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:d1ccccacc364a361d094666b053da590997a0ec0d9afe8137d5b89c4bd2507df
+oid sha256:5ccace6503665f578c154b8e4f7541e9b7fd29cc3d2eef53fe6e7b0015cbd447
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11febc9122e37d97e645bb77c2c3fbb8ed24fdc01f388d0b11ccccee8e02b51e
+oid sha256:2d9a1d4897173b9cbd27464e2ad43a612aa4d763b5ab3dc581f2f46e1c8761a8
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dc3e5265caade9b4765ce3bea88afed07b875a6b1b6dbe83b1b96d505d55d4b
+oid sha256:c70a576494e56c909be11c04fa488ebbe191aee3195b0dd47c32f36094b31b77
 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": 2.112858772277832,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.06745362563237774,
+  "best_metric": 2.090728282928467,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.08431703204047218,
   "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": 6.898,
       "eval_steps_per_second": 3.477,
       "step": 20
+    },
+    {
+      "epoch": 0.07082630691399663,
+      "grad_norm": 2.9609220027923584,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.1288,
+      "step": 21
+    },
+    {
+      "epoch": 0.07419898819561552,
+      "grad_norm": 2.6516270637512207,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.2109,
+      "step": 22
+    },
+    {
+      "epoch": 0.0775716694772344,
+      "grad_norm": 2.68251895904541,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.2448,
+      "step": 23
+    },
+    {
+      "epoch": 0.08094435075885328,
+      "grad_norm": 2.136423110961914,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.9205,
+      "step": 24
+    },
+    {
+      "epoch": 0.08431703204047218,
+      "grad_norm": 2.8987932205200195,
+      "learning_rate": 0.0,
+      "loss": 2.1777,
+      "step": 25
+    },
+    {
+      "epoch": 0.08431703204047218,
+      "eval_loss": 2.090728282928467,
+      "eval_runtime": 18.0988,
+      "eval_samples_per_second": 6.907,
+      "eval_steps_per_second": 3.481,
+      "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": 3699128496291840.0,
+  "total_flos": 4623910620364800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null