Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a012c2820ba0237cc64680cf69e9d38ebfbed5a291b322a883ca90225048e22
+oid sha256:cf92c290b15d13b1cd7c77b8d3a67a7751fc83e99ca24317f8ff42454594a981
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22bcc63d0ef26744cc14aa28d5fb394da8e5ae65fcbcb85b1dc16cb403704391
+oid sha256:490d7da7acdc2b522a683761c687689a7f7449036cc824f2a1f8c1b0b5f8e0af
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5742dd433ee3ae60e4b3a90fdad43ff46cc6ea4b4f2744fa31781352ce7ddb2b
+oid sha256:d21a9ba0e8e620bc7c4b0103ff676969c00bc4869f3f878cafe019f7db4fe00c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc1c972811a5b35b45ca0f9da96ca5d4ccad8141bb4c6eedf8ef5c25d450faff
+oid sha256:17aec51f080c21d526f91c05c94b07bf25af41368aa4c84d6f7ad6356f598c23
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adb9c6b9c0c2d5452cfb6e67cd9803d35665084bb5eaec4c9434f39252459f5a
+oid sha256:e0093bf299349b49047cdebfcba8383ad8db1ffad4fe76031c8db99f4d70dccc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99006e2dcbe2a806a4e5201319fb8556cfc5e36b099db46ef1a3899ca6ff4a37
+oid sha256:6bd2a91fa18437ac891368dcdc208083c6650384c20992659d701885f986281f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:344fc18df9c84f214bc47e69d1bbde70d66cf3ec6caeac9cd529dfb5814c4b9a
+oid sha256:051dee7dfbeecb34b46e8409ffafec324501f465585234624669bc8c9e863ae4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0223414897918701,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.9400705052878966,
+  "best_metric": 1.0160294771194458,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 1.262044653349001,
   "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": 99.066,
       "eval_steps_per_second": 25.757,
       "step": 75
+    },
+    {
+      "epoch": 0.9526047786917352,
+      "grad_norm": 0.49434900283813477,
+      "learning_rate": 2.3444344707738015e-05,
+      "loss": 1.4486,
+      "step": 76
+    },
+    {
+      "epoch": 0.9651390520955738,
+      "grad_norm": 0.17201216518878937,
+      "learning_rate": 2.2400865784401e-05,
+      "loss": 1.0346,
+      "step": 77
+    },
+    {
+      "epoch": 0.9776733254994124,
+      "grad_norm": 0.20286938548088074,
+      "learning_rate": 2.1393033535713093e-05,
+      "loss": 0.9808,
+      "step": 78
+    },
+    {
+      "epoch": 0.990207598903251,
+      "grad_norm": 0.32843250036239624,
+      "learning_rate": 2.0421950011441354e-05,
+      "loss": 1.1024,
+      "step": 79
+    },
+    {
+      "epoch": 1.0113591852722288,
+      "grad_norm": 1.1532492637634277,
+      "learning_rate": 1.9488677077162295e-05,
+      "loss": 2.3248,
+      "step": 80
+    },
+    {
+      "epoch": 1.0238934586760673,
+      "grad_norm": 0.1928626447916031,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 1.1929,
+      "step": 81
+    },
+    {
+      "epoch": 1.036427732079906,
+      "grad_norm": 0.16608740389347076,
+      "learning_rate": 1.77396025983391e-05,
+      "loss": 1.0818,
+      "step": 82
+    },
+    {
+      "epoch": 1.0489620054837445,
+      "grad_norm": 0.17658193409442902,
+      "learning_rate": 1.6925713641057904e-05,
+      "loss": 1.0452,
+      "step": 83
+    },
+    {
+      "epoch": 1.0614962788875832,
+      "grad_norm": 0.17382438480854034,
+      "learning_rate": 1.6153458356909176e-05,
+      "loss": 0.9723,
