Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fe1545aa7bba18d86342ca413f1ad8a6e8ab90f8a9918716932171b01d1ce18
+oid sha256:6182900296463f398b3e017d2a714cd57ca934396131027be69fb76589d48be4
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51cc47858cf791c7d899dd1cbe85fc9c8622cc4e3b6ca74f7f07a8b7d31707e8
+oid sha256:d1fe0c7b90773ff855db437a294115db21cd8ee8c5bc0161b463427f71e2a709
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38e1ddb23afa2e296b14836e20e2ca9a75c65fee5b88f92f611363621dd11a26
+oid sha256:2575b0780e8f916aed1cf378dd7b132d9d137358d0b785c2a0f09675acbbc181
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e5a05a511d9a48b42765fcc16350df17a308181d846566182a033e0e010665
+oid sha256:de6d0aa2c08d32270969bce0c7780d1eb2800c0d0b3585d172124e2322115587
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebfb9d036be10b4b32fef0914fd0826c9e2bbe50b3e604d9c85bc69823fff844
+oid sha256:165a96ac848454f809561f1b6e4f43abae4cb63f2da569865d1e01fe42c5376a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:601c26cb85598f859d33b753b50afe5eb40d773e74f084d6a140914620d60e14
+oid sha256:d608a3f3ad33bcb4bb9728cdbfa2d961740da2d8508c84d4d5f7e0cf58b4d95f
 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": 1.1770575046539307,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3714020427112349,
+  "best_metric": 0.58182692527771,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7428040854224698,
   "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": 87.976,
       "eval_steps_per_second": 11.045,
       "step": 25
+    },
+    {
+      "epoch": 0.3862581244196843,
+      "grad_norm": 36.5875129699707,
+      "learning_rate": 5e-05,
+      "loss": 1.5001,
+      "step": 26
+    },
+    {
+      "epoch": 0.4011142061281337,
+      "grad_norm": 34.303001403808594,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.4433,
+      "step": 27
+    },
+    {
+      "epoch": 0.4159702878365831,
+      "grad_norm": 23.18646240234375,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.1508,
+      "step": 28
+    },
+    {
+      "epoch": 0.4308263695450325,
+      "grad_norm": 11.81425952911377,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.8306,
+      "step": 29
+    },
+    {
+      "epoch": 0.4456824512534819,
+      "grad_norm": 2.6169583797454834,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7217,
+      "step": 30
+    },
+    {
+      "epoch": 0.4605385329619313,
+      "grad_norm": 3.431042194366455,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.6407,
+      "step": 31
+    },
+    {
+      "epoch": 0.4753946146703807,
+      "grad_norm": 4.28667688369751,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.6873,
+      "step": 32
+    },
+    {
+      "epoch": 0.49025069637883006,
+      "grad_norm": 4.567568302154541,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.7423,
+      "step": 33
+    },
+    {
+      "epoch": 0.5051067780872794,
+      "grad_norm": 4.059289932250977,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6076,
+      "step": 34
+    },
+    {
+      "epoch": 0.5199628597957289,
+      "grad_norm": 3.825510263442993,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.6326,
+      "step": 35
+    },
+    {
+      "epoch": 0.5348189415041783,
+      "grad_norm": 3.840282917022705,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.6146,
+      "step": 36
+    },
+    {
+      "epoch": 0.5496750232126276,
+      "grad_norm": 3.1612565517425537,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.592,
+      "step": 37
+    },
+    {
+      "epoch": 0.564531104921077,
+      "grad_norm": 7.4375152587890625,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6791,
+      "step": 38
+    },
+    {
+      "epoch": 0.5793871866295265,
+      "grad_norm": 9.302700996398926,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.7181,
+      "step": 39
+    },
+    {
+      "epoch": 0.5942432683379758,
+      "grad_norm": 10.623868942260742,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7565,
+      "step": 40
+    },
+    {
+      "epoch": 0.6090993500464252,
+      "grad_norm": 9.322834014892578,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7648,
+      "step": 41
+    },
+    {
+      "epoch": 0.6239554317548747,
+      "grad_norm": 8.413629531860352,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7066,
+      "step": 42
+    },
+    {
+      "epoch": 0.6388115134633241,
+      "grad_norm": 8.376091957092285,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6616,
+      "step": 43
+    },
+    {
+      "epoch": 0.6536675951717734,
+      "grad_norm": 5.510131359100342,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6197,
+      "step": 44
+    },
+    {
+      "epoch": 0.6685236768802229,
+      "grad_norm": 3.85404109954834,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6553,
+      "step": 45
+    },
+    {
+      "epoch": 0.6833797585886723,
+      "grad_norm": 3.293433904647827,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5575,
+      "step": 46
+    },
+    {
+      "epoch": 0.6982358402971216,
+      "grad_norm": 2.279066324234009,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.5872,
+      "step": 47
+    },
+    {
+      "epoch": 0.713091922005571,
+      "grad_norm": 1.610314965248108,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5384,
+      "step": 48
+    },
+    {
+      "epoch": 0.7279480037140205,
+      "grad_norm": 2.1705985069274902,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.5126,
+      "step": 49
+    },
+    {
+      "epoch": 0.7428040854224698,
+      "grad_norm": 7.541657447814941,
+      "learning_rate": 0.0,
+      "loss": 0.6703,
+      "step": 50
+    },
+    {
+      "epoch": 0.7428040854224698,
+      "eval_loss": 0.58182692527771,
+      "eval_runtime": 5.1498,
+      "eval_samples_per_second": 88.16,
+      "eval_steps_per_second": 11.068,
+      "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": 5.300992813406618e+16,
+  "total_flos": 1.0598674582837658e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null