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:c675209fd28e581c81be4eb27bc5fe1afe66497f4903d76b6b0b11409a0994c0
+oid sha256:2ac7319a147381dcd68d6ec114465f3b01387bf8e940ba4c3c0bac5d4d509055
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc6d563876275238fb3d73911e1e19e9fd07f952bcea26bfafd9146009ecfa84
+oid sha256:7fa5b049288d32cfe0a1d68652a25e4f3b762a52264debd8b3471ffb0a05d1f1
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78b20c94812b66d771fb2886f8ed3a67b247d2c22a8a49d92655a44f876bcec2
+oid sha256:efb3c2b12d533e9cf792925b48c81fd16a9bb10a625964cb42887e776743ed3c
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23d504e951f907a47cebf36055faa9e3b057e4107de8b3e5b4cda3219951db28
+oid sha256:c54c9f5415a37a24fcc7a1cdfefdc2d2b584030e0aeb656e2e84369cb16eae22
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d2c751655e7f18559d1bbdf1ec13d155e667920c7ac91c6848b460fec21509e
+oid sha256:3c1458a61f249eda592f8a915b2afec1a717b536aa6fafccf6fe154df87d5a3a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6468c9936167df03012866d1771a80d8b5fcbd47c90a98ab4852bc31af499bd4
+oid sha256:381116c8cd2cc48805a42edf99b238581134b3fbd49a6ed4d12b4068af1cf8c8
 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": 1.9013075828552246,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0188821752265861,
+  "best_metric": 1.8846580982208252,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0377643504531722,
   "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": 24.207,
       "eval_steps_per_second": 3.026,
       "step": 25
+    },
+    {
+      "epoch": 0.019637462235649546,
+      "grad_norm": 6.776696681976318,
+      "learning_rate": 5e-05,
+      "loss": 1.8883,
+      "step": 26
+    },
+    {
+      "epoch": 0.02039274924471299,
+      "grad_norm": 7.159153938293457,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.9433,
+      "step": 27
+    },
+    {
+      "epoch": 0.021148036253776436,
+      "grad_norm": 6.303608417510986,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.9532,
+      "step": 28
+    },
+    {
+      "epoch": 0.02190332326283988,
+      "grad_norm": 5.578258037567139,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.9145,
+      "step": 29
+    },
+    {
+      "epoch": 0.022658610271903322,
+      "grad_norm": 5.26440954208374,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.8993,
+      "step": 30
+    },
+    {
+      "epoch": 0.023413897280966767,
+      "grad_norm": 5.3654985427856445,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.8948,
+      "step": 31
+    },
+    {
+      "epoch": 0.02416918429003021,
+      "grad_norm": 5.753653526306152,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.9263,
+      "step": 32
+    },
+    {
+      "epoch": 0.024924471299093656,
+      "grad_norm": 5.539957523345947,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.881,
+      "step": 33
+    },
+    {
+      "epoch": 0.0256797583081571,
+      "grad_norm": 5.666808128356934,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.8992,
+      "step": 34
+    },
+    {
+      "epoch": 0.026435045317220542,
+      "grad_norm": 6.2148332595825195,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.8657,
+      "step": 35
+    },
+    {
+      "epoch": 0.027190332326283987,
+      "grad_norm": 6.8241424560546875,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.8997,
+      "step": 36
+    },
+    {
+      "epoch": 0.027945619335347432,
+      "grad_norm": 7.615296840667725,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.8148,
+      "step": 37
+    },
+    {
+      "epoch": 0.028700906344410877,
+      "grad_norm": 6.124070167541504,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8583,
+      "step": 38
+    },
+    {
+      "epoch": 0.02945619335347432,
+      "grad_norm": 4.771143913269043,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.9552,
+      "step": 39
+    },
+    {
+      "epoch": 0.030211480362537766,
+      "grad_norm": 4.553677558898926,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.888,
+      "step": 40
+    },
+    {
+      "epoch": 0.030966767371601207,
+      "grad_norm": 4.59923791885376,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.9062,
+      "step": 41
+    },
+    {
+      "epoch": 0.03172205438066465,
+      "grad_norm": 5.005655288696289,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.9308,
+      "step": 42
+    },
+    {
+      "epoch": 0.0324773413897281,
+      "grad_norm": 4.9266486167907715,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.909,
+      "step": 43
+    },
+    {
+      "epoch": 0.03323262839879154,
+      "grad_norm": 5.109602928161621,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.9391,
+      "step": 44
+    },
+    {
+      "epoch": 0.033987915407854986,
+      "grad_norm": 4.969670295715332,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.9203,
+      "step": 45
+    },
+    {
+      "epoch": 0.03474320241691843,
+      "grad_norm": 5.118282318115234,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.8753,
+      "step": 46
+    },
+    {
+      "epoch": 0.035498489425981876,
+      "grad_norm": 5.58473539352417,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.864,
+      "step": 47
+    },
+    {
+      "epoch": 0.03625377643504532,
+      "grad_norm": 5.797006130218506,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.8489,
+      "step": 48
+    },
+    {
+      "epoch": 0.03700906344410876,
+      "grad_norm": 6.1970906257629395,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.7839,
+      "step": 49
+    },
+    {
+      "epoch": 0.0377643504531722,
+      "grad_norm": 7.363020896911621,
+      "learning_rate": 0.0,
+      "loss": 1.7918,
+      "step": 50
+    },
+    {
+      "epoch": 0.0377643504531722,
+      "eval_loss": 1.8846580982208252,
+      "eval_runtime": 366.273,
+      "eval_samples_per_second": 24.353,
+      "eval_steps_per_second": 3.044,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null