Training in progress, step 163, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85032ceca520f8b48db3ce2a47ec0fcae1899990454f97b39212143ffa55785a
+oid sha256:edfbbd768e951195c3fdc3debad971efb58b2ae48df3c82c3f4338bf0225c7a5
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42c06c623b7cb8281763844c7de9cced42aecdf476b697f9edfdf1b7c939cea9
+oid sha256:aa7a7bf8f2cc1f7940ce5c735bee2d4ea81ce38d21c77b06d60ed3da983d8edd
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6841daf949ca1d59ffa9c38bc182934d53c27335e7abe319fccca79972556ca3
+oid sha256:ee34784d39577c00d7a8591f8428aa17f24e890f5c1d13459bd20b5da9d391d1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a7ca8e55af6b4feda97946cf69d286f368ca3c1d50f3951c0dcbfa4faae95ae
+oid sha256:12941659ba57889c47a9773e7344f67ad687782a9ee6c5cf9f13124ff6930a81
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8207164e65c023390018e471df1c8a2d6b63497b02538e7c9479a46941ee2ec7
+oid sha256:8b23b09fcceafad989e22d3c5bbe6f603a6310692431da25b23a21791e836e2b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf9d6db6d338497d7f96bb6781178aab234997fa413b22da388194e8a349725
+oid sha256:4ce7462caf9a10b59e3581eb947dcbdee5483a496386edb74edc5bc2b195b850
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ea272cd4197c9309705eb2746849abb3b66dd82041e4d35136512f2a6d5e004
+oid sha256:d9584b990eb1d762133ca744b2d560c00d1b8e953f0c718d599b13b400bf125a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.9801422357559204,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 2.771667146559171,
+  "epoch": 3.0149726461272675,
   "eval_steps": 25,
-  "global_step": 150,
+  "global_step": 163,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1113,6 +1113,97 @@
       "eval_samples_per_second": 261.698,
       "eval_steps_per_second": 68.042,
       "step": 150
+    },
+    {
+      "epoch": 2.7900950187158076,
+      "grad_norm": 0.47503483295440674,
+      "learning_rate": 1.1291093570728562e-05,
+      "loss": 1.9973,
+      "step": 151
+    },
+    {
+      "epoch": 2.8085228908724447,
+      "grad_norm": 0.7801658511161804,
+      "learning_rate": 1.1085710876940912e-05,
+      "loss": 2.0129,
+      "step": 152
+    },
+    {
+      "epoch": 2.8269507630290813,
+      "grad_norm": 0.6917530298233032,
+      "learning_rate": 1.0897911135788709e-05,
+      "loss": 2.0055,
+      "step": 153
+    },
+    {
+      "epoch": 2.8453786351857184,
+      "grad_norm": 0.7652437686920166,
+      "learning_rate": 1.072776954088251e-05,
+      "loss": 2.0203,
+      "step": 154
+    },
+    {
+      "epoch": 2.863806507342355,
+      "grad_norm": 0.6981119513511658,
+      "learning_rate": 1.0575354215643268e-05,
+      "loss": 1.9213,
+      "step": 155
+    },
+    {
+      "epoch": 2.882234379498992,
+      "grad_norm": 0.7254536151885986,
+      "learning_rate": 1.0440726186026288e-05,
+      "loss": 2.0316,
+      "step": 156
+    },
+    {
+      "epoch": 2.9006622516556293,
+      "grad_norm": 0.5838481187820435,
+      "learning_rate": 1.0323939356086828e-05,
+      "loss": 1.9561,
+      "step": 157
+    },
+    {
+      "epoch": 2.919090123812266,
+      "grad_norm": 0.48237353563308716,
+      "learning_rate": 1.022504048639738e-05,
+      "loss": 1.9832,
+      "step": 158
+    },
+    {
+      "epoch": 2.937517995968903,
+      "grad_norm": 1.3573530912399292,
+      "learning_rate": 1.0144069175325029e-05,
+      "loss": 2.0506,
+      "step": 159
+    },
+    {
+      "epoch": 2.9559458681255397,
+      "grad_norm": 1.1986020803451538,
+      "learning_rate": 1.0081057843176601e-05,
+      "loss": 1.9252,
+      "step": 160
+    },
+    {
+      "epoch": 2.974373740282177,
+      "grad_norm": 0.5769727826118469,
+      "learning_rate": 1.0036031719217808e-05,
+      "loss": 1.9839,
+      "step": 161
+    },
+    {
+      "epoch": 2.9928016124388135,
+      "grad_norm": 0.28778672218322754,
+      "learning_rate": 1.0009008831571633e-05,
+      "loss": 2.0119,
+      "step": 162
+    },
+    {
+      "epoch": 3.0149726461272675,
+      "grad_norm": 2.086949110031128,
+      "learning_rate": 1e-05,
+      "loss": 3.7483,
+      "step": 163
     }
   ],
   "logging_steps": 1,
@@ -1136,12 +1227,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1392626572984320.0,
+  "total_flos": 1513310000250880.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null