Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e34852a692adcea9228e361ccede36f0d44edec6b19af55f52bbda896f2db2d
+oid sha256:7db30c14ffb420f97a7e1385adadfb9be2ef1f120e2c574049e3d061c6090dc7
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aaf644517aa40aa3546dc9f160e7481a0ba8c16d48cd2cab771be6951fe53f0
+oid sha256:1b7d742b68cfdc55630a2b61b09fa31ffead88629481824ae481a1833553dc1b
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c68766c2a2515496d3b3f7c9a76c8262c3fa02a42f9d9bc7fbfac2492106aa
+oid sha256:d1d979c5f865c058bb440d028b82a0b788e3cb0d697c3ff611ba814842bc5583
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8540cfcc73ebaada84d9d1571c97a4d6419f1dd34d623f749cf99faeb63abe1
+oid sha256:23efff6ce69b932f35758c912f349b93d8a8a57ba758b9704df4a79b490bd983
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06703381a227bde8b3449848baf6c1e6291c98f5b613df9df1da1e13972d6861
+oid sha256:9be34e69d7e905c4e849e497da61d59973fbdeca0ea1bf178a1503de05e3ac82
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37ce4960774f87d575acaf1c8aa4c36da468df0bc51444e3a1a446f0dc3e1e3b
+oid sha256:c5c6cc5afdfac37ef2814e26da0e16131c4d203533cdae037c93fc9a0cd2630c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.2209298312664032,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.013842746400885935,
+  "epoch": 0.02768549280177187,
   "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": 13.792,
       "eval_steps_per_second": 1.724,
       "step": 25
+    },
+    {
+      "epoch": 0.014396456256921373,
+      "grad_norm": 98.28343963623047,
+      "learning_rate": 5e-05,
+      "loss": 0.8503,
+      "step": 26
+    },
+    {
+      "epoch": 0.014950166112956811,
+      "grad_norm": 14.48868465423584,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.018,
+      "step": 27
+    },
+    {
+      "epoch": 0.015503875968992248,
+      "grad_norm": 5.126861095428467,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0071,
+      "step": 28
+    },
+    {
+      "epoch": 0.016057585825027684,
+      "grad_norm": 1.48406982421875,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0024,
+      "step": 29
+    },
+    {
+      "epoch": 0.016611295681063124,
+      "grad_norm": 13.655170440673828,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0077,
+      "step": 30
+    },
+    {
+      "epoch": 0.01716500553709856,
+      "grad_norm": 8.702022552490234,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0046,
+      "step": 31
+    },
+    {
+      "epoch": 0.017718715393133997,
+      "grad_norm": 4.665962219238281,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0023,
+      "step": 32
+    },
+    {
+      "epoch": 0.018272425249169437,
+      "grad_norm": 1.7277586460113525,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0009,
+      "step": 33
+    },
+    {
+      "epoch": 0.018826135105204873,
+      "grad_norm": 0.4850597381591797,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0004,
+      "step": 34
+    },
+    {
+      "epoch": 0.01937984496124031,
+      "grad_norm": 0.1928061842918396,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0001,
+      "step": 35
+    },
+    {
+      "epoch": 0.019933554817275746,
+      "grad_norm": 0.04373222589492798,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0001,
+      "step": 36
+    },
+    {
+      "epoch": 0.020487264673311186,
+      "grad_norm": 323.9327087402344,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.4818,
+      "step": 37
+    },
+    {
+      "epoch": 0.021040974529346623,
+      "grad_norm": 266.1087951660156,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.7784,
+      "step": 38
+    },
+    {
+      "epoch": 0.02159468438538206,
+      "grad_norm": 0.04026114568114281,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0001,
+      "step": 39
+    },
+    {
+      "epoch": 0.0221483942414175,
+      "grad_norm": 0.03933119773864746,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0001,
+      "step": 40
+    },
+    {
+      "epoch": 0.022702104097452935,
+      "grad_norm": 0.04323228821158409,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0001,
+      "step": 41
+    },
+    {
+      "epoch": 0.023255813953488372,
+      "grad_norm": 0.06206133961677551,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0001,
+      "step": 42
+    },
+    {
+      "epoch": 0.023809523809523808,
+      "grad_norm": 0.015565506182610989,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.024363233665559248,
+      "grad_norm": 0.057457469403743744,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0001,
+      "step": 44
+    },
+    {
+      "epoch": 0.024916943521594685,
+      "grad_norm": 0.010861905291676521,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.02547065337763012,
+      "grad_norm": 0.016795886680483818,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.02602436323366556,
+      "grad_norm": 0.04295491799712181,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0001,
+      "step": 47
+    },
+    {
+      "epoch": 0.026578073089700997,
+      "grad_norm": 0.08125736564397812,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0002,
+      "step": 48
+    },
+    {
+      "epoch": 0.027131782945736434,
+      "grad_norm": 101.67281341552734,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.1258,
+      "step": 49
+    },
+    {
+      "epoch": 0.02768549280177187,
+      "grad_norm": 486.48394775390625,
+      "learning_rate": 0.0,
+      "loss": 2.7297,
+      "step": 50
+    },
+    {
+      "epoch": 0.02768549280177187,
+      "eval_loss": 0.3239246606826782,
+      "eval_runtime": 882.1015,
+      "eval_samples_per_second": 13.793,
+      "eval_steps_per_second": 1.724,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.483568811343872e+17,
+  "total_flos": 2.967137622687744e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null