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:db15625c3d7fe115e4d98d5878900400decfdb5c352a0a7ac5cfc12bfeb12862
+oid sha256:3387fdb9ca66d88c9f813369fb34b03e2f6ebe3c21e7741ba9aa0d0f879b4b9c
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fda69ca09bf5031f806c6b87b8314c57ecccc84cbd23e6266af5fa03fe9667fe
+oid sha256:ee1b25bca9903b4d902b404d6c1767a5b6a56e1c7983fb3487ccae49da3b7aac
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4b82d94a3f3ba4658ccb6aa5c8b6ba7ae6394ee1ce2647f24e42e072d6200c3
+oid sha256:f58b98283f0cf134b4005d9b921adb02a846a23631404be12129392a65cfe4e3
 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": 0.17875705659389496,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.03372681281618887,
+  "best_metric": 0.1660141497850418,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.04215851602023609,
   "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": 5.262,
       "eval_steps_per_second": 2.631,
       "step": 20
+    },
+    {
+      "epoch": 0.03541315345699832,
+      "grad_norm": 5.7535295486450195,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.4698,
+      "step": 21
+    },
+    {
+      "epoch": 0.03709949409780776,
+      "grad_norm": 2.8564772605895996,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.2599,
+      "step": 22
+    },
+    {
+      "epoch": 0.0387858347386172,
+      "grad_norm": 0.8172993063926697,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.0864,
+      "step": 23
+    },
+    {
+      "epoch": 0.04047217537942664,
+      "grad_norm": 3.7000441551208496,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.2295,
+      "step": 24
+    },
+    {
+      "epoch": 0.04215851602023609,
+      "grad_norm": 3.757780075073242,
+      "learning_rate": 0.0,
+      "loss": 0.944,
+      "step": 25
+    },
+    {
+      "epoch": 0.04215851602023609,
+      "eval_loss": 0.1660141497850418,
+      "eval_runtime": 47.4874,
+      "eval_samples_per_second": 5.265,
+      "eval_steps_per_second": 2.632,
+      "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": 6332448610713600.0,
+  "total_flos": 7915560763392000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null