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:ea5f72cd800cb34fe37fce825e69fa6b5e90ac70a3d721a9d867a3246db2a12d
+oid sha256:296d00ccd9fa2379e606fbcf47ea671c9e254e894cb91f620883e46fadfc2308
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dafcfbc990e3c27ce484a3d8b95ea22f59d2a844cf2d19d8c50914f7e8c7b42
+oid sha256:02172c4c304859925ea28e00c06a0258921089ea6d053d68aaed42d52abf6315
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f78407387bc0d5cc74e42fdea4df89f1f8f7190e2048b58df83ab6c6fa0d19
+oid sha256:fa2fb06a85811b339dd731794396486199bd99dc3c57345fa4dec2b0c46f1a40
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:697eb5c311706d748c20f07b0521bb9d1f71aee638eb745112aecf80a82e51da
+oid sha256:d4ffe1cc6011db9bcd26d2a5ee9a2f60bf90f43b3c6aed165ee32997fe344b31
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0563247203826904,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.009444654325651681,
+  "best_metric": 1.04743492603302,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.014166981488477521,
   "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": 17.393,
       "eval_steps_per_second": 4.35,
       "step": 100
+    },
+    {
+      "epoch": 0.01038911975821685,
+      "grad_norm": 0.8509911894798279,
+      "learning_rate": 0.0002085764548830435,
+      "loss": 1.0203,
+      "step": 110
+    },
+    {
+      "epoch": 0.011333585190782017,
+      "grad_norm": 0.8470553755760193,
+      "learning_rate": 0.00020524128762162305,
+      "loss": 0.9954,
+      "step": 120
+    },
+    {
+      "epoch": 0.012278050623347185,
+      "grad_norm": 0.9998864531517029,
+      "learning_rate": 0.00020143724248105043,
+      "loss": 0.9616,
+      "step": 130
+    },
+    {
+      "epoch": 0.013222516055912353,
+      "grad_norm": 1.3236018419265747,
+      "learning_rate": 0.0001971828523868693,
+      "loss": 1.0109,
+      "step": 140
+    },
+    {
+      "epoch": 0.014166981488477521,
+      "grad_norm": 1.5146818161010742,
+      "learning_rate": 0.0001924988442999686,
+      "loss": 0.8894,
+      "step": 150
+    },
+    {
+      "epoch": 0.014166981488477521,
+      "eval_loss": 1.04743492603302,
+      "eval_runtime": 256.4077,
+      "eval_samples_per_second": 17.386,
+      "eval_steps_per_second": 4.349,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6906205528064e+16,
+  "total_flos": 2.5317253054464e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null