Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c003eeb836dfb367e51399a2fee80d8bb2403d147710787003df3b01c31f58e
+oid sha256:a6e2fca64caa87f0a222dacbfb713ef88edc04cc0d46fba601487d07abe53df4
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35732ff3ea1c896c380e3324eb2b246bf26b44153ad6bd71187130c9eb9f0a0b
+oid sha256:c64cbaa861439571fc77cb1cfb69ea78bdeb1f69f5030a455513f4f4c3ea88ad
 size 432492970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac4c4d3e2a63413186fdc624383f0085bcb1896dfa4dd2647931a2a1e5d987b6
+oid sha256:2ad636d5cf633a906fc3f3ccc5e2d0efef31060640b5f5a43055356e4a3ba83f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9240790605545044,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.012938702895034774,
+  "best_metric": 1.9052269458770752,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.019408054342552158,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 5.122,
       "eval_steps_per_second": 2.565,
       "step": 20
+    },
+    {
+      "epoch": 0.013585638039786511,
+      "grad_norm": 1.2617974281311035,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 1.8909,
+      "step": 21
+    },
+    {
+      "epoch": 0.015526443474041727,
+      "grad_norm": 1.3320506811141968,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 2.0138,
+      "step": 24
+    },
+    {
+      "epoch": 0.016173378618793467,
+      "eval_loss": 1.9086711406707764,
+      "eval_runtime": 127.1109,
+      "eval_samples_per_second": 5.122,
+      "eval_steps_per_second": 2.565,
+      "step": 25
+    },
+    {
+      "epoch": 0.017467248908296942,
+      "grad_norm": 1.3089834451675415,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 1.8714,
+      "step": 27
+    },
+    {
+      "epoch": 0.019408054342552158,
+      "grad_norm": 1.2991094589233398,
+      "learning_rate": 0.0,
+      "loss": 1.9236,
+      "step": 30
+    },
+    {
+      "epoch": 0.019408054342552158,
+      "eval_loss": 1.9052269458770752,
+      "eval_runtime": 127.0918,
+      "eval_samples_per_second": 5.122,
+      "eval_steps_per_second": 2.565,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8236125420257280.0,
+  "total_flos": 1.235418813038592e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null