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:ec159972588e1e9412073285cfb268a38424d2b96ee12b1b35749023719d0b6b
+oid sha256:a4b1b274c329a27ee220bf56c92d0ace7b9017a77c268bf0ee1e37a81f620096
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9679eae8875071a36578b871b071085630982f2f167521f652403e769b030a0a
+oid sha256:187088ca9f41bddb150a5e5687e4b4b45a1cc649b7f4990efbe71ee8847b0f0b
 size 243802484

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3d87de47daf871a14b2443ec4b57b05bdec6962dde441e7e2a5ce44470f7bb7
+oid sha256:c9d4fefa40ec1ecedf2ca60fea54d152650fb45aea678540d9daa6b7dd6309e9
 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": 1.125113606452942,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.11350737797956867,
+  "epoch": 0.22701475595913734,
   "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": 36.974,
       "eval_steps_per_second": 4.684,
       "step": 25
+    },
+    {
+      "epoch": 0.11804767309875142,
+      "grad_norm": 0.45543304085731506,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.2383,
+      "step": 26
+    },
+    {
+      "epoch": 0.12258796821793416,
+      "grad_norm": 0.5423667430877686,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.1882,
+      "step": 27
+    },
+    {
+      "epoch": 0.1271282633371169,
+      "grad_norm": 0.45114219188690186,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.1249,
+      "step": 28
+    },
+    {
+      "epoch": 0.13166855845629966,
+      "grad_norm": 0.4604540467262268,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.1833,
+      "step": 29
+    },
+    {
+      "epoch": 0.1362088535754824,
+      "grad_norm": 0.49046003818511963,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.1793,
+      "step": 30
+    },
+    {
+      "epoch": 0.14074914869466515,
+      "grad_norm": 0.5115222334861755,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.1548,
+      "step": 31
+    },
+    {
+      "epoch": 0.1452894438138479,
+      "grad_norm": 0.48150011897087097,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.0399,
+      "step": 32
+    },
+    {
+      "epoch": 0.14982973893303064,
+      "grad_norm": 0.5298136472702026,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.1891,
+      "step": 33
+    },
+    {
+      "epoch": 0.1543700340522134,
+      "grad_norm": 0.4817681908607483,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.0856,
+      "step": 34
+    },
+    {
+      "epoch": 0.15891032917139614,
+      "grad_norm": 0.5052300095558167,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.0734,
+      "step": 35
+    },
+    {
+      "epoch": 0.16345062429057888,
+      "grad_norm": 0.5191230177879333,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.0951,
+      "step": 36
+    },
+    {
+      "epoch": 0.16799091940976163,
+      "grad_norm": 0.49014902114868164,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.0811,
+      "step": 37
+    },
+    {
+      "epoch": 0.17253121452894438,
+      "grad_norm": 0.558128297328949,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.1841,
+      "step": 38
+    },
+    {
+      "epoch": 0.17707150964812712,
+      "grad_norm": 0.5571663975715637,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.0598,
+      "step": 39
+    },
+    {
+      "epoch": 0.18161180476730987,
+      "grad_norm": 0.5573685765266418,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.013,
+      "step": 40
+    },
+    {
+      "epoch": 0.18615209988649262,
+      "grad_norm": 0.5625842213630676,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.0995,
+      "step": 41
+    },
+    {
+      "epoch": 0.19069239500567536,
+      "grad_norm": 0.6718692183494568,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.0627,
+      "step": 42
+    },
+    {
+      "epoch": 0.1952326901248581,
+      "grad_norm": 0.6249908208847046,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.0266,
+      "step": 43
+    },
+    {
+      "epoch": 0.19977298524404086,
+      "grad_norm": 0.6505060791969299,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.0113,
+      "step": 44
+    },
+    {
+      "epoch": 0.2043132803632236,
+      "grad_norm": 0.7362877130508423,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.0885,
+      "step": 45
+    },
+    {
+      "epoch": 0.20885357548240635,
+      "grad_norm": 0.7237470746040344,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.9956,
+      "step": 46
+    },
+    {
+      "epoch": 0.2133938706015891,
+      "grad_norm": 0.8162877559661865,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.0847,
+      "step": 47
+    },
+    {
+      "epoch": 0.21793416572077184,
+      "grad_norm": 0.8599759340286255,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.0561,
+      "step": 48
+    },
+    {
+      "epoch": 0.2224744608399546,
+      "grad_norm": 1.2603548765182495,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.0098,
+      "step": 49
+    },
+    {
+      "epoch": 0.22701475595913734,
+      "grad_norm": 1.499512791633606,
+      "learning_rate": 0.0,
+      "loss": 1.2965,
+      "step": 50
+    },
+    {
+      "epoch": 0.22701475595913734,
+      "eval_loss": 1.127669095993042,
+      "eval_runtime": 10.241,
+      "eval_samples_per_second": 36.227,
+      "eval_steps_per_second": 4.589,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8820793244909568.0,
+  "total_flos": 1.5934336184352768e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null