Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:329779a9d75f81c59138e004c74680cb2f6109c19967aebb8a6af114432882d1
+oid sha256:392586bbd1d2e0bfd03a12554658d1e295050b4c5ddf2a9b1f635b349bbf03df
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:664c4791853bfcdd7ad0bd0ff4f7aa982b6789073a49409259639cbe20c19306
+oid sha256:9cffc1441a3bb67007c6dc9aadc468cd33a3680bdb5d757caafe5fc9ae7d64cd
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:818f16670711f557472473aa4463545c4162b79354ecd58d3965097bd34e18c6
+oid sha256:b05e3ff61da4b09e0b44b4180d36a0787a179101f6710bc48bb92a55540b2bff
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4ffe1cc6011db9bcd26d2a5ee9a2f60bf90f43b3c6aed165ee32997fe344b31
+oid sha256:c41568ec8d15c28a2145796b65c5977bed142a18699c02f8db4b41d7a5440c4c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.2884583473205566,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.054122316435143425,
+  "best_metric": 2.2128450870513916,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.07216308858019123,
   "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": 15.957,
       "eval_steps_per_second": 3.993,
       "step": 150
+    },
+    {
+      "epoch": 0.057730470864152984,
+      "grad_norm": 1.366658329963684,
+      "learning_rate": 0.00018740803823691298,
+      "loss": 2.172,
+      "step": 160
+    },
+    {
+      "epoch": 0.06133862529316255,
+      "grad_norm": 1.5560624599456787,
+      "learning_rate": 0.00018193523609311556,
+      "loss": 2.3027,
+      "step": 170
+    },
+    {
+      "epoch": 0.06494677972217211,
+      "grad_norm": 1.9186638593673706,
+      "learning_rate": 0.00017610710081049675,
+      "loss": 2.1255,
+      "step": 180
+    },
+    {
+      "epoch": 0.06855493415118168,
+      "grad_norm": 2.413241386413574,
+      "learning_rate": 0.00016995202647831142,
+      "loss": 2.1701,
+      "step": 190
+    },
+    {
+      "epoch": 0.07216308858019123,
+      "grad_norm": 4.694942474365234,
+      "learning_rate": 0.00016350000000000002,
+      "loss": 2.0427,
+      "step": 200
+    },
+    {
+      "epoch": 0.07216308858019123,
+      "eval_loss": 2.2128450870513916,
+      "eval_runtime": 73.3767,
+      "eval_samples_per_second": 15.904,
+      "eval_steps_per_second": 3.979,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.922745058820096e+16,
+  "total_flos": 3.893850675137741e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null