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:b10a88e79cec861cda3937af7d336bc19ba7311b761d3b28a6a346450e70786e
+oid sha256:31f11d332f9b6dc57ff368c4541d90eec660999d6b5da12e7309484a69e587fe
 size 28348936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a285d62a33e5ed4725494a100acc1cb4687cca15f5b0c5ddd1a0fbcb66026e9d
+oid sha256:694bfa958a26caa6df49966ab05c48c469659a52a1f0265b68e010a713f5402c
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40dab678f8341cb1f6a50c07bf4f3f2e6d7185a7a6a288def2d3180b15023b3f
+oid sha256:0b594340431d8590d25b498cff50fac77ea17ecff143e5f985cfbfcf2d2941e1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.2570910453796387,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0443213296398892,
+  "best_metric": 2.2525382041931152,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.055401662049861494,
   "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": 9.031,
       "eval_steps_per_second": 4.516,
       "step": 20
+    },
+    {
+      "epoch": 0.04653739612188366,
+      "grad_norm": 0.25449350476264954,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.2546,
+      "step": 21
+    },
+    {
+      "epoch": 0.04875346260387812,
+      "grad_norm": 0.27934402227401733,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.3185,
+      "step": 22
+    },
+    {
+      "epoch": 0.05096952908587258,
+      "grad_norm": 0.30601152777671814,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.2477,
+      "step": 23
+    },
+    {
+      "epoch": 0.05318559556786703,
+      "grad_norm": 0.2692031264305115,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.1358,
+      "step": 24
+    },
+    {
+      "epoch": 0.055401662049861494,
+      "grad_norm": 0.2555137276649475,
+      "learning_rate": 0.0,
+      "loss": 2.1936,
+      "step": 25
+    },
+    {
+      "epoch": 0.055401662049861494,
+      "eval_loss": 2.2525382041931152,
+      "eval_runtime": 21.5929,
+      "eval_samples_per_second": 8.799,
+      "eval_steps_per_second": 4.4,
+      "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": 1298095480504320.0,
+  "total_flos": 1622619350630400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null