Training in progress, step 51, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0597fd954a495a4574d079876556af7dc78291d1eba0b359319fac397d618fea
+oid sha256:882501016e7da9f9c985f21c46eeacd36b8f92c3430a5fb59a2709c32fd452b3
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d000a0f6db723570bcc9a58d512a3f951dc1ba2b2e564704c61f97d77cc11de
+oid sha256:6f2f51659a281d95d59867c4f00453208960058821ac12fe9ad212166d34b454
 size 71077780

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc4e8b66a404bfdb805327ab2b6ef7b63cf58156e40dc3720553d3fdfe4adb4c
+oid sha256:8f0b6d45eb32a5807a395fa08c892bd606b7a21d12cf647262446bf41d74b62a
 size 15088

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99d87e481a8a808b4c3165ff6ff4c083d8f9a9099d1b67ee2434907a5968100e
+oid sha256:e9df01cdc526c0388edfe2377485436d61e2dbc669c82b41f6a9c6520205fda3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20e9b8d736cfc5fa649eabe167389a2c49bb76d034b848248cf0431c51e0ad03
+oid sha256:6fbf23d607616a79f8f7bd26b40da25dc792bcf09da8c3f7bdd91e2fa633336b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d32bfbe0307771af00f3d27cd68fa5791ed9a6d32b6f3601fc4ec37ae7f3d6e8
+oid sha256:300baa0c69212cce2a824e720000b3f1eca702fa8e78047210aebd380b9202b1
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:749b285552796e5e7c57d49cd40c321bb443d41481421bf176375b0746855301
+oid sha256:4fd3f520534f7ee772b2563dcf3f598aa00e76146178df3a6e24ec16d733872d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.5307759046554565,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 2.9411764705882355,
+  "epoch": 3.0,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 51,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,13 @@
       "eval_samples_per_second": 15.973,
       "eval_steps_per_second": 1.111,
       "step": 50
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.1972215622663498,
+      "learning_rate": 0.0,
+      "loss": 1.485,
+      "step": 51
     }
   ],
   "logging_steps": 1,
@@ -396,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.404685864927232e+16,
+  "total_flos": 1.435595821809664e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null