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:e360a37ea2207c6a50042b1be2292e0639990f616a6930bc7ab70ac892ce8dff
+oid sha256:ae9c45632286cdab1a675c2cd636ce32344e3e9e6c8cd816358c1a2248bf8af2
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87e2def3c2d1f30f2986e285f5f8e6f9d54d775c2755f166ff6d5581f29ccadb
+oid sha256:12cc016bebc9afb4b95c3adf9181e40306afafeb7c195ee45a17fcf666b33a27
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a77c88f54db541ac04f4669750bdc75cad1193b47cd6632266064f4f31970d3
+oid sha256:1752c61b723de8d72f0a32ad16bf55c4cf716e69a352156d0bf4f6526e09caf7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b41a495b138b29b50238c27efe195985aa453c3f94759b66bcc90189e6af54e3
+oid sha256:ee9f4bf9737a7e25ad2e5dbd6b1b69d4a6660a8884496a4079e7973968ab8466
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae32454d5054ea35808b2ba7d5cc59a04ad37d81c7ecc5b58580637439ca1651
+oid sha256:2d52357344c021ea130a6a430e653e6914e670db87b7955902282e573e374c5c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59e279f158472cf27b61a872bae710dea9ed7f3a7de38abd2f901a6a7a3fb8b7
+oid sha256:78e31b69f60361296bdb9e6f62ada30e6bbe065d7f084f9a64519e970805cc90
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.809256911277771,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.007323324789454412,
+  "best_metric": 0.8066132068634033,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.014646649578908825,
   "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": 12.346,
       "eval_steps_per_second": 3.21,
       "step": 25
+    },
+    {
+      "epoch": 0.007616257781032589,
+      "grad_norm": 0.18660973012447357,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.5492,
+      "step": 26
+    },
+    {
+      "epoch": 0.007909190772610765,
+      "grad_norm": 0.21695637702941895,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.6171,
+      "step": 27
+    },
+    {
+      "epoch": 0.008202123764188942,
+      "grad_norm": 0.2558394968509674,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.6352,
+      "step": 28
+    },
+    {
+      "epoch": 0.008495056755767118,
+      "grad_norm": 0.30923590064048767,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.7514,
+      "step": 29
+    },
+    {
+      "epoch": 0.008787989747345295,
+      "grad_norm": 0.29804402589797974,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.7326,
+      "step": 30
+    },
+    {
+      "epoch": 0.009080922738923471,
+      "grad_norm": 0.3356321454048157,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.7845,
+      "step": 31
+    },
+    {
+      "epoch": 0.009373855730501647,
+      "grad_norm": 0.3836168348789215,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.8783,
+      "step": 32
+    },
+    {
+      "epoch": 0.009666788722079824,
+      "grad_norm": 0.4422508776187897,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.0204,
+      "step": 33
+    },
+    {
+      "epoch": 0.009959721713658,
+      "grad_norm": 0.6576272249221802,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.0405,
+      "step": 34
+    },
+    {
+      "epoch": 0.010252654705236177,
+      "grad_norm": 0.8195415139198303,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.0154,
+      "step": 35
+    },
+    {
+      "epoch": 0.010545587696814353,
+      "grad_norm": 0.7149752974510193,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.9485,
+      "step": 36
+    },
+    {
+      "epoch": 0.01083852068839253,
+      "grad_norm": 0.5546535849571228,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.8952,
+      "step": 37
+    },
+    {
+      "epoch": 0.011131453679970706,
+      "grad_norm": 0.22018006443977356,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.5962,
+      "step": 38
+    },
+    {
+      "epoch": 0.011424386671548882,
+      "grad_norm": 0.17659281194210052,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.5691,
+      "step": 39
+    },
+    {
+      "epoch": 0.011717319663127059,
+      "grad_norm": 0.20161019265651703,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.6794,
+      "step": 40
+    },
+    {
+      "epoch": 0.012010252654705237,
+      "grad_norm": 0.2220175713300705,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.7288,
+      "step": 41
+    },
+    {
+      "epoch": 0.012303185646283413,
+      "grad_norm": 0.22722084820270538,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.7078,
+      "step": 42
+    },
+    {
+      "epoch": 0.01259611863786159,
+      "grad_norm": 0.2322564572095871,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.7349,
+      "step": 43
+    },
+    {
+      "epoch": 0.012889051629439766,
+      "grad_norm": 0.2695636451244354,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.789,
+      "step": 44
+    },
+    {
+      "epoch": 0.013181984621017943,
+      "grad_norm": 0.2991158664226532,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.9157,
+      "step": 45
+    },
+    {
+      "epoch": 0.013474917612596119,
+      "grad_norm": 0.28474679589271545,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.016,
+      "step": 46
+    },
+    {
+      "epoch": 0.013767850604174296,
+      "grad_norm": 0.33788153529167175,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.9079,
+      "step": 47
+    },
+    {
+      "epoch": 0.014060783595752472,
+      "grad_norm": 0.38621529936790466,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.9021,
+      "step": 48
+    },
+    {
+      "epoch": 0.014353716587330648,
+      "grad_norm": 0.4887455105781555,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.8839,
+      "step": 49
+    },
+    {
+      "epoch": 0.014646649578908825,
+      "grad_norm": 0.754707932472229,
+      "learning_rate": 1e-05,
+      "loss": 0.9356,
+      "step": 50
+    },
+    {
+      "epoch": 0.014646649578908825,
+      "eval_loss": 0.8066132068634033,
+      "eval_runtime": 4.0311,
+      "eval_samples_per_second": 12.404,
+      "eval_steps_per_second": 3.225,
+      "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": 3.015747257237504e+17,
+  "total_flos": 6.027764453490033e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null