Training in progress, step 125, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0b6629f9a628046b42cab9ba8ec96e666db193829fb8f82b3bdc6bc3c07db62
+oid sha256:ea533a8edad2e186e6dc13f37d10ba5327defb69716ff7f37454c2c9954abe3f
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ea6add8ea8acb575e1a84be47f4c177f60fc62268f58257b79c40a66c8fe4f8
+oid sha256:eb3381d078e6ecf2406b957a967c8c5d95ac8267beaa4a55a8e9c935dfd2eeff
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e45551cb1b7733d02b63753f4a12c2e3034feaded1b94c233e55f5107699fad
+oid sha256:9261c4c40220670a7edbad71de1a08039e483f33679a9a176dd7c228765ebefc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37a72dc9166af8ddb65ce338c3cf8aa5c519dc4e357ca053b385aba6a74b71bb
+oid sha256:03e9c3cb452fe294f65c78c2fab42ae3065f3d6551c282a3495643221b60a78e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65bfbc676382f216a0f150b0902da9031d8fcefd396cc621c571b7689e39c14a
+oid sha256:ae3a13368de0b5e74afa25a40a37cee212e56b0c5b7a164138e75a700fd2b788
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:557344b810e9aa2ccb7cd30cb75fd0ca14049b1b501d4a2c51f58428dc49ae3d
+oid sha256:00d8c96a8b4c96ff6dff384e25b5c7953b2640eef5b3d7b930c5356c47c63a2e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b88cf1ca29131bea6a1c678610dbfd2c6c90cc06115bb015c84ed8386046423a
+oid sha256:72e23a2d1e485599a7b5fae1501ffcbc43db47e90bf1e1f6de6ac821e4368041
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8542066812515259,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.6414111044297455,
+  "best_metric": 0.8382258415222168,
+  "best_model_checkpoint": "miner_id_24/checkpoint-125",
+  "epoch": 0.8017638805371818,
   "eval_steps": 25,
-  "global_step": 100,
+  "global_step": 125,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -747,6 +747,189 @@
       "eval_samples_per_second": 48.618,
       "eval_steps_per_second": 12.641,
       "step": 100
+    },
+    {
+      "epoch": 0.6478252154740429,
+      "grad_norm": 0.3350529968738556,
+      "learning_rate": 3.3355505398627566e-05,
+      "loss": 0.9972,
+      "step": 101
+    },
+    {
+      "epoch": 0.6542393265183404,
+      "grad_norm": 0.3845514953136444,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.8938,
+      "step": 102
+    },
+    {
+      "epoch": 0.6606534375626378,
+      "grad_norm": 0.39235520362854004,
+      "learning_rate": 3.165520338277653e-05,
+      "loss": 0.8996,
+      "step": 103
+    },
+    {
+      "epoch": 0.6670675486069353,
+      "grad_norm": 0.38063177466392517,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 0.8417,
+      "step": 104
+    },
+    {
+      "epoch": 0.6734816596512327,
+      "grad_norm": 0.39507997035980225,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.7897,
+      "step": 105
+    },
+    {
+      "epoch": 0.6798957706955302,
+      "grad_norm": 0.37488269805908203,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 0.8193,
+      "step": 106
+    },
+    {
+      "epoch": 0.6863098817398277,
+      "grad_norm": 0.45661434531211853,
+      "learning_rate": 2.8391065823638806e-05,
+      "loss": 0.8756,
+      "step": 107
+    },
+    {
+      "epoch": 0.6927239927841251,
+      "grad_norm": 0.4090655744075775,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.811,
+      "step": 108
+    },
+    {
+      "epoch": 0.6991381038284226,
+      "grad_norm": 0.4572974443435669,
+      "learning_rate": 2.6833443751717347e-05,
+      "loss": 0.8338,
+      "step": 109
+    },
+    {
+      "epoch": 0.70555221487272,
+      "grad_norm": 0.4468700587749481,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 0.7846,
+      "step": 110
+    },
+    {
+      "epoch": 0.7119663259170175,
+      "grad_norm": 0.47316402196884155,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.7582,
+      "step": 111
+    },
+    {
+      "epoch": 0.7183804369613149,
+      "grad_norm": 0.5286366939544678,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 0.7915,
+      "step": 112
+    },
+    {
+      "epoch": 0.7247945480056124,
+      "grad_norm": 0.32154494524002075,
+      "learning_rate": 2.3881912489797885e-05,
+      "loss": 1.0302,
+      "step": 113
+    },
+    {
+      "epoch": 0.7312086590499098,
+      "grad_norm": 0.36848995089530945,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.9236,
+      "step": 114
+    },
+    {
+      "epoch": 0.7376227700942073,
+      "grad_norm": 0.3812990188598633,
+      "learning_rate": 2.2493621707311002e-05,
+      "loss": 0.8507,
+      "step": 115
+    },
+    {
+      "epoch": 0.7440368811385047,
+      "grad_norm": 0.37178778648376465,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 0.9149,
+      "step": 116
+    },
+    {
+      "epoch": 0.7504509921828022,
+      "grad_norm": 0.36262521147727966,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.8503,
+      "step": 117
+    },
+    {
+      "epoch": 0.7568651032270997,
+      "grad_norm": 0.3932304084300995,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 0.8351,
+      "step": 118
+    },
+    {
+      "epoch": 0.7632792142713971,
+      "grad_norm": 0.4190768301486969,
+      "learning_rate": 1.9905198260820328e-05,
+      "loss": 0.8448,
+      "step": 119
+    },
+    {
+      "epoch": 0.7696933253156946,
+      "grad_norm": 0.40936529636383057,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.7507,
+      "step": 120
+    },
+    {
+      "epoch": 0.776107436359992,
+      "grad_norm": 0.43789592385292053,
+      "learning_rate": 1.8709992807963285e-05,
+      "loss": 0.8046,
+      "step": 121
+    },
+    {
+      "epoch": 0.7825215474042895,
+      "grad_norm": 0.44734787940979004,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 0.8344,
+      "step": 122
+    },
+    {
+      "epoch": 0.7889356584485869,
+      "grad_norm": 0.48436063528060913,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.8474,
+      "step": 123
+    },
+    {
+      "epoch": 0.7953497694928844,
+      "grad_norm": 0.5177507996559143,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 0.7806,
+      "step": 124
+    },
+    {
+      "epoch": 0.8017638805371818,
+      "grad_norm": 0.6930881142616272,
+      "learning_rate": 1.6528965819717413e-05,
+      "loss": 0.8634,
+      "step": 125
+    },
+    {
+      "epoch": 0.8017638805371818,
+      "eval_loss": 0.8382258415222168,
+      "eval_runtime": 1.018,
+      "eval_samples_per_second": 49.116,
+      "eval_steps_per_second": 12.77,
+      "step": 125
     }
   ],
   "logging_steps": 1,
@@ -775,7 +958,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.666963004886876e+17,
+  "total_flos": 2.08367120092758e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null