Training in progress, step 660, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b85f1036fa48942ac7486d858cc48f682e95cca9c0b176deb8e1209794783e3f
+oid sha256:e07e035f586498dc8981df34e67630b046d3efe96532d54935045c70e2732a5c
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8700f592f8694a133077ca98a3c7d64b45dafeddcbc6707a59113cc8b0be9fa
+oid sha256:a4391b36bfb3153386e6ba9b7fa9813c558d76ab5b72d79ffcddc8628bda27c5
 size 25859412

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc9ebbfcd05d563f3eb0a9368aa4eb8d694b62d379d7c6d75e0122b26b2d54f2
+oid sha256:769f27da95e3db89c4ac50ba3b676be7452e7102a0fceebe0dba03240f9a0912
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:722eb9ff1d0c7c189e054d20a9b60f10e7dc830acb7392fcfd3f1f1fb83248cd
+oid sha256:1b5ebb4c43b35cc5c443696fa48cabff1cc53c72b887ea3e6159a2871f0a2068
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:901b63cd18dc344319a14316685a7b1c3e515fee5a8d795dd4dde69eae24e401
+oid sha256:c7ab0379217213a80cc6c5b608182019ce004207aeec4e881e08eb21bd107b24
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f30fc41dd2911d2de1fe9d5beb039e31c9096e748dfa60eef527b74708246b55
+oid sha256:86bbbbd5fa142eccd9cc0d90c2a1f214e26f81abc61d8b8108e38ba0231a465d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4afed64a95f2db46916c1364014bb9fa4017f80b408b7495f38e4599e5b4791
+oid sha256:f9067d6a23df796f52db826028f8c78fda475923b094eba9dfa934d7463044e0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6789116263389587,
-  "best_model_checkpoint": "miner_id_24/checkpoint-620",
-  "epoch": 4.830188679245283,
+  "best_metric": 0.6788897514343262,
+  "best_model_checkpoint": "miner_id_24/checkpoint-660",
+  "epoch": 4.981132075471698,
   "eval_steps": 20,
-  "global_step": 640,
+  "global_step": 660,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -313,6 +313,14 @@
       "eval_samples_per_second": 312.336,
       "eval_steps_per_second": 2.448,
       "step": 640
+    },
+    {
+      "epoch": 4.981132075471698,
+      "eval_loss": 0.6788897514343262,
+      "eval_runtime": 2.8412,
+      "eval_samples_per_second": 314.3,
+      "eval_steps_per_second": 2.464,
+      "step": 660
     }
   ],
   "logging_steps": 100,
@@ -327,7 +335,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -336,12 +344,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.399842416162243e+17,
+  "total_flos": 9.693587491667313e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null