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:e8f124971f6e45e066092c45814571663abeeb1c7c37d9b8a60eedfc0a06e172
+oid sha256:a9ac5f431e68bc0be3e94d65a484f12f766b83dc919f1a2a7192b4fa03404081
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fe17862cdc22820617ba77c353485eff09dcb153edbcbcced750cf2df5f273b
+oid sha256:464594457eec030889e13ff4a83de8b19dfb54d7712bd3f1c4259eaf0755261d
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e59ab75e1b6101343865e80667c2c665b321f766aee719369a3ca5a3689ff09
+oid sha256:4d11c7a6a55b1fb167809df49e86bfb5922b63262ff5a72c4acf98ce212bd8ed
 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": 0.7629328370094299,
   "best_model_checkpoint": "miner_id_besimray/checkpoint-140",
-  "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": 23.385,
       "eval_steps_per_second": 2.424,
       "step": 140
+    },
+    {
+      "epoch": 1.8135048231511255,
+      "grad_norm": 0.2787846624851227,
+      "learning_rate": 2.032460157676452e-06,
+      "loss": 0.697,
+      "step": 141
+    },
+    {
+      "epoch": 1.8263665594855305,
+      "grad_norm": 0.26291611790657043,
+      "learning_rate": 1.6070411401370334e-06,
+      "loss": 0.7866,
+      "step": 142
+    },
+    {
+      "epoch": 1.8392282958199357,
+      "grad_norm": 0.22387652099132538,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.6242,
+      "step": 143
+    },
+    {
+      "epoch": 1.852090032154341,
+      "grad_norm": 0.25877615809440613,
+      "learning_rate": 9.0502382320653e-07,
+      "loss": 0.7036,
+      "step": 144
+    },
+    {
+      "epoch": 1.864951768488746,
+      "grad_norm": 0.24913811683654785,
+      "learning_rate": 6.287790106757396e-07,
+      "loss": 0.7355,
+      "step": 145
+    },
+    {
+      "epoch": 1.877813504823151,
+      "grad_norm": 0.22730277478694916,
+      "learning_rate": 4.025706004760932e-07,
+      "loss": 0.6122,
+      "step": 146
+    },
+    {
+      "epoch": 1.8906752411575563,
+      "grad_norm": 0.2412744015455246,
+      "learning_rate": 2.265124953543918e-07,
+      "loss": 0.7369,
+      "step": 147
+    },
+    {
+      "epoch": 1.9035369774919615,
+      "grad_norm": 0.23351891338825226,
+      "learning_rate": 1.0069334586854107e-07,
+      "loss": 0.6705,
+      "step": 148
+    },
+    {
+      "epoch": 1.9163987138263665,
+      "grad_norm": 0.2615411877632141,
+      "learning_rate": 2.5176505749346936e-08,
+      "loss": 0.7548,
+      "step": 149
+    },
+    {
+      "epoch": 1.9292604501607717,
+      "grad_norm": 0.29780200123786926,
+      "learning_rate": 0.0,
+      "loss": 0.8051,
+      "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