Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc9d5859805c8cdadc8b1ce58d7da658f70771def4371a299bade37c327bced2
+oid sha256:a2b9407b620fdb59f036c7f8ccb6328fded799cf66d9b7bf6cc3ba62f97ed143
 size 275341720

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ba583148ec7a0d8e9a29f36764f63453b52975981f74c8cc1472628d4d2525a
-size 140565460
+oid sha256:fcefdc11f7981009b3721f49c1a2dd5abcc7aab0d6a139fcda0dd7da735f3390
+size 140566100

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9529df318d9288149acf43f189ac46f41812e3687614c7d2071bb02772ab0e45
+oid sha256:d9d0876d646de043f67fa1acf41da539d93624f2dbcb715e55b9e6b565a2de90
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:110c23ba7ac9436ac98f0e4bb88f393b7c16138e63fbbb47259fe31aa44af728
+oid sha256:735a1b0cd55f79037943936c337afc90625099f161e9c9087d89d1e07502d69f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7187796831130981,
   "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.10850694444444445,
+  "epoch": 0.13020833333333334,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 9.784,
       "eval_steps_per_second": 2.461,
       "step": 250
+    },
+    {
+      "epoch": 0.11284722222222222,
+      "grad_norm": 0.9789396524429321,
+      "learning_rate": 0.0001176322813380051,
+      "loss": 0.8391,
+      "step": 260
+    },
+    {
+      "epoch": 0.1171875,
+      "grad_norm": 1.4175513982772827,
+      "learning_rate": 0.00011021679639881638,
+      "loss": 0.8921,
+      "step": 270
+    },
+    {
+      "epoch": 0.12152777777777778,
+      "grad_norm": 1.268831729888916,
+      "learning_rate": 0.00010278320360118368,
+      "loss": 0.5002,
+      "step": 280
+    },
+    {
+      "epoch": 0.12586805555555555,
+      "grad_norm": 0.8849596977233887,
+      "learning_rate": 9.536771866199493e-05,
+      "loss": 0.602,
+      "step": 290
+    },
+    {
+      "epoch": 0.13020833333333334,
+      "grad_norm": 1.0034514665603638,
+      "learning_rate": 8.800646907847192e-05,
+      "loss": 0.8343,
+      "step": 300
+    },
+    {
+      "epoch": 0.13020833333333334,
+      "eval_loss": 0.7189058065414429,
+      "eval_runtime": 49.5602,
+      "eval_samples_per_second": 9.786,
+      "eval_steps_per_second": 2.462,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -244,7 +287,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.32795627772969e+16,
+  "total_flos": 5.19181980621865e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null