Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49fcf21e4d0f98ca44cd5af0528b980ded815b728e6f871d22571172eb82874d
+oid sha256:e13e99c5062b9604c0257858de37c4e28b18457f8ffb7d780cc25a55be8d5683
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ded699a7d8a585cea31a488449cb498c8505f419210dd587006f519237af099f
+oid sha256:77a4af86ef889822fda9383e3485f94b43a3c21ed1bfcc795e3b7082b2a0a278
 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": 1.0654079914093018,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.02476780185758514,
+  "best_metric": 1.0428497791290283,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.030959752321981424,
   "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": 7.072,
       "eval_steps_per_second": 3.536,
       "step": 20
+    },
+    {
+      "epoch": 0.026006191950464396,
+      "grad_norm": 1.670902132987976,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.2316,
+      "step": 21
+    },
+    {
+      "epoch": 0.027244582043343655,
+      "grad_norm": 3.631291151046753,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.381,
+      "step": 22
+    },
+    {
+      "epoch": 0.02848297213622291,
+      "grad_norm": 2.2851688861846924,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.7788,
+      "step": 23
+    },
+    {
+      "epoch": 0.029721362229102165,
+      "grad_norm": 1.936628818511963,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.0911,
+      "step": 24
+    },
+    {
+      "epoch": 0.030959752321981424,
+      "grad_norm": 2.9614367485046387,
+      "learning_rate": 0.0,
+      "loss": 1.2838,
+      "step": 25
+    },
+    {
+      "epoch": 0.030959752321981424,
+      "eval_loss": 1.0428497791290283,
+      "eval_runtime": 48.116,
+      "eval_samples_per_second": 7.066,
+      "eval_steps_per_second": 3.533,
+      "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