Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c30befa3469eb30dbe3f351ddbe616d832d54ac48f756bf2767cd891ca0fdf6
+oid sha256:de139c0059603b115e809648c77d98ad2b61760f4916ed14d5263bef1881782f
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb9b4282c960da245c18d044c46830ebe3f0f2cd2b02c93a2a4c46eee1b9da52
+oid sha256:d8cc145b71cf5d8313bc5be7940eb203cce272aef2c711990a10b9cfcd9ca478
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff8a1c31d3e49b297b4c3eaa6350303377b39258a670e4aa8ecd61c92c2adbb0
+oid sha256:c863dc94d5911906e4fdde62047559027cb59c121484a770f63204eba8b6db44
 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": 2.7688686847686768,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.000995681232653366,
+  "best_metric": 2.760641574859619,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0012446015408167075,
   "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": 15.376,
       "eval_steps_per_second": 7.688,
       "step": 20
+    },
+    {
+      "epoch": 0.0010454652942860343,
+      "grad_norm": 5.849582195281982,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 12.337,
+      "step": 21
+    },
+    {
+      "epoch": 0.0010952493559187027,
+      "grad_norm": 5.729010581970215,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 9.919,
+      "step": 22
+    },
+    {
+      "epoch": 0.001145033417551371,
+      "grad_norm": 7.823572158813477,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 12.8348,
+      "step": 23
+    },
+    {
+      "epoch": 0.0011948174791840392,
+      "grad_norm": 6.173159122467041,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 11.1361,
+      "step": 24
+    },
+    {
+      "epoch": 0.0012446015408167075,
+      "grad_norm": 7.098884105682373,
+      "learning_rate": 0.0,
+      "loss": 12.071,
+      "step": 25
+    },
+    {
+      "epoch": 0.0012446015408167075,
+      "eval_loss": 2.760641574859619,
+      "eval_runtime": 550.7561,
+      "eval_samples_per_second": 15.357,
+      "eval_steps_per_second": 7.679,
+      "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": 167029977907200.0,
+  "total_flos": 212071769702400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null