Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76ed789327e973a3bb8e47a7ccdce489a6c96f9cb726bb427bc5db3e54905898
+oid sha256:2232bec3b9126beebadfbb23b936c4dad57aa405908c7de07b4b06a0421bbbc1
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ba1019bbf87efbaa0de74c415d20380557a44d39946a3610f64b294252d3caa
+oid sha256:10987656c92d162b01e9f47e4bde389b9163ae95719200490cb6183f0a303024
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b047250531bd2d5ea5ba55912795d43094211ef8b7742fa867556fa20ba34133
+oid sha256:d1a38037c230407566bd6e40d04ec416671cca79dc75b002b2c0337dcfe67893
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4de4e47a8e936ece29eeafd62986b4cd997ed52c5d9f3c9915f2cd50fbfa11d4
+oid sha256:786f6ad08acf7e474840f044f85887a6924762e8ea5ff460ccea2ad64bdf6ba0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5188d2ca412d671040dd9291ab948bea5b2e0430ef528e5423bd546f865d3f0c
+oid sha256:dede88c13fc8848937e77bccefd415e1dce2aa3ccbe170bd8ec102ae275c47a4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0d3b6020ff042970aefd3227640eadaed46d0405eda0f3aba5bd147ca1566ce
+oid sha256:9cc7fcae584d0f71e3805f7eac3f7706559a34ae86fc44f00e511392ad0162d2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
+oid sha256:1fd9769bcb04586b7ead175b588f12a0bbbeba72d5f308b868ba8f36b77aa801
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 10.357850074768066,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.9795918367346939,
+  "epoch": 1.2453061224489796,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 95,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,146 @@
       "eval_samples_per_second": 461.853,
       "eval_steps_per_second": 120.082,
       "step": 75
+    },
+    {
+      "epoch": 0.9926530612244898,
+      "grad_norm": 0.10444188117980957,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 10.362,
+      "step": 76
+    },
+    {
+      "epoch": 1.010204081632653,
+      "grad_norm": 0.19977551698684692,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 19.1788,
+      "step": 77
+    },
+    {
+      "epoch": 1.023265306122449,
+      "grad_norm": 0.11170919239521027,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 9.8607,
+      "step": 78
+    },
+    {
+      "epoch": 1.036326530612245,
+      "grad_norm": 0.10081058740615845,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 10.283,
+      "step": 79
+    },
+    {
+      "epoch": 1.0493877551020407,
+      "grad_norm": 0.09270654618740082,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 10.3654,
+      "step": 80
+    },
+    {
+      "epoch": 1.0624489795918368,
+      "grad_norm": 0.09391531348228455,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 10.328,
+      "step": 81
+    },
+    {
+      "epoch": 1.0755102040816327,
+      "grad_norm": 0.09005478024482727,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 10.4514,
+      "step": 82
+    },
+    {
+      "epoch": 1.0885714285714285,
+      "grad_norm": 0.07758020609617233,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 10.3433,
+      "step": 83
+    },
+    {
+      "epoch": 1.1016326530612246,
+      "grad_norm": 0.08793393522500992,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 10.2283,
+      "step": 84
+    },
+    {
+      "epoch": 1.1146938775510205,
+      "grad_norm": 0.08602005243301392,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 10.4169,
+      "step": 85
+    },
+    {
+      "epoch": 1.1277551020408163,
+      "grad_norm": 0.0865188017487526,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 10.4049,
+      "step": 86
+    },
+    {
+      "epoch": 1.1408163265306122,
+      "grad_norm": 0.08879414200782776,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 10.4035,
+      "step": 87
+    },
+    {
+      "epoch": 1.1538775510204082,
+      "grad_norm": 0.1172807589173317,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 10.6301,
+      "step": 88
+    },
+    {
+      "epoch": 1.166938775510204,
+      "grad_norm": 0.07411655783653259,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 8.18,
+      "step": 89
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.13027232885360718,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 12.4071,
+      "step": 90
+    },
+    {
+      "epoch": 1.193061224489796,
+      "grad_norm": 0.10894075036048889,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 10.2247,
+      "step": 91
+    },
+    {
+      "epoch": 1.2061224489795919,
+      "grad_norm": 0.09735233336687088,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 10.3904,
+      "step": 92
+    },
+    {
+      "epoch": 1.2191836734693877,
+      "grad_norm": 0.09232284873723984,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 10.2204,
+      "step": 93
+    },
+    {
+      "epoch": 1.2322448979591836,
+      "grad_norm": 0.07823080569505692,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 10.2978,
+      "step": 94
+    },
+    {
+      "epoch": 1.2453061224489796,
+      "grad_norm": 0.08124446123838425,
+      "learning_rate": 1e-05,
+      "loss": 10.4621,
+      "step": 95
     }
   ],
   "logging_steps": 1,
@@ -587,12 +727,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 64259009544192.0,
+  "total_flos": 81392963420160.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null