Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:997fbebd379cc607bb1c4f6b46d6a63d2c5674a7d3cb9bf62788787342cb5904
+oid sha256:4ca4ed73b833d1cdd2bdfb44cea87d4c15cd9dc94270e74589bc32fd8dec3b7d
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d4e6e703c3ae58a7ee1d7e3186ec008025663ef080e3fc3a5e35825dfbf0aa
+oid sha256:c0a49ad3e5fd3e40ff97a32ca0b4e3dbaea638c1f023aa8f3b21931f405b9c87
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48c3d0371c6ea16c11e51847c0e9252ab1cb3c98c2217205c5579fd2e2e6bfda
+oid sha256:743a06d6c5a0527ed68b61aa93f5b682b2bd5892568483ad8a4d527b2d107a52
 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": 2.1492695808410645,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.007399186089530152,
+  "best_metric": 2.136228561401367,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.00924898261191269,
   "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": 10.917,
       "eval_steps_per_second": 5.463,
       "step": 20
+    },
+    {
+      "epoch": 0.00776914539400666,
+      "grad_norm": 2.2477540969848633,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 9.283,
+      "step": 21
+    },
+    {
+      "epoch": 0.008139104698483167,
+      "grad_norm": 2.4080300331115723,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 7.3326,
+      "step": 22
+    },
+    {
+      "epoch": 0.008509064002959674,
+      "grad_norm": 2.310375452041626,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 8.8764,
+      "step": 23
+    },
+    {
+      "epoch": 0.008879023307436182,
+      "grad_norm": 1.7543952465057373,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 7.3545,
+      "step": 24
+    },
+    {
+      "epoch": 0.00924898261191269,
+      "grad_norm": 2.327606201171875,
+      "learning_rate": 0.0,
+      "loss": 8.9908,
+      "step": 25
+    },
+    {
+      "epoch": 0.00924898261191269,
+      "eval_loss": 2.136228561401367,
+      "eval_runtime": 104.7135,
+      "eval_samples_per_second": 10.877,
+      "eval_steps_per_second": 5.443,
+      "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": 1835906755461120.0,
+  "total_flos": 2294883444326400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null