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:cdcbb04a44ff90424436d90982ea38bb5ccb03d23c82e9ec3d54e82a2e0c2556
+oid sha256:854f384691adc9a4eb5c0423cc89493b41ecb13bf23bbe0518e6b77931dbfbd7
 size 10636096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66be79cf0e78dcafcbf5054f9a906de62f3e95aded8ea693d80f27c7c6e06e63
+oid sha256:237cf80be7737c4e284a70cd69c0afb31a2114539e88226e3becd778ab8d20ca
 size 5561210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bd9d61ad6fd47e6850ff9995b1f7f95a31d82a53ea4af2eff197d30322288ac
+oid sha256:5e5a43122d2b1cc06057fb43bde76e5d787bd9696b1adddf63b6f6cf043e9c61
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c0cbab52df187d8502a1b66e46607ea8ce4ac36a84891208388bc9974f53e8
+oid sha256:2e87d47519e32af310d5ce258e0454d331221391a1b9ee9143859120658f7a9a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4573153853416443,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.010000111112345693,
+  "best_metric": 0.457046240568161,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.011111234569272993,
   "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": 29.218,
       "eval_steps_per_second": 14.609,
       "step": 450
+    },
+    {
+      "epoch": 0.010222335803731152,
+      "grad_norm": 2.536789655685425,
+      "learning_rate": 9.684576015420278e-07,
+      "loss": 1.8336,
+      "step": 460
+    },
+    {
+      "epoch": 0.010444560495116613,
+      "grad_norm": 3.7959041595458984,
+      "learning_rate": 5.463099816548579e-07,
+      "loss": 2.0835,
+      "step": 470
+    },
+    {
+      "epoch": 0.010666785186502072,
+      "grad_norm": 1.8431352376937866,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 2.028,
+      "step": 480
+    },
+    {
+      "epoch": 0.010889009877887532,
+      "grad_norm": 2.2419610023498535,
+      "learning_rate": 6.089874350439506e-08,
+      "loss": 1.6921,
+      "step": 490
+    },
+    {
+      "epoch": 0.011111234569272993,
+      "grad_norm": 2.6612582206726074,
+      "learning_rate": 0.0,
+      "loss": 2.0871,
+      "step": 500
+    },
+    {
+      "epoch": 0.011111234569272993,
+      "eval_loss": 0.457046240568161,
+      "eval_runtime": 646.8977,
+      "eval_samples_per_second": 29.291,
+      "eval_steps_per_second": 14.645,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "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": 978318513930240.0,
+  "total_flos": 1087140286955520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null