Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b67ddad24a5888e91bf681c83298eee26617a5578138ced45888ba6be330fc
+oid sha256:47b7ebf2902b2a07f7ea2535994bdad3615a8f0ab4563e45a903f02b32f57283
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c73bc72debf386e2c36c561a99ca71c87d00c275123b07d8008bc462049f466
+oid sha256:bf786dd14b0811f274964d9a68546892677186e3507a506e1825106470480916
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10e42003eeaa7e3634e469fed070b1b1d3ecaaf8edad837bd4893e0c7415da96
+oid sha256:fdf01e2f573e4c0a520091ab55a625babf975c24160921fd3cf96006054217ee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afbddc242ced46f745f057a8ae6c242cb208cc8c07c450e2e13f98a4e78227eb
+oid sha256:e1bd5e0b1abc9327c71d57aae52a46f7c0ab15b77158b2f2fa6d9b1a513a5267
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 9.236889839172363,
   "best_model_checkpoint": "miner_id_besimray/checkpoint-5",
-  "epoch": 0.003056234718826406,
+  "epoch": 0.004074979625101874,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 3.065,
       "eval_steps_per_second": 0.307,
       "step": 15
+    },
+    {
+      "epoch": 0.0032599837000814994,
+      "grad_norm": 1.3874351302323995e+19,
+      "learning_rate": 1.9999982199133416e-05,
+      "loss": 8.5286,
+      "step": 16
+    },
+    {
+      "epoch": 0.0034637326813365932,
+      "grad_norm": 9.607972408157798e+18,
+      "learning_rate": 1.9999975771045303e-05,
+      "loss": 7.7833,
+      "step": 17
+    },
+    {
+      "epoch": 0.003667481662591687,
+      "grad_norm": Infinity,
+      "learning_rate": 1.9999968354022266e-05,
+      "loss": 10.4327,
+      "step": 18
+    },
+    {
+      "epoch": 0.003871230643846781,
+      "grad_norm": Infinity,
+      "learning_rate": 1.999995994806504e-05,
+      "loss": 8.3376,
+      "step": 19
+    },
+    {
+      "epoch": 0.004074979625101874,
+      "grad_norm": Infinity,
+      "learning_rate": 1.999995055317446e-05,
+      "loss": 9.8773,
+      "step": 20
+    },
+    {
+      "epoch": 0.004074979625101874,
+      "eval_loss": 9.251687049865723,
+      "eval_runtime": 841.2776,
+      "eval_samples_per_second": 3.07,
+      "eval_steps_per_second": 0.308,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.37779979747328e+16,
+  "total_flos": 1.83706639663104e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null