Training in progress, step 132, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65c3c008fbebe693d48c3c3c289982803a9089ddc206dd90739ec5a2574c1f40
+oid sha256:0477ae16092e920f1a70285ec0f6d2a1ad995f8c873e61b0e023ffc0d47ff57d
 size 130583912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:154095e3f56c856d2019627a7a0e1deb4d5a420097aba2ee5ff882113dacde7f
+oid sha256:3a1c59e022210ab0f0eb69ca2730f81f70cad23d48653d5cd87a7b12ca7f7112
 size 261311226

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2de528baee32c70568e916c3b8f97af886cc74df910fe8ed9e8f92fd7c304f60
+oid sha256:4628cfb5a20dd1151dbfc415cbd7fc7464cb18b044ebb8faa5231ab7e2521acf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33fdeac700456f590554babdb1bb06f3350befc1bacd0a19b3d33f64c1a1c32d
+oid sha256:86e6e29d81cb95f8c8a14f9b3d672190de4431bdbc9834b879a12c3bb9d7d827
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.39477089047431946,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 1.5173067804646752,
+  "epoch": 2.002844950213371,
   "eval_steps": 25,
-  "global_step": 100,
+  "global_step": 132,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -747,6 +747,238 @@
       "eval_samples_per_second": 11.898,
       "eval_steps_per_second": 11.898,
       "step": 100
+    },
+    {
+      "epoch": 1.5324798482693218,
+      "grad_norm": 8.945897102355957,
+      "learning_rate": 4.5308376785048434e-05,
+      "loss": 11.1062,
+      "step": 101
+    },
+    {
+      "epoch": 1.5476529160739687,
+      "grad_norm": 9.844161987304688,
+      "learning_rate": 4.257717175284103e-05,
+      "loss": 10.4609,
+      "step": 102
+    },
+    {
+      "epoch": 1.5628259838786156,
+      "grad_norm": 9.294745445251465,
+      "learning_rate": 3.991719503517014e-05,
+      "loss": 10.6322,
+      "step": 103
+    },
+    {
+      "epoch": 1.5779990516832623,
+      "grad_norm": 9.901968002319336,
+      "learning_rate": 3.733021036942205e-05,
+      "loss": 11.3513,
+      "step": 104
+    },
+    {
+      "epoch": 1.593172119487909,
+      "grad_norm": 9.366765975952148,
+      "learning_rate": 3.481793309451e-05,
+      "loss": 10.2632,
+      "step": 105
+    },
+    {
+      "epoch": 1.6083451872925556,
+      "grad_norm": 8.39588451385498,
+      "learning_rate": 3.238202901349345e-05,
+      "loss": 10.2529,
+      "step": 106
+    },
+    {
+      "epoch": 1.6235182550972025,
+      "grad_norm": 8.285764694213867,
+      "learning_rate": 3.0024113289042094e-05,
+      "loss": 9.9579,
+      "step": 107
+    },
+    {
+      "epoch": 1.6386913229018494,
+      "grad_norm": 8.389649391174316,
+      "learning_rate": 2.774574937247831e-05,
+      "loss": 10.3428,
+      "step": 108
+    },
+    {
+      "epoch": 1.653864390706496,
+      "grad_norm": 8.863457679748535,
+      "learning_rate": 2.554844796710716e-05,
+      "loss": 9.0607,
+      "step": 109
+    },
+    {
+      "epoch": 1.6690374585111427,
+      "grad_norm": 8.510146141052246,
+      "learning_rate": 2.3433666026522153e-05,
+      "loss": 9.3396,
+      "step": 110
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 9.09020709991455,
+      "learning_rate": 2.1402805788550138e-05,
+      "loss": 9.223,
+      "step": 111
+    },
+    {
+      "epoch": 1.6993835941204363,
+      "grad_norm": 8.539032936096191,
+      "learning_rate": 1.945721384547671e-05,
+      "loss": 7.2793,
+      "step": 112
+    },
+    {
+      "epoch": 1.714556661925083,
+      "grad_norm": 9.459700584411621,
+      "learning_rate": 1.759818025116787e-05,
+      "loss": 7.6996,
+      "step": 113
+    },
+    {
+      "epoch": 1.7297297297297298,
+      "grad_norm": 11.580260276794434,
+      "learning_rate": 1.5826937665680693e-05,
