Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e627e80e0915d6e99dc459164617284f6c3079b17e4f0b7dc05cd83dabe65ab7
+oid sha256:002e3e3ab599f644a743e04d51b488f931a0002a3e46136843f968c6f681a3e7
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d6c7502296e350b901521164ead0836427c49b1ac94506d264da1ae3ec2be0e
+oid sha256:9b0c161fc1e752bbfc3a43662c761dbb8300866d1f9d464ee5452a9ee7b92ec4
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfd8fc40428d55617cf70685e733c231373976aceeaeb0b3082f6b4a1ece5e07
+oid sha256:35ebd066afa798db84ab0a57f97dc181787a6012d06456e71180b94da0c30142
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0db0205cf37887636e31665ab1051856b2efe4ed0485b1a8cad32db1f6dfbb
+oid sha256:1173c3cbf86b725051d7e94252382f4f9be9dc9f6afe0d4b01afed08d5bf2028
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.9104496240615845,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.3597122302158273,
+  "epoch": 0.3996802557953637,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 11.654,
       "eval_steps_per_second": 2.919,
       "step": 450
+    },
+    {
+      "epoch": 0.3677058353317346,
+      "grad_norm": 0.4546515643596649,
+      "learning_rate": 3.9513070142914725e-06,
+      "loss": 0.8285,
+      "step": 460
+    },
+    {
+      "epoch": 0.37569944044764186,
+      "grad_norm": 0.4213729500770569,
+      "learning_rate": 2.2289447251518195e-06,
+      "loss": 0.8871,
+      "step": 470
+    },
+    {
+      "epoch": 0.38369304556354916,
+      "grad_norm": 0.39084315299987793,
+      "learning_rate": 9.92656988359823e-07,
+      "loss": 0.9132,
+      "step": 480
+    },
+    {
+      "epoch": 0.39168665067945646,
+      "grad_norm": 0.6356387734413147,
+      "learning_rate": 2.4846687349793185e-07,
+      "loss": 0.8769,
+      "step": 490
+    },
+    {
+      "epoch": 0.3996802557953637,
+      "grad_norm": 1.5205575227737427,
+      "learning_rate": 0.0,
+      "loss": 0.9026,
+      "step": 500
+    },
+    {
+      "epoch": 0.3996802557953637,
+      "eval_loss": 0.9150660037994385,
+      "eval_runtime": 45.1962,
+      "eval_samples_per_second": 11.66,
+      "eval_steps_per_second": 2.921,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.2223929926025216e+17,
+  "total_flos": 1.3612634890410394e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null