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:cda8d0b05da30063260d1fe3ba165c38615d53623f4c17020b70260a8529757b
+oid sha256:9f80e777b1da1d01555f1fc3a859cdf7f932fbd61556a4adb9d56a16d99ef725
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ab9a994209582cea1796ad3c948c0393310ac19d6be4394b3d2ce17ba8a99da
+oid sha256:d9d35f3a875f43856192f3a8a120a4ccd0e3f43036a320181e6e77fdda4f6763
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14833899d51ab320cf3170fa4d675f844b0c5db254515da9b096d5cf1c5fcb66
+oid sha256:c6ab01f4c9d42b00b05b668ad17a2a34be28c6c0271b3ec70b76a141bc3f622d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:719b4d5c2dc4989a7135ec9c066b243dfca46fe23e90bcd7de278bfd21dd9f03
+oid sha256:11abf9e818626eaf305e377b76e9ada1ed45f1390acf9d253410b0ce59baee48
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db84059c88a626c8d9336e2d537d16bb731de5b42ab3a5cb1d6f251610f5bc5c
+oid sha256:6e86dc448c66be7271348cbd247a1a40b51e700b6e1d537ca4b4dcb8fa866207
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d74422640230f6a8c3f3c5b2b7fd9cea63a69d2ed6c3d0e65afb86ec3e151b38
+oid sha256:071925676dd610c74b0625e4dc0aada775c9350e777321d2549e6d356abbcbb1
 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": 3.9233860969543457,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.044958974935371473,
+  "best_metric": 3.659489154815674,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.08991794987074295,
   "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": 37.609,
       "eval_steps_per_second": 4.707,
       "step": 25
+    },
+    {
+      "epoch": 0.04675733393278633,
+      "grad_norm": 1.887658953666687,
+      "learning_rate": 5e-05,
+      "loss": 3.5318,
+      "step": 26
+    },
+    {
+      "epoch": 0.04855569293020119,
+      "grad_norm": 1.7948553562164307,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.3642,
+      "step": 27
+    },
+    {
+      "epoch": 0.05035405192761605,
+      "grad_norm": 1.6475787162780762,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.3877,
+      "step": 28
+    },
+    {
+      "epoch": 0.05215241092503091,
+      "grad_norm": 1.607811450958252,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.4879,
+      "step": 29
+    },
+    {
+      "epoch": 0.05395076992244577,
+      "grad_norm": 1.7005120515823364,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.6429,
+      "step": 30
+    },
+    {
+      "epoch": 0.05574912891986063,
+      "grad_norm": 1.7422455549240112,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.587,
+      "step": 31
+    },
+    {
+      "epoch": 0.057547487917275486,
+      "grad_norm": 1.6355663537979126,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.5677,
+      "step": 32
+    },
+    {
+      "epoch": 0.059345846914690345,
+      "grad_norm": 1.731115460395813,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.7815,
+      "step": 33
+    },
+    {
+      "epoch": 0.061144205912105204,
+      "grad_norm": 1.6795060634613037,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.7316,
+      "step": 34
+    },
+    {
+      "epoch": 0.06294256490952006,
+      "grad_norm": 1.6759228706359863,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.8109,
+      "step": 35
+    },
+    {
+      "epoch": 0.06474092390693492,
+      "grad_norm": 1.653753399848938,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 4.1712,
+      "step": 36
+    },
+    {
+      "epoch": 0.06653928290434978,
+      "grad_norm": 1.7878714799880981,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 4.1051,
+      "step": 37
+    },
+    {
+      "epoch": 0.06833764190176464,
+      "grad_norm": 1.6746171712875366,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.97,
+      "step": 38
+    },
+    {
+      "epoch": 0.0701360008991795,
+      "grad_norm": 1.775249719619751,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.8569,
+      "step": 39
+    },
+    {
+      "epoch": 0.07193435989659436,
+      "grad_norm": 1.6178361177444458,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.9099,
+      "step": 40
+    },
+    {
+      "epoch": 0.07373271889400922,
+      "grad_norm": 1.8096075057983398,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.1256,
+      "step": 41
+    },
+    {
+      "epoch": 0.07553107789142408,
+      "grad_norm": 1.727738857269287,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.3099,
+      "step": 42
+    },
+    {
+      "epoch": 0.07732943688883893,
+      "grad_norm": 1.73582923412323,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.5413,
+      "step": 43
+    },
+    {
+      "epoch": 0.0791277958862538,
+      "grad_norm": 1.7474498748779297,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.7499,
+      "step": 44
+    },
+    {
+      "epoch": 0.08092615488366865,
+      "grad_norm": 1.7811682224273682,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.5255,
+      "step": 45
+    },
+    {
+      "epoch": 0.08272451388108351,
+      "grad_norm": 1.751634955406189,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.8033,
+      "step": 46
+    },
+    {
+      "epoch": 0.08452287287849837,
+      "grad_norm": 1.661466360092163,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.6937,
+      "step": 47
+    },
+    {
+      "epoch": 0.08632123187591323,
+      "grad_norm": 1.6849561929702759,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.9422,
+      "step": 48
+    },
+    {
+      "epoch": 0.08811959087332809,
+      "grad_norm": 1.6296294927597046,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.9785,
+      "step": 49
+    },
+    {
+      "epoch": 0.08991794987074295,
+      "grad_norm": 1.6093735694885254,
+      "learning_rate": 0.0,
+      "loss": 4.2984,
+      "step": 50
+    },
+    {
+      "epoch": 0.08991794987074295,
+      "eval_loss": 3.659489154815674,
+      "eval_runtime": 99.7649,
+      "eval_samples_per_second": 37.558,
+      "eval_steps_per_second": 4.701,
+      "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": 2.8348766388381286e+17,
+  "total_flos": 5.671510799768617e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null