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:fdef284dab20e2833240fa0dadf266efdba15dcf16ef515a0b00e6741181c15b
+oid sha256:9d09933e9d3e90075831245e0b350a4d0eb07bdcf2b0b0764053aab9a824e9a6
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dc2d29b17c86018a0f3b47395af144bc4d72aa3c9da6967b6603d194dfafe5f
+oid sha256:aa9b741436ae2312cb2515fded81976985d51d2fd88557990efc09907fc72db7
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07346ea648a1680bf68423eaa169e4ebda4e48f5697c27eb1d53663b45d94b3c
+oid sha256:1421b25bb192335b3657acd15f64c81947bfcb995d46b7c7c2f653aa46cfe4b4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a7c1078eb5a1a7c3016e3bc1b27b5075c61ea30d4750bf448abc31716e92a9c
+oid sha256:1164ae497156bc73ad6aea2c09c8b9bf103d80abc111b82a8d3df6753edffe06
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.1938797235488892,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.010610830120609769,
+  "epoch": 0.014147773494146358,
   "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": 9.015,
       "eval_steps_per_second": 2.255,
       "step": 150
+    },
+    {
+      "epoch": 0.011318218795317086,
+      "grad_norm": 3.3262979984283447,
+      "learning_rate": 0.00017709199943488106,
+      "loss": 2.3911,
+      "step": 160
+    },
+    {
+      "epoch": 0.012025607470024405,
+      "grad_norm": 2.9702227115631104,
+      "learning_rate": 0.00017192045245496238,
+      "loss": 2.4674,
+      "step": 170
+    },
+    {
+      "epoch": 0.012732996144731723,
+      "grad_norm": 2.9937350749969482,
+      "learning_rate": 0.00016641313195854277,
+      "loss": 2.4761,
+      "step": 180
+    },
+    {
+      "epoch": 0.01344038481943904,
+      "grad_norm": 3.6195473670959473,
+      "learning_rate": 0.0001605968690574869,
+      "loss": 2.4561,
+      "step": 190
+    },
+    {
+      "epoch": 0.014147773494146358,
+      "grad_norm": 12.492778778076172,
+      "learning_rate": 0.0001545,
+      "loss": 2.039,
+      "step": 200
+    },
+    {
+      "epoch": 0.014147773494146358,
+      "eval_loss": 1.1949822902679443,
+      "eval_runtime": 660.2682,
+      "eval_samples_per_second": 9.016,
+      "eval_steps_per_second": 2.255,
+      "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": 5.36624253370368e+16,
+  "total_flos": 7.15499004493824e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null