Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fa2bd185978b07fcf8fbd2816946a53fa4b790e5da42390631abd869eb40b5b
+oid sha256:1472264743750352cdbd01a3a6627f2da89a45874b03a447561b13522fa9da18
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3619bb114f4a820c7c0aad2d447494a828d35a8f7a3de546cdc592b67638285
+oid sha256:ab1ac281d9e7f7fe23a97b2fd738cf37fd5de6df5d17e43abb49b0ee7d033a46
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:624625fc85d4bfaf4f331f37d87ab8637b0395f3dbbdee75ed8f737ed97c373a
+oid sha256:ed39698dad08c33d253bc340ecc8b1fd8dfab1b4cd94d9655d3d269bac0d07b0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d78c03aa72ddc58051f7e4448aff6f243503050d3ad7850f97ee9ad269ea7a9f
+oid sha256:958f429a81639075104a21e006951af69803e28329ea8197ce1b0335372bb5c5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e2620f2a78452f1b3d59f4a09a6c522bcb614d2eec70ed830bc9341bdd7a1b4
+oid sha256:7356a2e71f18e856566abcfc955d97cba4c8bebadf44393d149b5858c59c0a6c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9dd36c440872d6d6bb216a60564200250913e8f8d8e081cd868f57946b816f0
+oid sha256:e7fc3b518d82eb7fbc41ea63dc7721af0dedb3371d3b107f93e5c31b489a0bbe
 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": 3.7035763263702393,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0035167153878277687,
+  "best_metric": 3.5896806716918945,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.007033430775655537,
   "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": 16.727,
       "eval_steps_per_second": 4.349,
       "step": 25
+    },
+    {
+      "epoch": 0.0036573840033408797,
+      "grad_norm": 0.719357430934906,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.8378,
+      "step": 26
+    },
+    {
+      "epoch": 0.0037980526188539903,
+      "grad_norm": 0.8073096871376038,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.5049,
+      "step": 27
+    },
+    {
+      "epoch": 0.003938721234367101,
+      "grad_norm": 0.8840256929397583,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.9195,
+      "step": 28
+    },
+    {
+      "epoch": 0.0040793898498802115,
+      "grad_norm": 1.1521762609481812,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.4451,
+      "step": 29
+    },
+    {
+      "epoch": 0.0042200584653933225,
+      "grad_norm": 1.198631763458252,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.6565,
+      "step": 30
+    },
+    {
+      "epoch": 0.0043607270809064335,
+      "grad_norm": 1.3765795230865479,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.7224,
+      "step": 31
+    },
+    {
+      "epoch": 0.0045013956964195445,
+      "grad_norm": 1.346805214881897,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.6726,
+      "step": 32
+    },
+    {
+      "epoch": 0.004642064311932655,
+      "grad_norm": 1.2883901596069336,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.7782,
+      "step": 33
+    },
+    {
+      "epoch": 0.004782732927445766,
+      "grad_norm": 1.4923596382141113,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.7878,
+      "step": 34
+    },
+    {
+      "epoch": 0.004923401542958877,
+      "grad_norm": 1.637706995010376,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.9159,
+      "step": 35
+    },
+    {
+      "epoch": 0.005064070158471987,
+      "grad_norm": 1.7289783954620361,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 4.0645,
+      "step": 36
+    },
+    {
+      "epoch": 0.005204738773985098,
+      "grad_norm": 2.8105924129486084,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 4.4649,
+      "step": 37
+    },
+    {
+      "epoch": 0.005345407389498209,
+      "grad_norm": 0.6356281638145447,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.8927,
+      "step": 38
+    },
+    {
+      "epoch": 0.00548607600501132,
+      "grad_norm": 0.5997741222381592,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.3777,
+      "step": 39
+    },
+    {
+      "epoch": 0.00562674462052443,
+      "grad_norm": 0.7866092324256897,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.7802,
+      "step": 40
+    },
+    {
+      "epoch": 0.005767413236037541,
+      "grad_norm": 0.8625376224517822,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.0477,
+      "step": 41
+    },
+    {
+      "epoch": 0.005908081851550652,
+      "grad_norm": 0.9740644693374634,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.5105,
+      "step": 42
+    },
+    {
+      "epoch": 0.006048750467063762,
+      "grad_norm": 1.083276629447937,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.5828,
+      "step": 43
+    },
+    {
+      "epoch": 0.006189419082576873,
+      "grad_norm": 1.3166731595993042,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.7169,
+      "step": 44
+    },
+    {
+      "epoch": 0.006330087698089984,
+      "grad_norm": 1.4437602758407593,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.7671,
+      "step": 45
+    },
+    {
+      "epoch": 0.006470756313603095,
+      "grad_norm": 1.6273506879806519,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.6367,
+      "step": 46
+    },
+    {
+      "epoch": 0.006611424929116205,
+      "grad_norm": 1.676190972328186,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.6023,
+      "step": 47
+    },
+    {
+      "epoch": 0.006752093544629316,
+      "grad_norm": 2.3617000579833984,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.9218,
+      "step": 48
+    },
+    {
+      "epoch": 0.006892762160142427,
+      "grad_norm": 2.1535112857818604,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 4.0372,
+      "step": 49
+    },
+    {
+      "epoch": 0.007033430775655537,
+      "grad_norm": 3.9727821350097656,
+      "learning_rate": 1e-05,
+      "loss": 4.6256,
+      "step": 50
+    },
+    {
+      "epoch": 0.007033430775655537,
+      "eval_loss": 3.5896806716918945,
+      "eval_runtime": 3.0738,
+      "eval_samples_per_second": 16.266,
+      "eval_steps_per_second": 4.229,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null