Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39fe1c7013ca4935b0680e329448b31d152765e592b23c589d4c3c72a6e812da
+oid sha256:5d2b620540484c1514f3d2b36b066c75cfaf9f11908fa5735220dee538cf1feb
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3171a19f102415ed31fe2530946bfb379c5801d8987b9b1579f4fd2a5a9829c
+oid sha256:5658fd00688a4dc66464e87b5d2ad80e9b8e8119d87b230d4762f11a396de16e
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0f278ae0169c67b2e3a7ea3ed3d8243cbecc2d257acd488f9153fa8035a660a
+oid sha256:dc2f2ce88981253045577dade89aaf8e3cb24a1977bd1f26f1b91e2c8476e835
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f527b446c13442d94c80614e70b773619474336700ac52ab45be434ce005047e
+oid sha256:b1aaeab3587a565c876f7cb0f865ba08342e22f8bdae318809f0df2d22d48ebf
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:870dd63a1019900c6b676f6d307318c25c55cf66461393c8e01041214a83c6ab
+oid sha256:0f770cfe542faf42c61c245afcdd06283b84a4432f92542185f4f4a8f27de6f2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46b36ca1acfda0e91a94608fde05012a6f06a147c922986566601847147614ad
+oid sha256:565122db383f3a42fb9fefc86b645eab0f7ff8d63546a6d825e55f156ed3eda9
 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": 0.5564234256744385,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.424561403508772,
+  "best_metric": 0.5148377418518066,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.849122807017544,
   "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": 45.476,
       "eval_steps_per_second": 11.824,
       "step": 25
+    },
+    {
+      "epoch": 1.4807017543859649,
+      "grad_norm": 0.514499306678772,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.5322,
+      "step": 26
+    },
+    {
+      "epoch": 1.5368421052631578,
+      "grad_norm": 1.3492696285247803,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.5253,
+      "step": 27
+    },
+    {
+      "epoch": 1.592982456140351,
+      "grad_norm": 8.684250831604004,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.5889,
+      "step": 28
+    },
+    {
+      "epoch": 1.6491228070175439,
+      "grad_norm": 4.966437339782715,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.5758,
+      "step": 29
+    },
+    {
+      "epoch": 1.7052631578947368,
+      "grad_norm": 1.8969244956970215,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.5262,
+      "step": 30
+    },
+    {
+      "epoch": 1.76140350877193,
+      "grad_norm": 0.863268256187439,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.5292,
+      "step": 31
+    },
+    {
+      "epoch": 1.8175438596491227,
+      "grad_norm": 1.0687530040740967,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.5327,
+      "step": 32
+    },
+    {
+      "epoch": 1.8736842105263158,
+      "grad_norm": 0.693556010723114,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.514,
+      "step": 33
+    },
+    {
+      "epoch": 1.9298245614035088,
+      "grad_norm": 0.7252716422080994,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.513,
+      "step": 34
+    },
+    {
+      "epoch": 2.007017543859649,
+      "grad_norm": 1.274886965751648,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.7899,
+      "step": 35
+    },
+    {
+      "epoch": 2.0631578947368423,
+      "grad_norm": 0.9708092212677002,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.4782,
+      "step": 36
+    },
+    {
+      "epoch": 2.119298245614035,
+      "grad_norm": 1.8682626485824585,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.4983,
+      "step": 37
+    },
+    {
+      "epoch": 2.175438596491228,
+      "grad_norm": 1.828751564025879,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.4672,
+      "step": 38
+    },
+    {
+      "epoch": 2.231578947368421,
+      "grad_norm": 1.5000618696212769,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4001,
+      "step": 39
+    },
+    {
+      "epoch": 2.287719298245614,
+      "grad_norm": 3.3551089763641357,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.5201,
+      "step": 40
+    },
+    {
+      "epoch": 2.343859649122807,
+      "grad_norm": 3.0689375400543213,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.5169,
+      "step": 41
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 5.023514747619629,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.5385,
+      "step": 42
+    },
+    {
+      "epoch": 2.456140350877193,
+      "grad_norm": 3.491212844848633,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.4854,
+      "step": 43
+    },
+    {
+      "epoch": 2.512280701754386,
+      "grad_norm": 2.627638578414917,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.4843,
+      "step": 44
+    },
+    {
+      "epoch": 2.568421052631579,
+      "grad_norm": 2.429570436477661,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.4815,
+      "step": 45
+    },
+    {
+      "epoch": 2.624561403508772,
+      "grad_norm": 2.0413661003112793,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.4781,
+      "step": 46
+    },
+    {
+      "epoch": 2.680701754385965,
+      "grad_norm": 1.6629382371902466,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.3971,
+      "step": 47
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 2.297358512878418,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.4365,
+      "step": 48
+    },
+    {
+      "epoch": 2.7929824561403507,
+      "grad_norm": 1.6660325527191162,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.431,
+      "step": 49
+    },
+    {
+      "epoch": 2.849122807017544,
+      "grad_norm": 1.7556473016738892,
+      "learning_rate": 1e-05,
+      "loss": 0.3768,
+      "step": 50
+    },
+    {
+      "epoch": 2.849122807017544,
+      "eval_loss": 0.5148377418518066,
+      "eval_runtime": 1.1005,
+      "eval_samples_per_second": 45.435,
+      "eval_steps_per_second": 11.813,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null