Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9a346b50209499f302120ef7c326683aae7d05926df39f3f0fb1167cd27de11
+oid sha256:81a9c5cc3dc2b5de6e48d2de9030ffd6f6dc498e3cd9c54599b28137aabff540
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dcd40133987adf4ce7a60a7a688ad534b754a17e546a91f69e24313ad3bd54d
+oid sha256:dfa591af2e1b5a17a6aaf7b0c38b7afbf08490f2225963355c467ee2f165a395
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05c71ee8bda9503e4931ba5641721d39e5bf43006e55c983e05cdabfcfc91531
+oid sha256:5ce86ec7c52e0ea1934821ce400e552a42d98d47469408394d43e4449acc20e2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94b9042fa38cf526104b737f857e9d702be752b5aa270e00c9b442be34110c16
+oid sha256:f070a65929db09579068d22dd4380feb73bdf18db9ba4332d1d872eae42b233b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d08571959569c847f67439c1989b132977850575531191103c7db5ed4c518f0
+oid sha256:9de48f819526ad8f4cc78acfb40afc2805479dea2962bc54d61ef75926a35484
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b69c956c7b9c390eaeba9b1f909cc5dea02dca877965013c17a278c90ec9c7e
+oid sha256:0dbf128f28b1ce78eae206dd9f95f375774ee7bbf8d40b149260ab135509c59d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.1842418909072876,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.012234286588163328,
+  "best_metric": 0.10041240602731705,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.024468573176326655,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 11.467,
       "eval_steps_per_second": 2.981,
       "step": 25
+    },
+    {
+      "epoch": 0.012723658051689861,
+      "grad_norm": 66.65270233154297,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 23.626,
+      "step": 26
+    },
+    {
+      "epoch": 0.013213029515216393,
+      "grad_norm": 65.94048309326172,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.2734,
+      "step": 27
+    },
+    {
+      "epoch": 0.013702400978742927,
+      "grad_norm": 39.36450958251953,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 5.2368,
+      "step": 28
+    },
+    {
+      "epoch": 0.01419177244226946,
+      "grad_norm": 26.995254516601562,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.9399,
+      "step": 29
+    },
+    {
+      "epoch": 0.014681143905795993,
+      "grad_norm": 48.19501876831055,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 4.256,
+      "step": 30
+    },
+    {
+      "epoch": 0.015170515369322526,
+      "grad_norm": 38.060523986816406,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 4.526,
+      "step": 31
+    },
+    {
+      "epoch": 0.01565988683284906,
+      "grad_norm": 29.63587760925293,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.6329,
+      "step": 32
+    },
+    {
+      "epoch": 0.016149258296375594,
+      "grad_norm": 22.62843132019043,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.8267,
+      "step": 33
+    },
+    {
+      "epoch": 0.016638629759902126,
+      "grad_norm": 16.35435676574707,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.0877,
+      "step": 34
+    },
+    {
+      "epoch": 0.017128001223428658,
+      "grad_norm": 14.545948028564453,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.6081,
+      "step": 35
+    },
+    {
+      "epoch": 0.017617372686955193,
+      "grad_norm": 15.168474197387695,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.6549,
+      "step": 36
+    },
+    {
+      "epoch": 0.018106744150481725,
+      "grad_norm": 18.33909797668457,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.3991,
+      "step": 37
+    },
+    {
+      "epoch": 0.018596115614008257,
+      "grad_norm": 27.920658111572266,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 13.3818,
+      "step": 38
+    },
+    {
+      "epoch": 0.019085487077534793,
+      "grad_norm": 34.187782287597656,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 9.2926,
+      "step": 39
+    },
+    {
+      "epoch": 0.019574858541061325,
+      "grad_norm": 33.19221878051758,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.6248,
+      "step": 40
+    },
+    {
+      "epoch": 0.020064230004587857,
+      "grad_norm": 37.695045471191406,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 4.091,
+      "step": 41
+    },
+    {
+      "epoch": 0.020553601468114392,
+      "grad_norm": 17.131343841552734,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.1963,
+      "step": 42
+    },
+    {
+      "epoch": 0.021042972931640924,
+      "grad_norm": 22.822057723999023,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.8351,
+      "step": 43
+    },
+    {
+      "epoch": 0.021532344395167456,
+      "grad_norm": 21.45277976989746,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.5591,
+      "step": 44
+    },
+    {
+      "epoch": 0.022021715858693988,
+      "grad_norm": 16.33228874206543,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.2325,
+      "step": 45
+    },
+    {
+      "epoch": 0.022511087322220524,
+      "grad_norm": 17.173385620117188,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.5415,
+      "step": 46
+    },
+    {
+      "epoch": 0.023000458785747056,
+      "grad_norm": 14.72747802734375,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.9581,
+      "step": 47
+    },
+    {
+      "epoch": 0.023489830249273588,
+      "grad_norm": 14.60140609741211,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.8449,
+      "step": 48
+    },
+    {
+      "epoch": 0.023979201712800123,
+      "grad_norm": 12.501975059509277,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.9781,
+      "step": 49
+    },
+    {
+      "epoch": 0.024468573176326655,
+      "grad_norm": 13.437914848327637,
+      "learning_rate": 1e-05,
+      "loss": 1.8146,
+      "step": 50
+    },
+    {
+      "epoch": 0.024468573176326655,
+      "eval_loss": 0.10041240602731705,
+      "eval_runtime": 4.3583,
+      "eval_samples_per_second": 11.472,
+      "eval_steps_per_second": 2.983,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.8325485410779136e+17,
+  "total_flos": 5.6659811474866176e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null