+      "step": 84
+    },
+    {
+      "epoch": 1.074030552291422,
+      "grad_norm": 0.18274889886379242,
+      "learning_rate": 1.5423681195707997e-05,
+      "loss": 0.972,
+      "step": 85
+    },
+    {
+      "epoch": 1.0865648256952605,
+      "grad_norm": 0.19719198346138,
+      "learning_rate": 1.4737180158065644e-05,
+      "loss": 0.9441,
+      "step": 86
+    },
+    {
+      "epoch": 1.0990990990990992,
+      "grad_norm": 0.23278285562992096,
+      "learning_rate": 1.4094705922787687e-05,
+      "loss": 0.9647,
+      "step": 87
+    },
+    {
+      "epoch": 1.1116333725029377,
+      "grad_norm": 0.26890018582344055,
+      "learning_rate": 1.3496961026017687e-05,
+      "loss": 1.0008,
+      "step": 88
+    },
+    {
+      "epoch": 1.1241676459067764,
+      "grad_norm": 0.34293997287750244,
+      "learning_rate": 1.2944599093024267e-05,
+      "loss": 1.1211,
+      "step": 89
+    },
+    {
+      "epoch": 1.136701919310615,
+      "grad_norm": 0.36756041646003723,
+      "learning_rate": 1.2438224123471442e-05,
+      "loss": 1.1147,
+      "step": 90
+    },
+    {
+      "epoch": 1.1492361927144537,
+      "grad_norm": 0.47754383087158203,
+      "learning_rate": 1.1978389830953907e-05,
+      "loss": 1.1506,
+      "step": 91
+    },
+    {
+      "epoch": 1.1617704661182922,
+      "grad_norm": 0.9767032265663147,
+      "learning_rate": 1.1565599037519316e-05,
+      "loss": 1.5687,
+      "step": 92
+    },
+    {
+      "epoch": 1.1743047395221309,
+      "grad_norm": 0.27648741006851196,
+      "learning_rate": 1.1200303123839742e-05,
+      "loss": 1.2947,
+      "step": 93
+    },
+    {
+      "epoch": 1.1868390129259694,
+      "grad_norm": 0.16597148776054382,
+      "learning_rate": 1.088290153563358e-05,
+      "loss": 1.1376,
+      "step": 94
+    },
+    {
+      "epoch": 1.199373286329808,
+      "grad_norm": 0.18325175344944,
+      "learning_rate": 1.0613741346877497e-05,
+      "loss": 1.0643,
+      "step": 95
+    },
+    {
+      "epoch": 1.2119075597336466,
+      "grad_norm": 0.17501665651798248,
+      "learning_rate": 1.0393116880286118e-05,
+      "loss": 0.9975,
+      "step": 96
+    },
+    {
+      "epoch": 1.2244418331374853,
+      "grad_norm": 0.1747180074453354,
+      "learning_rate": 1.0221269385474488e-05,
+      "loss": 0.9486,
+      "step": 97
+    },
+    {
+      "epoch": 1.2369761065413238,
+      "grad_norm": 0.18863636255264282,
+      "learning_rate": 1.0098386775155147e-05,
+      "loss": 0.9441,
+      "step": 98
+    },
+    {
+      "epoch": 1.2495103799451626,
+      "grad_norm": 0.21438157558441162,
+      "learning_rate": 1.0024603419658329e-05,
+      "loss": 0.9852,
+      "step": 99
+    },
+    {
+      "epoch": 1.262044653349001,
+      "grad_norm": 0.2572687864303589,
+      "learning_rate": 1e-05,
+      "loss": 1.0719,
+      "step": 100
+    },
+    {
+      "epoch": 1.262044653349001,
+      "eval_loss": 1.0160294771194458,
+      "eval_runtime": 0.504,
+      "eval_samples_per_second": 99.214,
+      "eval_steps_per_second": 25.796,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -587,12 +770,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.26601158625067e+17,
+  "total_flos": 1.6898819529847603e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null