Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ec0d54c2751596e58d47be54f421399b8e002c24abd1b444f5aa5cdb4221078
+oid sha256:c7835360bcd692d20be2d009ed27ae7d9327b50bc450594fe71d3e3c1e319eef
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da0af5fe8c60151f9fb9498636864d59e7f66e62914d40ec6478429d881739e4
+oid sha256:5265d75c613cb23c336fb11edab7a20e1f66a2c9d14d95e706baa28bcaa09dfd
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a02ccd592b9c97d18a4e4b8fa703499d2d2d06dfc749f3b4408626858acfb3e
+oid sha256:902093d3478ee4caf96b9f02b61634cdc54fd5a95c26eca89c96a65aef3c5ed4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cd62d399a2450f21c7bec0f65f92f467b6df40bae3ff61b19e25062ffc80260
+oid sha256:292f236c37f22c287cc737dd1428bf82b9a9008a84eb2f517544aab166f8a97f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.2864845991134644,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0025268051917424006,
+  "epoch": 0.0033690735889898675,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 16.399,
       "eval_steps_per_second": 4.1,
       "step": 150
+    },
+    {
+      "epoch": 0.002695258871191894,
+      "grad_norm": 1.4711071252822876,
+      "learning_rate": 0.00018654836833674362,
+      "loss": 1.2392,
+      "step": 160
+    },
+    {
+      "epoch": 0.0028637125506413875,
+      "grad_norm": 1.2519170045852661,
+      "learning_rate": 0.0001811006707899361,
+      "loss": 1.1692,
+      "step": 170
+    },
+    {
+      "epoch": 0.0030321662300908806,
+      "grad_norm": 1.6822906732559204,
+      "learning_rate": 0.0001752992700728339,
+      "loss": 1.2182,
+      "step": 180
+    },
+    {
+      "epoch": 0.003200619909540374,
+      "grad_norm": 1.8712016344070435,
+      "learning_rate": 0.00016917243002657602,
+      "loss": 1.2522,
+      "step": 190
+    },
+    {
+      "epoch": 0.0033690735889898675,
+      "grad_norm": 4.799688339233398,
+      "learning_rate": 0.00016275,
+      "loss": 1.4872,
+      "step": 200
+    },
+    {
+      "epoch": 0.0033690735889898675,
+      "eval_loss": 1.3280550241470337,
+      "eval_runtime": 1524.6163,
+      "eval_samples_per_second": 16.394,
+      "eval_steps_per_second": 4.099,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -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": 2.8378911700156416e+16,
+  "total_flos": 3.790140366598963e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null