Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:743a17f9cb51b4373285054192f47b3d4cc01d30189d607632beb36868530e76
+oid sha256:6c2820bef08450717e312c546e4176785f4c6142863d3abd355111c7614db415
 size 37762064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051a2e2ecf48177a06afd5f75bf025458e1ea2dcf4c1e3232a10f4afb05824b2
+oid sha256:49aefdcc0d247db8f6d6a3dba5aceff2873f607081003c67843c8b094bbfe786
 size 19283770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74a6fed904b71ac961f57839a0cafc9ce692b4390791ad7d64834529ffdcd7fa
+oid sha256:3230f1bf402a17b12cbef0c7bdf70dd52d6c6e666f3e88ceffac3602f0ad66bd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8705639243125916,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.364741641337386,
+  "best_metric": 0.8201571106910706,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.48632218844984804,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -389,6 +389,126 @@
       "eval_samples_per_second": 148.561,
       "eval_steps_per_second": 37.301,
       "step": 150
+    },
+    {
+      "epoch": 0.3720364741641337,
+      "grad_norm": 1461.7186279296875,
+      "learning_rate": 1.435357758543015e-05,
+      "loss": 5.1148,
+      "step": 153
+    },
+    {
+      "epoch": 0.37933130699088147,
+      "grad_norm": 1224.365478515625,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 3.9842,
+      "step": 156
+    },
+    {
+      "epoch": 0.38662613981762917,
+      "grad_norm": 635.9539794921875,
+      "learning_rate": 1.1056136061894384e-05,
+      "loss": 3.4588,
+      "step": 159
+    },
+    {
+      "epoch": 0.3939209726443769,
+      "grad_norm": 797.1043701171875,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 4.1315,
+      "step": 162
+    },
+    {
+      "epoch": 0.4012158054711246,
+      "grad_norm": 592.1983032226562,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 3.3113,
+      "step": 165
+    },
+    {
+      "epoch": 0.4085106382978723,
+      "grad_norm": 751.4596557617188,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 3.6361,
+      "step": 168
+    },
+    {
+      "epoch": 0.4158054711246201,
+      "grad_norm": 1344.918701171875,
+      "learning_rate": 5.6388590278194096e-06,
+      "loss": 3.3631,
+      "step": 171
+    },
+    {
+      "epoch": 0.4231003039513678,
+      "grad_norm": 934.5332641601562,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 3.4403,
+      "step": 174
+    },
+    {
+      "epoch": 0.43039513677811553,
+      "grad_norm": 732.6083374023438,
+      "learning_rate": 3.5722980755146517e-06,
+      "loss": 4.0096,
+      "step": 177
+    },
+    {
+      "epoch": 0.4376899696048632,
+      "grad_norm": 591.6499633789062,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 3.5339,
+      "step": 180
+    },
+    {
+      "epoch": 0.4449848024316109,
+      "grad_norm": 957.0849609375,
+      "learning_rate": 1.962316193157593e-06,
+      "loss": 3.0528,
+      "step": 183
+    },
+    {
+      "epoch": 0.4522796352583587,
+      "grad_norm": 605.1629638671875,
+      "learning_rate": 1.333670137599713e-06,
+      "loss": 3.1099,
+      "step": 186
+    },
+    {
+      "epoch": 0.4595744680851064,
+      "grad_norm": 631.7711181640625,
+      "learning_rate": 8.247462563808817e-07,
+      "loss": 3.2638,
+      "step": 189
+    },
+    {
+      "epoch": 0.4668693009118541,
+      "grad_norm": 571.2025146484375,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 3.2275,
+      "step": 192
+    },
+    {
+      "epoch": 0.47416413373860183,
+      "grad_norm": 574.7122192382812,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 3.141,
+      "step": 195
+    },
+    {
+      "epoch": 0.48145896656534953,
+      "grad_norm": 524.1749267578125,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 2.3163,
+      "step": 198
+    },
+    {
+      "epoch": 0.48632218844984804,
+      "eval_loss": 0.8201571106910706,
+      "eval_runtime": 4.6233,
+      "eval_samples_per_second": 149.894,
+      "eval_steps_per_second": 37.636,
+      "step": 200
     }
   ],
   "logging_steps": 3,
@@ -412,12 +532,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4940298253762560.0,
+  "total_flos": 6608875809669120.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null