Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e96a13da4826246a1cf1e55faffb9311868139dfee5ab56a7b0c1d3c854a7591
+oid sha256:b77510b8b903f0a4e4a0cee1f83a306857aa9f2d9bf7d52e5c6a72c9eb97c13b
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6714ff7b22089fceeaaa7c8684acfe28e48fc3a933fdaa127f84926fd12e3a1b
+oid sha256:2db5a8ccf74e7b941bf1f9d7f799868cf0177e633386a4034884ac3a198c532e
 size 91850618

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:174a7966d8ee200d94ac34d97a48fa4d5c40eeee9935fb41add1a8f8ed2a38e9
+oid sha256:f4eef8db51829d5e56655c00580f23c56a5d4f044ca896b2ff10b4ed6707084d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:735a1b0cd55f79037943936c337afc90625099f161e9c9087d89d1e07502d69f
+oid sha256:e4edd2cafd3d507df56f5f20b4a96c47a9d3caf3610b7118aaa38eea9544bff7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8545441031455994,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.07259528130671507,
+  "best_metric": 0.8212170600891113,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.08469449485783424,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,49 @@
       "eval_samples_per_second": 32.761,
       "eval_steps_per_second": 8.19,
       "step": 300
+    },
+    {
+      "epoch": 0.0750151240169389,
+      "grad_norm": 0.856940507888794,
+      "learning_rate": 8.07353181186354e-05,
+      "loss": 0.7956,
+      "step": 310
+    },
+    {
+      "epoch": 0.07743496672716274,
+      "grad_norm": 0.9584810137748718,
+      "learning_rate": 7.35896900990681e-05,
+      "loss": 0.7721,
+      "step": 320
+    },
+    {
+      "epoch": 0.07985480943738657,
+      "grad_norm": 1.5156158208847046,
+      "learning_rate": 6.660439780120536e-05,
+      "loss": 0.9232,
+      "step": 330
+    },
+    {
+      "epoch": 0.0822746521476104,
+      "grad_norm": 2.322288990020752,
+      "learning_rate": 5.981347286696324e-05,
+      "loss": 0.8629,
+      "step": 340
+    },
+    {
+      "epoch": 0.08469449485783424,
+      "grad_norm": 1.789493441581726,
+      "learning_rate": 5.325000000000002e-05,
+      "loss": 0.8331,
+      "step": 350
+    },
+    {
+      "epoch": 0.08469449485783424,
+      "eval_loss": 0.8212170600891113,
+      "eval_runtime": 53.0695,
+      "eval_samples_per_second": 32.787,
+      "eval_steps_per_second": 8.197,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.418868761296896e+16,
+  "total_flos": 1.655346888179712e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null