Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01abd88bea61466afacc2064bd943b194ccce1b809b929cf8b12087953416884
+oid sha256:8ba4b25ba6a739a18db7ecb3cdb48426cfe8f5bbee6d822772e891e626534758
 size 871457448

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4123f635592dbc7dcd7af93c89a8fd6b3042e4ed04132266169639dd76e9fce9
+oid sha256:9efbb44e9b7ae4dc6c907bd6830222580650543262c57f2c64fa211af1df1c95
 size 443280340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06ca51295357a6d600fd0c726212784b1970da6cf307dff1168b6e51a8a8255f
+oid sha256:408e731885eaf62f055e184c26ba6b5dd3f756fddb2da8641a7afb09824a5f0b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf23606550b94276a6908d6c21e49c1f83625cfca51cf2aaf23007a5bba6f9ae
+oid sha256:b7c7899de0498c56772fe2d4540cd3b507332f81b22696cdb603022318e1af58
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3310236930847168,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.00810307106393323,
+  "epoch": 0.010804094751910975,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,21 @@
       "eval_samples_per_second": 8.448,
       "eval_steps_per_second": 0.264,
       "step": 150
+    },
+    {
+      "epoch": 0.010804094751910975,
+      "grad_norm": 1.1472487449645996,
+      "learning_rate": 0.000201,
+      "loss": 1.3044,
+      "step": 200
+    },
+    {
+      "epoch": 0.010804094751910975,
+      "eval_loss": 1.34417724609375,
+      "eval_runtime": 1843.9296,
+      "eval_samples_per_second": 8.454,
+      "eval_steps_per_second": 0.265,
+      "step": 200
     }
   ],
   "logging_steps": 50,
@@ -74,7 +89,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -88,7 +103,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.295416427544576e+17,
+  "total_flos": 1.727221903392768e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null