Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17cadc048220e3a70472c6de341215e22785ef389947a3f2cb5021ff19c9a727
+oid sha256:27be61d77ab52cfec6b98c4dec582a33e8c058c9a003f6710f3ea82d3a2d96c7
 size 912336848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de26fd62dc109df9ed6159f8144e2859bbd1afa933f83df1a105e9493e6eee85
+oid sha256:0e1b6d905fd0ee0433229b0ffad51d668e79f5d5e5e92c646a6901dd16ba7fda
 size 463916756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09cbf29821d67ea37a69b5596a2b6b019c1fa77850ddbf4f16c024c353bd8c68
+oid sha256:f72b528e44d44c291a92bd836ecbc654016e05530332958b9a387cb064921a83
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e959ae44ed59e1d9df727fe405a413d7ba7165046402e1b6aa379cddd545297
+oid sha256:dc6d7a4e5542db8278bbb08501029d28a2952cf2860b91c35fe25fb2510ba81c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.549039363861084,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.21226415094339623,
+  "epoch": 0.2358490566037736,
   "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": 11.257,
       "eval_steps_per_second": 2.824,
       "step": 450
+    },
+    {
+      "epoch": 0.2169811320754717,
+      "grad_norm": 2.356222629547119,
+      "learning_rate": 4.0868910785073565e-06,
+      "loss": 1.5565,
+      "step": 460
+    },
+    {
+      "epoch": 0.22169811320754718,
+      "grad_norm": 1.6187357902526855,
+      "learning_rate": 2.3054281225835e-06,
+      "loss": 1.6258,
+      "step": 470
+    },
+    {
+      "epoch": 0.22641509433962265,
+      "grad_norm": 2.198584794998169,
+      "learning_rate": 1.026718747764327e-06,
+      "loss": 1.4634,
+      "step": 480
+    },
+    {
+      "epoch": 0.23113207547169812,
+      "grad_norm": 282.218994140625,
+      "learning_rate": 2.5699269758854715e-07,
+      "loss": 8.4345,
+      "step": 490
+    },
+    {
+      "epoch": 0.2358490566037736,
+      "grad_norm": 216.46652221679688,
+      "learning_rate": 0.0,
+      "loss": 9.0112,
+      "step": 500
+    },
+    {
+      "epoch": 0.2358490566037736,
+      "eval_loss": 2.089921474456787,
+      "eval_runtime": 79.124,
+      "eval_samples_per_second": 11.286,
+      "eval_steps_per_second": 2.831,
+      "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": 1.30551191175168e+17,
+  "total_flos": 1.4505687908352e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null