Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89698065e8e2f09c47a2523945d02b0d700a6e7e9682f02876feb1c2df0b556e
+oid sha256:1fa8d826125079ec9c5474ab65c06145915471c18bc66f1805c7d717cadd029e
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c6bbb2ae050e5de748c89daebe89c76d78ce1d43502c409aef1191b1d589edd
+oid sha256:130d8ef83feeaaf7c5ecb1613710a52b6dfa277de7c2d71c5a4215216ab69e20
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad8d45468f3e2058e4054b1300023f160078727b78fd8ca1d82d4d66de05c95e
+oid sha256:5ddb3a14e37d35591e2f920bed97a2ab497a50f4ae5ff4f56d4a7abfd88cf5f7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22a860b36e177d944f54f688d2f30a0a558f05a29fd2b863008a05217bc84467
+oid sha256:194456d3c9e165255d5406a0f3f62973b0bede79d91784f72431350783e27ae7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.07654841244220734,
   "best_model_checkpoint": "miner_id_besimray/checkpoint-120",
-  "epoch": 1.8006430868167203,
+  "epoch": 1.9292604501607717,
   "eval_steps": 20,
-  "global_step": 140,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1051,6 +1051,76 @@
       "eval_samples_per_second": 23.712,
       "eval_steps_per_second": 2.458,
       "step": 140
+    },
+    {
+      "epoch": 1.8135048231511255,
+      "grad_norm": 0.7514206767082214,
+      "learning_rate": 2.032460157676452e-06,
+      "loss": 0.0471,
+      "step": 141
+    },
+    {
+      "epoch": 1.8263665594855305,
+      "grad_norm": 1.090172529220581,
+      "learning_rate": 1.6070411401370334e-06,
+      "loss": 0.0541,
+      "step": 142
+    },
+    {
+      "epoch": 1.8392282958199357,
+      "grad_norm": 1.1606374979019165,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0473,
+      "step": 143
+    },
+    {
+      "epoch": 1.852090032154341,
+      "grad_norm": 0.8554772734642029,
+      "learning_rate": 9.0502382320653e-07,
+      "loss": 0.0556,
+      "step": 144
+    },
+    {
+      "epoch": 1.864951768488746,
+      "grad_norm": 1.0313165187835693,
+      "learning_rate": 6.287790106757396e-07,
+      "loss": 0.0651,
+      "step": 145
+    },
+    {
+      "epoch": 1.877813504823151,
+      "grad_norm": 1.2343289852142334,
+      "learning_rate": 4.025706004760932e-07,
+      "loss": 0.0919,
+      "step": 146
+    },
+    {
+      "epoch": 1.8906752411575563,
+      "grad_norm": 0.6673130393028259,
+      "learning_rate": 2.265124953543918e-07,
+      "loss": 0.0284,
+      "step": 147
+    },
+    {
+      "epoch": 1.9035369774919615,
+      "grad_norm": 0.460891991853714,
+      "learning_rate": 1.0069334586854107e-07,
+      "loss": 0.0221,
+      "step": 148
+    },
+    {
+      "epoch": 1.9163987138263665,
+      "grad_norm": 1.798021674156189,
+      "learning_rate": 2.5176505749346936e-08,
+      "loss": 0.1315,
+      "step": 149
+    },
+    {
+      "epoch": 1.9292604501607717,
+      "grad_norm": 0.5896714925765991,
+      "learning_rate": 0.0,
+      "loss": 0.0268,
+      "step": 150
     }
   ],
   "logging_steps": 1,
@@ -1074,12 +1144,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.32938145759232e+16,
+  "total_flos": 3.58265259884544e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null