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:ebebc8a19fd7b6d5dd18de5ebb1757251a686bc8736a6d24aa1aebbe285cfd61
+oid sha256:2451ef5c714b551282f80fe78c2f713ecca707b41f1870afb3b498c1e38e5e49
 size 2185308216

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2faa1236b041a91db75d142c93c7481ce047ed75543d814470a67cfcef9a98e
+oid sha256:a1c0786bbf484ee7641c10b16ce18c7a2de4f3847a72cfeb2e07763303e98d04
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
+oid sha256:d36cf02c5c091e1cf6b7a556033f9afe92924f5c6d18c68aeec7f759f6f16a6c
 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": 0.542029082775116,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.004711980209683119,
+  "best_metric": 0.540064811706543,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.005889975262103899,
   "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": 4.152,
       "eval_steps_per_second": 2.076,
       "step": 20
+    },
+    {
+      "epoch": 0.004947579220167276,
+      "grad_norm": 0.362483412027359,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.4542,
+      "step": 21
+    },
+    {
+      "epoch": 0.005183178230651431,
+      "grad_norm": 0.3919994831085205,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.5401,
+      "step": 22
+    },
+    {
+      "epoch": 0.005418777241135587,
+      "grad_norm": 0.3926795721054077,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.5272,
+      "step": 23
+    },
+    {
+      "epoch": 0.005654376251619743,
+      "grad_norm": 0.4079397916793823,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.5501,
+      "step": 24
+    },
+    {
+      "epoch": 0.005889975262103899,
+      "grad_norm": 0.39526617527008057,
+      "learning_rate": 0.0,
+      "loss": 0.5403,
+      "step": 25
+    },
+    {
+      "epoch": 0.005889975262103899,
+      "eval_loss": 0.540064811706543,
+      "eval_runtime": 451.99,
+      "eval_samples_per_second": 3.956,
+      "eval_steps_per_second": 1.978,
+      "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": 7398261019115520.0,
+  "total_flos": 9247826273894400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null