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:e99c2876b0436f5e3419fbec0c9f29b61de1a6f5ff7d109ce7a0e60d7c85c7f1
+oid sha256:5f542f2ba8c3c048f8fac3bb0882ad2fddb116ddea9e138ce1b57c0b3b9ae9e8
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:851c47cb7df87f13ec9f82939ae56f647104d15d8b60b67b72d8ba2b0ec0178b
+oid sha256:f54b97c47efae967ee0067a3760f32eea35f56c106fbedd4f2ea79c311c4f0cc
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:365651aa0e51277de73593a95bc9bf346743b863ae1bdfb9972c187d31e0183b
+oid sha256:b5a43bf8a1c20c4072b58c75190d2f4d05a4f2496bd6cf09e11c903b63e4de85
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e89b502f2afedc29a1b81cde77246a9e2ec9acd1c586efd97a36afe806bc0184
+oid sha256:a531afdb82744928d6d68902b72eb1f49c60679a2ba5e2196ccdf3c3886687cd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a468e818605d345d0ef2d8a38a9d618f73897b39df98d3b7620331b2260cc1f
+oid sha256:3cc0c231d4bfd9dc6588923e0bf2d786a2330f60df8ed3bdeb206e027c410f1a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57230fd29296a8182922cf4a706e59232d34375692d20c753e82da54505f7b43
+oid sha256:35f1315d997b9be4e9016fbcfe39f08c4b40fcdedfe2e5a3331c9dff1464620c
 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": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.42328042328042326,
+  "epoch": 0.8465608465608465,
   "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": 29.766,
       "eval_steps_per_second": 3.739,
       "step": 25
+    },
+    {
+      "epoch": 0.4402116402116402,
+      "grad_norm": 0.0,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 0.0,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.4740740740740741,
+      "grad_norm": 0.0,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.491005291005291,
+      "grad_norm": 0.0,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.5079365079365079,
+      "grad_norm": 0.0,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.5248677248677248,
+      "grad_norm": 0.0,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.5417989417989418,
+      "grad_norm": 0.0,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.5587301587301587,
+      "grad_norm": 0.0,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.5756613756613757,
+      "grad_norm": 0.0,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.0,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.6095238095238096,
+      "grad_norm": 0.0,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.6264550264550265,
+      "grad_norm": 0.0,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.6433862433862434,
+      "grad_norm": 0.0,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.6603174603174603,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.6772486772486772,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.6941798941798942,
+      "grad_norm": 0.0,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.0,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.728042328042328,
+      "grad_norm": 0.0,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.744973544973545,
+      "grad_norm": 0.0,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.0,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.7788359788359789,
+      "grad_norm": 0.0,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.7957671957671958,
+      "grad_norm": 0.0,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.8126984126984127,
+      "grad_norm": 0.0,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.8296296296296296,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.8465608465608465,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.8465608465608465,
+      "eval_loss": NaN,
+      "eval_runtime": 13.3791,
+      "eval_samples_per_second": 29.748,
+      "eval_steps_per_second": 3.737,
+      "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