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:ca2703fcf183071968647577e4f87d13b7f25a213baf5dbd544e4593ba4b8da5
+oid sha256:3cdeaca79f290c1140a0971cf6822e010d26967a0af48c035bf2d4e58cb00fb9
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75141177aa5e48ec01ff7facebc3358f2f1bfa54c4396432c2ce2054c4bbd2cb
+oid sha256:2a1ab580e6ce190e0933e45e7820384d7d62bc877daf1bcb1b70231f448a5e6a
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:591276f9abdf5960cf2af3763135c0e40ad3a86ebfac955bb9fc8bae6ca1ff74
+oid sha256:07b54192036e87adbcb0a518b1909dfe69188fb4d07e4ad0b470cc764c463932
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec921036490adafe489586d055596bc944d8ca2226cf1d48e9215b8e54f05ab9
+oid sha256:3f7ebe090d18648495a503c82197c73a5b40c2633d7bc6b0df2abc5d279698cf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad0c674387c0cc0add461e65faa0aecaf1ecd8c445b05ff5892f73541958d7a3
+oid sha256:abe97bc21889f79b128eac0bb26cbb53bad7cd1eb43e967a655d27c04adcccfb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d700d17d478b093bb0b22cc56305dd40a02ee0df21b7e62bd5280d0d66366fb
+oid sha256:3968e3c56fe77c0b4d7b8c5acc2d72ad0f9c95d4b5dd62302eb34008f932d7c8
 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": 1.0297096967697144,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01390578828437337,
+  "best_metric": 1.0076379776000977,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.02781157656874674,
   "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": 87.591,
       "eval_steps_per_second": 10.949,
       "step": 25
+    },
+    {
+      "epoch": 0.014462019815748305,
+      "grad_norm": 0.09419423341751099,
+      "learning_rate": 5e-05,
+      "loss": 0.4267,
+      "step": 26
+    },
+    {
+      "epoch": 0.01501825134712324,
+      "grad_norm": 0.1334831416606903,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.6666,
+      "step": 27
+    },
+    {
+      "epoch": 0.015574482878498174,
+      "grad_norm": 0.144070565700531,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.6366,
+      "step": 28
+    },
+    {
+      "epoch": 0.01613071440987311,
+      "grad_norm": 0.1303204894065857,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.633,
+      "step": 29
+    },
+    {
+      "epoch": 0.016686945941248043,
+      "grad_norm": 0.14772789180278778,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.732,
+      "step": 30
+    },
+    {
+      "epoch": 0.01724317747262298,
+      "grad_norm": 0.1663038730621338,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7748,
+      "step": 31
+    },
+    {
+      "epoch": 0.017799409003997915,
+      "grad_norm": 0.21385891735553741,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.008,
+      "step": 32
+    },
+    {
+      "epoch": 0.01835564053537285,
+      "grad_norm": 0.29136043787002563,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.1981,
+      "step": 33
+    },
+    {
+      "epoch": 0.018911872066747784,
+      "grad_norm": 0.358648419380188,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.2509,
+      "step": 34
+    },
+    {
+      "epoch": 0.01946810359812272,
+      "grad_norm": 0.40348002314567566,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.3403,
+      "step": 35
+    },
+    {
+      "epoch": 0.020024335129497653,
+      "grad_norm": 0.5576580762863159,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.385,
+      "step": 36
+    },
+    {
+      "epoch": 0.020580566660872587,
+      "grad_norm": 0.9451633095741272,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.5531,
+      "step": 37
+    },
+    {
+      "epoch": 0.021136798192247522,
+      "grad_norm": 0.10654843598604202,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4292,
+      "step": 38
+    },
+    {
+      "epoch": 0.021693029723622456,
+      "grad_norm": 0.10906118899583817,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.5853,
+      "step": 39
+    },
+    {
+      "epoch": 0.022249261254997394,
+      "grad_norm": 0.1391826868057251,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7037,
+      "step": 40
+    },
+    {
+      "epoch": 0.02280549278637233,
+      "grad_norm": 0.13406039774417877,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6435,
+      "step": 41
+    },
+    {
+      "epoch": 0.023361724317747263,
+      "grad_norm": 0.1331794112920761,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6847,
+      "step": 42
+    },
+    {
+      "epoch": 0.023917955849122197,
+      "grad_norm": 0.1532629281282425,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8577,
+      "step": 43
+    },
+    {
+      "epoch": 0.024474187380497132,
+      "grad_norm": 0.17151039838790894,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8592,
+      "step": 44
+    },
+    {
+      "epoch": 0.025030418911872066,
+      "grad_norm": 0.24025927484035492,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.1217,
+      "step": 45
+    },
+    {
+      "epoch": 0.025586650443247,
+      "grad_norm": 0.2666977047920227,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.1314,
+      "step": 46
+    },
+    {
+      "epoch": 0.026142881974621935,
+      "grad_norm": 0.3222261369228363,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.2233,
+      "step": 47
+    },
+    {
+      "epoch": 0.026699113505996873,
+      "grad_norm": 0.42572563886642456,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.3975,
+      "step": 48
+    },
+    {
+      "epoch": 0.027255345037371807,
+      "grad_norm": 0.5978182554244995,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.3051,
+      "step": 49
+    },
+    {
+      "epoch": 0.02781157656874674,
+      "grad_norm": 1.0638318061828613,
+      "learning_rate": 0.0,
+      "loss": 1.7991,
+      "step": 50
+    },
+    {
+      "epoch": 0.02781157656874674,
+      "eval_loss": 1.0076379776000977,
+      "eval_runtime": 138.2815,
+      "eval_samples_per_second": 87.589,
+      "eval_steps_per_second": 10.949,
+      "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": 5.304303857382195e+16,
+  "total_flos": 1.0608607728186163e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null