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:b5bd5b3c6dcde861558f7e9e44c228c4046b93a9a734d20a22f7acd1b14ec57b
+oid sha256:99f5d06a5decfad8b86d48ce751090fb53f055d7a3d5eaf39e90baeac54fc6ac
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53872f445483765bfda62260a92a16ed4b724542db1f1472592b7216d1031658
+oid sha256:27b7a3b63825e0f49aaf2aff3e7ad27accadfb9a14c35930f29121f7112cfb55
 size 9568884

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13caed2486e1da8a0948af7d72cd477768bf513db1ce28ff265331bf837f1d26
+oid sha256:77c0b39f972747f023b304d3c62bc019403b09c50215b45f49bae9378cf18456
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55777a62bf7f2ea823eb8ae44539d8fad2b3742eda9a67334d081523ea8a1fdc
+oid sha256:6cac6a6a12f9fbb422638c2f9c613b574deeea31b99b461abc1aba72b7453c01
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8bb503db4e06ee680e1b47429d8e2fb144d4a5001e10c8f2fd1759db8b3580b
+oid sha256:69f162e40fad931184c3a4dd761b45c8ea0aa41821332c7888492d82817795ef
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72999cbe5329d0fccf9bb6ff5c1d1e79bb2e0f7db521586685b152d8f193c715
+oid sha256:310874b8e37f71ef774f9ecff3ab15c76d9819b427a8598c5d9d0cbfb05ca057
 size 15024

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": 0.14818401634693146,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.013527223537368955,
+  "best_metric": 0.14158989489078522,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.016909029421711193,
   "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": 201.148,
       "eval_steps_per_second": 25.204,
       "step": 20
+    },
+    {
+      "epoch": 0.014203584714237404,
+      "grad_norm": 1.814172625541687,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.1932,
+      "step": 21
+    },
+    {
+      "epoch": 0.014879945891105851,
+      "grad_norm": 1.426396131515503,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0932,
+      "step": 22
+    },
+    {
+      "epoch": 0.015556307067974298,
+      "grad_norm": 1.169958472251892,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.1249,
+      "step": 23
+    },
+    {
+      "epoch": 0.016232668244842745,
+      "grad_norm": 1.2674089670181274,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.08,
+      "step": 24
+    },
+    {
+      "epoch": 0.016909029421711193,
+      "grad_norm": 1.5442484617233276,
+      "learning_rate": 0.0,
+      "loss": 0.1493,
+      "step": 25
+    },
+    {
+      "epoch": 0.016909029421711193,
+      "eval_loss": 0.14158989489078522,
+      "eval_runtime": 12.4618,
+      "eval_samples_per_second": 199.811,
+      "eval_steps_per_second": 25.037,
+      "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": 870348039913472.0,
+  "total_flos": 1079587723280384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null