Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c074cdb4f0cd6944a298347e82d6afe27602f7e8c6658a1f2096908f7386c29
+oid sha256:740fe1d330cd0996aab039be91566bf0a439c1cfcc3f01ae575677888e016590
 size 203456160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48167ae37382d1554d3f14bda3fa752839b4395d9f674848325a1da7c2984ebf
+oid sha256:c71087512af0243a3f19932fd6a247244614195d9338b62e66b2920698a06379
 size 407121750

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:432d5e3a319ee1a6eecca6bad17d3cd0bbde0ace8151692fff8f401769e4810f
+oid sha256:294a3c0bc2eaaf5fa39425038005f2082bcd579ed3aaa403218f7b760b4c1800
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50560a092f780774261595a92e46585ee289404a3dfdf790ba7c86823bfa4a2b
+oid sha256:6a2f370fc2662683d37d65c83dcc7375f77b9a2adec415cd67fffb3ded951c23
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52884ae0762e1bafe1de26f4b9e67057dfc03e49eb253c07f05333f81480a03f
+oid sha256:c76a604f9874b85def3e9923b59c88d845df0295612811052e801728afe0427b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6624d3d0dbd9ca66587a9042a9e9ccffa1ab07988396582e70b5777e09bb0ac7
+oid sha256:e92f4d4e63b747332866df1b9dca3fb40c5d31cd80a5bbd0d5205c29ddef5a78
 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": 0.9989131093025208,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.007199553627675084,
+  "best_metric": 0.9670636057853699,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.014399107255350168,
   "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": 17.583,
       "eval_steps_per_second": 2.199,
       "step": 25
+    },
+    {
+      "epoch": 0.0074875357727820875,
+      "grad_norm": 0.10815276950597763,
+      "learning_rate": 5e-05,
+      "loss": 0.6209,
+      "step": 26
+    },
+    {
+      "epoch": 0.007775517917889091,
+      "grad_norm": 0.1368241310119629,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.7482,
+      "step": 27
+    },
+    {
+      "epoch": 0.008063500062996094,
+      "grad_norm": 0.15245234966278076,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7919,
+      "step": 28
+    },
+    {
+      "epoch": 0.008351482208103098,
+      "grad_norm": 0.18799570202827454,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7771,
+      "step": 29
+    },
+    {
+      "epoch": 0.008639464353210101,
+      "grad_norm": 0.21786896884441376,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7728,
+      "step": 30
+    },
+    {
+      "epoch": 0.008927446498317105,
+      "grad_norm": 0.2124146670103073,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8384,
+      "step": 31
+    },
+    {
+      "epoch": 0.009215428643424107,
+      "grad_norm": 0.19935545325279236,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8588,
+      "step": 32
+    },
+    {
+      "epoch": 0.00950341078853111,
+      "grad_norm": 0.2223549634218216,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8311,
+      "step": 33
+    },
+    {
+      "epoch": 0.009791392933638114,
+      "grad_norm": 0.2216961681842804,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8041,
+      "step": 34
+    },
+    {
+      "epoch": 0.010079375078745118,
+      "grad_norm": 0.2412797063589096,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.0052,
+      "step": 35
+    },
+    {
+      "epoch": 0.010367357223852122,
+      "grad_norm": 0.31129807233810425,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1186,
+      "step": 36
+    },
+    {
+      "epoch": 0.010655339368959125,
+      "grad_norm": 0.402089923620224,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.1256,
+      "step": 37
+    },
+    {
+      "epoch": 0.010943321514066127,
+      "grad_norm": 0.09018302708864212,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6192,
+      "step": 38
+    },
+    {
+      "epoch": 0.01123130365917313,
+      "grad_norm": 0.11462491005659103,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6657,
+      "step": 39
+    },
+    {
+      "epoch": 0.011519285804280134,
+      "grad_norm": 0.1192009299993515,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6754,
+      "step": 40
+    },
+    {
+      "epoch": 0.011807267949387138,
+      "grad_norm": 0.15262356400489807,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.846,
+      "step": 41
+    },
+    {
+      "epoch": 0.012095250094494142,
+      "grad_norm": 0.14349691569805145,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.761,
+      "step": 42
+    },
+    {
+      "epoch": 0.012383232239601145,
+      "grad_norm": 0.1615252047777176,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.7902,
+      "step": 43
+    },
+    {
+      "epoch": 0.012671214384708147,
+      "grad_norm": 0.18619227409362793,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7834,
+      "step": 44
+    },
+    {
+      "epoch": 0.012959196529815151,
+      "grad_norm": 0.1851702183485031,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8416,
+      "step": 45
+    },
+    {
+      "epoch": 0.013247178674922155,
+      "grad_norm": 0.25002363324165344,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8841,
+      "step": 46
+    },
+    {
+      "epoch": 0.013535160820029158,
+      "grad_norm": 0.24446968734264374,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.8925,
+      "step": 47
+    },
+    {
+      "epoch": 0.013823142965136162,
+      "grad_norm": 0.2574883997440338,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.9444,
+      "step": 48
+    },
+    {
+      "epoch": 0.014111125110243166,
+      "grad_norm": 0.31319063901901245,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.9889,
+      "step": 49
+    },
+    {
+      "epoch": 0.014399107255350168,
+      "grad_norm": 0.37628719210624695,
+      "learning_rate": 0.0,
+      "loss": 1.1596,
+      "step": 50
+    },
+    {
+      "epoch": 0.014399107255350168,
+      "eval_loss": 0.9670636057853699,
+      "eval_runtime": 1334.3641,
+      "eval_samples_per_second": 17.531,
+      "eval_steps_per_second": 2.192,
+      "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": 1.3469808143735194e+17,
+  "total_flos": 2.6947910513564058e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null