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:e428201636aa64c11c144521a9430fecbd72e6a371424359c31fe1b9f2a972f8
+oid sha256:909212922a5345aa578d9b1b45d32dd60ee37c3ca52648fa8fbc54b561fdb19c
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c49d4c5c48d6c419ff5e0303478d2eed2704dc19a6fb2f98b31a70d9f9f8eeb6
+oid sha256:8b9b3a81defebfeeab3a5df7177e605277962ddbca56c35bad839cdece3f584e
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8febc93c8fcf92d491ea7cbc1fc6a662583d43b0a72fdca3a550c194df77e11
+oid sha256:edf64ddaf4a2a05719304dfc37e5bd7dbd8606afe0243e381ba7a8b73d2c765d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1546f084086715834389ed44b67b814f6f5bab89ca6b7f34d2f9fff371fec01b
+oid sha256:e7890a4fcc2891517168a288d89048984d60308d6e7ac75c9550a8d0dfdaec9e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fb36110fbb4ceab5aed585179b989c3dfa9b30e9f9a16515cb89a59206f2c24
+oid sha256:5242811caa1e2f72d73a507b565d3accfb953b9d7fba7e43edc28f9b78bc93b4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00fd78cb62810535d698a7649d511e7eb62caa553a8425ace6d6360f50039393
+oid sha256:2216e4dcb8bb509e2573e50ccfc695ef46e2360c98c2ef27453a8cc0aaf583af
 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": 0.3565179407596588,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.2408912978018669,
+  "best_metric": 0.33776161074638367,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.32118839706915586,
   "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": 99.395,
       "eval_steps_per_second": 25.843,
       "step": 75
+    },
+    {
+      "epoch": 0.24410318177255846,
+      "grad_norm": 2.8982174396514893,
+      "learning_rate": 2.3444344707738015e-05,
+      "loss": 0.6377,
+      "step": 76
+    },
+    {
+      "epoch": 0.24731506574325002,
+      "grad_norm": 2.408865451812744,
+      "learning_rate": 2.2400865784401e-05,
+      "loss": 0.4874,
+      "step": 77
+    },
+    {
+      "epoch": 0.25052694971394157,
+      "grad_norm": 2.227947473526001,
+      "learning_rate": 2.1393033535713093e-05,
+      "loss": 0.3836,
+      "step": 78
+    },
+    {
+      "epoch": 0.2537388336846331,
+      "grad_norm": 1.9388247728347778,
+      "learning_rate": 2.0421950011441354e-05,
+      "loss": 0.2834,
+      "step": 79
+    },
+    {
+      "epoch": 0.2569507176553247,
+      "grad_norm": 1.9769359827041626,
+      "learning_rate": 1.9488677077162295e-05,
+      "loss": 0.3367,
+      "step": 80
+    },
+    {
+      "epoch": 0.2601626016260163,
+      "grad_norm": 2.0125112533569336,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 0.3863,
+      "step": 81
+    },
+    {
+      "epoch": 0.26337448559670784,
+      "grad_norm": 1.9390735626220703,
+      "learning_rate": 1.77396025983391e-05,
+      "loss": 0.393,
+      "step": 82
+    },
+    {
+      "epoch": 0.2665863695673994,
+      "grad_norm": 1.5394026041030884,
+      "learning_rate": 1.6925713641057904e-05,
+      "loss": 0.6196,
+      "step": 83
+    },
+    {
+      "epoch": 0.26979825353809095,
+      "grad_norm": 2.0069022178649902,
+      "learning_rate": 1.6153458356909176e-05,
+      "loss": 0.3049,
+      "step": 84
+    },
+    {
+      "epoch": 0.2730101375087825,
+      "grad_norm": 1.0801819562911987,
+      "learning_rate": 1.5423681195707997e-05,
+      "loss": 0.2012,
+      "step": 85
+    },
+    {
+      "epoch": 0.27622202147947406,
+      "grad_norm": 1.3949787616729736,
+      "learning_rate": 1.4737180158065644e-05,
+      "loss": 0.2644,
+      "step": 86
+    },
+    {
+      "epoch": 0.2794339054501656,
+      "grad_norm": 1.527002215385437,
+      "learning_rate": 1.4094705922787687e-05,
+      "loss": 0.2278,
+      "step": 87
+    },
+    {
+      "epoch": 0.28264578942085716,
+      "grad_norm": 1.6759589910507202,
+      "learning_rate": 1.3496961026017687e-05,
+      "loss": 0.3889,
+      "step": 88
+    },
+    {
+      "epoch": 0.2858576733915487,
+      "grad_norm": 2.828400135040283,
+      "learning_rate": 1.2944599093024267e-05,
+      "loss": 0.5727,
+      "step": 89
+    },
+    {
+      "epoch": 0.28906955736224027,
+      "grad_norm": 2.203261375427246,
+      "learning_rate": 1.2438224123471442e-05,
+      "loss": 0.3116,
+      "step": 90
+    },
+    {
+      "epoch": 0.2922814413329318,
+      "grad_norm": 1.2678191661834717,
+      "learning_rate": 1.1978389830953907e-05,
+      "loss": 0.232,
+      "step": 91
+    },
+    {
+      "epoch": 0.29549332530362343,
+      "grad_norm": 1.533488154411316,
+      "learning_rate": 1.1565599037519316e-05,
+      "loss": 0.3384,
+      "step": 92
+    },
+    {
+      "epoch": 0.298705209274315,
+      "grad_norm": 1.5737160444259644,
+      "learning_rate": 1.1200303123839742e-05,
+      "loss": 0.3892,
+      "step": 93
+    },
+    {
+      "epoch": 0.30191709324500654,
+      "grad_norm": 2.21943998336792,
+      "learning_rate": 1.088290153563358e-05,
+      "loss": 0.4123,
+      "step": 94
+    },
+    {
+      "epoch": 0.3051289772156981,
+      "grad_norm": 1.0407116413116455,
+      "learning_rate": 1.0613741346877497e-05,
+      "loss": 0.4279,
+      "step": 95
+    },
+    {
+      "epoch": 0.30834086118638965,
+      "grad_norm": 1.2876520156860352,
+      "learning_rate": 1.0393116880286118e-05,
+      "loss": 0.4044,
+      "step": 96
+    },
+    {
+      "epoch": 0.3115527451570812,
+      "grad_norm": 1.4480308294296265,
+      "learning_rate": 1.0221269385474488e-05,
+      "loss": 0.1674,
+      "step": 97
+    },
+    {
+      "epoch": 0.31476462912777275,
+      "grad_norm": 0.8228076100349426,
+      "learning_rate": 1.0098386775155147e-05,
+      "loss": 0.2878,
+      "step": 98
+    },
+    {
+      "epoch": 0.3179765130984643,
+      "grad_norm": 1.4703351259231567,
+      "learning_rate": 1.0024603419658329e-05,
+      "loss": 0.2122,
+      "step": 99
+    },
+    {
+      "epoch": 0.32118839706915586,
+      "grad_norm": 0.9804506897926331,
+      "learning_rate": 1e-05,
+      "loss": 0.1397,
+      "step": 100
+    },
+    {
+      "epoch": 0.32118839706915586,
+      "eval_loss": 0.33776161074638367,
+      "eval_runtime": 0.5035,
+      "eval_samples_per_second": 99.308,
+      "eval_steps_per_second": 25.82,
+      "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": 1.250124588122112e+17,
+  "total_flos": 1.666832784162816e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null