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:d43521ef01e47813ccdd2d1d79a99d91862c6c980818e2792c40ead49fc446e8
+oid sha256:5b74ad8cb5f824562633c2db98e85fdca51950a7b7cb6e579f4ae37c22761448
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ae896ffb3f0169e181c5a93a02c66beaf896e4d1ad536736738e95e1df5cdc9
+oid sha256:6f280bf5ec83dbf870753c5a0350e7631203d245df89b8ab2ed225684ef3c5dd
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27d83eb67e060ab91c60c8f47c4ec88ccf1c8e70310efe657f8ab72b26826baa
+oid sha256:d1583f52c85147ee0746c7c6922d8bcc4628653792dc4b46e07a3bb144488997
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0adf4d2bca0d601e9a7a3bb50592ae6259a26b0af244c286c87a2ef2e30d36ce
+oid sha256:d4ff9358150587d846cd1d91596ec269f0c8611b23fc3e8fca3ba38974b004ba
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e07dbe38f57b0f0b16fc042c83b1d5affb6ea975e361887f29710bd61e325e41
+oid sha256:f918c5896726ed42ddb19417a1fe6b73de6dbc6f761874200559c21a5de8ac2b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:921dd77f6d1448c7fef95cd11fc1be24a4121832cad58a90108d714f60152375
+oid sha256:c02e3174a74dd177cc144501d6dfb0be7d21b629abbaac48c221d1171fe13462
 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": 0.576792299747467,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.46296296296296297,
+  "best_metric": 0.5340929627418518,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.9259259259259259,
   "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": 87.462,
       "eval_steps_per_second": 11.053,
       "step": 25
+    },
+    {
+      "epoch": 0.48148148148148145,
+      "grad_norm": 0.16417062282562256,
+      "learning_rate": 5e-05,
+      "loss": 0.5861,
+      "step": 26
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.1619228571653366,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5484,
+      "step": 27
+    },
+    {
+      "epoch": 0.5185185185185185,
+      "grad_norm": 0.17447136342525482,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5745,
+      "step": 28
+    },
+    {
+      "epoch": 0.5370370370370371,
+      "grad_norm": 0.18351832032203674,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.5973,
+      "step": 29
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.1494884341955185,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5367,
+      "step": 30
+    },
+    {
+      "epoch": 0.5740740740740741,
+      "grad_norm": 0.16889017820358276,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5395,
+      "step": 31
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.1729159951210022,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.6008,
+      "step": 32
+    },
+    {
+      "epoch": 0.6111111111111112,
+      "grad_norm": 0.16859622299671173,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5238,
+      "step": 33
+    },
+    {
+      "epoch": 0.6296296296296297,
+      "grad_norm": 0.18731187283992767,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5243,
+      "step": 34
+    },
+    {
+      "epoch": 0.6481481481481481,
+      "grad_norm": 0.19786499440670013,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.5568,
+      "step": 35
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.20120374858379364,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.5174,
+      "step": 36
+    },
+    {
+      "epoch": 0.6851851851851852,
+      "grad_norm": 0.24167144298553467,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.543,
+      "step": 37
+    },
+    {
+      "epoch": 0.7037037037037037,
+      "grad_norm": 0.15936322510242462,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5167,
+      "step": 38
+    },
+    {
+      "epoch": 0.7222222222222222,
+      "grad_norm": 0.14347104728221893,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.5224,
+      "step": 39
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.15032237768173218,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5412,
+      "step": 40
+    },
+    {
+      "epoch": 0.7592592592592593,
+      "grad_norm": 0.14347581565380096,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5128,
+      "step": 41
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.15086627006530762,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5582,
+      "step": 42
+    },
+    {
+      "epoch": 0.7962962962962963,
+      "grad_norm": 0.13948625326156616,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4918,
+      "step": 43
+    },
+    {
+      "epoch": 0.8148148148148148,
+      "grad_norm": 0.1540198177099228,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5425,
+      "step": 44
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.15320159494876862,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.5285,
+      "step": 45
+    },
+    {
+      "epoch": 0.8518518518518519,
+      "grad_norm": 0.16808032989501953,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.493,
+      "step": 46
+    },
+    {
+      "epoch": 0.8703703703703703,
+      "grad_norm": 0.17464371025562286,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.525,
+      "step": 47
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.18388594686985016,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5178,
+      "step": 48
+    },
+    {
+      "epoch": 0.9074074074074074,
+      "grad_norm": 0.20205292105674744,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.5219,
+      "step": 49
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 0.3138573467731476,
+      "learning_rate": 0.0,
+      "loss": 0.4853,
+      "step": 50
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "eval_loss": 0.5340929627418518,
+      "eval_runtime": 4.1714,
+      "eval_samples_per_second": 87.26,
+      "eval_steps_per_second": 11.027,
+      "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