Training in progress, step 240, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45af38183fac4bdd87c06ee94f18b22a7da1068712890ae4063748b65e92320a
+oid sha256:eea176b2890f5c039b27382d7c55bd1ece54713333c0ee47f4372f34e426564c
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc8aaca7431e39887e25a3b439419774272ece5fa8db24c537c5201d3f93250b
+oid sha256:7f80fdd9f8732871c70824003344dbea9f535560e1447468a53254338e40aee6
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4145db56e94116de16125ac48b142c9c5702f370950afc0d1127ba20ea13b21f
+oid sha256:a329987e98f6034737aac0f1b5e07f42a7e6f741cd8b93f9ba9996e6dd5f9b04
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21bd9360c166d9c3550bf3e56da2dc8de427467685d616ad1024770199c37aea
+oid sha256:6a53d552dcaadb831ec7d361f91d388f352dfbf94dc56ae13700304776b06cd3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.161059856414795,
   "best_model_checkpoint": "miner_id_besimray/checkpoint-225",
-  "epoch": 1.236842105263158,
+  "epoch": 1.263157894736842,
   "eval_steps": 5,
-  "global_step": 235,
+  "global_step": 240,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2036,6 +2036,49 @@
       "eval_samples_per_second": 4.436,
       "eval_steps_per_second": 0.444,
       "step": 235
+    },
+    {
+      "epoch": 1.2421052631578948,
+      "grad_norm": 1.3955504894256592,
+      "learning_rate": 1.7280528409146097e-05,
+      "loss": 1.6323,
+      "step": 236
+    },
+    {
+      "epoch": 1.2473684210526317,
+      "grad_norm": 0.9354751110076904,
+      "learning_rate": 1.7257576857089397e-05,
+      "loss": 1.2273,
+      "step": 237
+    },
+    {
+      "epoch": 1.2526315789473683,
+      "grad_norm": 0.7192204594612122,
+      "learning_rate": 1.7234544239679807e-05,
+      "loss": 1.2498,
+      "step": 238
+    },
+    {
+      "epoch": 1.2578947368421054,
+      "grad_norm": 0.706244170665741,
+      "learning_rate": 1.721143081418601e-05,
+      "loss": 1.0584,
+      "step": 239
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.7391364574432373,
+      "learning_rate": 1.7188236838779297e-05,
+      "loss": 1.1814,
+      "step": 240
+    },
+    {
+      "epoch": 1.263157894736842,
+      "eval_loss": 1.162298321723938,
+      "eval_runtime": 22.5363,
+      "eval_samples_per_second": 4.437,
+      "eval_steps_per_second": 0.444,
+      "step": 240
     }
   ],
   "logging_steps": 1,
@@ -2050,7 +2093,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -2059,12 +2102,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.65281961279488e+16,
+  "total_flos": 5.77309237051392e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null