Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:339c1190f432c23d6c1daf8f6677fadcb579fad0f870eb787a951b9c14e19662
+oid sha256:5042f8a561684e9506daa9b1f3e3156c2b07e5d473aac129374ea13414aca881
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b3a455ca5d5edd307fad8171fde0e04728e9c4ef9b8b0d4022306f40abeaa05
+oid sha256:8877c52a866e45f27159132f589aab65dc6de784badb94ae2f79912d15cbb161
 size 83282170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de5a71f85b9114cd14ba8af960a46ef128aa17617f8a68ea324dbe570a75123f
+oid sha256:7431b5c49493e7b14b5469a1aaaf6bceb2f0f8370e90470c84f2c14a9669c9dd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7af249df5fe11a9896f83a1f972a51ac4c516f61ca7fde0473cca60d389d7ec
+oid sha256:4677d15317405bcdd600dfdae9d04715d81517a0dbc7789a073149e371184d8c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.739220380783081,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00423998304006784,
+  "best_metric": 1.7265019416809082,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0052999788000848,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 7.067,
       "eval_steps_per_second": 3.535,
       "step": 20
+    },
+    {
+      "epoch": 0.0044519821920712315,
+      "grad_norm": 0.87850421667099,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.7883,
+      "step": 21
+    },
+    {
+      "epoch": 0.004663981344074624,
+      "grad_norm": 0.8680698871612549,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.4036,
+      "step": 22
+    },
+    {
+      "epoch": 0.004875980496078016,
+      "grad_norm": 0.7863142490386963,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.8092,
+      "step": 23
+    },
+    {
+      "epoch": 0.005087979648081407,
+      "grad_norm": 0.7802051305770874,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.7099,
+      "step": 24
+    },
+    {
+      "epoch": 0.0052999788000848,
+      "grad_norm": 0.744226336479187,
+      "learning_rate": 0.0,
+      "loss": 1.5709,
+      "step": 25
+    },
+    {
+      "epoch": 0.0052999788000848,
+      "eval_loss": 1.7265019416809082,
+      "eval_runtime": 281.6034,
+      "eval_samples_per_second": 7.056,
+      "eval_steps_per_second": 3.53,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2000389322833920.0,
+  "total_flos": 2500486653542400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null