Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a1afa422d3bd63b74d693a7fb6435e982dfddf0eb1c543ebc6e4f3f73b6c434
+oid sha256:6112681977402ecd51d1a5b58e0d1c43d3bae3946fa5984a8c7271e396b4c4c2
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c3fa857a21f16395f16816e62314345f5bc15af999bad691c6219f005b497b3
+oid sha256:bafef6ea8ebdfdbbecb4fa4241d66558b5cb4fafffd330f79a3d1b2937a5a25c
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba5249158a9341467ec9a458f4c55976aaf99613f1ceca0d1b229df5dde335a
+oid sha256:fe90c93dda13d661f9638045de6557adef3111740432416064352f53d7e5ccec
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63348abc915cc10b4aefe32f946a737326b87c65a4b83f47569c8676fff4643f
+oid sha256:797960b3dcb35372652b4ccef35fe6f60f92d1382b6f207a0c3c9ab051d23a3d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1a08e35270ed54ec380226dd3f79657210fb7cc81f90f8a7dca7c415e692186
+oid sha256:5f52f9472930ffc114b64548b0027cd90b5adc91acb95612b1201881b3dfb826
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56b59d63cb4d2c6afca1aec9e0eb5e90b218ec05ba6313baa0ec5d6bcf2c57ee
+oid sha256:220fb4198ad2b455737494e5e102d6dd7dab5c06e1707f86c52f21a7b22b226e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d5f446d81df8b8e6d5d3423a874831fec3d08bffbe4980db71b54ceb3e7bd4
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.047884464263916,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.4416635995583364,
+  "best_metric": 2.043283700942993,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.5888847994111152,
   "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": 62.613,
       "eval_steps_per_second": 3.913,
       "step": 75
+    },
+    {
+      "epoch": 0.44755244755244755,
+      "grad_norm": 0.3272382915019989,
+      "learning_rate": 1.4938160786375572e-05,
+      "loss": 1.9332,
+      "step": 76
+    },
+    {
+      "epoch": 0.4534412955465587,
+      "grad_norm": 0.27222368121147156,
+      "learning_rate": 1.3778739760445552e-05,
+      "loss": 1.9674,
+      "step": 77
+    },
+    {
+      "epoch": 0.45933014354066987,
+      "grad_norm": 0.19433099031448364,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 1.9804,
+      "step": 78
+    },
+    {
+      "epoch": 0.465218991534781,
+      "grad_norm": 0.1676786243915558,
+      "learning_rate": 1.157994445715706e-05,
+      "loss": 2.0109,
+      "step": 79
+    },
+    {
+      "epoch": 0.4711078395288922,
+      "grad_norm": 0.17873966693878174,
+      "learning_rate": 1.0542974530180327e-05,
+      "loss": 2.0455,
+      "step": 80
+    },
+    {
+      "epoch": 0.47699668752300334,
+      "grad_norm": 0.28810998797416687,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.0922,
+      "step": 81
+    },
+    {
+      "epoch": 0.48288553551711444,
+      "grad_norm": 0.33509114384651184,
+      "learning_rate": 8.599558442598998e-06,
+      "loss": 2.1399,
+      "step": 82
+    },
+    {
+      "epoch": 0.4887743835112256,
+      "grad_norm": 0.1772329956293106,
+      "learning_rate": 7.695237378953223e-06,
+      "loss": 2.04,
+      "step": 83
+    },
+    {
+      "epoch": 0.49466323150533675,
+      "grad_norm": 0.148110032081604,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 2.0358,
+      "step": 84
+    },
+    {
+      "epoch": 0.5005520794994479,
+      "grad_norm": 0.18066157400608063,
+      "learning_rate": 6.026312439675552e-06,
+      "loss": 2.0521,
+      "step": 85
+    },
+    {
+      "epoch": 0.5064409274935591,
+      "grad_norm": 0.20170331001281738,
+      "learning_rate": 5.263533508961827e-06,
+      "loss": 2.0911,
+      "step": 86
+    },
+    {
+      "epoch": 0.5123297754876702,
+      "grad_norm": 0.18142713606357574,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 2.0878,
+      "step": 87
+    },
+    {
+      "epoch": 0.5182186234817814,
+      "grad_norm": 0.2858962416648865,
+      "learning_rate": 3.885512251130763e-06,
+      "loss": 2.0152,
+      "step": 88
+    },
+    {
+      "epoch": 0.5241074714758925,
+      "grad_norm": 0.2654035985469818,
+      "learning_rate": 3.271776770026963e-06,
+      "loss": 1.956,
+      "step": 89
+    },
+    {
+      "epoch": 0.5299963194700037,
+      "grad_norm": 0.22185058891773224,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 1.9699,
+      "step": 90
+    },
+    {
+      "epoch": 0.5358851674641149,
+      "grad_norm": 0.20620515942573547,
+      "learning_rate": 2.1982109232821178e-06,
+      "loss": 1.9748,
+      "step": 91
+    },
+    {
+      "epoch": 0.541774015458226,
+      "grad_norm": 0.16488178074359894,
+      "learning_rate": 1.7395544861325718e-06,
+      "loss": 2.0295,
+      "step": 92
+    },
+    {
+      "epoch": 0.5476628634523372,
+      "grad_norm": 0.23059582710266113,
+      "learning_rate": 1.333670137599713e-06,
+      "loss": 2.0521,
+      "step": 93
+    },
+    {
+      "epoch": 0.5535517114464483,
+      "grad_norm": 0.3593960702419281,
+      "learning_rate": 9.810017062595322e-07,
+      "loss": 2.1417,
+      "step": 94
+    },
+    {
+      "epoch": 0.5594405594405595,
+      "grad_norm": 0.2265915423631668,
+      "learning_rate": 6.819348298638839e-07,
+      "loss": 2.0803,
+      "step": 95
+    },
+    {
+      "epoch": 0.5653294074346706,
+      "grad_norm": 0.16412103176116943,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 2.0429,
+      "step": 96
+    },
+    {
+      "epoch": 0.5712182554287818,
+      "grad_norm": 0.14830361306667328,
+      "learning_rate": 2.458548727494292e-07,
+      "loss": 2.0344,
+      "step": 97
+    },
+    {
+      "epoch": 0.5771071034228928,
+      "grad_norm": 0.17310212552547455,
+      "learning_rate": 1.0931863906127327e-07,
+      "loss": 2.0696,
+      "step": 98
+    },
+    {
+      "epoch": 0.582995951417004,
+      "grad_norm": 0.17108841240406036,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 2.0661,
+      "step": 99
+    },
+    {
+      "epoch": 0.5888847994111152,
+      "grad_norm": 0.20385785400867462,
+      "learning_rate": 0.0,
+      "loss": 2.1085,
+      "step": 100
+    },
+    {
+      "epoch": 0.5888847994111152,
+      "eval_loss": 2.043283700942993,
+      "eval_runtime": 36.3966,
+      "eval_samples_per_second": 62.863,
+      "eval_steps_per_second": 3.929,
+      "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": 4.856649777728717e+17,
+  "total_flos": 6.494295660659999e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null