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:d0a12d1098da8f60affc9f3095a8c6f4aeaeea212ce5197e5b16e8d403fa2977
+oid sha256:551f486e0b99e42594c086a0547a95883f39e41ab07d42c8fc2aaeaec061b25f
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae89fe495464ec7f022fad25477b8aa219a0ff8108141d6a1796b0ec02f6aa55
+oid sha256:cb559e7ed39871f9602a9ad41b98b5e80e370a6a0373342ae1dd482b5112cf4f
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0964d2fd73a713fc62857172b87e86c7bee614106e58af8c1d06e8f5e8486502
+oid sha256:c1c11f254dd0e6d1e0434bea107088b69cb1723e64d1fe3a899dd322b349f20a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb25036549fd830a2819e541fd84b3a51b14d5339ea3570cc701a6aa2e6f05bc
+oid sha256:f0117c3608c32ed523557fad92f41b1fc1c5532edd58f4fdfc64d4590c38ffe0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e13648d5be4f2cd27559a59b091f44eec0075d8f97d4d67ed0f8c7cc151d0add
+oid sha256:89cabb0a9e83562a5580c1519993357763999b74f972648c80532fc6f0162225
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7549b221dd631938479adc83b8da26027ddd489de1a8f752352224323df6b2de
+oid sha256:4f6fc2dffc76712e7727510e99659b295b5f48d0671fd765897c1e575233749b
 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": 2.626925230026245,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06532745386248572,
+  "best_metric": 2.5868492126464844,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13065490772497143,
   "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": 87.797,
       "eval_steps_per_second": 11.0,
       "step": 25
+    },
+    {
+      "epoch": 0.06794055201698514,
+      "grad_norm": 0.2307354360818863,
+      "learning_rate": 5e-05,
+      "loss": 2.3779,
+      "step": 26
+    },
+    {
+      "epoch": 0.07055365017148457,
+      "grad_norm": 0.233708456158638,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.3673,
+      "step": 27
+    },
+    {
+      "epoch": 0.073166748325984,
+      "grad_norm": 0.27781909704208374,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.4519,
+      "step": 28
+    },
+    {
+      "epoch": 0.07577984648048343,
+      "grad_norm": 0.2605210840702057,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.4452,
+      "step": 29
+    },
+    {
+      "epoch": 0.07839294463498285,
+      "grad_norm": 0.2625426948070526,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.4593,
+      "step": 30
+    },
+    {
+      "epoch": 0.08100604278948229,
+      "grad_norm": 0.28291064500808716,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.5734,
+      "step": 31
+    },
+    {
+      "epoch": 0.0836191409439817,
+      "grad_norm": 0.3215564489364624,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.5779,
+      "step": 32
+    },
+    {
+      "epoch": 0.08623223909848114,
+      "grad_norm": 0.40029940009117126,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.7664,
+      "step": 33
+    },
+    {
+      "epoch": 0.08884533725298056,
+      "grad_norm": 0.4789843261241913,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.6643,
+      "step": 34
+    },
+    {
+      "epoch": 0.09145843540748,
+      "grad_norm": 0.5274697542190552,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.7978,
+      "step": 35
+    },
+    {
+      "epoch": 0.09407153356197942,
+      "grad_norm": 0.6247810125350952,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.5879,
+      "step": 36
+    },
+    {
+      "epoch": 0.09668463171647886,
+      "grad_norm": 0.8597372770309448,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.905,
+      "step": 37
+    },
+    {
+      "epoch": 0.09929772987097828,
+      "grad_norm": 0.2140260934829712,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.4018,
+      "step": 38
+    },
+    {
+      "epoch": 0.10191082802547771,
+      "grad_norm": 0.19503909349441528,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.4463,
+      "step": 39
+    },
+    {
+      "epoch": 0.10452392617997713,
+      "grad_norm": 0.2137904167175293,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.4112,
+      "step": 40
+    },
+    {
+      "epoch": 0.10713702433447657,
+      "grad_norm": 0.22088205814361572,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.4364,
+      "step": 41
+    },
+    {
+      "epoch": 0.10975012248897599,
+      "grad_norm": 0.21924644708633423,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.5638,
+      "step": 42
+    },
+    {
+      "epoch": 0.11236322064347543,
+      "grad_norm": 0.2636262774467468,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.6048,
+      "step": 43
+    },
+    {
+      "epoch": 0.11497631879797485,
+      "grad_norm": 0.2927165627479553,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.5676,
+      "step": 44
+    },
+    {
+      "epoch": 0.11758941695247428,
+      "grad_norm": 0.29179003834724426,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.427,
+      "step": 45
+    },
+    {
+      "epoch": 0.1202025151069737,
+      "grad_norm": 0.3900332748889923,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.6848,
+      "step": 46
+    },
+    {
+      "epoch": 0.12281561326147314,
+      "grad_norm": 0.5040877461433411,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.6233,
+      "step": 47
+    },
+    {
+      "epoch": 0.12542871141597256,
+      "grad_norm": 0.581149697303772,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.5518,
+      "step": 48
+    },
+    {
+      "epoch": 0.12804180957047198,
+      "grad_norm": 0.7256733775138855,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.756,
+      "step": 49
+    },
+    {
+      "epoch": 0.13065490772497143,
+      "grad_norm": 1.146926999092102,
+      "learning_rate": 0.0,
+      "loss": 3.0167,
+      "step": 50
+    },
+    {
+      "epoch": 0.13065490772497143,
+      "eval_loss": 2.5868492126464844,
+      "eval_runtime": 29.3665,
+      "eval_samples_per_second": 87.787,
+      "eval_steps_per_second": 10.999,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null