Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c48040d5f4dcdfb0212cdd9847d4104bc15bb453b626c43fd198d81ee08fca2
+oid sha256:2d9099e48c88368196f53da6145de1e5b909d83a04cdb25649c3821e9671c531
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fe89604d961d4a51883d86fdae4d4686eafa9a8c2e6271cdd5c860d86a4ca86
+oid sha256:dcefe8355b1a065530f4c4574e78760e6d1dd32ba4b7393ac87f9488aefc60d4
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65072b1b6c28a74f8da9eb58e2888536595e89ac6c79dde321f112aa66624e44
+oid sha256:d6e0ee519c15bc05b1bfbfcced8d67967611c1404b61e2b1f0088852646eda38
 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": 1.7709662914276123,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.006428801028608165,
+  "best_metric": 1.7614490985870361,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.008036001285760206,
   "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": 5.35,
       "eval_steps_per_second": 2.675,
       "step": 20
+    },
+    {
+      "epoch": 0.006750241080038573,
+      "grad_norm": 2.53360652923584,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 6.6023,
+      "step": 21
+    },
+    {
+      "epoch": 0.007071681131468981,
+      "grad_norm": 2.14629864692688,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 6.6719,
+      "step": 22
+    },
+    {
+      "epoch": 0.007393121182899389,
+      "grad_norm": 2.85324764251709,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 6.5182,
+      "step": 23
+    },
+    {
+      "epoch": 0.007714561234329798,
+      "grad_norm": 2.843808650970459,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 7.1167,
+      "step": 24
+    },
+    {
+      "epoch": 0.008036001285760206,
+      "grad_norm": 3.727983236312866,
+      "learning_rate": 0.0,
+      "loss": 7.3145,
+      "step": 25
+    },
+    {
+      "epoch": 0.008036001285760206,
+      "eval_loss": 1.7614490985870361,
+      "eval_runtime": 246.737,
+      "eval_samples_per_second": 5.309,
+      "eval_steps_per_second": 2.655,
+      "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": 7916534869524480.0,
+  "total_flos": 9842178486435840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null