+      "loss": 7.68,
+      "step": 114
+    },
+    {
+      "epoch": 1.7449027975343765,
+      "grad_norm": 8.748165130615234,
+      "learning_rate": 1.4144660537929287e-05,
+      "loss": 13.0615,
+      "step": 115
+    },
+    {
+      "epoch": 1.7600758653390232,
+      "grad_norm": 9.052087783813477,
+      "learning_rate": 1.2552464326949302e-05,
+      "loss": 13.9056,
+      "step": 116
+    },
+    {
+      "epoch": 1.7752489331436698,
+      "grad_norm": 9.413413047790527,
+      "learning_rate": 1.105140476227575e-05,
+      "loss": 13.1337,
+      "step": 117
+    },
+    {
+      "epoch": 1.7904220009483167,
+      "grad_norm": 8.633859634399414,
+      "learning_rate": 9.64247714392597e-06,
+      "loss": 11.1511,
+      "step": 118
+    },
+    {
+      "epoch": 1.8055950687529636,
+      "grad_norm": 7.859529972076416,
+      "learning_rate": 8.32661568245081e-06,
+      "loss": 10.06,
+      "step": 119
+    },
+    {
+      "epoch": 1.8207681365576103,
+      "grad_norm": 8.01181697845459,
+      "learning_rate": 7.104692879492624e-06,
+      "loss": 10.4743,
+      "step": 120
+    },
+    {
+      "epoch": 1.835941204362257,
+      "grad_norm": 9.660663604736328,
+      "learning_rate": 5.977518949259735e-06,
+      "loss": 11.0629,
+      "step": 121
+    },
+    {
+      "epoch": 1.8511142721669036,
+      "grad_norm": 8.536215782165527,
+      "learning_rate": 4.945841281301943e-06,
+      "loss": 10.3549,
+      "step": 122
+    },
+    {
+      "epoch": 1.8662873399715505,
+      "grad_norm": 8.264043807983398,
+      "learning_rate": 4.010343944942618e-06,
+      "loss": 9.8312,
+      "step": 123
+    },
+    {
+      "epoch": 1.8814604077761974,
+      "grad_norm": 8.763490676879883,
+      "learning_rate": 3.1716472356963286e-06,
+      "loss": 8.8429,
+      "step": 124
+    },
+    {
+      "epoch": 1.896633475580844,
+      "grad_norm": 9.253498077392578,
+      "learning_rate": 2.430307263972547e-06,
+      "loss": 10.0951,
+      "step": 125
+    },
+    {
+      "epoch": 1.896633475580844,
+      "eval_loss": 0.3835863471031189,
+      "eval_runtime": 4.1958,
+      "eval_samples_per_second": 11.917,
+      "eval_steps_per_second": 11.917,
+      "step": 125
+    },
+    {
+      "epoch": 1.9118065433854907,
+      "grad_norm": 8.449151039123535,
+      "learning_rate": 1.7868155863384415e-06,
+      "loss": 9.1299,
+      "step": 126
+    },
+    {
+      "epoch": 1.9269796111901374,
+      "grad_norm": 8.359270095825195,
+      "learning_rate": 1.2415988795847765e-06,
+      "loss": 9.0518,
+      "step": 127
+    },
+    {
+      "epoch": 1.9421526789947843,
+      "grad_norm": 8.54788589477539,
+      "learning_rate": 7.950186578116413e-07,
+      "loss": 7.7242,
+      "step": 128
+    },
+    {
+      "epoch": 1.9573257467994312,
+      "grad_norm": 8.631213188171387,
+      "learning_rate": 4.473710327209945e-07,
+      "loss": 6.4852,
+      "step": 129
+    },
+    {
+      "epoch": 1.9724988146040778,
+      "grad_norm": 8.945975303649902,
+      "learning_rate": 1.988865172754206e-07,
+      "loss": 7.753,
+      "step": 130
+    },
+    {
+      "epoch": 1.9876718824087245,
+      "grad_norm": 8.31573486328125,
+      "learning_rate": 4.972987285304375e-08,
+      "loss": 11.2559,
+      "step": 131
+    },
+    {
+      "epoch": 2.002844950213371,
+      "grad_norm": 8.791767120361328,
+      "learning_rate": 0.0,
+      "loss": 9.4748,
+      "step": 132
     }
   ],
   "logging_steps": 1,
@@ -770,12 +1002,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.391015187972096e+17,
+  "total_flos": 1.8361400481231667e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null