Training in progress, step 57, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e06887e57bccf26bfa464b05cf707fb5f49905d6ad19b210174430cbaaf299
+oid sha256:4019e5e2ee3905012f017a11dc93adc3af980844814ac0151c4debd6f3fd058f
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:149b1da70fde035175bf3fd48570ef5358019f1d2cc553b043b929e3c369e158
+oid sha256:678e87e4c0d1ad51f8a9133259d3b2af309119f8237efd7eb5f9f5fc8906abb3
 size 118090

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31be078cef3b36a38079147563c69ce8a51556d45f7db524d91fdbb73c14fd36
+oid sha256:5c072ffb44dd93d6b0540139cc206787d6527c0de44147802b349ec6fbded86c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91528eddcfea1e6a60ec09b6e3a3e3df071c92896878ae2beecbf3447a714577
+oid sha256:55b9d370a87ea641503296db7c08d5cc50ae8f35e20bc73be575990e87daccc9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e27a19e1b1ee46e9534914d4b7ba1e5b6f21cf94f09b47481368788faedcabef
+oid sha256:c53b808c0ba6b8213c3e98ef8b3395169ba2bf41285582dc79c17b53778739be
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:601969e05e80fcb55350db79a2637f4e164d594e2b582971e7059f6aa859e9d1
+oid sha256:4046746657c8c08717b79078344c783b965802ac6887de20c33d54887205f611
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b67e3782bfe21b65ca00b1ed626af2159c71bfb2945419e3b11baa4ed5492e1
+oid sha256:78101091e2f719951fa8c5fb573717e4daf2a10dba3a43d58e809a7005b3b47c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.734221458435059,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.7699115044247788,
+  "epoch": 2.017699115044248,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 57,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,55 @@
       "eval_samples_per_second": 920.765,
       "eval_steps_per_second": 36.831,
       "step": 50
+    },
+    {
+      "epoch": 1.8053097345132745,
+      "grad_norm": 0.10223124921321869,
+      "learning_rate": 1.1902516998535666e-05,
+      "loss": 11.5613,
+      "step": 51
+    },
+    {
+      "epoch": 1.8407079646017699,
+      "grad_norm": 0.08183666318655014,
+      "learning_rate": 8.299636258812197e-06,
+      "loss": 11.7158,
+      "step": 52
+    },
+    {
+      "epoch": 1.8761061946902655,
+      "grad_norm": 0.09326402842998505,
+      "learning_rate": 5.329623741843531e-06,
+      "loss": 11.7962,
+      "step": 53
+    },
+    {
+      "epoch": 1.911504424778761,
+      "grad_norm": 0.10565122961997986,
+      "learning_rate": 3.0057442445119872e-06,
+      "loss": 11.7664,
+      "step": 54
+    },
+    {
+      "epoch": 1.9469026548672566,
+      "grad_norm": 0.11125579476356506,
+      "learning_rate": 1.3383767767829956e-06,
+      "loss": 11.8781,
+      "step": 55
+    },
+    {
+      "epoch": 1.9823008849557522,
+      "grad_norm": 0.13728636503219604,
+      "learning_rate": 3.349682065270254e-07,
+      "loss": 12.3971,
+      "step": 56
+    },
+    {
+      "epoch": 2.017699115044248,
+      "grad_norm": 0.16288495063781738,
+      "learning_rate": 0.0,
+      "loss": 20.1629,
+      "step": 57
     }
   ],
   "logging_steps": 1,
@@ -404,12 +453,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 86572518604800.0,
+  "total_flos": 98692671209472.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null