Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70af637dff5a760131f568f8ae519d6b28c368072e247feb458e14a3691f44b2
+oid sha256:5dfb158b0f8325a81bf65433739c917c751234c9ed0a34de4eed55565a2c9acf
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76a0f9542d719558675318b27553df24e7389d78872103d902c2e303504def59
+oid sha256:37b6db88a554d1768d204edecb7b81b8f17fae74a315dc766120f82bc54add75
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88d99ef26f56fac17aa539d947794f2a183726a5af097762cf569d81c824e911
+oid sha256:052c144a65e9bfd062da20365b39c3034e77d1b4642ea6ea0017cbf667143bac
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5bde94f9b34aa85a006d644a5de35f1f3be8be9b07a947e231fb410a21bc17a
+oid sha256:4492093515079c35cc94bb7c529ae03a5ba31e0f3c47eed2a4a06ecd1d834859
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7825afd2d569e06a78067676dcdb223b918b7c5fa7134a0ba3a2ab5d68ee300c
+oid sha256:a27a9cb059c9f9be5d32d1094ae3e879dde56f1715b0c3331a7e1b53a72dc3f9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec32e3367caf041ef499976aa7367063c9555d59e5643d27a779851497ea08d7
+oid sha256:0f5e89226d16b180c8f432e181a69a287e36124b582c22ec5fdf1d89dae56ede
 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": 0.0021165155339986086,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06363347120585428,
+  "best_metric": 0.0017724342178553343,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12726694241170855,
   "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": 41.349,
       "eval_steps_per_second": 5.171,
       "step": 25
+    },
+    {
+      "epoch": 0.06617881005408845,
+      "grad_norm": 0.02505287528038025,
+      "learning_rate": 5e-05,
+      "loss": 0.0005,
+      "step": 26
+    },
+    {
+      "epoch": 0.06872414890232262,
+      "grad_norm": 0.09753460437059402,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0009,
+      "step": 27
+    },
+    {
+      "epoch": 0.07126948775055679,
+      "grad_norm": 0.07497745752334595,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0007,
+      "step": 28
+    },
+    {
+      "epoch": 0.07381482659879096,
+      "grad_norm": 0.04772750288248062,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0005,
+      "step": 29
+    },
+    {
+      "epoch": 0.07636016544702513,
+      "grad_norm": 0.02046908438205719,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0003,
+      "step": 30
+    },
+    {
+      "epoch": 0.0789055042952593,
+      "grad_norm": 0.026618817821145058,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0004,
+      "step": 31
+    },
+    {
+      "epoch": 0.08145084314349348,
+      "grad_norm": 0.018914973363280296,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0003,
+      "step": 32
+    },
+    {
+      "epoch": 0.08399618199172765,
+      "grad_norm": 0.010556931607425213,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0003,
+      "step": 33
+    },
+    {
+      "epoch": 0.08654152083996182,
+      "grad_norm": 0.012361941859126091,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0003,
+      "step": 34
+    },
+    {
+      "epoch": 0.08908685968819599,
+      "grad_norm": 0.010758999735116959,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0003,
+      "step": 35
+    },
+    {
+      "epoch": 0.09163219853643016,
+      "grad_norm": 0.012884964235126972,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0003,
+      "step": 36
+    },
+    {
+      "epoch": 0.09417753738466433,
+      "grad_norm": 8.187239646911621,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0799,
+      "step": 37
+    },
+    {
+      "epoch": 0.0967228762328985,
+      "grad_norm": 0.14753367006778717,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0006,
+      "step": 38
+    },
+    {
+      "epoch": 0.09926821508113268,
+      "grad_norm": 0.006080153398215771,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0002,
+      "step": 39
+    },
+    {
+      "epoch": 0.10181355392936685,
+      "grad_norm": 0.005331439431756735,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0002,
+      "step": 40
+    },
+    {
+      "epoch": 0.10435889277760102,
+      "grad_norm": 0.005517337471246719,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0002,
+      "step": 41
+    },
+    {
+      "epoch": 0.10690423162583519,
+      "grad_norm": 0.0055676475167274475,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0002,
+      "step": 42
+    },
+    {
+      "epoch": 0.10944957047406936,
+      "grad_norm": 0.00436694361269474,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0002,
+      "step": 43
+    },
+    {
+      "epoch": 0.11199490932230353,
+      "grad_norm": 0.00402417266741395,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0001,
+      "step": 44
+    },
+    {
+      "epoch": 0.1145402481705377,
+      "grad_norm": 0.004294692073017359,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0001,
+      "step": 45
+    },
+    {
+      "epoch": 0.11708558701877188,
+      "grad_norm": 0.0037219019141048193,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0001,
+      "step": 46
+    },
+    {
+      "epoch": 0.11963092586700605,
+      "grad_norm": 0.004236804321408272,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0002,
+      "step": 47
+    },
+    {
+      "epoch": 0.12217626471524022,
+      "grad_norm": 0.010510016232728958,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0003,
+      "step": 48
+    },
+    {
+      "epoch": 0.12472160356347439,
+      "grad_norm": 0.014029012061655521,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0003,
+      "step": 49
+    },
+    {
+      "epoch": 0.12726694241170855,
+      "grad_norm": 10.742281913757324,
+      "learning_rate": 0.0,
+      "loss": 1.1588,
+      "step": 50
+    },
+    {
+      "epoch": 0.12726694241170855,
+      "eval_loss": 0.0017724342178553343,
+      "eval_runtime": 64.0427,
+      "eval_samples_per_second": 41.332,
+      "eval_steps_per_second": 5.168,
+      "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": 2.631221648430203e+17,
+  "total_flos": 5.260799806149755e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null