Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5321b9b24d87cea0ab8ca473e5e824d7f9c33fb0c2b4ecd89f0464cf80f5f883
+oid sha256:29823f4e08b18743fec2278d0a24fba91846a1bbe1838f5c71ac01c15fea6da1
 size 1163996488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4e3002892411f1f6dd3862afccbc704c1e716a0cd285403e57f845ea26a7f3a
+oid sha256:2febce13ec52a548e34b9db0f50c7fb2dfb945379b97f53fb52a73c2635c2f2c
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c7b0794dc4da930fd6bdb7425e203350d470d04552fbe2ccdb7d7390d92b97f
+oid sha256:4787c2c04c07c1ae6e2c20c42952d1e91343f26f99f548d3534a1670bc4a5f0c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
+oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9572558403015137,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.22560631697687536,
+  "best_metric": 1.613823652267456,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.338409475465313,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -262,6 +262,133 @@
       "eval_samples_per_second": 13.46,
       "eval_steps_per_second": 3.369,
       "step": 100
+    },
+    {
+      "epoch": 0.23011844331641285,
+      "grad_norm": 2.131408929824829,
+      "learning_rate": 5.247918773366112e-05,
+      "loss": 2.2441,
+      "step": 102
+    },
+    {
+      "epoch": 0.23688663282571912,
+      "grad_norm": 2.081399440765381,
+      "learning_rate": 5e-05,
+      "loss": 2.3219,
+      "step": 105
+    },
+    {
+      "epoch": 0.2436548223350254,
+      "grad_norm": 1.4835395812988281,
+      "learning_rate": 4.7520812266338885e-05,
+      "loss": 2.176,
+      "step": 108
+    },
+    {
+      "epoch": 0.25042301184433163,
+      "grad_norm": 1.476472020149231,
+      "learning_rate": 4.504772348747687e-05,
+      "loss": 1.9463,
+      "step": 111
+    },
+    {
+      "epoch": 0.2571912013536379,
+      "grad_norm": 1.4163830280303955,
+      "learning_rate": 4.2586817614407895e-05,
+      "loss": 2.0727,
+      "step": 114
+    },
+    {
+      "epoch": 0.2639593908629442,
+      "grad_norm": 1.5342260599136353,
+      "learning_rate": 4.0144148627425993e-05,
+      "loss": 1.858,
+      "step": 117
+    },
+    {
+      "epoch": 0.2707275803722504,
+      "grad_norm": 1.5253146886825562,
+      "learning_rate": 3.772572564296005e-05,
+      "loss": 1.8902,
+      "step": 120
+    },
+    {
+      "epoch": 0.27749576988155666,
+      "grad_norm": 1.7602707147598267,
+      "learning_rate": 3.533749813077677e-05,
+      "loss": 1.6547,
+      "step": 123
+    },
+    {
+      "epoch": 0.28426395939086296,
+      "grad_norm": 1.6635607481002808,
+      "learning_rate": 3.298534127791785e-05,
+      "loss": 1.8572,
+      "step": 126
+    },
+    {
+      "epoch": 0.2910321489001692,
+      "grad_norm": 1.924639105796814,
+      "learning_rate": 3.0675041535377405e-05,
+      "loss": 1.8875,
+      "step": 129
+    },
+    {
+      "epoch": 0.29780033840947545,
+      "grad_norm": 1.8324716091156006,
+      "learning_rate": 2.8412282383075363e-05,
+      "loss": 1.5726,
+      "step": 132
+    },
+    {
+      "epoch": 0.30456852791878175,
+      "grad_norm": 2.137519121170044,
+      "learning_rate": 2.6202630348146324e-05,
+      "loss": 1.6311,
+      "step": 135
+    },
+    {
+      "epoch": 0.311336717428088,
+      "grad_norm": 2.6914830207824707,
+      "learning_rate": 2.405152131093926e-05,
+      "loss": 1.8127,
+      "step": 138
+    },
+    {
+      "epoch": 0.31810490693739424,
+      "grad_norm": 2.32242751121521,
+      "learning_rate": 2.196424713241637e-05,
+      "loss": 1.536,
+      "step": 141
+    },
+    {
+      "epoch": 0.3248730964467005,
+      "grad_norm": 2.783191204071045,
+      "learning_rate": 1.9945942635848748e-05,
+      "loss": 1.6442,
+      "step": 144
+    },
+    {
+      "epoch": 0.3316412859560068,
+      "grad_norm": 3.8185131549835205,
+      "learning_rate": 1.800157297483417e-05,
+      "loss": 1.5812,
+      "step": 147
+    },
+    {
+      "epoch": 0.338409475465313,
+      "grad_norm": 4.207033157348633,
+      "learning_rate": 1.6135921418712956e-05,
+      "loss": 1.4215,
+      "step": 150
+    },
+    {
+      "epoch": 0.338409475465313,
+      "eval_loss": 1.613823652267456,
+      "eval_runtime": 55.6384,
+      "eval_samples_per_second": 13.426,
+      "eval_steps_per_second": 3.361,
+      "step": 150
     }
   ],
   "logging_steps": 3,
@@ -290,7 +417,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.330496579567616e+17,
+  "total_flos": 1.995744869351424e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null