Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27d2ffeaff17fa220273c3d441af252a8687e8b1c6b9fc05b1453bd54abc4e11
+oid sha256:5ef6f5479a7140700df3d8df2cd3d647b4b06949e0aab9e79c71359c0bae52ca
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8959c2699f789991803def38c9e8314f1ae030601d2b151a7dd80196324d1f0d
+oid sha256:91241bab8251b5f521434049995a8d7d63d824b2d80567cd6115748c97836264
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12f0ad0b06082cca3193f6f5f2df64db4f13ac17feb42a1819888373af9a1dee
+oid sha256:e2281d341c790676f03f48f0d785ae5b26eff9d73c2c3bc49b2ecb4722f2cd5f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abaad29d63df3a15839bd804dac167d05be1ebadd12aac47a8ded08db454c144
+oid sha256:9ccd3c572ef20998bcb1ae4071c2dfc825c4f5f667751835ca783692a0d80f46
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:599ee2150c4bd2049788b1de6a5bb2ca3a9feec5e3cee4a7e3168f0a2fb93f78
+oid sha256:8725a629b9d3eefe8bc61bdc10a316f84881107e88a23956d3beafe37fa0af36
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1fb8fe897ad25264cf48849ab1ebe8f1fd54c07f6a1fcbb230064a70d1b6aa4
+oid sha256:292df9665dd4fb4ff0491075aacd126bdb68cffa8fec38f10aa671c64088de16
 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": 0.49585384130477905,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6589785831960461,
+  "best_metric": 0.14452199637889862,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.3410214168039538,
   "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": 66.923,
       "eval_steps_per_second": 17.4,
       "step": 25
+    },
+    {
+      "epoch": 0.685337726523888,
+      "grad_norm": 2.4734058380126953,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.598,
+      "step": 26
+    },
+    {
+      "epoch": 0.7116968698517299,
+      "grad_norm": 3.428785562515259,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.672,
+      "step": 27
+    },
+    {
+      "epoch": 0.7380560131795717,
+      "grad_norm": 2.8462884426116943,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.6942,
+      "step": 28
+    },
+    {
+      "epoch": 0.7644151565074135,
+      "grad_norm": 2.8353283405303955,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.534,
+      "step": 29
+    },
+    {
+      "epoch": 0.7907742998352554,
+      "grad_norm": 1.8473469018936157,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.1867,
+      "step": 30
+    },
+    {
+      "epoch": 0.8171334431630972,
+      "grad_norm": 1.3983721733093262,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.1956,
+      "step": 31
+    },
+    {
+      "epoch": 0.8434925864909391,
+      "grad_norm": 1.2318115234375,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.2022,
+      "step": 32
+    },
+    {
+      "epoch": 0.8698517298187809,
+      "grad_norm": 0.9489920735359192,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.1785,
+      "step": 33
+    },
+    {
+      "epoch": 0.8962108731466227,
+      "grad_norm": 1.4298465251922607,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.2614,
+      "step": 34
+    },
+    {
+      "epoch": 0.9225700164744646,
+      "grad_norm": 1.7149752378463745,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.3176,
+      "step": 35
+    },
+    {
+      "epoch": 0.9489291598023064,
+      "grad_norm": 2.3903605937957764,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.389,
+      "step": 36
+    },
+    {
+      "epoch": 0.9752883031301482,
+      "grad_norm": 3.662409543991089,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.4364,
+      "step": 37
+    },
+    {
+      "epoch": 1.0247116968698518,
+      "grad_norm": 4.705199718475342,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.6616,
+      "step": 38
+    },
+    {
+      "epoch": 1.0510708401976936,
+      "grad_norm": 0.9721773266792297,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.1232,
+      "step": 39
+    },
+    {
+      "epoch": 1.0774299835255354,
+      "grad_norm": 0.9221625924110413,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.1,
+      "step": 40
+    },
+    {
+      "epoch": 1.1037891268533773,
+      "grad_norm": 1.6013553142547607,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.1023,
+      "step": 41
+    },
+    {
+      "epoch": 1.130148270181219,
+      "grad_norm": 1.0896989107131958,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.093,
+      "step": 42
+    },
+    {
+      "epoch": 1.156507413509061,
+      "grad_norm": 1.2368277311325073,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.1512,
+      "step": 43
+    },
+    {
+      "epoch": 1.1828665568369028,
+      "grad_norm": 1.908003807067871,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.2024,
+      "step": 44
+    },
+    {
+      "epoch": 1.2092257001647446,
+      "grad_norm": 2.1720011234283447,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.2848,
+      "step": 45
+    },
+    {
+      "epoch": 1.2355848434925865,
+      "grad_norm": 3.783008575439453,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.3299,
+      "step": 46
+    },
+    {
+      "epoch": 1.2619439868204283,
+      "grad_norm": 2.4560554027557373,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.2846,
+      "step": 47
+    },
+    {
+      "epoch": 1.2883031301482701,
+      "grad_norm": 1.1371558904647827,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0989,
+      "step": 48
+    },
+    {
+      "epoch": 1.314662273476112,
+      "grad_norm": 0.7374827861785889,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0588,
+      "step": 49
+    },
+    {
+      "epoch": 1.3410214168039538,
+      "grad_norm": 0.9319198727607727,
+      "learning_rate": 1e-05,
+      "loss": 0.0628,
+      "step": 50
+    },
+    {
+      "epoch": 1.3410214168039538,
+      "eval_loss": 0.14452199637889862,
+      "eval_runtime": 0.747,
+      "eval_samples_per_second": 66.931,
+      "eval_steps_per_second": 17.402,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null