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:c63f4b8f75065a968390faa517af2060e552c62f2f3da3c4aadc74a287c5265c
+oid sha256:3531aa80694a830a953784b5e3436b60aa18ea6ce5d1550050b205fa400c4af8
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2036c9fdef3f679f60f074a16913aef9d7dfd7f8d4512c56bd542849b515d1b8
+oid sha256:a46bca6740c1af85c1c42cf46ceb726fa9cb532f928626a13455af01ba72826b
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:064935db1cd9e018fcc6db2d3b780b787eb48f50d6e2d5c6a79336820f433c8b
+oid sha256:75b91291aaa23420164aab29bc887dc28b41051af11c010c6c020d2587797ebf
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7aee3638b6537bfdf12e2f47265f6811fa7fea818d6478a96514e4abff50588
+oid sha256:4417b2a27b9fa0fe59a7b1a414bf20878d9c230887dd7847bd6be512ae6a7757
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73e1e5562445b035bbfc531dfee6deaa722269039b3c1c0aa79c16c36e08a042
+oid sha256:86b618f092a9684542b1089609d91379877109f6ae854ec0c41eafa57a0f32a8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75bd45967030df1f9164ade6c1b697e32927aa79d718d5499eb6b2a5b9692845
+oid sha256:21710cdeaa431397cbb008d7219074127121fc693481d2ac0a0deec3f6284994
 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": 0.8012549877166748,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.007707871663936795,
+  "best_metric": 0.7913834452629089,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.01541574332787359,
   "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": 15.904,
       "eval_steps_per_second": 1.988,
       "step": 25
+    },
+    {
+      "epoch": 0.008016186530494268,
+      "grad_norm": 0.17478090524673462,
+      "learning_rate": 5e-05,
+      "loss": 0.5289,
+      "step": 26
+    },
+    {
+      "epoch": 0.008324501397051738,
+      "grad_norm": 0.21040455996990204,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.6474,
+      "step": 27
+    },
+    {
+      "epoch": 0.00863281626360921,
+      "grad_norm": 0.2507893741130829,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.688,
+      "step": 28
+    },
+    {
+      "epoch": 0.008941131130166683,
+      "grad_norm": 0.2768246829509735,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7392,
+      "step": 29
+    },
+    {
+      "epoch": 0.009249445996724155,
+      "grad_norm": 0.30327269434928894,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7756,
+      "step": 30
+    },
+    {
+      "epoch": 0.009557760863281627,
+      "grad_norm": 0.3187962770462036,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7812,
+      "step": 31
+    },
+    {
+      "epoch": 0.009866075729839097,
+      "grad_norm": 0.3353966772556305,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8312,
+      "step": 32
+    },
+    {
+      "epoch": 0.01017439059639657,
+      "grad_norm": 0.47117725014686584,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.0347,
+      "step": 33
+    },
+    {
+      "epoch": 0.010482705462954042,
+      "grad_norm": 0.6944525837898254,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9954,
+      "step": 34
+    },
+    {
+      "epoch": 0.010791020329511514,
+      "grad_norm": 0.8677866458892822,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.9753,
+      "step": 35
+    },
+    {
+      "epoch": 0.011099335196068986,
+      "grad_norm": 0.7612897157669067,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.9018,
+      "step": 36
+    },
+    {
+      "epoch": 0.011407650062626458,
+      "grad_norm": 0.713799238204956,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8853,
+      "step": 37
+    },
+    {
+      "epoch": 0.011715964929183928,
+      "grad_norm": 0.21678361296653748,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5908,
+      "step": 38
+    },
+    {
+      "epoch": 0.0120242797957414,
+      "grad_norm": 0.17549093067646027,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.5526,
+      "step": 39
+    },
+    {
+      "epoch": 0.012332594662298873,
+      "grad_norm": 0.18322467803955078,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.626,
+      "step": 40
+    },
+    {
+      "epoch": 0.012640909528856345,
+      "grad_norm": 0.1947597861289978,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6811,
+      "step": 41
+    },
+    {
+      "epoch": 0.012949224395413817,
+      "grad_norm": 0.20802932977676392,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6998,
+      "step": 42
+    },
+    {
+      "epoch": 0.013257539261971289,
+      "grad_norm": 0.22858428955078125,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.7557,
+      "step": 43
+    },
+    {
+      "epoch": 0.01356585412852876,
+      "grad_norm": 0.22575457394123077,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7919,
+      "step": 44
+    },
+    {
+      "epoch": 0.013874168995086231,
+      "grad_norm": 0.26835131645202637,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7941,
+      "step": 45
+    },
+    {
+      "epoch": 0.014182483861643704,
+      "grad_norm": 0.28373661637306213,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.981,
+      "step": 46
+    },
+    {
+      "epoch": 0.014490798728201176,
+      "grad_norm": 0.3139655888080597,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.9227,
+      "step": 47
+    },
+    {
+      "epoch": 0.014799113594758648,
+      "grad_norm": 0.3588656485080719,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.9109,
+      "step": 48
+    },
+    {
+      "epoch": 0.01510742846131612,
+      "grad_norm": 0.4004943072795868,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.9345,
+      "step": 49
+    },
+    {
+      "epoch": 0.01541574332787359,
+      "grad_norm": 0.5666626691818237,
+      "learning_rate": 0.0,
+      "loss": 0.8735,
+      "step": 50
+    },
+    {
+      "epoch": 0.01541574332787359,
+      "eval_loss": 0.7913834452629089,
+      "eval_runtime": 1386.0623,
+      "eval_samples_per_second": 15.765,
+      "eval_steps_per_second": 1.971,
+      "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": 3.013882221376307e+17,
+  "total_flos": 6.046414715465236e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null