Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6135ff686719b9be6331acbf6b47398de1d1c4aa9219c86f7ac7425405443bc4
+oid sha256:07b0e909cdfe7d161b6f5bf72fc7a94d1aa6aa8c181c34453e6951107a9cd39f
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32fff42a104ae71013247c4a56151e2ce99ed97dd39ba205186d342a5f81324b
+oid sha256:8456a8db082fa56b574b57ba41eaf2a8bc24d8a9359f4c91bd7a09a706af4ef1
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31219084b467b97768d0c2266a9ac1fa136aa77e7a456c5fe811bd8a008c304d
+oid sha256:50c0ae168e2ac6423fc22e5c53b5afe9cd2a546fa9508290240454dc5b510159
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e364602b08d6e7bce980ac532681b92b90e8573a99149b3bfe3fc9c168a42778
+oid sha256:fa227bfc5d392392afa2a54851b7dcbf15cf8ba848c20449a4aec2d922256866
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:465a00ab0425765e7347a156c4b8feff78bd094df0231f37892a2473663631ec
+oid sha256:b5287b38cd630aab26ddfbc0b0a2e825c95832185fbe17db2cc7cd867181b6dc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9913e481e3398d89683d00a3e7aebbd363947d2c1209e74fa33e7051afbfb940
+oid sha256:4494aa87bcf898f5c06998891d4aee323c55900b54a38390c1b9b9b9777cc078
 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": 1.3022475242614746,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.18636434228917534,
+  "best_metric": 1.296454668045044,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.24848578971890045,
   "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": 42.783,
       "eval_steps_per_second": 11.124,
       "step": 75
+    },
+    {
+      "epoch": 0.18884920018636434,
+      "grad_norm": 0.11220304667949677,
+      "learning_rate": 2.3444344707738015e-05,
+      "loss": 1.047,
+      "step": 76
+    },
+    {
+      "epoch": 0.19133405808355336,
+      "grad_norm": 0.1274535059928894,
+      "learning_rate": 2.2400865784401e-05,
+      "loss": 1.1196,
+      "step": 77
+    },
+    {
+      "epoch": 0.19381891598074236,
+      "grad_norm": 0.13804402947425842,
+      "learning_rate": 2.1393033535713093e-05,
+      "loss": 1.1235,
+      "step": 78
+    },
+    {
+      "epoch": 0.19630377387793135,
+      "grad_norm": 0.14971572160720825,
+      "learning_rate": 2.0421950011441354e-05,
+      "loss": 1.1777,
+      "step": 79
+    },
+    {
+      "epoch": 0.19878863177512035,
+      "grad_norm": 0.18402217328548431,
+      "learning_rate": 1.9488677077162295e-05,
+      "loss": 1.179,
+      "step": 80
+    },
+    {
+      "epoch": 0.20127348967230937,
+      "grad_norm": 0.21275171637535095,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 1.2864,
+      "step": 81
+    },
+    {
+      "epoch": 0.20375834756949837,
+      "grad_norm": 0.2665954530239105,
+      "learning_rate": 1.77396025983391e-05,
+      "loss": 1.2847,
+      "step": 82
+    },
+    {
+      "epoch": 0.20624320546668737,
+      "grad_norm": 0.3545299768447876,
+      "learning_rate": 1.6925713641057904e-05,
+      "loss": 1.4364,
+      "step": 83
+    },
+    {
+      "epoch": 0.20872806336387636,
+      "grad_norm": 0.44620993733406067,
+      "learning_rate": 1.6153458356909176e-05,
+      "loss": 1.4322,
+      "step": 84
+    },
+    {
+      "epoch": 0.2112129212610654,
+      "grad_norm": 0.5365117788314819,
+      "learning_rate": 1.5423681195707997e-05,
+      "loss": 1.3801,
+      "step": 85
+    },
+    {
+      "epoch": 0.2136977791582544,
+      "grad_norm": 0.6859667897224426,
+      "learning_rate": 1.4737180158065644e-05,
+      "loss": 1.5157,
+      "step": 86
+    },
+    {
+      "epoch": 0.21618263705544338,
+      "grad_norm": 1.0796610116958618,
+      "learning_rate": 1.4094705922787687e-05,
+      "loss": 1.8931,
+      "step": 87
+    },
+    {
+      "epoch": 0.2186674949526324,
+      "grad_norm": 0.15191839635372162,
+      "learning_rate": 1.3496961026017687e-05,
+      "loss": 1.0785,
+      "step": 88
+    },
+    {
+      "epoch": 0.2211523528498214,
+      "grad_norm": 0.12437998503446579,
+      "learning_rate": 1.2944599093024267e-05,
+      "loss": 1.0752,
+      "step": 89
+    },
+    {
+      "epoch": 0.2236372107470104,
+      "grad_norm": 0.12759096920490265,
+      "learning_rate": 1.2438224123471442e-05,
+      "loss": 1.0812,
+      "step": 90
+    },
+    {
+      "epoch": 0.2261220686441994,
+      "grad_norm": 0.14436273276805878,
+      "learning_rate": 1.1978389830953907e-05,
+      "loss": 1.1591,
+      "step": 91
+    },
+    {
+      "epoch": 0.22860692654138842,
+      "grad_norm": 0.1650199145078659,
+      "learning_rate": 1.1565599037519316e-05,
+      "loss": 1.1473,
+      "step": 92
+    },
+    {
+      "epoch": 0.23109178443857742,
+      "grad_norm": 0.1937108039855957,
+      "learning_rate": 1.1200303123839742e-05,
+      "loss": 1.2184,
+      "step": 93
+    },
+    {
+      "epoch": 0.23357664233576642,
+      "grad_norm": 0.2247273474931717,
+      "learning_rate": 1.088290153563358e-05,
+      "loss": 1.3174,
+      "step": 94
+    },
+    {
+      "epoch": 0.23606150023295544,
+      "grad_norm": 0.2764604687690735,
+      "learning_rate": 1.0613741346877497e-05,
+      "loss": 1.3146,
+      "step": 95
+    },
+    {
+      "epoch": 0.23854635813014444,
+      "grad_norm": 0.359423965215683,
+      "learning_rate": 1.0393116880286118e-05,
+      "loss": 1.4263,
+      "step": 96
+    },
+    {
+      "epoch": 0.24103121602733343,
+      "grad_norm": 0.4706696569919586,
+      "learning_rate": 1.0221269385474488e-05,
+      "loss": 1.3916,
+      "step": 97
+    },
+    {
+      "epoch": 0.24351607392452243,
+      "grad_norm": 0.598770797252655,
+      "learning_rate": 1.0098386775155147e-05,
+      "loss": 1.575,
+      "step": 98
+    },
+    {
+      "epoch": 0.24600093182171145,
+      "grad_norm": 0.7586723566055298,
+      "learning_rate": 1.0024603419658329e-05,
+      "loss": 1.5519,
+      "step": 99
+    },
+    {
+      "epoch": 0.24848578971890045,
+      "grad_norm": 1.7414568662643433,
+      "learning_rate": 1e-05,
+      "loss": 2.0062,
+      "step": 100
+    },
+    {
+      "epoch": 0.24848578971890045,
+      "eval_loss": 1.296454668045044,
+      "eval_runtime": 1.1762,
+      "eval_samples_per_second": 42.511,
+      "eval_steps_per_second": 11.053,
+      "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