Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ac2f57ef27892165b3debba456bc051f731e94989ee5b9a36e7e2853a39d79b
+oid sha256:6d7ebc7c2c21c761cb4536a7a1c7a14729d13ca112f548caf08efe9e066fa168
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd8b9b9f0d216ca578eed74ffdddc0d676160ffd313d1829d6183770b1970e3b
+oid sha256:579955f860e60e6ef5716e7aedc41ec5de601c41addad7dedc49149a766356e4
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c63aa8a5b7bd80c1beba2503d930f42cbc4a94e6c1354e3b960a10e83d64456c
+oid sha256:d00d20cace0117a590e41827920241c0ef26bf135d8e5a4a409b30729caeafb9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d475cc83b156b8e4773efe5d7a02026190c2fa8656874e6dc8eacee45430e255
+oid sha256:db48a9408af4c725d611f5156bef391afb3c00bfef00aa579599322c11ccdc65
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0d5d96bb8ddda7a546d9e505af9afffadb3ef4cde661f1fad8195d24569bc14
+oid sha256:93bad2e7e51df4a62e40d203287452d31e3a622220daecdbab7b5dda3b5782eb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbb0033cd8af120fcbc1a7dde9f2990fc598a196f277872cd108b50aa2072054
+oid sha256:e980aca005661c95cb0da765be7063fec89fc82ce0f9c2cce805c701e207035e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
+oid sha256:0b823f3900a3c8aa20bff7ce05b4e552f6bc019793f00b0bb20027204b5c704a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6014140844345093,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.03157063930544594,
+  "best_metric": 1.5624194145202637,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.0473559589581689,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 11.085,
       "eval_steps_per_second": 2.882,
       "step": 50
+    },
+    {
+      "epoch": 0.032202052091554856,
+      "grad_norm": 0.2147873342037201,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.1322,
+      "step": 51
+    },
+    {
+      "epoch": 0.032833464877663775,
+      "grad_norm": 0.24819572269916534,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 1.2126,
+      "step": 52
+    },
+    {
+      "epoch": 0.033464877663772694,
+      "grad_norm": 0.3118667006492615,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 1.4319,
+      "step": 53
+    },
+    {
+      "epoch": 0.03409629044988161,
+      "grad_norm": 0.3383065164089203,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.4539,
+      "step": 54
+    },
+    {
+      "epoch": 0.03472770323599053,
+      "grad_norm": 0.36920657753944397,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 1.4881,
+      "step": 55
+    },
+    {
+      "epoch": 0.03535911602209945,
+      "grad_norm": 0.36341094970703125,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 1.5277,
+      "step": 56
+    },
+    {
+      "epoch": 0.03599052880820837,
+      "grad_norm": 0.39822858572006226,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.6063,
+      "step": 57
+    },
+    {
+      "epoch": 0.03662194159431729,
+      "grad_norm": 0.38986867666244507,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 1.6374,
+      "step": 58
+    },
+    {
+      "epoch": 0.03725335438042621,
+      "grad_norm": 0.41126537322998047,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 1.6176,
+      "step": 59
+    },
+    {
+      "epoch": 0.037884767166535126,
+      "grad_norm": 0.49524790048599243,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.5901,
+      "step": 60
+    },
+    {
+      "epoch": 0.03851617995264404,
+      "grad_norm": 0.6080181002616882,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 1.697,
+      "step": 61
+    },
+    {
+      "epoch": 0.03914759273875296,
+      "grad_norm": 1.0019196271896362,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 1.7872,
+      "step": 62
+    },
+    {
+      "epoch": 0.039779005524861875,
+      "grad_norm": 0.32042133808135986,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.3077,
+      "step": 63
+    },
+    {
+      "epoch": 0.040410418310970794,
+      "grad_norm": 0.2187422215938568,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 1.2076,
+      "step": 64
+    },
+    {
+      "epoch": 0.04104183109707971,
+      "grad_norm": 0.24013711512088776,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 1.3274,
+      "step": 65
+    },
+    {
+      "epoch": 0.04167324388318863,
+      "grad_norm": 0.2474597990512848,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.3793,
+      "step": 66
+    },
+    {
+      "epoch": 0.04230465666929755,
+      "grad_norm": 0.2827232778072357,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 1.4785,
+      "step": 67
+    },
+    {
+      "epoch": 0.04293606945540647,
+      "grad_norm": 0.3119887113571167,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 1.4926,
+      "step": 68
+    },
+    {
+      "epoch": 0.04356748224151539,
+      "grad_norm": 0.32945671677589417,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.5326,
+      "step": 69
+    },
+    {
+      "epoch": 0.04419889502762431,
+      "grad_norm": 0.37132251262664795,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 1.6272,
+      "step": 70
+    },
+    {
+      "epoch": 0.044830307813733226,
+      "grad_norm": 0.4000647962093353,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 1.5623,
+      "step": 71
+    },
+    {
+      "epoch": 0.045461720599842145,
+      "grad_norm": 0.43274882435798645,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.6642,
+      "step": 72
+    },
+    {
+      "epoch": 0.046093133385951064,
+      "grad_norm": 0.4920554459095001,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 1.7317,
+      "step": 73
+    },
+    {
+      "epoch": 0.04672454617205998,
+      "grad_norm": 0.6907088160514832,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 1.7506,
+      "step": 74
+    },
+    {
+      "epoch": 0.0473559589581689,
+      "grad_norm": 1.1546982526779175,
+      "learning_rate": 1e-05,
+      "loss": 1.7811,
+      "step": 75
+    },
+    {
+      "epoch": 0.0473559589581689,
+      "eval_loss": 1.5624194145202637,
+      "eval_runtime": 4.4827,
+      "eval_samples_per_second": 11.154,
+      "eval_steps_per_second": 2.9,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -404,12 +587,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.97378185780265e+17,
+  "total_flos": 8.963470388814152e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null