Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:708dc087ced38cf58974b2bff4c67e45ecd875aab1cce17d0494d0a07b15ad37
+oid sha256:48f830125a3b6e8ab69c3fbc0505135fb1c2aeeb9b5aa68cf108a0f95852e226
 size 203456160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaeb0cd72edcd017fbddc377d01d8e78a711b8f48edebb13b4dcb93a8958d870
+oid sha256:e887af0170b0d4ddfabb27bf43385ca1dd823a4812538f4a85a9a13ab9edcdeb
 size 407121750

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36a4b7c47896bb024858cc9e47faf4058227bfdbcfc2f7f9ded65fd49a4034cf
+oid sha256:a8babef3d3b0a76df24a05ebcd5bfca5ec97575f54fd40240c2ae433da8ea658
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a470e3f406cf84d6124d5ba552a5fd27d267bbc4ae80e5ab1d0618a75b80be52
+oid sha256:5d9d21821ec2ab14e76f9f3925783a981eab629732723c72b8669e4de73ffb23
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03f54bbbd9383bbd5d10956a47be05af8894728f29f673eea4a1dedb1b6554f8
+oid sha256:d894b77b1e8dea5003540e95b5dbe6d652edd3dbc5a5f7148bb3ce8730153708
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e5fe73b006a109520e305232d1807d79ee5c8c59eaa0c75919632ee5b776074
+oid sha256:738fbed2243fea0719776ca6f267174b7190f11840653259d730c9afbed6f063
 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": 0.3561660051345825,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.29542097488921715,
+  "best_metric": 0.35179558396339417,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5908419497784343,
   "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": 23.747,
       "eval_steps_per_second": 3.0,
       "step": 25
+    },
+    {
+      "epoch": 0.3072378138847858,
+      "grad_norm": 0.7805519700050354,
+      "learning_rate": 5e-05,
+      "loss": 0.3636,
+      "step": 26
+    },
+    {
+      "epoch": 0.3190546528803545,
+      "grad_norm": 3.7027106285095215,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3872,
+      "step": 27
+    },
+    {
+      "epoch": 0.3308714918759232,
+      "grad_norm": 0.6524713039398193,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3544,
+      "step": 28
+    },
+    {
+      "epoch": 0.34268833087149186,
+      "grad_norm": 0.9396346807479858,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3462,
+      "step": 29
+    },
+    {
+      "epoch": 0.35450516986706054,
+      "grad_norm": 1.9516257047653198,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.3545,
+      "step": 30
+    },
+    {
+      "epoch": 0.3663220088626292,
+      "grad_norm": 0.5772966742515564,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.3595,
+      "step": 31
+    },
+    {
+      "epoch": 0.37813884785819796,
+      "grad_norm": 0.86551433801651,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3441,
+      "step": 32
+    },
+    {
+      "epoch": 0.38995568685376664,
+      "grad_norm": 0.8409296870231628,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.3684,
+      "step": 33
+    },
+    {
+      "epoch": 0.4017725258493353,
+      "grad_norm": 2.4118385314941406,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3616,
+      "step": 34
+    },
+    {
+      "epoch": 0.413589364844904,
+      "grad_norm": 0.6091898679733276,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3364,
+      "step": 35
+    },
+    {
+      "epoch": 0.4254062038404727,
+      "grad_norm": 0.6151113510131836,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3399,
+      "step": 36
+    },
+    {
+      "epoch": 0.43722304283604135,
+      "grad_norm": 1.0913517475128174,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3344,
+      "step": 37
+    },
+    {
+      "epoch": 0.44903988183161003,
+      "grad_norm": 2.2895851135253906,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3643,
+      "step": 38
+    },
+    {
+      "epoch": 0.4608567208271787,
+      "grad_norm": 4.044822692871094,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4437,
+      "step": 39
+    },
+    {
+      "epoch": 0.4726735598227474,
+      "grad_norm": 3.535907506942749,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4124,
+      "step": 40
+    },
+    {
+      "epoch": 0.4844903988183161,
+      "grad_norm": 3.7408993244171143,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.419,
+      "step": 41
+    },
+    {
+      "epoch": 0.4963072378138848,
+      "grad_norm": 3.162598133087158,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3991,
+      "step": 42
+    },
+    {
+      "epoch": 0.5081240768094535,
+      "grad_norm": 1.1125186681747437,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.3423,
+      "step": 43
+    },
+    {
+      "epoch": 0.5199409158050221,
+      "grad_norm": 0.45383548736572266,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3333,
+      "step": 44
+    },
+    {
+      "epoch": 0.5317577548005908,
+      "grad_norm": 1.0506929159164429,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.3556,
+      "step": 45
+    },
+    {
+      "epoch": 0.5435745937961596,
+      "grad_norm": 1.0979819297790527,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.3554,
+      "step": 46
+    },
+    {
+      "epoch": 0.5553914327917282,
+      "grad_norm": 2.562333822250366,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3518,
+      "step": 47
+    },
+    {
+      "epoch": 0.5672082717872969,
+      "grad_norm": 0.9119501113891602,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3309,
+      "step": 48
+    },
+    {
+      "epoch": 0.5790251107828656,
+      "grad_norm": 1.5554051399230957,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.3076,
+      "step": 49
+    },
+    {
+      "epoch": 0.5908419497784343,
+      "grad_norm": 3.618457317352295,
+      "learning_rate": 0.0,
+      "loss": 0.3793,
+      "step": 50
+    },
+    {
+      "epoch": 0.5908419497784343,
+      "eval_loss": 0.35179558396339417,
+      "eval_runtime": 23.9788,
+      "eval_samples_per_second": 23.771,
+      "eval_steps_per_second": 3.003,
+      "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": 1.8645399427979674e+17,
+  "total_flos": 3.7091737698146714e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null