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:d04616e6c9686651e05f84b2adc3fb90f7d6e048cf74d21563c6d943bcf92852
+oid sha256:f90f29add083e70435ccfcdb9324896e0d661ce675afea96492133329ed27409
 size 1157746040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01321ee8817ba8cbfc6b83e36bb9e16d95f16224618253ce7a07e38446310da7
-size 588699796
+oid sha256:17f29963d218f536f17aa1aea587ddabfad09e50c404853c0317e3fff1876cb9
+size 588700500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb645e3b6031e469fc3dcf414b1ef1eace69472cb72bdef1b342fb8a8df199b9
+oid sha256:be935466c588a753f80b4b6fd059919104354d0102b7a2dca4181c83f51ce99e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb9254c45787266aeb2f2d77203ac5705f2dafc0eddb0332e9ac78a896bc3b27
+oid sha256:cf9d37d8ac9041b1174177f2abdfd03da05c909db05db7e02be2b5adefcdb593
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.7082891464233398,
   "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.07105300554213444,
+  "epoch": 0.08526360665056132,
   "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": 9.06,
       "eval_steps_per_second": 2.274,
       "step": 250
+    },
+    {
+      "epoch": 0.0738951257638198,
+      "grad_norm": 2.337188959121704,
+      "learning_rate": 0.0001137664317165683,
+      "loss": 1.7002,
+      "step": 260
+    },
+    {
+      "epoch": 0.07673724598550519,
+      "grad_norm": 3.3565144538879395,
+      "learning_rate": 0.00010659464816035761,
+      "loss": 1.4179,
+      "step": 270
+    },
+    {
+      "epoch": 0.07957936620719057,
+      "grad_norm": 3.4117555618286133,
+      "learning_rate": 9.940535183964242e-05,
+      "loss": 1.667,
+      "step": 280
+    },
+    {
+      "epoch": 0.08242148642887594,
+      "grad_norm": 4.477943420410156,
+      "learning_rate": 9.22335682834317e-05,
+      "loss": 1.3015,
+      "step": 290
+    },
+    {
+      "epoch": 0.08526360665056132,
+      "grad_norm": 9.481433868408203,
+      "learning_rate": 8.511423770030617e-05,
+      "loss": 1.6444,
+      "step": 300
+    },
+    {
+      "epoch": 0.08526360665056132,
+      "eval_loss": 2.061939239501953,
+      "eval_runtime": 82.2643,
+      "eval_samples_per_second": 9.008,
+      "eval_steps_per_second": 2.261,
+      "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": 4.390310087177011e+16,
+  "total_flos": 5.215556344165171e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null