Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcc457fd82f27efdda10fed960e386036a4b33abb33221deb7837e50eb062a57
+oid sha256:e969e52342803b299b7ed319dcf94e15a8c84105f20d3e213c87987284453833
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe9f1bff8d6faa01cf6769f239cc539972d3f7c6cc4228301e1f324d9e8af757
+oid sha256:b4cb59a5ee934befa564064aaaf64c328c626a692b4093f3e04137e10811edf2
 size 56950996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed7a65e4257438282c61302a05f6983560de4e3a6f299917cf5ff5127f020898
+oid sha256:cf3db837f33a4e5d1f0863b8fcce835716b9cd562fb153c4a26c2c7dce10c99d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d1f0f5a6a174cd37a4de7168d2654831d469666ae99ac8ac3662c8eaf7683b5
+oid sha256:e3fefa9335f6222d1a14d72f837041665420095d7f813e43c216743bd291bfe3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5773412585258484,
   "best_model_checkpoint": "miner_id_24/checkpoint-880",
-  "epoch": 0.9948186528497409,
+  "epoch": 1.0362694300518134,
   "eval_steps": 40,
-  "global_step": 960,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -270,6 +270,21 @@
       "eval_samples_per_second": 9.715,
       "eval_steps_per_second": 0.333,
       "step": 960
+    },
+    {
+      "epoch": 1.0362694300518134,
+      "grad_norm": 0.8339794278144836,
+      "learning_rate": 0.000299768901482495,
+      "loss": 1.0328,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0362694300518134,
+      "eval_loss": 0.5930935740470886,
+      "eval_runtime": 21.0358,
+      "eval_samples_per_second": 9.698,
+      "eval_steps_per_second": 0.333,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -284,7 +299,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -293,12 +308,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.128126001905664e+17,
+  "total_flos": 3.258924645482496e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null