Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5900ced9e0a551302abbf231f91206deb31b3c203f75b3a1be4944f2ad1af113
+oid sha256:dc54772e627ada106d58d148cbe1cab0e7dcf2a21863e00e76ff7abbfeaad5e2
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deaca7973296910a5c170e0fceb467194941a15c3217c13ca0d604c8abbe2981
+oid sha256:9724a393802a1ced09b5864d6dbca655e703dbd25b9051cf5d414da9babdabad
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:673ae7a52a50c6a7475ff538f82896bcbf815917a32d98ddc4a9be819e364c21
+oid sha256:326688693e766328e101609b0ff4ea0cff3ff732adf951e6f9163d7588a0c66a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cc4380324b89106e42717852a4e9bdfd31284d87326ca3986b525c773437a1e
+oid sha256:813ba29450486a1690f638b7179a04610ea3d95e73ccff3f11876bc22e6a174e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a79a956126850b2d3650389b62449a18d9d0c9bb89b9a1badee290135e8aa6c
+oid sha256:2463c1bf827757950902d50cf99c46269c4ab62ee6c1dfaa532265d9de4d9e8d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04bb243c047597988d47f7ee79d0982d2f7878a043a705cd7f10b1efebc0dc77
+oid sha256:22af2a10f1bac31a491526da1e6e9939ac3dc5c7bd4f8bd9d1179f50e0270ccb
 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": 0.7768014669418335,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7092198581560284,
+  "best_metric": 0.712428867816925,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.4184397163120568,
   "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": 29.979,
       "eval_steps_per_second": 3.779,
       "step": 25
+    },
+    {
+      "epoch": 0.7375886524822695,
+      "grad_norm": 1.9908738136291504,
+      "learning_rate": 5e-05,
+      "loss": 0.5038,
+      "step": 26
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "grad_norm": 1.0437350273132324,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.1081,
+      "step": 27
+    },
+    {
+      "epoch": 0.7943262411347518,
+      "grad_norm": 0.9461138248443604,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.955,
+      "step": 28
+    },
+    {
+      "epoch": 0.8226950354609929,
+      "grad_norm": 0.891750693321228,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.8951,
+      "step": 29
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.8280903100967407,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7861,
+      "step": 30
+    },
+    {
+      "epoch": 0.8794326241134752,
+      "grad_norm": 0.7851285934448242,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7437,
+      "step": 31
+    },
+    {
+      "epoch": 0.9078014184397163,
+      "grad_norm": 0.8078291416168213,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.6323,
+      "step": 32
+    },
+    {
+      "epoch": 0.9361702127659575,
+      "grad_norm": 0.9439874887466431,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5738,
+      "step": 33
+    },
+    {
+      "epoch": 0.9645390070921985,
+      "grad_norm": 0.9965519309043884,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.515,
+      "step": 34
+    },
+    {
+      "epoch": 0.9929078014184397,
+      "grad_norm": 2.3316826820373535,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.5279,
+      "step": 35
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "grad_norm": 2.271655559539795,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.5823,
+      "step": 36
+    },
+    {
+      "epoch": 1.049645390070922,
+      "grad_norm": 1.21628737449646,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8529,
+      "step": 37
+    },
+    {
+      "epoch": 1.0780141843971631,
+      "grad_norm": 1.0844900608062744,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7737,
+      "step": 38
+    },
+    {
+      "epoch": 1.1063829787234043,
+      "grad_norm": 1.1579043865203857,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.7175,
+      "step": 39
+    },
+    {
+      "epoch": 1.1347517730496455,
+      "grad_norm": 1.0415334701538086,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6545,
+      "step": 40
+    },
+    {
+      "epoch": 1.1631205673758864,
+      "grad_norm": 1.0493574142456055,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5808,
+      "step": 41
+    },
+    {
+      "epoch": 1.1914893617021276,
+      "grad_norm": 1.1408480405807495,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4883,
+      "step": 42
+    },
+    {
+      "epoch": 1.2198581560283688,
+      "grad_norm": 1.1568186283111572,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4347,
+      "step": 43
+    },
+    {
+      "epoch": 1.24822695035461,
+      "grad_norm": 1.0467925071716309,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2627,
+      "step": 44
+    },
+    {
+      "epoch": 1.2765957446808511,
+      "grad_norm": 1.4136056900024414,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.4537,
+      "step": 45
+    },
+    {
+      "epoch": 1.3049645390070923,
+      "grad_norm": 1.066475749015808,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8176,
+      "step": 46
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.0925204753875732,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7644,
+      "step": 47
+    },
+    {
+      "epoch": 1.3617021276595744,
+      "grad_norm": 1.2347716093063354,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6749,
+      "step": 48
+    },
+    {
+      "epoch": 1.3900709219858156,
+      "grad_norm": 1.0493576526641846,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.6014,
+      "step": 49
+    },
+    {
+      "epoch": 1.4184397163120568,
+      "grad_norm": 1.1798675060272217,
+      "learning_rate": 0.0,
+      "loss": 0.5534,
+      "step": 50
+    },
+    {
+      "epoch": 1.4184397163120568,
+      "eval_loss": 0.712428867816925,
+      "eval_runtime": 7.9435,
+      "eval_samples_per_second": 29.961,
+      "eval_steps_per_second": 3.777,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null