Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63df0a1bd0540cf1a0dae8fcfaab391eae21fb4f651002209e3714a70784bcf0
+oid sha256:22f542ef3c12557248365ffb8d03822ccdcce594def050f25d299948bd2d73e6
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0301e3ec03adfafe9f233cdd70dd3cf266ad765007072f55ccc725b4477e18f9
+oid sha256:3b087798b65e7ff828166ef6c070ab0e6de2cd7df9237cd5f8c9b87c1d2b2930
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fbca2f1d57093774cb4aeeec38d1c6ef1abd4364d6c971a7ba9c45ecb05bb5a
+oid sha256:559aa10059625f99af0899b7c5f5630a2beb9dd0a9b126808387cef62811e8c3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:125cb9d95ee16dae18caa5bc1572dfec1ee85d40c30e7a29fa39a2081f5f2f8f
+oid sha256:7b31dc274602e6a897b3edc3dd34801a1dd3d615256f6dce9f5dd3160b952f33
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46038ab0e283dc204fc05fec283e1b1ec7abaebfcbaf1e014e9867f2a1222bc0
+oid sha256:d8bf563e6017f9f6e309dcd72e42652626daddbfcececac5383a8a2ba542453b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935570032a97263d452551eb51363d628a856781073a14d72cd69a0c5ede5327
+oid sha256:14a79cb554d4a2af36be69c632cb1fe8d04a03d3813ae95e76af048425ae0c05
 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": 0.08920711278915405,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3606853020739405,
+  "best_metric": 0.032030824571847916,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.721370604147881,
   "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": 18.631,
       "eval_steps_per_second": 2.354,
       "step": 25
+    },
+    {
+      "epoch": 0.3751127141568981,
+      "grad_norm": 1.3733659982681274,
+      "learning_rate": 5e-05,
+      "loss": 0.1326,
+      "step": 26
+    },
+    {
+      "epoch": 0.38954012623985573,
+      "grad_norm": 1.0818101167678833,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0961,
+      "step": 27
+    },
+    {
+      "epoch": 0.40396753832281335,
+      "grad_norm": 0.9106768369674683,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.09,
+      "step": 28
+    },
+    {
+      "epoch": 0.41839495040577096,
+      "grad_norm": 0.8540586233139038,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0719,
+      "step": 29
+    },
+    {
+      "epoch": 0.4328223624887286,
+      "grad_norm": 0.49809011816978455,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0355,
+      "step": 30
+    },
+    {
+      "epoch": 0.4472497745716862,
+      "grad_norm": 1.1465601921081543,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.1165,
+      "step": 31
+    },
+    {
+      "epoch": 0.4616771866546438,
+      "grad_norm": 1.0467514991760254,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0794,
+      "step": 32
+    },
+    {
+      "epoch": 0.47610459873760147,
+      "grad_norm": 0.6225173473358154,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0427,
+      "step": 33
+    },
+    {
+      "epoch": 0.4905320108205591,
+      "grad_norm": 0.7643168568611145,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.053,
+      "step": 34
+    },
+    {
+      "epoch": 0.5049594229035167,
+      "grad_norm": 0.3798767626285553,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0249,
+      "step": 35
+    },
+    {
+      "epoch": 0.5193868349864743,
+      "grad_norm": 0.45972785353660583,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0295,
+      "step": 36
+    },
+    {
+      "epoch": 0.5338142470694319,
+      "grad_norm": 0.8855461478233337,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0541,
+      "step": 37
+    },
+    {
+      "epoch": 0.5482416591523895,
+      "grad_norm": 0.8349403738975525,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0784,
+      "step": 38
+    },
+    {
+      "epoch": 0.5626690712353472,
+      "grad_norm": 1.1553421020507812,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0662,
+      "step": 39
+    },
+    {
+      "epoch": 0.5770964833183048,
+      "grad_norm": 0.6340785026550293,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0282,
+      "step": 40
+    },
+    {
+      "epoch": 0.5915238954012624,
+      "grad_norm": 0.7049694657325745,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0432,
+      "step": 41
+    },
+    {
+      "epoch": 0.60595130748422,
+      "grad_norm": 0.3650566339492798,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0179,
+      "step": 42
+    },
+    {
+      "epoch": 0.6203787195671776,
+      "grad_norm": 0.7143826484680176,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0569,
+      "step": 43
+    },
+    {
+      "epoch": 0.6348061316501352,
+      "grad_norm": 0.7505943179130554,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0829,
+      "step": 44
+    },
+    {
+      "epoch": 0.6492335437330928,
+      "grad_norm": 0.2939123213291168,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0217,
+      "step": 45
+    },
+    {
+      "epoch": 0.6636609558160504,
+      "grad_norm": 0.6556983590126038,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0513,
+      "step": 46
+    },
+    {
+      "epoch": 0.6780883678990082,
+      "grad_norm": 0.6699650883674622,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0262,
+      "step": 47
+    },
+    {
+      "epoch": 0.6925157799819658,
+      "grad_norm": 0.3060078024864197,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0176,
+      "step": 48
+    },
+    {
+      "epoch": 0.7069431920649234,
+      "grad_norm": 0.27289947867393494,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0141,
+      "step": 49
+    },
+    {
+      "epoch": 0.721370604147881,
+      "grad_norm": 0.819500207901001,
+      "learning_rate": 0.0,
+      "loss": 0.0505,
+      "step": 50
+    },
+    {
+      "epoch": 0.721370604147881,
+      "eval_loss": 0.032030824571847916,
+      "eval_runtime": 25.0605,
+      "eval_samples_per_second": 18.635,
+      "eval_steps_per_second": 2.354,
+      "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": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null