Training in progress, step 153, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff3a93f9afafc81c90829f318608e63ed6b45fe8356425786d42bd846cbf5b1
+oid sha256:7293f4cdf32af40aed31b991a15074e4e5daa1db0ab6345bf37f14b4dee5a783
 size 72936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:411e9ac3fe9c98184c851d57e5b1d8a628dd1caad89d3cdb3fb7ae212b866e4c
+oid sha256:d43fcf7ee4b76c83ac0365744b09ba2d9ea62288e56f51fcada9d46e9921785f
 size 151106

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18e38d9e525f7790b7e2fe0f598950624f973dbbb39aa0ad40167fc099b9d40c
+oid sha256:e055063a7efeb2cd20a33898c83149c5850d3fa4fa9b099bd478dcc1ffa034d4
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e9c5ee5e27f666d0042bac898d1c838b31653f183c04bbf53ecb406a784e3dd
+oid sha256:5e25cf20b10a56ef167a38c56aab7eb6a17c1052cd67f0fe127b47cb5e877048
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44e4aa2f4acf9c089d4b3e8a1ca75ddbf88e4110c008ade5fc2cbccf30d4c72b
+oid sha256:e269d9351ac1d508868a3948abc29bafe223d9bfde8fcb631abc812fd3dbcf05
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b8f8abba37b4ae938d370249f9673f8910e984b7ef4f4d9a399353a3f7bc3a3
+oid sha256:21a4522acbf8aaab5d4b2ce214f69cc0b11a02f78235ce165b1f3e9f6807a25f
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:339e849f0ed31d48633840441bf59c6717ec4aab73f8b59923e20b88c91b0d32
+oid sha256:3a998d2ea3dbde83ebed1475971c66bbeedd0311013cbaaa0b0d3840d95792ad
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7730fbadfcfbd42711011bdcf50e4246666f43355936dd5a417ab1fda26b7166
+oid sha256:01d508c66d83a3dba946cbd876240e4344f070453257550d188b9d99f2773734
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:120c9b5e2753d2374e43cc710aea7ecae115d83dae9ee19e396be7cd90b4bd35
+oid sha256:8f1f540ec4f4abba0dd4494356ec2370c3895bbcb67147e938d2d274ff355be6
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f29b132d5d9d0d60a7173e09a69d22bbc193248d4743e3ed17a96ef52aaef252
+oid sha256:6c1ffb973357ab1b957c2114bf58ae116a8173af809a318da339b851f6b39b32
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e618c561766e531a3b508498a52b6a60ed26e61c8d989456e9bc321d17c91c51
+oid sha256:3e80c77d0f985cdc2ae889979d6f64528d8acd1c039d2a4379d31400b142f489
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 12.421979904174805,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 2.9411764705882355,
+  "epoch": 3.0,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 153,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,27 @@
       "eval_samples_per_second": 864.993,
       "eval_steps_per_second": 27.66,
       "step": 150
+    },
+    {
+      "epoch": 2.9607843137254903,
+      "grad_norm": 0.059388499706983566,
+      "learning_rate": 1.4125874125874126e-06,
+      "loss": 12.4267,
+      "step": 151
+    },
+    {
+      "epoch": 2.980392156862745,
+      "grad_norm": 0.09108266234397888,
+      "learning_rate": 7.062937062937063e-07,
+      "loss": 12.4191,
+      "step": 152
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.06379084289073944,
+      "learning_rate": 0.0,
+      "loss": 12.4279,
+      "step": 153
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1133,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4627995033600.0,
+  "total_flos": 4720554934272.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null