Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67261fa22d0d98fb03da7d030ab8d61b4f6667fd140dbb952b901e0cb14a9990
+oid sha256:31c28a09eee6bfb1a78f61b7c87b039903c2799f87db8ad26e59343aa0b68d27
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6aa4989696bdd19d6e029ce6e7e5bd088ffa30b0df043f0f8169add9f616d88
+oid sha256:4ec5b9780704cd2044deb0ca4dd397cc48f76c890b4017a967a021e4d6726083
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3b93b998129c562042cd2f7094d3fbc863ceb2202e913a646d3cb90ae67959e
+oid sha256:e86e29da3d28f4d8655051294d94928d777faf363f4186542370163ecc4066e3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.717280387878418,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.045641259698767686,
+  "best_metric": 2.47334361076355,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.09128251939753537,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 67.873,
       "eval_steps_per_second": 8.53,
       "step": 25
+    },
+    {
+      "epoch": 0.04746691008671839,
+      "grad_norm": 3.201265811920166,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.1979,
+      "step": 26
+    },
+    {
+      "epoch": 0.0492925604746691,
+      "grad_norm": 3.3780765533447266,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.3203,
+      "step": 27
+    },
+    {
+      "epoch": 0.051118210862619806,
+      "grad_norm": 3.628631591796875,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.2478,
+      "step": 28
+    },
+    {
+      "epoch": 0.05294386125057052,
+      "grad_norm": 3.380159854888916,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.4871,
+      "step": 29
+    },
+    {
+      "epoch": 0.05476951163852122,
+      "grad_norm": 3.7136998176574707,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.5813,
+      "step": 30
+    },
+    {
+      "epoch": 0.05659516202647193,
+      "grad_norm": 3.7535629272460938,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.5976,
+      "step": 31
+    },
+    {
+      "epoch": 0.05842081241442264,
+      "grad_norm": 3.559950590133667,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.7981,
+      "step": 32
+    },
+    {
+      "epoch": 0.06024646280237335,
+      "grad_norm": 4.081882953643799,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.6634,
+      "step": 33
+    },
+    {
+      "epoch": 0.06207211319032405,
+      "grad_norm": 3.7420055866241455,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 2.8191,
+      "step": 34
+    },
+    {
+      "epoch": 0.06389776357827476,
+      "grad_norm": 3.7731378078460693,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.7214,
+      "step": 35
+    },
+    {
+      "epoch": 0.06572341396622547,
+      "grad_norm": 5.522697925567627,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.6663,
+      "step": 36
+    },
+    {
+      "epoch": 0.06754906435417618,
+      "grad_norm": 8.51200008392334,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 2.8907,
+      "step": 37
+    },
+    {
+      "epoch": 0.06937471474212688,
+      "grad_norm": 8.823360443115234,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 3.0241,
+      "step": 38
+    },
+    {
+      "epoch": 0.07120036513007759,
+      "grad_norm": 7.192963600158691,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.5329,
+      "step": 39
+    },
+    {
+      "epoch": 0.0730260155180283,
+      "grad_norm": 4.3827900886535645,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.2836,
+      "step": 40
+    },
+    {
+      "epoch": 0.07485166590597901,
+      "grad_norm": 6.091566562652588,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.5218,
+      "step": 41
+    },
+    {
+      "epoch": 0.07667731629392971,
+      "grad_norm": 4.062016487121582,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.4963,
+      "step": 42
+    },
+    {
+      "epoch": 0.07850296668188042,
+      "grad_norm": 6.100872993469238,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.3811,
+      "step": 43
+    },
+    {
+      "epoch": 0.08032861706983113,
+      "grad_norm": 6.234488010406494,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.4821,
+      "step": 44
+    },
+    {
+      "epoch": 0.08215426745778183,
+      "grad_norm": 4.917290210723877,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.8305,
+      "step": 45
+    },
+    {
+      "epoch": 0.08397991784573254,
+      "grad_norm": 4.923922538757324,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.3685,
+      "step": 46
+    },
+    {
+      "epoch": 0.08580556823368325,
+      "grad_norm": 4.869322776794434,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.1955,
+      "step": 47
+    },
+    {
+      "epoch": 0.08763121862163396,
+      "grad_norm": 7.294736385345459,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 3.4359,
+      "step": 48
+    },
+    {
+      "epoch": 0.08945686900958466,
+      "grad_norm": 6.816267967224121,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.4971,
+      "step": 49
+    },
+    {
+      "epoch": 0.09128251939753537,
+      "grad_norm": 17.410608291625977,
+      "learning_rate": 0.0,
+      "loss": 4.105,
+      "step": 50
+    },
+    {
+      "epoch": 0.09128251939753537,
+      "eval_loss": 2.47334361076355,
+      "eval_runtime": 13.6191,
+      "eval_samples_per_second": 67.773,
+      "eval_steps_per_second": 8.517,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3401809133568000.0,
+  "total_flos": 6803618267136000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null