Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:748a6d2c77da6eaa18da4936a1954e4cfcbcbcab342c8206203d100c92913975
+oid sha256:e7e5f1f8241e7d21dacb809ce7889a351a94f49752adfe8d08b97dd800f204bd
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f1476e205e231a0f0511b343f31853ba450801bf35bb3d2dec712744b4eabbf
+oid sha256:a08ab0037b487ea45525fca0447fa6533c7ce3ff8530444642366d92e93aec93
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d7def6ff561954dab3362e02af582a7db05eff8f104ff6af2153244d3b393b5
+oid sha256:2c2188aa982e769b5a248931c6961089baf8810770ba81754f14798fc88a0fc2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8232bc2ebba850f4e8aafc66ca6dbc62035b5de29f1717cf346d1f1efc6735e5
+oid sha256:64b22d9cf6e43e5d1a875969eb2f23d137197b204901c7e069844627d70e0dfc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14f5e588d22c6102215df31d56b019bfa970fa2ebde4173794a8dbe200c819ba
+oid sha256:71e1ecafad9620cda97b69bf9f033a2096a420d071bb1e349dbe05093db0af5f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b624a4f10bee24e6bfc3a52bd2699fb4e0f76d22892a4feafdab90138d75fe2e
+oid sha256:6e752ea650d9401853aabe9ee0bb82ca4c8b68565e34a9b2818c443f5afff675
 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": 2.9423482418060303,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3372681281618887,
+  "best_metric": 2.2613911628723145,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6745362563237775,
   "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": 15.156,
       "eval_steps_per_second": 1.91,
       "step": 25
+    },
+    {
+      "epoch": 0.35075885328836426,
+      "grad_norm": 327.58599853515625,
+      "learning_rate": 5e-05,
+      "loss": 3.0293,
+      "step": 26
+    },
+    {
+      "epoch": 0.3642495784148398,
+      "grad_norm": 362.6495056152344,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.3553,
+      "step": 27
+    },
+    {
+      "epoch": 0.3777403035413153,
+      "grad_norm": 316.2618103027344,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.9598,
+      "step": 28
+    },
+    {
+      "epoch": 0.3912310286677909,
+      "grad_norm": 237.7189178466797,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.7075,
+      "step": 29
+    },
+    {
+      "epoch": 0.40472175379426645,
+      "grad_norm": 114.92796325683594,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.4807,
+      "step": 30
+    },
+    {
+      "epoch": 0.418212478920742,
+      "grad_norm": 48.19389724731445,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.4164,
+      "step": 31
+    },
+    {
+      "epoch": 0.4317032040472175,
+      "grad_norm": 71.13121032714844,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.3391,
+      "step": 32
+    },
+    {
+      "epoch": 0.4451939291736931,
+      "grad_norm": 78.83213806152344,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.2943,
+      "step": 33
+    },
+    {
+      "epoch": 0.45868465430016864,
+      "grad_norm": 71.80233001708984,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.3639,
+      "step": 34
+    },
+    {
+      "epoch": 0.47217537942664417,
+      "grad_norm": 74.17680358886719,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.4181,
+      "step": 35
+    },
+    {
+      "epoch": 0.4856661045531197,
+      "grad_norm": 69.19786071777344,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.2874,
+      "step": 36
+    },
+    {
+      "epoch": 0.4991568296795953,
+      "grad_norm": 66.0870132446289,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.34,
+      "step": 37
+    },
+    {
+      "epoch": 0.5126475548060708,
+      "grad_norm": 43.74034881591797,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.3367,
+      "step": 38
+    },
+    {
+      "epoch": 0.5261382799325464,
+      "grad_norm": 63.72829055786133,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.2909,
+      "step": 39
+    },
+    {
+      "epoch": 0.5396290050590219,
+      "grad_norm": 79.226318359375,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.2279,
+      "step": 40
+    },
+    {
+      "epoch": 0.5531197301854974,
+      "grad_norm": 74.6691665649414,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.232,
+      "step": 41
+    },
+    {
+      "epoch": 0.5666104553119731,
+      "grad_norm": 71.57418823242188,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.1768,
+      "step": 42
+    },
+    {
+      "epoch": 0.5801011804384486,
+      "grad_norm": 63.76176452636719,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.3299,
+      "step": 43
+    },
+    {
+      "epoch": 0.5935919055649241,
+      "grad_norm": 51.7007942199707,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.2503,
+      "step": 44
+    },
+    {
+      "epoch": 0.6070826306913997,
+      "grad_norm": 39.83833694458008,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.3118,
+      "step": 45
+    },
+    {
+      "epoch": 0.6205733558178752,
+      "grad_norm": 38.03684616088867,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.3047,
+      "step": 46
+    },
+    {
+      "epoch": 0.6340640809443507,
+      "grad_norm": 34.288970947265625,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.2329,
+      "step": 47
+    },
+    {
+      "epoch": 0.6475548060708263,
+      "grad_norm": 31.958253860473633,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.2962,
+      "step": 48
+    },
+    {
+      "epoch": 0.6610455311973018,
+      "grad_norm": 39.0740966796875,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.3091,
+      "step": 49
+    },
+    {
+      "epoch": 0.6745362563237775,
+      "grad_norm": 87.91134643554688,
+      "learning_rate": 0.0,
+      "loss": 2.4479,
+      "step": 50
+    },
+    {
+      "epoch": 0.6745362563237775,
+      "eval_loss": 2.2613911628723145,
+      "eval_runtime": 33.0075,
+      "eval_samples_per_second": 15.148,
+      "eval_steps_per_second": 1.909,
+      "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": 2.829013890367488e+17,
+  "total_flos": 5.658027780734976e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null