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:aa28d61d6cedaa71a90acb6f6fcedbaaa222b302ee36c92a91f2525ec154ae12
+oid sha256:75bfba01cfa7084a7d6fbac043ee87fc92eab81a81135ebf12029a91df8c82b6
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ce6f826e10ff98c9db36f4370f66f8681cc15a02b1841d2560c6dc9c7af82d8
+oid sha256:5443034b49ffb4526236deb77e7cb0b7a469c2090ffaa6522fbcddeb10e6164d
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c697c473a332dbf1920d763623c73e50ba54d83feaad77dca0c5311c25e79af0
+oid sha256:304c46057b5982c6191c95ba2c5abfc93667d2a71777f89623ea017c6f9b37ec
 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": 1.6069304943084717,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.001661371046456088,
+  "best_metric": 1.5643208026885986,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.00207671380807011,
   "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": 7.338,
       "eval_steps_per_second": 3.67,
       "step": 20
+    },
+    {
+      "epoch": 0.0017444395987788923,
+      "grad_norm": 0.8257535696029663,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.8202,
+      "step": 21
+    },
+    {
+      "epoch": 0.0018275081511016967,
+      "grad_norm": 0.39779406785964966,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.4466,
+      "step": 22
+    },
+    {
+      "epoch": 0.0019105767034245011,
+      "grad_norm": 0.5848168134689331,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.4848,
+      "step": 23
+    },
+    {
+      "epoch": 0.0019936452557473053,
+      "grad_norm": 0.5994840860366821,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.8308,
+      "step": 24
+    },
+    {
+      "epoch": 0.00207671380807011,
+      "grad_norm": 0.39819470047950745,
+      "learning_rate": 0.0,
+      "loss": 0.528,
+      "step": 25
+    },
+    {
+      "epoch": 0.00207671380807011,
+      "eval_loss": 1.5643208026885986,
+      "eval_runtime": 692.8523,
+      "eval_samples_per_second": 7.316,
+      "eval_steps_per_second": 3.659,
+      "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": 2234632612085760.0,
+  "total_flos": 2808666677575680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null