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:ef1e48c0a8c1b17de6362ec56784914c3ad7cc3dfc6cf6f4a65fdb64d08281e7
+oid sha256:8b59a2b33e79a46f96564fca186246a8649cdac29f631597790c0a199b77f26a
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6eb7a6d9f4820f73c8b9d2613469b9bdc3ada75de1ee86607f04ed44e9f8d34
+oid sha256:d09b24791eccb53639fcf1693bd8ec648a3f07185e641395dd93fa45b34a19f5
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:845614e2f59fda4ead6c0973115f7f83016732685fe92124b66ae3eb92f9d67d
+oid sha256:4a5ba63017d7a3a2bc9c7bc3cb5325cda5dded5f3ccff50ace77f75d09aa367f
 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": 1.2084153890609741,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.017185821697099892,
+  "best_metric": 1.2040976285934448,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.021482277121374866,
   "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": 5.799,
       "eval_steps_per_second": 2.899,
       "step": 20
+    },
+    {
+      "epoch": 0.01804511278195489,
+      "grad_norm": 0.3168874979019165,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.1815,
+      "step": 21
+    },
+    {
+      "epoch": 0.01890440386680988,
+      "grad_norm": 0.3309725821018219,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.2765,
+      "step": 22
+    },
+    {
+      "epoch": 0.019763694951664877,
+      "grad_norm": 0.29042884707450867,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.2331,
+      "step": 23
+    },
+    {
+      "epoch": 0.02062298603651987,
+      "grad_norm": 0.30278280377388,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.0275,
+      "step": 24
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "grad_norm": 0.39869019389152527,
+      "learning_rate": 0.0,
+      "loss": 1.1904,
+      "step": 25
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "eval_loss": 1.2040976285934448,
+      "eval_runtime": 84.8485,
+      "eval_samples_per_second": 5.775,
+      "eval_steps_per_second": 2.887,
+      "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": 5944875946082304.0,
+  "total_flos": 7410735768403968.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null