Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc849f67df44c0f94d94e50d3138d44e678691377fbca6c6a6eb5a5ada8845e
+oid sha256:ef5463f385d48f30c4a26ae83fa799d370bb13b74172a5051aa28391e66953b9
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58ea048ccc35d066e768949acd5b2b5723823827ea6db1d1ee2200d23cdf55d5
+oid sha256:acede6328cead2129ceb2046d3096e3c893ef00756ca9d2cfa9d714b2a7e374d
 size 37134740

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b61b7f19e5d89fcee16059d0b521fd7346a03cdf1b23e4aaf0a3720db2476c1
+oid sha256:73385c360c3998af7d2188779cfee97efaecb97fe03699568d1fb79d6f105504
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bb9c0d62d6b3cf0976c16f73e9bd814b298ebffa1786831bc2a68d8e48809b9
+oid sha256:5ad54995b081fae25638228c5d9c8f38ca277e5c5ad00bc3e49897b543f84405
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.2006784677505493,
   "best_model_checkpoint": "miner_id_24/checkpoint-550",
-  "epoch": 0.35912504080966373,
+  "epoch": 0.3917727717923604,
   "eval_steps": 50,
-  "global_step": 550,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -488,6 +488,49 @@
       "eval_samples_per_second": 61.459,
       "eval_steps_per_second": 15.371,
       "step": 550
+    },
+    {
+      "epoch": 0.36565458700620307,
+      "grad_norm": 0.05688609927892685,
+      "learning_rate": 2.259661018213333e-06,
+      "loss": 1.1429,
+      "step": 560
+    },
+    {
+      "epoch": 0.3721841332027424,
+      "grad_norm": 0.08461929857730865,
+      "learning_rate": 1.2731645278655445e-06,
+      "loss": 1.2267,
+      "step": 570
+    },
+    {
+      "epoch": 0.37871367939928174,
+      "grad_norm": 0.17034894227981567,
+      "learning_rate": 5.665199789862907e-07,
+      "loss": 1.2762,
+      "step": 580
+    },
+    {
+      "epoch": 0.3852432255958211,
+      "grad_norm": 0.2856343984603882,
+      "learning_rate": 1.4173043232380557e-07,
+      "loss": 1.2923,
+      "step": 590
+    },
+    {
+      "epoch": 0.3917727717923604,
+      "grad_norm": 0.926727831363678,
+      "learning_rate": 0.0,
+      "loss": 1.2127,
+      "step": 600
+    },
+    {
+      "epoch": 0.3917727717923604,
+      "eval_loss": 1.2015607357025146,
+      "eval_runtime": 42.3181,
+      "eval_samples_per_second": 60.943,
+      "eval_steps_per_second": 15.242,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -502,7 +545,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -511,12 +554,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.942571079965082e+16,
+  "total_flos": 9.759171124867891e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null