Training in progress, step 160, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05a9134086f04aaf109815906f18423ab3ce8d6e505044a2e436597e63ac66aa
+oid sha256:e2737a5b2b664488a6760720bf8f7b0800c4aff5686b549441f71a51dbf2936e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed42d45141484ad4e2d377a32d3d78fbcbe08ce9af63a5bdf9c52376535118da
+oid sha256:89f99cde8e0d4c1a5d284b765033e4de43b51035c42dbac3779173361b1246f6
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25331c901a2b44ead3ad152cdbe6be884abba42a0b6e921dadb3a67ac6e4e427
+oid sha256:22baeb617fbf458c1c774fdf5681592667b128ead691c19e018ef96010b3aff7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8fa6a7a6709edeb55cdf23229934c07be2d8aae0e4056fbdb6ff2482d0eb3d3
+oid sha256:ac2f052986474c47aa92ee09f81c986cf5cd3c01bde827e5d887e85b2bbda4c2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.533050298690796,
   "best_model_checkpoint": "miner_id_24/checkpoint-130",
-  "epoch": 0.21178962230850687,
+  "epoch": 0.22590893046240734,
   "eval_steps": 10,
-  "global_step": 150,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1185,6 +1185,84 @@
       "eval_samples_per_second": 1.935,
       "eval_steps_per_second": 0.389,
       "step": 150
+    },
+    {
+      "epoch": 0.21320155312389694,
+      "grad_norm": 0.4451688826084137,
+      "learning_rate": 0.00016184643766056317,
+      "loss": 1.3055,
+      "step": 151
+    },
+    {
+      "epoch": 0.21461348393928698,
+      "grad_norm": 0.4681131839752197,
+      "learning_rate": 0.00016134135287043669,
+      "loss": 1.6771,
+      "step": 152
+    },
+    {
+      "epoch": 0.21602541475467701,
+      "grad_norm": 0.3876592218875885,
+      "learning_rate": 0.00016083374657755134,
+      "loss": 1.945,
+      "step": 153
+    },
+    {
+      "epoch": 0.21743734557006705,
+      "grad_norm": 0.45364028215408325,
+      "learning_rate": 0.00016032363964761363,
+      "loss": 1.6876,
+      "step": 154
+    },
+    {
+      "epoch": 0.21884927638545712,
+      "grad_norm": 0.3172266185283661,
+      "learning_rate": 0.00015981105304912162,
+      "loss": 1.7737,
+      "step": 155
+    },
+    {
+      "epoch": 0.22026120720084716,
+      "grad_norm": 0.3841560184955597,
+      "learning_rate": 0.00015929600785250257,
+      "loss": 1.6019,
+      "step": 156
+    },
+    {
+      "epoch": 0.2216731380162372,
+      "grad_norm": 0.39578792452812195,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 1.8585,
+      "step": 157
+    },
+    {
+      "epoch": 0.22308506883162724,
+      "grad_norm": 0.4143383800983429,
+      "learning_rate": 0.0001582586264510396,
+      "loss": 1.6767,
+      "step": 158
+    },
+    {
+      "epoch": 0.2244969996470173,
+      "grad_norm": 0.43308305740356445,
+      "learning_rate": 0.00015773633288888197,
+      "loss": 1.7304,
+      "step": 159
+    },
+    {
+      "epoch": 0.22590893046240734,
+      "grad_norm": 0.3537898063659668,
+      "learning_rate": 0.00015721166601221698,
+      "loss": 1.0026,
+      "step": 160
+    },
+    {
+      "epoch": 0.22590893046240734,
+      "eval_loss": 1.5331158638000488,
+      "eval_runtime": 385.352,
+      "eval_samples_per_second": 1.936,
+      "eval_steps_per_second": 0.389,
+      "step": 160
     }
   ],
   "logging_steps": 1,
@@ -1199,7 +1277,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -1208,12 +1286,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.59507839123456e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 5,
   "trial_name": null,
   "trial_params": null