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:e88ebe2be20788bc539651b679a971a801ee85910b8abd6df89ad42bd3c3a98d
+oid sha256:5887739cc11f1d5ec00ca4a2c146bc68b40357a54e2a95686a9f99d7c8094377
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d51f71196ad4e4a8a836f94df07d58951f608b6543cbc049b2ade08dbd0b685c
+oid sha256:61f3448d79ba269255a40eacba053f85258bf941232c4747f1d3a424462fcf35
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f81882bc0516d4b960f29597047d8635d2fc194ec9f38f0e37d605856653d7bf
+oid sha256:e54bb037e91b5565f74b43ee03a04b406f9f312288f5ed598079d0dfeb1d562d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44be7752e8f250f5c645b94c737a086e3ba6f8529fa94bf2d0ed1a0911f14f5a
+oid sha256:08c6d9b93a9a31eb6ebeb3ab3dc09ba23202435e453d5c3be3fefb3bbf21d637
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5598700642585754,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.02962962962962963,
+  "epoch": 0.03950617283950617,
   "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": 13.501,
       "eval_steps_per_second": 3.375,
       "step": 150
+    },
+    {
+      "epoch": 0.03160493827160494,
+      "grad_norm": 4.6154303550720215,
+      "learning_rate": 0.0001753726596345424,
+      "loss": 1.3221,
+      "step": 160
+    },
+    {
+      "epoch": 0.03358024691358025,
+      "grad_norm": 4.596099853515625,
+      "learning_rate": 0.00017025132184860355,
+      "loss": 1.0724,
+      "step": 170
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 7.3407769203186035,
+      "learning_rate": 0.00016479747048321714,
+      "loss": 0.8462,
+      "step": 180
+    },
+    {
+      "epoch": 0.037530864197530864,
+      "grad_norm": 11.159585952758789,
+      "learning_rate": 0.00015903767615401616,
+      "loss": 1.2544,
+      "step": 190
+    },
+    {
+      "epoch": 0.03950617283950617,
+      "grad_norm": 60.502098083496094,
+      "learning_rate": 0.000153,
+      "loss": 2.454,
+      "step": 200
+    },
+    {
+      "epoch": 0.03950617283950617,
+      "eval_loss": 0.7290850877761841,
+      "eval_runtime": 157.1167,
+      "eval_samples_per_second": 13.57,
+      "eval_steps_per_second": 3.392,
+      "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": 3.523832597132083e+16,
+  "total_flos": 4.677574741878374e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null