Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e10f72075416dd01693a4428f4ef24afbe9312b6e858ca6eb78710ddb73a7a6
+oid sha256:51bd4449262e01591613e75b4874562d6a7f99d879af2fdbccb3ad5650b0c08d
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4c4b3e15a12cc59c3fb2b0efeb561e59a89c1c1b3e25c86031bf59f3a298d7a
+oid sha256:34547959def078ee626db0677c82922488c8c45b36b7716e88a9fe1dcd7fe557
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7e9640d4ee338e0ada9ea4a3325fe57301bd24c13e483bf584bec72e97daf9a
+oid sha256:3634100da79e841a7b07de5f5ee202ab9ae12a4461d7b8ff6af74a3bcc113ee7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e5ecd37a42c1743f356ca0008df458f8714de6485089e94588f380ef5e2e5c7
+oid sha256:2434fa7b023cdc36a78095b97a68e3767dea0fda6538663c83d5369aa96cb203
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ac111ca32dde46d03bf1a8b6b1071c455ad3e86f9f95b4667564b2202ea6d4a
+oid sha256:ebec62efb843f4c8ce456ed4bc1a8806fb7cba1d3af125955287a64d77488543
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:012c0d92f23e2961c7355a9c6872230fc392b50a0f85f1fb9b643004c95aac7f
+oid sha256:42ee1485c330bf7c73b931e6b633da51002d8ce1077126d5e7d247bd0c0d9028
 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": 2.0798914432525635,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.14342058085335246,
+  "best_metric": 2.0552337169647217,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.28684116170670493,
   "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": 21.565,
       "eval_steps_per_second": 5.607,
       "step": 25
+    },
+    {
+      "epoch": 0.14915740408748657,
+      "grad_norm": 0.8789831399917603,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.0176,
+      "step": 26
+    },
+    {
+      "epoch": 0.15489422732162064,
+      "grad_norm": 0.7552365660667419,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.0347,
+      "step": 27
+    },
+    {
+      "epoch": 0.16063105055575475,
+      "grad_norm": 0.7255383729934692,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.0319,
+      "step": 28
+    },
+    {
+      "epoch": 0.16636787378988885,
+      "grad_norm": 0.6077660918235779,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.0892,
+      "step": 29
+    },
+    {
+      "epoch": 0.17210469702402295,
+      "grad_norm": 0.6108137369155884,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.136,
+      "step": 30
+    },
+    {
+      "epoch": 0.17784152025815705,
+      "grad_norm": 0.5934994220733643,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.1457,
+      "step": 31
+    },
+    {
+      "epoch": 0.18357834349229116,
+      "grad_norm": 0.6903460025787354,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.1845,
+      "step": 32
+    },
+    {
+      "epoch": 0.18931516672642523,
+      "grad_norm": 0.7553473114967346,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.1721,
+      "step": 33
+    },
+    {
+      "epoch": 0.19505198996055934,
+      "grad_norm": 0.6441723108291626,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.1604,
+      "step": 34
+    },
+    {
+      "epoch": 0.20078881319469344,
+      "grad_norm": 0.6534947156906128,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.2357,
+      "step": 35
+    },
+    {
+      "epoch": 0.20652563642882754,
+      "grad_norm": 0.7235612869262695,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.2682,
+      "step": 36
+    },
+    {
+      "epoch": 0.21226245966296164,
+      "grad_norm": 0.823871374130249,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.1796,
+      "step": 37
+    },
+    {
+      "epoch": 0.21799928289709572,
+      "grad_norm": 0.597427248954773,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.0255,
+      "step": 38
+    },
+    {
+      "epoch": 0.22373610613122982,
+      "grad_norm": 0.5601063966751099,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.0086,
+      "step": 39
+    },
+    {
+      "epoch": 0.22947292936536393,
+      "grad_norm": 0.5171627402305603,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.0457,
+      "step": 40
+    },
+    {
+      "epoch": 0.23520975259949803,
+      "grad_norm": 0.4960695207118988,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.083,
+      "step": 41
+    },
+    {
+      "epoch": 0.24094657583363213,
+      "grad_norm": 0.5252531170845032,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.151,
+      "step": 42
+    },
+    {
+      "epoch": 0.24668339906776623,
+      "grad_norm": 0.5390699505805969,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.0963,
+      "step": 43
+    },
+    {
+      "epoch": 0.2524202223019003,
+      "grad_norm": 0.5302374958992004,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.1092,
+      "step": 44
+    },
+    {
+      "epoch": 0.2581570455360344,
+      "grad_norm": 0.5492846965789795,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.1484,
+      "step": 45
+    },
+    {
+      "epoch": 0.2638938687701685,
+      "grad_norm": 0.5892692804336548,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.094,
+      "step": 46
+    },
+    {
+      "epoch": 0.2696306920043026,
+      "grad_norm": 0.6070543527603149,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.1678,
+      "step": 47
+    },
+    {
+      "epoch": 0.2753675152384367,
+      "grad_norm": 0.6533297300338745,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.185,
+      "step": 48
+    },
+    {
+      "epoch": 0.2811043384725708,
+      "grad_norm": 0.6883774995803833,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.0919,
+      "step": 49
+    },
+    {
+      "epoch": 0.28684116170670493,
+      "grad_norm": 0.9473681449890137,
+      "learning_rate": 1e-05,
+      "loss": 2.1555,
+      "step": 50
+    },
+    {
+      "epoch": 0.28684116170670493,
+      "eval_loss": 2.0552337169647217,
+      "eval_runtime": 2.3263,
+      "eval_samples_per_second": 21.494,
+      "eval_steps_per_second": 5.588,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null