Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e2446240d353c1f64cd3e199db9012e63178e7af9c88c8e7b4eb27f0e98311f
+oid sha256:85f011a34046b6096ee0ee36b5807fb5ce0698cb170d9ea1d69b6e2bea5a5cb2
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4b86cf7e073f97eabad82028f7649b86b9c8f16c4ae8ca878f05af20e6145f9
+oid sha256:5f420036f34db53076133388a78fceb9c0431ee2247317b43b2c379e1b74ca75
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17e33bc2ae45877b03713d1b54e9f0e817e6bd75f767e38ef69da10a08dd2c60
+oid sha256:df7f2990010235b504c68672f1e5f14dd3dc9391974bcae7dca89c49b46c5863
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd7cf500208b0b7f84d388a948be38cab3fa49ec9e5ed4521e775b2c1f3ef453
+oid sha256:debca7aba43b980bfea4b7bfb85075c00dd93d0ca0b163523a96099f24c727ea
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.31679707765579224,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.13303769401330376,
+  "best_metric": 0.3108082711696625,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.17738359201773837,
   "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": 12.445,
       "eval_steps_per_second": 3.118,
       "step": 150
+    },
+    {
+      "epoch": 0.1419068736141907,
+      "grad_norm": 0.9246871471405029,
+      "learning_rate": 0.00017279364993403443,
+      "loss": 0.312,
+      "step": 160
+    },
+    {
+      "epoch": 0.15077605321507762,
+      "grad_norm": 2.4459915161132812,
+      "learning_rate": 0.00016774762593906525,
+      "loss": 0.3171,
+      "step": 170
+    },
+    {
+      "epoch": 0.15964523281596452,
+      "grad_norm": 1.1200841665267944,
+      "learning_rate": 0.00016237397827022866,
+      "loss": 0.2871,
+      "step": 180
+    },
+    {
+      "epoch": 0.16851441241685144,
+      "grad_norm": 1.3566011190414429,
+      "learning_rate": 0.00015669888679881007,
+      "loss": 0.171,
+      "step": 190
+    },
+    {
+      "epoch": 0.17738359201773837,
+      "grad_norm": 1.6793667078018188,
+      "learning_rate": 0.00015075,
+      "loss": 0.1994,
+      "step": 200
+    },
+    {
+      "epoch": 0.17738359201773837,
+      "eval_loss": 0.3108082711696625,
+      "eval_runtime": 38.1848,
+      "eval_samples_per_second": 12.44,
+      "eval_steps_per_second": 3.116,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.77448931786752e+16,
+  "total_flos": 5.015876915743949e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null