Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5df163ebf407a0f122d515e182fbe67b3e71a8c3c7149f5a1f29d72e42a1e04a
+oid sha256:7997e256afb4d99620f55f73cb2ddc6de7b7543555955818d86309f948262069
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec7c2542623acdee3f576c7dd7b622800da6d5278c3ca231e30659efcb0e56f7
+oid sha256:2de0581ffd9f9b2d7e408422ad4f94b445bf73ec720e1fad7bb32381ead4d422
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:012f56f4220e646aa90e84f6d9f89f9500b001673d4aa9efcd2ad25f1f3c77b8
+oid sha256:dfe596af63fdb13ad699743be4b9fd9be8207e2db8d285e4a1b682f24f3242f0
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc279cea0cef4ebf0d674e37a8c419065552468f9f1e895f1982e0eb91d77c95
+oid sha256:572cb32ee8e4b4a03afb371a4a369ff0108a1f72097d376bd0911ed3748717d0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e268279e30e7092e5d1ecfb78114c0346bc04354f1c5a65c7aa0e89532897c55
+oid sha256:de98358326d65559153cbef8a6368995daa61c3da1fe6f4dce455652d29f1cbe
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84905f341286d6868c37e1ed81eabd562dbe5776221d370265d1c2d30b1a787f
+oid sha256:5c6cb8ffe1d536999cb98e1ea6cb281f79ca4234ee762fa5364ee254a109dd59
 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": 1.4937388896942139,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5563282336578581,
+  "best_metric": 1.4836927652359009,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.1182197496522948,
   "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": 5.337,
       "eval_steps_per_second": 1.388,
       "step": 25
+    },
+    {
+      "epoch": 0.5785813630041725,
+      "grad_norm": 0.3235774636268616,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.5641,
+      "step": 26
+    },
+    {
+      "epoch": 0.6008344923504868,
+      "grad_norm": 0.36498793959617615,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.5675,
+      "step": 27
+    },
+    {
+      "epoch": 0.6230876216968011,
+      "grad_norm": 0.3361755311489105,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.5869,
+      "step": 28
+    },
+    {
+      "epoch": 0.6453407510431154,
+      "grad_norm": 0.38626089692115784,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.5792,
+      "step": 29
+    },
+    {
+      "epoch": 0.6675938803894298,
+      "grad_norm": 0.41537216305732727,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.5387,
+      "step": 30
+    },
+    {
+      "epoch": 0.6898470097357441,
+      "grad_norm": 0.5004784464836121,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.5281,
+      "step": 31
+    },
+    {
+      "epoch": 0.7121001390820584,
+      "grad_norm": 0.4615420699119568,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.4667,
+      "step": 32
+    },
+    {
+      "epoch": 0.7343532684283728,
+      "grad_norm": 0.41852062940597534,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.4371,
+      "step": 33
+    },
+    {
+      "epoch": 0.7566063977746871,
+      "grad_norm": 0.2556873857975006,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.6198,
+      "step": 34
+    },
+    {
+      "epoch": 0.7788595271210014,
+      "grad_norm": 0.27681005001068115,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.589,
+      "step": 35
+    },
+    {
+      "epoch": 0.8011126564673157,
+      "grad_norm": 0.28919461369514465,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.5619,
+      "step": 36
+    },
+    {
+      "epoch": 0.8233657858136301,
+      "grad_norm": 0.3032487630844116,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.5334,
+      "step": 37
+    },
+    {
+      "epoch": 0.8456189151599444,
+      "grad_norm": 0.32653772830963135,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.555,
+      "step": 38
+    },
+    {
+      "epoch": 0.8678720445062587,
+      "grad_norm": 0.5661789774894714,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.5973,
+      "step": 39
+    },
+    {
+      "epoch": 0.8901251738525731,
+      "grad_norm": 0.38925230503082275,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.5983,
+      "step": 40
+    },
+    {
+      "epoch": 0.9123783031988874,
+      "grad_norm": 0.4309825003147125,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.4893,
+      "step": 41
+    },
+    {
+      "epoch": 0.9346314325452016,
+      "grad_norm": 0.44985729455947876,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.5213,
+      "step": 42
+    },
+    {
+      "epoch": 0.9568845618915159,
+      "grad_norm": 0.5200555920600891,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.4216,
+      "step": 43
+    },
+    {
+      "epoch": 0.9791376912378303,
+      "grad_norm": 0.3593793213367462,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.4851,
+      "step": 44
+    },
+    {
+      "epoch": 1.0069541029207232,
+      "grad_norm": 0.4502297639846802,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.2216,
+      "step": 45
+    },
+    {
+      "epoch": 1.0292072322670376,
+      "grad_norm": 0.2939792275428772,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.4284,
+      "step": 46
+    },
+    {
+      "epoch": 1.0514603616133518,
+      "grad_norm": 0.2818860411643982,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.4967,
+      "step": 47
+    },
+    {
+      "epoch": 1.0737134909596662,
+      "grad_norm": 0.32414528727531433,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.4624,
+      "step": 48
+    },
+    {
+      "epoch": 1.0959666203059806,
+      "grad_norm": 0.355913370847702,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.4607,
+      "step": 49
+    },
+    {
+      "epoch": 1.1182197496522948,
+      "grad_norm": 0.3229123055934906,
+      "learning_rate": 1e-05,
+      "loss": 1.5119,
+      "step": 50
+    },
+    {
+      "epoch": 1.1182197496522948,
+      "eval_loss": 1.4836927652359009,
+      "eval_runtime": 9.3523,
+      "eval_samples_per_second": 5.346,
+      "eval_steps_per_second": 1.39,
+      "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": 5.852248692941128e+17,
+  "total_flos": 1.1690990744528486e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null