Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:433d56dc76083cb059d60ef24f532a1b8012314a670458dfb8310fe1e1591c95
+oid sha256:d0b6629f9a628046b42cab9ba8ec96e666db193829fb8f82b3bdc6bc3c07db62
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b92751f4b20e75eaa14da19b90f1ab13480087054428a4c0d401036dfb6ac41
+oid sha256:1ea6add8ea8acb575e1a84be47f4c177f60fc62268f58257b79c40a66c8fe4f8
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef287f4d129e16c1be2a6d9274834361a2314f3e93306e2f68a2038b7df959db
+oid sha256:5e45551cb1b7733d02b63753f4a12c2e3034feaded1b94c233e55f5107699fad
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d852e8f5f81e0cab6890f467096252da1139a278824fe37f3c8942c5eb9770e
+oid sha256:37a72dc9166af8ddb65ce338c3cf8aa5c519dc4e357ca053b385aba6a74b71bb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d73e7a0ecb30a99cbdfcf5294c035a1607fc9fe8fb9bf248e040f45b1c4ed0
+oid sha256:65bfbc676382f216a0f150b0902da9031d8fcefd396cc621c571b7689e39c14a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:622caafed4311025a250cc617d5ea7d83f8800dd0509bfa4e0512afe18da2242
+oid sha256:557344b810e9aa2ccb7cd30cb75fd0ca14049b1b501d4a2c51f58428dc49ae3d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38b483de1bf1f4ff353f1ec4a8c9df2b2847b745cbf851617486bbe747b1c0c0
+oid sha256:b88cf1ca29131bea6a1c678610dbfd2c6c90cc06115bb015c84ed8386046423a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.880484402179718,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.4810583283223091,
+  "best_metric": 0.8542066812515259,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.6414111044297455,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 49.469,
       "eval_steps_per_second": 12.862,
       "step": 75
+    },
+    {
+      "epoch": 0.48747243936660656,
+      "grad_norm": 0.34252408146858215,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 0.9852,
+      "step": 76
+    },
+    {
+      "epoch": 0.493886550410904,
+      "grad_norm": 0.4102064073085785,
+      "learning_rate": 5.598166982655526e-05,
+      "loss": 0.9529,
+      "step": 77
+    },
+    {
+      "epoch": 0.5003006614552015,
+      "grad_norm": 0.4815739095211029,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.918,
+      "step": 78
+    },
+    {
+      "epoch": 0.5067147724994989,
+      "grad_norm": 0.4241974651813507,
+      "learning_rate": 5.4018330173444754e-05,
+      "loss": 0.8912,
+      "step": 79
+    },
+    {
+      "epoch": 0.5131288835437964,
+      "grad_norm": 0.44345757365226746,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 0.9079,
+      "step": 80
+    },
+    {
+      "epoch": 0.5195429945880938,
+      "grad_norm": 0.48125022649765015,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.8695,
+      "step": 81
+    },
+    {
+      "epoch": 0.5259571056323913,
+      "grad_norm": 0.41340336203575134,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 0.7949,
+      "step": 82
+    },
+    {
+      "epoch": 0.5323712166766887,
+      "grad_norm": 0.4205497205257416,
+      "learning_rate": 5.0100990631661606e-05,
+      "loss": 0.7923,
+      "step": 83
+    },
+    {
+      "epoch": 0.5387853277209862,
+      "grad_norm": 0.4334363639354706,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.7829,
+      "step": 84
+    },
+    {
+      "epoch": 0.5451994387652837,
+      "grad_norm": 0.4538995623588562,
+      "learning_rate": 4.8154447621453744e-05,
+      "loss": 0.8175,
+      "step": 85
+    },
+    {
+      "epoch": 0.5516135498095811,
+      "grad_norm": 0.5367742776870728,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 0.8247,
+      "step": 86
+    },
+    {
+      "epoch": 0.5580276608538786,
+      "grad_norm": 0.6540936231613159,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.8939,
+      "step": 87
+    },
+    {
+      "epoch": 0.564441771898176,
+      "grad_norm": 0.32181909680366516,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 0.9774,
+      "step": 88
+    },
+    {
+      "epoch": 0.5708558829424735,
+      "grad_norm": 0.3461693227291107,
+      "learning_rate": 4.430413484532222e-05,
+      "loss": 0.9442,
+      "step": 89
+    },
+    {
+      "epoch": 0.5772699939867709,
+      "grad_norm": 0.39385172724723816,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.946,
+      "step": 90
+    },
+    {
+      "epoch": 0.5836841050310684,
+      "grad_norm": 0.35734453797340393,
+      "learning_rate": 4.240769436860537e-05,
+      "loss": 0.8235,
+      "step": 91
+    },
+    {
+      "epoch": 0.5900982160753658,
+      "grad_norm": 0.3919447362422943,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 0.7648,
+      "step": 92
+    },
+    {
+      "epoch": 0.5965123271196633,
+      "grad_norm": 0.3950856328010559,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.8024,
+      "step": 93
+    },
+    {
+      "epoch": 0.6029264381639607,
+      "grad_norm": 0.40364179015159607,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 0.9059,
+      "step": 94
+    },
+    {
+      "epoch": 0.6093405492082582,
+      "grad_norm": 0.4102337062358856,
+      "learning_rate": 3.8690288277233435e-05,
+      "loss": 0.8092,
+      "step": 95
+    },
+    {
+      "epoch": 0.6157546602525557,
+      "grad_norm": 0.4184516668319702,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.8231,
+      "step": 96
+    },
+    {
+      "epoch": 0.6221687712968531,
+      "grad_norm": 0.47536927461624146,
+      "learning_rate": 3.687639895635684e-05,
+      "loss": 0.8002,
+      "step": 97
+    },
+    {
+      "epoch": 0.6285828823411506,
+      "grad_norm": 0.4901541769504547,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 0.8575,
+      "step": 98
+    },
+    {
+      "epoch": 0.634996993385448,
+      "grad_norm": 0.5419043302536011,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.8291,
+      "step": 99
+    },
+    {
+      "epoch": 0.6414111044297455,
+      "grad_norm": 0.6231566667556763,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 0.8435,
+      "step": 100
+    },
+    {
+      "epoch": 0.6414111044297455,
+      "eval_loss": 0.8542066812515259,
+      "eval_runtime": 1.0284,
+      "eval_samples_per_second": 48.618,
+      "eval_steps_per_second": 12.641,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -592,7 +775,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2502548088461722e+17,
+  "total_flos": 1.666963004886876e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null