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:be2af2abab7b2efd3e7d38a4526e15828391316a236baedc65a440e9fbe78093
+oid sha256:bc68b0cfa9622169566e42d9d13edbfc9d515f69dd95da9343abb14c78de3929
 size 844180648

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f3df18c03e8755043fed07c72f88035bda3256fa6a48d6617827becd9a4ba2f
+oid sha256:d55e6ca4db3cb0af34f66757ee2d2be817ce3486880fd48648984fb6154383aa
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:749495fde66e0d730a20260a384eaf66be07c6ba5e88842f4aa6a079c075ed23
+oid sha256:71954adcdee00cc6b558118e279276f43e0c38c594b98aeaed40aac711f39a0d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e3f684a4c5a3ef9ecf5deb88a57bbad966ddae9f00f302fa0c9f0f7d0407c0d
+oid sha256:ef0f8c60660f444c0049b57b1326467462232b4d4136a55b0102678a05122beb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d48ebf8ccc40c9ae558ee5d985535088b6407399914d60ad5cb93de2b994dfcf
+oid sha256:f61f2fae307309afe5da30e7dfef21216b0a8d806c55f5dd3d045a293422e854
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:507c5617755bc18f0c47749bab0a0760d7a99797a2be0d83079beed2a7cedbc2
+oid sha256:12da1a85a9b1fe276682d974f970e638b4a2db376d67888da65fdb41ad122a71
 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": 0.6493464112281799,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.14404033129276198,
+  "best_metric": 0.6429974436759949,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.28808066258552395,
   "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": 18.658,
       "eval_steps_per_second": 2.344,
       "step": 25
+    },
+    {
+      "epoch": 0.14980194454447246,
+      "grad_norm": 0.0377141535282135,
+      "learning_rate": 5e-05,
+      "loss": 0.4548,
+      "step": 26
+    },
+    {
+      "epoch": 0.15556355779618294,
+      "grad_norm": 0.03820684552192688,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4663,
+      "step": 27
+    },
+    {
+      "epoch": 0.1613251710478934,
+      "grad_norm": 0.03541272506117821,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4698,
+      "step": 28
+    },
+    {
+      "epoch": 0.16708678429960389,
+      "grad_norm": 0.03558218479156494,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4467,
+      "step": 29
+    },
+    {
+      "epoch": 0.17284839755131437,
+      "grad_norm": 0.03669212386012077,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5416,
+      "step": 30
+    },
+    {
+      "epoch": 0.17861001080302485,
+      "grad_norm": 0.03968456760048866,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5995,
+      "step": 31
+    },
+    {
+      "epoch": 0.18437162405473534,
+      "grad_norm": 0.044490545988082886,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.6668,
+      "step": 32
+    },
+    {
+      "epoch": 0.1901332373064458,
+      "grad_norm": 0.044313203543424606,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6971,
+      "step": 33
+    },
+    {
+      "epoch": 0.19589485055815628,
+      "grad_norm": 0.04487527161836624,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7246,
+      "step": 34
+    },
+    {
+      "epoch": 0.20165646380986677,
+      "grad_norm": 0.046701982617378235,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7647,
+      "step": 35
+    },
+    {
+      "epoch": 0.20741807706157725,
+      "grad_norm": 0.055860552936792374,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8081,
+      "step": 36
+    },
+    {
+      "epoch": 0.21317969031328773,
+      "grad_norm": 0.06121724843978882,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8244,
+      "step": 37
+    },
+    {
+      "epoch": 0.2189413035649982,
+      "grad_norm": 0.041338320821523666,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.559,
+      "step": 38
+    },
+    {
+      "epoch": 0.22470291681670868,
+      "grad_norm": 0.03439754247665405,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.5178,
+      "step": 39
+    },
+    {
+      "epoch": 0.23046453006841916,
+      "grad_norm": 0.03415605053305626,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5045,
+      "step": 40
+    },
+    {
+      "epoch": 0.23622614332012964,
+      "grad_norm": 0.034835852682590485,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.4983,
+      "step": 41
+    },
+    {
+      "epoch": 0.24198775657184013,
+      "grad_norm": 0.03588012605905533,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5212,
+      "step": 42
+    },
+    {
+      "epoch": 0.24774936982355059,
+      "grad_norm": 0.036689817905426025,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.5963,
+      "step": 43
+    },
+    {
+      "epoch": 0.2535109830752611,
+      "grad_norm": 0.042088426649570465,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6682,
+      "step": 44
+    },
+    {
+      "epoch": 0.2592725963269715,
+      "grad_norm": 0.041987087577581406,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6636,
+      "step": 45
+    },
+    {
+      "epoch": 0.265034209578682,
+      "grad_norm": 0.044161561876535416,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.693,
+      "step": 46
+    },
+    {
+      "epoch": 0.2707958228303925,
+      "grad_norm": 0.04928355664014816,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7714,
+      "step": 47
+    },
+    {
+      "epoch": 0.276557436082103,
+      "grad_norm": 0.051890455186367035,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7807,
+      "step": 48
+    },
+    {
+      "epoch": 0.28231904933381347,
+      "grad_norm": 0.05590865761041641,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8226,
+      "step": 49
+    },
+    {
+      "epoch": 0.28808066258552395,
+      "grad_norm": 0.07474499940872192,
+      "learning_rate": 0.0,
+      "loss": 0.929,
+      "step": 50
+    },
+    {
+      "epoch": 0.28808066258552395,
+      "eval_loss": 0.6429974436759949,
+      "eval_runtime": 61.939,
+      "eval_samples_per_second": 18.89,
+      "eval_steps_per_second": 2.373,
+      "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": 4.098817288495432e+17,
+  "total_flos": 8.215712770797076e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null