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:ae017579b1c1e5e7a75b6c39858a2c7c15165ef4d35de62c434bf1cf7080ea8f
+oid sha256:0c4b36ebddfbe58ce298e3aa08b88b43b5625c1581fa83373d055ecb84fd2f11
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20052cce896ac2434a17da8b6ed2e30b049eadefe3ccf497c14fe4178f122b87
+oid sha256:056bd18d8f9acc347758931546c4b724617f8abaf397ab45a33b972e16e3d058
 size 1001863522

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bad946cfbdb730bae2378559405d1188d3bda3470a8145207f1bdbee4577ff6
+oid sha256:c2a60c1cd826359b54f21f5411c5394c3e010fab6f40dfb3551f3cd99539c14d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a09a634c997cd3522fb1e58091863c97999a6b4a50d65c199e6c97414e22a9d
+oid sha256:dbe351bba2a4e6a258c9b63519088252d60c0cd6020c8345c7b20f1f00d2f880
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08c16773f1c73ee37abd9ca9e39d6218df4b910737959893b92541c204c5e8dc
+oid sha256:777eaa9c09a3a967d2cc298ed1fddfe35eccc39df36108fd151f3f138636e6f3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4037a66c2d5761bcda4d837e52c0b5100d01e17671386fe5354b02a7b469a5c
+oid sha256:82f69b315033382359e2b423aab21a2fc102518ce437bd703b84a334084ae0ac
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.011089812964200974,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.45662100456621,
+  "epoch": 0.91324200913242,
   "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": 10.397,
       "eval_steps_per_second": 1.324,
       "step": 25
+    },
+    {
+      "epoch": 0.4748858447488584,
+      "grad_norm": 0.5133668780326843,
+      "learning_rate": 5e-05,
+      "loss": 0.0056,
+      "step": 26
+    },
+    {
+      "epoch": 0.4931506849315068,
+      "grad_norm": 1.287654995918274,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0164,
+      "step": 27
+    },
+    {
+      "epoch": 0.5114155251141552,
+      "grad_norm": 0.18463000655174255,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0036,
+      "step": 28
+    },
+    {
+      "epoch": 0.5296803652968036,
+      "grad_norm": 0.03979532793164253,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0009,
+      "step": 29
+    },
+    {
+      "epoch": 0.547945205479452,
+      "grad_norm": 0.01812467910349369,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0005,
+      "step": 30
+    },
+    {
+      "epoch": 0.5662100456621004,
+      "grad_norm": 0.008781279437243938,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0002,
+      "step": 31
+    },
+    {
+      "epoch": 0.5844748858447488,
+      "grad_norm": 0.0651770532131195,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0015,
+      "step": 32
+    },
+    {
+      "epoch": 0.6027397260273972,
+      "grad_norm": 0.01783256232738495,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0005,
+      "step": 33
+    },
+    {
+      "epoch": 0.6210045662100456,
+      "grad_norm": 0.003473809454590082,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0001,
+      "step": 34
+    },
+    {
+      "epoch": 0.639269406392694,
+      "grad_norm": 0.003669138764962554,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0001,
+      "step": 35
+    },
+    {
+      "epoch": 0.6575342465753424,
+      "grad_norm": 0.03214825317263603,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0005,
+      "step": 36
+    },
+    {
+      "epoch": 0.6757990867579908,
+      "grad_norm": 0.4901163578033447,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0857,
+      "step": 37
+    },
+    {
+      "epoch": 0.6940639269406392,
+      "grad_norm": 0.011674696579575539,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0002,
+      "step": 38
+    },
+    {
+      "epoch": 0.7123287671232876,
+      "grad_norm": 0.009491109289228916,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0002,
+      "step": 39
+    },
+    {
+      "epoch": 0.730593607305936,
+      "grad_norm": 0.006969192996621132,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0002,
+      "step": 40
+    },
+    {
+      "epoch": 0.7488584474885844,
+      "grad_norm": 0.003321270225569606,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0001,
+      "step": 41
+    },
+    {
+      "epoch": 0.7671232876712328,
+      "grad_norm": 0.024109523743391037,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0005,
+      "step": 42
+    },
+    {
+      "epoch": 0.7853881278538812,
+      "grad_norm": 0.009124420583248138,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0002,
+      "step": 43
+    },
+    {
+      "epoch": 0.8036529680365296,
+      "grad_norm": 0.004407109692692757,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0002,
+      "step": 44
+    },
+    {
+      "epoch": 0.821917808219178,
+      "grad_norm": 0.003542846068739891,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0001,
+      "step": 45
+    },
+    {
+      "epoch": 0.8401826484018264,
+      "grad_norm": 0.014414651319384575,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0003,
+      "step": 46
+    },
+    {
+      "epoch": 0.8584474885844748,
+      "grad_norm": 0.1259673833847046,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.003,
+      "step": 47
+    },
+    {
+      "epoch": 0.8767123287671232,
+      "grad_norm": 0.01385512761771679,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0003,
+      "step": 48
+    },
+    {
+      "epoch": 0.8949771689497716,
+      "grad_norm": 0.005186452530324459,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0002,
+      "step": 49
+    },
+    {
+      "epoch": 0.91324200913242,
+      "grad_norm": 0.5546965003013611,
+      "learning_rate": 0.0,
+      "loss": 0.1002,
+      "step": 50
+    },
+    {
+      "epoch": 0.91324200913242,
+      "eval_loss": 0.01725011318922043,
+      "eval_runtime": 69.4723,
+      "eval_samples_per_second": 5.311,
+      "eval_steps_per_second": 0.677,
+      "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": 9.97605621643608e+17,
+  "total_flos": 1.9974437372229059e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null