,
+      "eval_runtime": 1.6348,
+      "eval_samples_per_second": 220.82,
+      "eval_steps_per_second": 55.664,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7768984780800.0,
+  "total_flos": 10358646374400.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null