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:f7b66f6090723f62f257f4a88ed37268419c5aa29de70218731c3d7d3df04ec2
+oid sha256:fd16d3f8eeadc7b5a7fbac8ebcda3ac96accbc1d71bcd1c8f99ba32a5aa5b7b6
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26c9e79349389ad3c95483354cc2bcaac8595e05b1d6091bf35a1426ce72e595
+oid sha256:fa74529dc974284876a66aa9cdd15f70da3fbe095d97beca75e654225403da34
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:547c44a2132c7c7fbd3e868ed287ca621943b4a89d905c66a5228ce0d532d50f
+oid sha256:639daeabf560df1dec25485d04e4ab2218e0a2a4dae347e7ecb9e60f75630adb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fcc915d4211fe6a876c4932626c79caef943e75f399c36c6c58bee73aadc576
+oid sha256:aef69dd7e26fe46dab4d74f9bdd6aeb53aed9c7bda800fa1f45c438cfd62556a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13823d501d62bdcdd040eddf351656761fe5a11a0598d62b9ab70768dafc9776
+oid sha256:effd0e039052c53ecc01cbe98489d5bfecab78726c8b62400c70a40458948a4e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c10489b781460038ed3b386566112b9c8c18f8922e26d3523f1993ff263a0eb
+oid sha256:47a2073490cb22317ba2c2a3e5232e2d286a9755dc327d9b7c91af02edd72fb7
 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": 0.05529414117336273,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.041390728476821195,
+  "best_metric": 0.04461386054754257,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.08278145695364239,
   "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": 17.512,
       "eval_steps_per_second": 4.553,
       "step": 25
+    },
+    {
+      "epoch": 0.04304635761589404,
+      "grad_norm": 15.081778526306152,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.8354,
+      "step": 26
+    },
+    {
+      "epoch": 0.04470198675496689,
+      "grad_norm": 13.045018196105957,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.4958,
+      "step": 27
+    },
+    {
+      "epoch": 0.046357615894039736,
+      "grad_norm": 10.834997177124023,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.3995,
+      "step": 28
+    },
+    {
+      "epoch": 0.048013245033112585,
+      "grad_norm": 10.475743293762207,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.1832,
+      "step": 29
+    },
+    {
+      "epoch": 0.04966887417218543,
+      "grad_norm": 10.040482521057129,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.8479,
+      "step": 30
+    },
+    {
+      "epoch": 0.05132450331125828,
+      "grad_norm": 9.801156044006348,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.9541,
+      "step": 31
+    },
+    {
+      "epoch": 0.052980132450331126,
+      "grad_norm": 9.155835151672363,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.8973,
+      "step": 32
+    },
+    {
+      "epoch": 0.054635761589403975,
+      "grad_norm": 9.182353019714355,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.6259,
+      "step": 33
+    },
+    {
+      "epoch": 0.056291390728476824,
+      "grad_norm": 8.900016784667969,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.5571,
+      "step": 34
+    },
+    {
+      "epoch": 0.057947019867549666,
+      "grad_norm": 6.651839733123779,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.2958,
+      "step": 35
+    },
+    {
+      "epoch": 0.059602649006622516,
+      "grad_norm": 9.37293815612793,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.2097,
+      "step": 36
+    },
+    {
+      "epoch": 0.061258278145695365,
+      "grad_norm": 3.1808083057403564,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.1149,
+      "step": 37
+    },
+    {
+      "epoch": 0.06291390728476821,
+      "grad_norm": 6.839907646179199,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.731,
+      "step": 38
+    },
+    {
+      "epoch": 0.06456953642384106,
+      "grad_norm": 10.234563827514648,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.3803,
+      "step": 39
+    },
+    {
+      "epoch": 0.06622516556291391,
+      "grad_norm": 10.767460823059082,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.2713,
+      "step": 40
+    },
+    {
+      "epoch": 0.06788079470198675,
+      "grad_norm": 13.208647727966309,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.0011,
+      "step": 41
+    },
+    {
+      "epoch": 0.0695364238410596,
+      "grad_norm": 9.809880256652832,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.8504,
+      "step": 42
+    },
+    {
+      "epoch": 0.07119205298013245,
+      "grad_norm": 7.994148254394531,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.6678,
+      "step": 43
+    },
+    {
+      "epoch": 0.0728476821192053,
+      "grad_norm": 10.173336029052734,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.7144,
+      "step": 44
+    },
+    {
+      "epoch": 0.07450331125827815,
+      "grad_norm": 11.309749603271484,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.6579,
+      "step": 45
+    },
+    {
+      "epoch": 0.076158940397351,
+      "grad_norm": 12.104318618774414,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.5522,
+      "step": 46
+    },
+    {
+      "epoch": 0.07781456953642384,
+      "grad_norm": 9.264493942260742,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.5053,
+      "step": 47
+    },
+    {
+      "epoch": 0.07947019867549669,
+      "grad_norm": 3.8863046169281006,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.1143,
+      "step": 48
+    },
+    {
+      "epoch": 0.08112582781456953,
+      "grad_norm": 8.043832778930664,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.2191,
+      "step": 49
+    },
+    {
+      "epoch": 0.08278145695364239,
+      "grad_norm": 3.410689115524292,
+      "learning_rate": 1e-05,
+      "loss": 0.0447,
+      "step": 50
+    },
+    {
+      "epoch": 0.08278145695364239,
+      "eval_loss": 0.04461386054754257,
+      "eval_runtime": 2.8406,
+      "eval_samples_per_second": 17.602,
+      "eval_steps_per_second": 4.577,
+      "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": 2.8307787998035968e+17,
+  "total_flos": 5.659789468945613e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null