Training in progress, step 66, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1e9ce52cba4d77aeaff2bdc865a6eb43d6562b1b36bf175216777d25df00d96
+oid sha256:c2b31591f56a427a8f69589ea82dd1c3756b3e0012b2b5aded5bdfa0d9c555b5
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de15d8b5176d38639a2987d5558b9f0965379c1e365265193b23283de48cde55
+oid sha256:115f8ed6594a2dc94885e58277a6540fc4a0f3b355872b7ce063d1b857a74dca
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c33017b58adca0b37b63e7d777cb4abb17e11c9bbabfd9de4f2f077ff3f5cd39
+oid sha256:af05b58d14742efc0d7e36b780a921063b113ca59bcd4fe39ebb642b64dc69a8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b1b0390b549ec498175fd6f7fa77879c9337de0459e3f2d212dea77d3def2e2
+oid sha256:cdc9f51b946f5557fc95c33439dc6f6d3a6ad2fa21939e9df8a60ce609b71f8f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdefa9c7550f1c3bb0c292825aceaed2f5438cbeebe6967c6c5b289a8592f7a9
+oid sha256:5754e263e62c11025c1b7009dc17edb68365d7facc534435d2ab3b01c5fbebfc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8d7069a53f31cfe07350ddbf59700b75b0278fa145e99fed88051bf5c155b89
+oid sha256:090ec60764bf90136b85c59aae65d6d4cfbb1c0453d166d883e22eb4d9a05223
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c0f87e22a22172ee9701122c5b35062b5ba2a80f8dc5427443bd9873d88d17
+oid sha256:3590c95beccaed6e985c8f99327ccb7e1e0604a90f734f2477dfbcb408474e61
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 3.5291860103607178,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 2.2901849217638692,
+  "epoch": 3.0256045519203414,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 66,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,118 @@
       "eval_samples_per_second": 10.217,
       "eval_steps_per_second": 2.656,
       "step": 50
+    },
+    {
+      "epoch": 2.3357041251778092,
+      "grad_norm": 0.3074302077293396,
+      "learning_rate": 2.165719935902685e-05,
+      "loss": 3.0223,
+      "step": 51
+    },
+    {
+      "epoch": 2.3812233285917497,
+      "grad_norm": 0.43086740374565125,
+      "learning_rate": 2.0214529598676836e-05,
+      "loss": 3.2073,
+      "step": 52
+    },
+    {
+      "epoch": 2.42674253200569,
+      "grad_norm": 0.5334138870239258,
+      "learning_rate": 1.8855661083370986e-05,
+      "loss": 3.475,
+      "step": 53
+    },
+    {
+      "epoch": 2.47226173541963,
+      "grad_norm": 0.35528457164764404,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.0396,
+      "step": 54
+    },
+    {
+      "epoch": 2.5177809388335706,
+      "grad_norm": 0.3946029543876648,
+      "learning_rate": 1.6402212549987762e-05,
+      "loss": 4.2628,
+      "step": 55
+    },
+    {
+      "epoch": 2.5633001422475106,
+      "grad_norm": 0.3490312397480011,
+      "learning_rate": 1.531354310432403e-05,
+      "loss": 3.2317,
+      "step": 56
+    },
+    {
+      "epoch": 2.608819345661451,
+      "grad_norm": 0.3952423334121704,
+      "learning_rate": 1.4320481809445051e-05,
+      "loss": 3.2827,
+      "step": 57
+    },
+    {
+      "epoch": 2.654338549075391,
+      "grad_norm": 0.4798361361026764,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.2247,
+      "step": 58
+    },
+    {
+      "epoch": 2.6998577524893315,
+      "grad_norm": 0.4341035783290863,
+      "learning_rate": 1.2630517066764069e-05,
+      "loss": 2.4414,
+      "step": 59
+    },
+    {
+      "epoch": 2.7453769559032715,
+      "grad_norm": 0.44139501452445984,
+      "learning_rate": 1.1937684892050604e-05,
+      "loss": 4.1782,
+      "step": 60
+    },
+    {
+      "epoch": 2.790896159317212,
+      "grad_norm": 0.3148343861103058,
+      "learning_rate": 1.1348593606245522e-05,
+      "loss": 3.0881,
+      "step": 61
+    },
+    {
+      "epoch": 2.8364153627311524,
+      "grad_norm": 0.403652161359787,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.3378,
+      "step": 62
+    },
+    {
+      "epoch": 2.8819345661450924,
+      "grad_norm": 0.44468310475349426,
+      "learning_rate": 1.0487057051584856e-05,
+      "loss": 3.375,
+      "step": 63
+    },
+    {
+      "epoch": 2.927453769559033,
+      "grad_norm": 0.5985783934593201,
+      "learning_rate": 1.0216687299751144e-05,
+      "loss": 3.8349,
+      "step": 64
+    },
+    {
+      "epoch": 2.972972972972973,
+      "grad_norm": 0.5112795829772949,
+      "learning_rate": 1.0054204470767243e-05,
+      "loss": 3.4318,
+      "step": 65
+    },
+    {
+      "epoch": 3.0256045519203414,
+      "grad_norm": 0.2921772003173828,
+      "learning_rate": 1e-05,
+      "loss": 3.1404,
+      "step": 66
     }
   ],
   "logging_steps": 1,
@@ -404,12 +516,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.94442481722327e+17,
+  "total_flos": 9.108787643746877e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null