Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62b9d90c8ba44b202a2cc0c49cfbc41d246d823a7b31e23a062f7a2cbfb353f1
+oid sha256:4e054fefc18ab0f8512c0951a82ea9ec842bb435a1c270facec3bdb680eb26be
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaba26b961f8580220b9da7bdf39728ea9df491ad69a8a290deb380ad5964ff7
+oid sha256:062ac452bdd95b33e2dae80ab328b2bb1254c62400ca1972f96956bcb7b77cea
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e00a385c6a4231f4efe44b1f8946161a187c9748730e431ce536485fbb3ac425
+oid sha256:2f607489d6de500a4fcb03ed311c3cdcd1ce783b4397a595b02e4db1de8c307c
 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": 2.7113993167877197,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.018194223334091427,
+  "best_metric": 2.6385581493377686,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.02274277916761428,
   "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": 6.806,
       "eval_steps_per_second": 3.41,
       "step": 20
+    },
+    {
+      "epoch": 0.019103934500795998,
+      "grad_norm": 3.1475400924682617,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.5124,
+      "step": 21
+    },
+    {
+      "epoch": 0.02001364566750057,
+      "grad_norm": 3.5368895530700684,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.6722,
+      "step": 22
+    },
+    {
+      "epoch": 0.02092335683420514,
+      "grad_norm": 3.516812801361084,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.5893,
+      "step": 23
+    },
+    {
+      "epoch": 0.02183306800090971,
+      "grad_norm": 3.4932944774627686,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.6304,
+      "step": 24
+    },
+    {
+      "epoch": 0.02274277916761428,
+      "grad_norm": 3.557847738265991,
+      "learning_rate": 0.0,
+      "loss": 2.6361,
+      "step": 25
+    },
+    {
+      "epoch": 0.02274277916761428,
+      "eval_loss": 2.6385581493377686,
+      "eval_runtime": 68.1336,
+      "eval_samples_per_second": 6.795,
+      "eval_steps_per_second": 3.405,
+      "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": 3485272092180480.0,
+  "total_flos": 4356590115225600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null