Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30ced72b3cc829450e332754c98c1129531b12cbc1087faf16579d1c8b822da1
+oid sha256:3e8218aba404fc5f68e7911309c7011f612df48f8e1598e188448ce6e29adc09
 size 203456160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aba94074b3bcd98fc69a4dc998308e6ee69fe527c7170698da85560f5c522732
+oid sha256:7d3753cf6595a9d22325c6db1f6c11853207f68c3f2e4c34f9b1f54f95bbec6d
 size 407121750

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:235987cd14d2b651bd083a2045910396be0aab90ff9f738c75760d88528349a3
+oid sha256:0017d054f399ae02d66bec2e7c0b81e4c469b5e125926b0e041136c01e7debf8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ed83c54ad01fcfcd8246932f708e99e17e8ef5c6e3595097b68d8c42cf78ec5
+oid sha256:409b87eefbbfc5af04df48b8cccf0428548d3efea659f10ffd25c2e2bc3de30b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0966a69a93e8ec900098984946f252e636d603335a1be19728cf108f6f5076ed
+oid sha256:b2a3eaa55c6d5537c27e4456768a8f475ec9b8f739daf816e638d7ac888011bb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56f556cc525b21d1e70dfd21e4724095b63d005b1d343403352d5b6e8f1a8a5b
+oid sha256:c9ed5c5b37f0763e77790b53d0f88a4fc69d787befcb63013221803055bb03c9
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8b460eb34577dc31e89c5d46049a264caffc8e9f90e68fb640444126fba5f4
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.0482399463653564,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.6369426751592355,
+  "epoch": 3.1910828025477707,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,41 @@
       "eval_samples_per_second": 29.076,
       "eval_steps_per_second": 3.965,
       "step": 25
+    },
+    {
+      "epoch": 2.738853503184713,
+      "grad_norm": 0.2180248200893402,
+      "learning_rate": 4.951556604879048e-06,
+      "loss": 0.9552,
+      "step": 26
+    },
+    {
+      "epoch": 2.840764331210191,
+      "grad_norm": 0.19627752900123596,
+      "learning_rate": 2.8058334845816213e-06,
+      "loss": 0.9294,
+      "step": 27
+    },
+    {
+      "epoch": 2.9426751592356686,
+      "grad_norm": 0.46095138788223267,
+      "learning_rate": 1.2536043909088191e-06,
+      "loss": 1.4176,
+      "step": 28
+    },
+    {
+      "epoch": 3.089171974522293,
+      "grad_norm": 0.2987149655818939,
+      "learning_rate": 3.143895053378698e-07,
+      "loss": 1.0826,
+      "step": 29
+    },
+    {
+      "epoch": 3.1910828025477707,
+      "grad_norm": 0.2547209560871124,
+      "learning_rate": 0.0,
+      "loss": 0.888,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -221,12 +256,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.4042109046266266e+17,
+  "total_flos": 1.68704369229824e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null