Training in progress, step 480, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ec4ac2ada50081a49c097e152cc228da090983b1e85f156ec63876ecd3a886d
+oid sha256:829d4884ac3d28a260767b65e6062c5c4341a140ada0003bc22ede1a750c8d80
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16ab9526ce43e132d14968409cc302b0bac6efc3dcaba90122e477d12a85c880
+oid sha256:08f481c6070144b05253ab4321c14dc6cfeb798461f064e0ffaef7f11be44420
 size 41120084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a998259191065e76e244e9c999b23198a2d595e190aa35c9fb807331bd4bd7c
+oid sha256:d477b3555de10308e24409304d69e660e19bd68fd4cef960dbbc90f2a1876376
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3dda9dfb240315ac47574ce73fc102718f73245e6bf5a8299b69650f0cbd0dc
+oid sha256:b63505c06bf1adf5d8fbaecbc4d305cd787092077aa62460c5b390353bf50532
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8627253174781799,
   "best_model_checkpoint": "miner_id_24/checkpoint-288",
-  "epoch": 2.064516129032258,
+  "epoch": 2.5806451612903225,
   "eval_steps": 96,
-  "global_step": 384,
+  "global_step": 480,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -75,6 +75,21 @@
       "eval_samples_per_second": 22.896,
       "eval_steps_per_second": 0.729,
       "step": 384
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 2.217721939086914,
+      "learning_rate": 0.00039958373224387655,
+      "loss": 0.9139,
+      "step": 480
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "eval_loss": 0.8767105340957642,
+      "eval_runtime": 6.9026,
+      "eval_samples_per_second": 22.745,
+      "eval_steps_per_second": 0.724,
+      "step": 480
     }
   ],
   "logging_steps": 96,
@@ -89,7 +104,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -103,7 +118,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2500650432659456e+17,
+  "total_flos": 1.562784897737687e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null