Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935fbf609b5733a76e093e62948836190b3272eb1d609cc7cbb419f072f1b250
+oid sha256:9695aa7b8de9a01476184738bb878ed2828ebebfb2645e19d9d0ef2c18e18a8a
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3828ec5ba6617d39fc817940e3603c07c3ee70c3a437fb14272faa8a0800e71
+oid sha256:1349f737740ff9e69a1f4b0408d6653a6632e8309b8b27094713a49bc555e796
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c6d05d84134bc054dc7899f24d2f88d3ea9e2a651e736719bc9e968bca1a100
+oid sha256:0cd0f468fa70a1cf7fad818916de3bad4e117e8ec50f05116c03d5cfd88dd0a8
 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": 0.8654800653457642,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.007209805335255948,
+  "best_metric": 0.8642035126686096,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.009012256669069935,
   "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": 4.344,
       "eval_steps_per_second": 2.174,
       "step": 20
+    },
+    {
+      "epoch": 0.007570295602018745,
+      "grad_norm": 0.5336175560951233,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.5656,
+      "step": 21
+    },
+    {
+      "epoch": 0.007930785868781542,
+      "grad_norm": 0.5913262963294983,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.8729,
+      "step": 22
+    },
+    {
+      "epoch": 0.00829127613554434,
+      "grad_norm": 0.6144100427627563,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 3.9989,
+      "step": 23
+    },
+    {
+      "epoch": 0.008651766402307137,
+      "grad_norm": 0.5489720106124878,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 3.3369,
+      "step": 24
+    },
+    {
+      "epoch": 0.009012256669069935,
+      "grad_norm": 0.596045970916748,
+      "learning_rate": 0.0,
+      "loss": 3.0519,
+      "step": 25
+    },
+    {
+      "epoch": 0.009012256669069935,
+      "eval_loss": 0.8642035126686096,
+      "eval_runtime": 267.2033,
+      "eval_samples_per_second": 4.375,
+      "eval_steps_per_second": 2.189,
+      "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": 6474278237110272.0,
+  "total_flos": 8103027479150592.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null