Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:927d60d734180a5382193bb6f208488d1daa72fec25592e4e21eea3f343cffc2
+oid sha256:65db0c61f6bc751ec3c71180f933e89ee030416f07f81df2ee0d61cd69706a0a
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f218f9b6e22482b76f07166b0ed7a53b26feb46b4f50574451199d9479fe3061
+oid sha256:de2785090f83dc159c050cdf1c62f4f4e299aa76a3b7bcbe17c3e160915f29da
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b556539d1d4705b7f0142c8cd9eed3c992ece026d253fc19151efc6408c2e70
+oid sha256:13a1e2a8f2d209c7c9662529a5423f857e3c01bfabd1198964c5e65eea0d0b2e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c4b8b1d3d79e7cbe607f49b2a8cf26bdfd1064723f7b701b01fc8ec55b61130
+oid sha256:bae5474f75c61c9a0d413df8aab34ab8256bdb971d495e89be4af58b9a649eaa
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42441f16c0c0be7218ad2a557ddd15fcaf33566c1d0e679c7e6978bcfa5de3ed
+oid sha256:3e7c294700ed36f2650cddab58c02f47a9f0848cf5f2dd7cf7c554e3ed585cb4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:189439e2ef482762e8f54b288f44a7758bec61626a9110512620bc89c832919e
+oid sha256:b8f75fb65da0bcb2461add98b4fba0e9c423c51132a687f95b29d21631f37a4a
 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": 1.6248844861984253,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0069270066672439175,
+  "best_metric": 1.574446678161621,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.013854013334487835,
   "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": 55.112,
       "eval_steps_per_second": 6.891,
       "step": 25
+    },
+    {
+      "epoch": 0.007204086933933674,
+      "grad_norm": 0.569159209728241,
+      "learning_rate": 5e-05,
+      "loss": 1.6105,
+      "step": 26
+    },
+    {
+      "epoch": 0.007481167200623431,
+      "grad_norm": 0.6634584069252014,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.5842,
+      "step": 27
+    },
+    {
+      "epoch": 0.0077582474673131875,
+      "grad_norm": 0.6659657955169678,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.614,
+      "step": 28
+    },
+    {
+      "epoch": 0.008035327734002944,
+      "grad_norm": 0.7010889053344727,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.6537,
+      "step": 29
+    },
+    {
+      "epoch": 0.008312408000692701,
+      "grad_norm": 0.6605480313301086,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.6621,
+      "step": 30
+    },
+    {
+      "epoch": 0.008589488267382457,
+      "grad_norm": 0.698592483997345,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.7071,
+      "step": 31
+    },
+    {
+      "epoch": 0.008866568534072214,
+      "grad_norm": 0.7084943056106567,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.5723,
+      "step": 32
+    },
+    {
+      "epoch": 0.009143648800761971,
+      "grad_norm": 0.6080454587936401,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.5525,
+      "step": 33
+    },
+    {
+      "epoch": 0.009420729067451727,
+      "grad_norm": 0.7002612352371216,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.6181,
+      "step": 34
+    },
+    {
+      "epoch": 0.009697809334141484,
+      "grad_norm": 0.6785765886306763,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.5518,
+      "step": 35
+    },
+    {
+      "epoch": 0.009974889600831241,
+      "grad_norm": 0.7487239241600037,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.5369,
+      "step": 36
+    },
+    {
+      "epoch": 0.010251969867520997,
+      "grad_norm": 0.8074867129325867,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.6678,
+      "step": 37
+    },
+    {
+      "epoch": 0.010529050134210753,
+      "grad_norm": 0.6005417704582214,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.6568,
+      "step": 38
+    },
+    {
+      "epoch": 0.010806130400900511,
+      "grad_norm": 0.596122145652771,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.5572,
+      "step": 39
+    },
+    {
+      "epoch": 0.011083210667590267,
+      "grad_norm": 0.5598776936531067,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.5768,
+      "step": 40
+    },
+    {
+      "epoch": 0.011360290934280023,
+      "grad_norm": 0.56935054063797,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.4968,
+      "step": 41
+    },
+    {
+      "epoch": 0.011637371200969781,
+      "grad_norm": 0.5927587151527405,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.5508,
+      "step": 42
+    },
+    {
+      "epoch": 0.011914451467659537,
+      "grad_norm": 0.8119907975196838,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.663,
+      "step": 43
+    },
+    {
+      "epoch": 0.012191531734349295,
+      "grad_norm": 0.6603608727455139,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.5939,
+      "step": 44
+    },
+    {
+      "epoch": 0.012468612001039051,
+      "grad_norm": 0.6734949350357056,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.6528,
+      "step": 45
+    },
+    {
+      "epoch": 0.012745692267728807,
+      "grad_norm": 0.6059690117835999,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.5085,
+      "step": 46
+    },
+    {
+      "epoch": 0.013022772534418565,
+      "grad_norm": 0.6954624056816101,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.501,
+      "step": 47
+    },
+    {
+      "epoch": 0.013299852801108321,
+      "grad_norm": 0.7555593252182007,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.5964,
+      "step": 48
+    },
+    {
+      "epoch": 0.013576933067798077,
+      "grad_norm": 0.7384346723556519,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.5567,
+      "step": 49
+    },
+    {
+      "epoch": 0.013854013334487835,
+      "grad_norm": 1.1048245429992676,
+      "learning_rate": 0.0,
+      "loss": 1.7697,
+      "step": 50
+    },
+    {
+      "epoch": 0.013854013334487835,
+      "eval_loss": 1.574446678161621,
+      "eval_runtime": 440.9601,
+      "eval_samples_per_second": 55.139,
+      "eval_steps_per_second": 6.894,
+      "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": 1.114626154561536e+17,
+  "total_flos": 2.229252309123072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null