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:c1e23e57b1c64340c0ab9b9b062e01fbc71e9feea529b7a4f9176996197251e0
+oid sha256:985044b042a621fa7cd045eaec5610e88cfd7ddf58b5908388017c44356fd7fc
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:291807e2f6281d74e16694d6bbfefdd3d52000341c5a64dbf47f551ab09a7c10
+oid sha256:a4a5c352f4959206e945f4b67eaaf4429b4c9b4320d5298c00b2637b59dd9dda
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e834ae347c825bf8de4727df7fc7ad9c66775ab4bea0cbac9fa179d7bbd4c4cd
+oid sha256:051544dd9b7ac504606fc8500401630511f0aec5cce0e837bebbe667fd61c8ef
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4208051570c53fd9959ac54d114647482c3679cbc6bddc2c97fd9b2d825bdbbe
+oid sha256:1ff26807f7b3851ef15be7424615828c0c550c8a7933afd35a2b3787f1e0dc3b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a77c6ea2cbf59622e27f3a8a238832c77cfdacf6a52c6a9796d502bf77959ac5
+oid sha256:6cfcc2472d5eb232843b5ef0f8ac0b8a651677a8aab1900bedc5e4b4fa976c8c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dbb7569727c379ab690c30c9b6b7367a71f5b949b9c553aa601461010c0c9de
+oid sha256:0dcc38eb6f3e3b9dd66da55ac210fdb402cc643216788be9b759f0b055082af7
 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": 0.7007076144218445,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2191780821917808,
+  "best_metric": 0.6969178318977356,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4383561643835616,
   "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": 32.73,
       "eval_steps_per_second": 4.128,
       "step": 25
+    },
+    {
+      "epoch": 0.22794520547945205,
+      "grad_norm": 1.066445231437683,
+      "learning_rate": 5e-05,
+      "loss": 0.7141,
+      "step": 26
+    },
+    {
+      "epoch": 0.23671232876712328,
+      "grad_norm": 0.6127803325653076,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.6957,
+      "step": 27
+    },
+    {
+      "epoch": 0.24547945205479452,
+      "grad_norm": 0.7028255462646484,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.6946,
+      "step": 28
+    },
+    {
+      "epoch": 0.25424657534246575,
+      "grad_norm": 0.7202122211456299,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.6816,
+      "step": 29
+    },
+    {
+      "epoch": 0.26301369863013696,
+      "grad_norm": 0.2293580323457718,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.6956,
+      "step": 30
+    },
+    {
+      "epoch": 0.2717808219178082,
+      "grad_norm": 1.1750402450561523,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7183,
+      "step": 31
+    },
+    {
+      "epoch": 0.28054794520547943,
+      "grad_norm": 0.39852091670036316,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7003,
+      "step": 32
+    },
+    {
+      "epoch": 0.2893150684931507,
+      "grad_norm": 0.5287603735923767,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6979,
+      "step": 33
+    },
+    {
+      "epoch": 0.2980821917808219,
+      "grad_norm": 0.6953926086425781,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7014,
+      "step": 34
+    },
+    {
+      "epoch": 0.30684931506849317,
+      "grad_norm": 0.5524169206619263,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.6915,
+      "step": 35
+    },
+    {
+      "epoch": 0.3156164383561644,
+      "grad_norm": 0.7208291888237,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.6864,
+      "step": 36
+    },
+    {
+      "epoch": 0.32438356164383564,
+      "grad_norm": 0.28683096170425415,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.6927,
+      "step": 37
+    },
+    {
+      "epoch": 0.33315068493150685,
+      "grad_norm": 0.3897854685783386,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6978,
+      "step": 38
+    },
+    {
+      "epoch": 0.3419178082191781,
+      "grad_norm": 0.2978964149951935,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6946,
+      "step": 39
+    },
+    {
+      "epoch": 0.3506849315068493,
+      "grad_norm": 0.4156556725502014,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.691,
+      "step": 40
+    },
+    {
+      "epoch": 0.3594520547945205,
+      "grad_norm": 0.15310971438884735,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6926,
+      "step": 41
+    },
+    {
+      "epoch": 0.3682191780821918,
+      "grad_norm": 0.3335914611816406,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6923,
+      "step": 42
+    },
+    {
+      "epoch": 0.376986301369863,
+      "grad_norm": 0.14917869865894318,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6942,
+      "step": 43
+    },
+    {
+      "epoch": 0.38575342465753426,
+      "grad_norm": 0.7024045586585999,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6965,
+      "step": 44
+    },
+    {
+      "epoch": 0.39452054794520547,
+      "grad_norm": 0.7428992390632629,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7004,
+      "step": 45
+    },
+    {
+      "epoch": 0.40328767123287673,
+      "grad_norm": 0.44110044836997986,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6889,
+      "step": 46
+    },
+    {
+      "epoch": 0.41205479452054794,
+      "grad_norm": 0.3936268091201782,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.6905,
+      "step": 47
+    },
+    {
+      "epoch": 0.4208219178082192,
+      "grad_norm": 0.5188143253326416,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6922,
+      "step": 48
+    },
+    {
+      "epoch": 0.4295890410958904,
+      "grad_norm": 0.46438923478126526,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.6922,
+      "step": 49
+    },
+    {
+      "epoch": 0.4383561643835616,
+      "grad_norm": 0.21112455427646637,
+      "learning_rate": 0.0,
+      "loss": 0.6954,
+      "step": 50
+    },
+    {
+      "epoch": 0.4383561643835616,
+      "eval_loss": 0.6969178318977356,
+      "eval_runtime": 23.5116,
+      "eval_samples_per_second": 32.707,
+      "eval_steps_per_second": 4.126,
+      "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": 2.987771858905989e+17,
+  "total_flos": 5.9736786926882e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null