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:ffe5e38735cccf7b48e4a47d8709f7d192da5380555fa01fef0c080613232996
+oid sha256:72aa959cf7758eadeb6ec242eb7e3f6269cf7472a9bd28741acc781778395857
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5b8255a9b42174c49e1a5aecc929135649d2670e55ec6c0fcb737de1fb085f
+oid sha256:7cd45b36494ef21f38be9ebc3d4f132da246772db4b5c64988beb7b1bf1c5ed7
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8195f5f8ab0a2152863fee8331a14f0c6fd922ebfbe0783423b8278beeaadd3
+oid sha256:89ffcad5a84b06fde95717df10413749838a6b711ecc83f3ebee00a93d200145
 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": 4.180180072784424,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.07428040854224698,
+  "best_metric": 4.173059463500977,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.09285051067780872,
   "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": 17.698,
       "eval_steps_per_second": 8.849,
       "step": 20
+    },
+    {
+      "epoch": 0.07799442896935933,
+      "grad_norm": 61.8924446105957,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 16.2944,
+      "step": 21
+    },
+    {
+      "epoch": 0.08170844939647168,
+      "grad_norm": 49.258201599121094,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 15.9243,
+      "step": 22
+    },
+    {
+      "epoch": 0.08542246982358404,
+      "grad_norm": 52.41282653808594,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 17.6994,
+      "step": 23
+    },
+    {
+      "epoch": 0.08913649025069638,
+      "grad_norm": 38.438812255859375,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 16.3655,
+      "step": 24
+    },
+    {
+      "epoch": 0.09285051067780872,
+      "grad_norm": 40.115882873535156,
+      "learning_rate": 0.0,
+      "loss": 17.5364,
+      "step": 25
+    },
+    {
+      "epoch": 0.09285051067780872,
+      "eval_loss": 4.173059463500977,
+      "eval_runtime": 6.5325,
+      "eval_samples_per_second": 17.451,
+      "eval_steps_per_second": 8.726,
+      "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": 175457131560960.0,
+  "total_flos": 219321414451200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null