Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eab9c493aa13cd2c8b1b8b6429cefefbca0eb83d3c230f2c5a462193313530b
+oid sha256:e08e849502b5ca7618c1529ebd14260eeedb0f3c6934ba1f949d1b5c05ca20ea
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:865b2fbbac623a33101e5b165e58a953bd08eaf9b66078877e80231ed1e60f68
+oid sha256:d167720cec9e786b920514e48cc6237999b4291bf5d03e777c01fbf99a6d6eef
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b92f2c4d40b75a1c427afcc3b9f446470aabb0e122237b7afe731531934f208
+oid sha256:1f20995103c299fea8f8f69c46bdc51fe8e0da6c299dc26d1f37190f8797826a
 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": 5.523056507110596,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.012202562538133009,
+  "best_metric": 5.487072944641113,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.01525320317266626,
   "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": 6.838,
       "eval_steps_per_second": 3.424,
       "step": 20
+    },
+    {
+      "epoch": 0.012812690665039659,
+      "grad_norm": 1.8376624584197998,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 5.4096,
+      "step": 21
+    },
+    {
+      "epoch": 0.013422818791946308,
+      "grad_norm": 1.71583890914917,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 5.3737,
+      "step": 22
+    },
+    {
+      "epoch": 0.014032946918852958,
+      "grad_norm": 1.852288842201233,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 5.3239,
+      "step": 23
+    },
+    {
+      "epoch": 0.01464307504575961,
+      "grad_norm": 1.8837882280349731,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 5.3845,
+      "step": 24
+    },
+    {
+      "epoch": 0.01525320317266626,
+      "grad_norm": 1.9514257907867432,
+      "learning_rate": 0.0,
+      "loss": 5.4464,
+      "step": 25
+    },
+    {
+      "epoch": 0.01525320317266626,
+      "eval_loss": 5.487072944641113,
+      "eval_runtime": 100.9583,
+      "eval_samples_per_second": 6.844,
+      "eval_steps_per_second": 3.427,
+      "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": 153447605207040.0,
+  "total_flos": 191809506508800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null