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:f026fe0b0986d4fcbdb73e4d116d8ce7171a367294cbc3d7eb3224b1fc834564
+oid sha256:21772db61fc31d0c6640c8ae49ee4a8b23db8504599b5407c20f15fae857cc00
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a7914826e3abc67bc2edf79b54131b74673411acedbe4a22e9bf192340aa06f
+oid sha256:a2e1f0c0f405a8493aeff7030c7ccb635c9f6c664c1e1461bdcea17e7c7ff776
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57c2120713eb29c07699c4d06ba8cae1bf11e543ad26e4fe7f56330cee4124a0
+oid sha256:0967be2d51842cb95c762a7e82efc19d76fd77c435e5a58b53b9b2fb7cb79ac3
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c20b0114c3406b45a6dbf5fe0b28a2765e5dc5c5d9837be6878dc375b4bf4511
+oid sha256:6701d2492c6517e36410eb2d7de18755e21dc80fb8395c77d96126b4da5deb8b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df76cb700faefe3052b6826cfa3226dfe2dc35885df772fecac553db6dcf24f0
+oid sha256:ba20e33b9c5816ddd304c9d78316cf84de1460894c50226016265202bdffeac6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f5b309de451b869b62f7606848ee1aa15d2adb03be5fb2c06f70306af25790f
+oid sha256:7360de165c60b67e8ab3c4e103eb7a659f13f12d8e3ec910b89feeaf3c42df7f
 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": 0.344561368227005,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.238532110091743,
+  "best_metric": 0.3359534740447998,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.477064220183486,
   "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": 14.794,
       "eval_steps_per_second": 1.93,
       "step": 25
+    },
+    {
+      "epoch": 1.2874617737003058,
+      "grad_norm": 73.28158569335938,
+      "learning_rate": 5e-05,
+      "loss": 0.5206,
+      "step": 26
+    },
+    {
+      "epoch": 1.3363914373088686,
+      "grad_norm": 84.08252716064453,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4166,
+      "step": 27
+    },
+    {
+      "epoch": 1.385321100917431,
+      "grad_norm": 95.0881118774414,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.3284,
+      "step": 28
+    },
+    {
+      "epoch": 1.4342507645259939,
+      "grad_norm": 84.19164276123047,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3914,
+      "step": 29
+    },
+    {
+      "epoch": 1.4831804281345566,
+      "grad_norm": 86.7741470336914,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.3869,
+      "step": 30
+    },
+    {
+      "epoch": 1.5321100917431192,
+      "grad_norm": 67.30615997314453,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5661,
+      "step": 31
+    },
+    {
+      "epoch": 1.581039755351682,
+      "grad_norm": 38.15361404418945,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.363,
+      "step": 32
+    },
+    {
+      "epoch": 1.6299694189602447,
+      "grad_norm": 62.01075744628906,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.3029,
+      "step": 33
+    },
+    {
+      "epoch": 1.6788990825688073,
+      "grad_norm": 23.574642181396484,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.289,
+      "step": 34
+    },
+    {
+      "epoch": 1.72782874617737,
+      "grad_norm": 39.977779388427734,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2959,
+      "step": 35
+    },
+    {
+      "epoch": 1.7767584097859328,
+      "grad_norm": 53.3297004699707,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4495,
+      "step": 36
+    },
+    {
+      "epoch": 1.8256880733944953,
+      "grad_norm": 35.10194778442383,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3355,
+      "step": 37
+    },
+    {
+      "epoch": 1.8746177370030581,
+      "grad_norm": 26.82624626159668,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2645,
+      "step": 38
+    },
+    {
+      "epoch": 1.9235474006116209,
+      "grad_norm": 57.93483352661133,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2688,
+      "step": 39
+    },
+    {
+      "epoch": 1.9724770642201834,
+      "grad_norm": 33.57123565673828,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2798,
+      "step": 40
+    },
+    {
+      "epoch": 2.036697247706422,
+      "grad_norm": 44.15616989135742,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.4424,
+      "step": 41
+    },
+    {
+      "epoch": 2.085626911314985,
+      "grad_norm": 36.59967041015625,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3808,
+      "step": 42
+    },
+    {
+      "epoch": 2.1345565749235473,
+      "grad_norm": 58.102577209472656,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2978,
+      "step": 43
+    },
+    {
+      "epoch": 2.18348623853211,
+      "grad_norm": 26.42946434020996,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2555,
+      "step": 44
+    },
+    {
+      "epoch": 2.232415902140673,
+      "grad_norm": 69.52690124511719,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.2367,
+      "step": 45
+    },
+    {
+      "epoch": 2.2813455657492354,
+      "grad_norm": 53.76517105102539,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5083,
+      "step": 46
+    },
+    {
+      "epoch": 2.330275229357798,
+      "grad_norm": 37.09881591796875,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3288,
+      "step": 47
+    },
+    {
+      "epoch": 2.379204892966361,
+      "grad_norm": 33.916202545166016,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3584,
+      "step": 48
+    },
+    {
+      "epoch": 2.4281345565749235,
+      "grad_norm": 34.20186233520508,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2662,
+      "step": 49
+    },
+    {
+      "epoch": 2.477064220183486,
+      "grad_norm": 34.20256805419922,
+      "learning_rate": 0.0,
+      "loss": 0.2307,
+      "step": 50
+    },
+    {
+      "epoch": 2.477064220183486,
+      "eval_loss": 0.3359534740447998,
+      "eval_runtime": 9.3234,
+      "eval_samples_per_second": 14.801,
+      "eval_steps_per_second": 1.931,
+      "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": 2.830247619723264e+17,
+  "total_flos": 5.660495239446528e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null