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:de07b587dcee0251f13720719dccb2976524829577ee77e088ea04d47c7fd0c0
+oid sha256:74e3f80db6d7e3772b0c70040614e4637ed04f3ca17ef105c96bf34a43c701cb
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7066979ba4b020765bf9b8370712fdb40ddd5e8aa335d08786f1fbaf9e27368f
+oid sha256:549c59835a65120ef8189b1d5abea719d2fec1382c25bbb1dd32cc7fb9da7f7c
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37bc76dfb3cff895e69226fc983b6727043d7d920a99e0bf1a35503f825fd2b
+oid sha256:bb3249c98d8a3e206f56eaca2d16298472251892cc161409a4c4042af87ea760
 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": 1.1568152904510498,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.01829407729247656,
+  "best_metric": 1.13201904296875,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0228675966155957,
   "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": 8.316,
       "eval_steps_per_second": 4.167,
       "step": 20
+    },
+    {
+      "epoch": 0.01920878115710039,
+      "grad_norm": 1.8821808099746704,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.1426,
+      "step": 21
+    },
+    {
+      "epoch": 0.020123485021724216,
+      "grad_norm": 1.9913781881332397,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.0652,
+      "step": 22
+    },
+    {
+      "epoch": 0.021038188886348046,
+      "grad_norm": 1.8149455785751343,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.0727,
+      "step": 23
+    },
+    {
+      "epoch": 0.021952892750971873,
+      "grad_norm": 2.112664222717285,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.2997,
+      "step": 24
+    },
+    {
+      "epoch": 0.0228675966155957,
+      "grad_norm": 1.8799444437026978,
+      "learning_rate": 0.0,
+      "loss": 1.1687,
+      "step": 25
+    },
+    {
+      "epoch": 0.0228675966155957,
+      "eval_loss": 1.13201904296875,
+      "eval_runtime": 55.4824,
+      "eval_samples_per_second": 8.309,
+      "eval_steps_per_second": 4.163,
+      "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": 978955586764800.0,
+  "total_flos": 1223694483456000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null