Training in progress, step 34, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a507963e4594477b9168d63b25deff854903b957f0015fb56030084fcd48009
+oid sha256:5b5e78a6a030366371e2297211abfea272e7dedabf869dabc754c268f69f1fc5
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3ffe72824a1f05c685df0cf4b52b467311e0ec15108e48d1c3cc82d6807336d
+oid sha256:d2f858aebf32a7594782248c8c5fb4e4fdace423693ee56a9dfaf5a85032370c
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46cc0f2f91770e589e519b76246485deed9615c4f79f5b3e96412b9dee37a355
+oid sha256:62a7ed1d3e68d53e70a58bd389273fdee2a5439e00738ef0e8dfa600c5442f01
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7386428dd50bcc7272f9f7899620eaa2655a78fabe4d5884e778770167dd3912
+oid sha256:1e2039c89fc9598f4be9186817a4832723bd9cf975631d90efa77292d07a7a76
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef31a76c3400db93ec42053e7049a6ac0894a4c1f152436a870a1bd32bb9a805
+oid sha256:3dc847943b2d93f392f59776f387f867b731e6931cc2f34910bb697f6e5e02f8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb6850c6f19969b4ed1e09f98131f0b11b9bb4e6081ccaf565e0ee81d7871c0
+oid sha256:243bbf6cce2cc85bd6dfaa38d94f0689fba104322c9a1e360cf60fa39c32147d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9df2a04f62b67211447d8ed44cee6691ed618e4d6af94df3c64d249c82d80c3
+oid sha256:1fe247b8abd9f098bbbafb55011dbe010f2fe145118845b911d1500aa9422fe0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.73397159576416,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.2320441988950277,
+  "epoch": 3.0386740331491713,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 34,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,69 @@
       "eval_samples_per_second": 241.993,
       "eval_steps_per_second": 31.841,
       "step": 25
+    },
+    {
+      "epoch": 2.320441988950276,
+      "grad_norm": 0.29126057028770447,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.7703,
+      "step": 26
+    },
+    {
+      "epoch": 2.408839779005525,
+      "grad_norm": 0.38691118359565735,
+      "learning_rate": 1.134947733186315e-05,
+      "loss": 11.6391,
+      "step": 27
+    },
+    {
+      "epoch": 2.4972375690607733,
+      "grad_norm": 0.4289560914039612,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.7,
+      "step": 28
+    },
+    {
+      "epoch": 2.585635359116022,
+      "grad_norm": 0.26441726088523865,
+      "learning_rate": 5.903936782582253e-06,
+      "loss": 11.8562,
+      "step": 29
+    },
+    {
+      "epoch": 2.6740331491712706,
+      "grad_norm": 0.4067860245704651,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.5272,
+      "step": 30
+    },
+    {
+      "epoch": 2.7624309392265194,
+      "grad_norm": 0.3586118817329407,
+      "learning_rate": 2.152983213389559e-06,
+      "loss": 11.6841,
+      "step": 31
+    },
+    {
+      "epoch": 2.8508287292817682,
+      "grad_norm": 0.3402305841445923,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.8628,
+      "step": 32
+    },
+    {
+      "epoch": 2.9392265193370166,
+      "grad_norm": 0.4240974187850952,
+      "learning_rate": 2.407636663901591e-07,
+      "loss": 11.7737,
+      "step": 33
+    },
+    {
+      "epoch": 3.0386740331491713,
+      "grad_norm": 0.5821945071220398,
+      "learning_rate": 0.0,
+      "loss": 20.9847,
+      "step": 34
     }
   ],
   "logging_steps": 1,
@@ -221,12 +284,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 81943068672000.0,
+  "total_flos": 111442573393920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null