Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11f113ad443907198cb37d74e3b6b0811e87ca211cbf9907bf1800fe154a4225
+oid sha256:1dc830ae39987f19c235bcd1155ceff5628372602ea0229dbdd659b0dab98917
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27ec4974bca95e5cd38ea0ff0776635bf5b944bb3d4603dab83196c7e8e6fc8a
+oid sha256:82e53628dcaeb890e2746422eaff257c40e088a4a086c375e7941781bff2fc0c
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6dea2078482e70f16e01c3cf5040d01914fa8e1a537c02740ac03410da8d4c3
+oid sha256:863a97a401790cb5825ddd42fae6b858ed63dbefcbc29410d7fdea8bc2dfc16f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b6cd3b9cb7580e662111af7abb75228cb0535d6019d1bdd8e7af75ee5293bca
+oid sha256:2ea07d93ed263c1fd4cffa636ba870623c49e35bc3f4cf3db2626b73029fc251
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ea7eeb7fa96e1032076a3efedd135016e87a9fe5518c853728c8e18999d5dee
+oid sha256:5095cdd6f5ff021c98f0d35d5faec532d9b67febe543c719e988c7890e116197
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dee70873c901dca6cd6793bfea21ef893d803f0d38dd96ed3108d894fc2cfe62
+oid sha256:a746eb44f0042c16f90abd588e67aabb5e36fe3e551cda59ac418932d282ba75
 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": 2.8326058387756348,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3436426116838488,
+  "best_metric": 2.7374379634857178,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6872852233676976,
   "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": 16.061,
       "eval_steps_per_second": 2.032,
       "step": 25
+    },
+    {
+      "epoch": 0.35738831615120276,
+      "grad_norm": 0.5904625654220581,
+      "learning_rate": 5e-05,
+      "loss": 3.0126,
+      "step": 26
+    },
+    {
+      "epoch": 0.3711340206185567,
+      "grad_norm": 0.6415864825248718,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.9682,
+      "step": 27
+    },
+    {
+      "epoch": 0.3848797250859107,
+      "grad_norm": 0.5782291889190674,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.9303,
+      "step": 28
+    },
+    {
+      "epoch": 0.39862542955326463,
+      "grad_norm": 0.5609015822410583,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.9249,
+      "step": 29
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 0.48684611916542053,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.8978,
+      "step": 30
+    },
+    {
+      "epoch": 0.4261168384879725,
+      "grad_norm": 0.45882076025009155,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.8614,
+      "step": 31
+    },
+    {
+      "epoch": 0.43986254295532645,
+      "grad_norm": 0.40644049644470215,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.7954,
+      "step": 32
+    },
+    {
+      "epoch": 0.4536082474226804,
+      "grad_norm": 0.4016781449317932,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.7111,
+      "step": 33
+    },
+    {
+      "epoch": 0.46735395189003437,
+      "grad_norm": 0.45421966910362244,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.7871,
+      "step": 34
+    },
+    {
+      "epoch": 0.48109965635738833,
+      "grad_norm": 0.48663410544395447,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.7124,
+      "step": 35
+    },
+    {
+      "epoch": 0.4948453608247423,
+      "grad_norm": 0.6618165373802185,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.921,
+      "step": 36
+    },
+    {
+      "epoch": 0.5085910652920962,
+      "grad_norm": 0.9185125231742859,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.6715,
+      "step": 37
+    },
+    {
+      "epoch": 0.5223367697594502,
+      "grad_norm": 0.3857472538948059,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.971,
+      "step": 38
+    },
+    {
+      "epoch": 0.5360824742268041,
+      "grad_norm": 0.3716031312942505,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.9631,
+      "step": 39
+    },
+    {
+      "epoch": 0.5498281786941581,
+      "grad_norm": 0.4130760133266449,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.9389,
+      "step": 40
+    },
+    {
+      "epoch": 0.563573883161512,
+      "grad_norm": 0.37855178117752075,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.8596,
+      "step": 41
+    },
+    {
+      "epoch": 0.5773195876288659,
+      "grad_norm": 0.3730044364929199,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.8893,
+      "step": 42
+    },
+    {
+      "epoch": 0.5910652920962199,
+      "grad_norm": 0.399122953414917,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.7885,
+      "step": 43
+    },
+    {
+      "epoch": 0.6048109965635738,
+      "grad_norm": 0.38850271701812744,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.8442,
+      "step": 44
+    },
+    {
+      "epoch": 0.6185567010309279,
+      "grad_norm": 0.41439515352249146,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.652,
+      "step": 45
+    },
+    {
+      "epoch": 0.6323024054982818,
+      "grad_norm": 0.41602662205696106,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.6787,
+      "step": 46
+    },
+    {
+      "epoch": 0.6460481099656358,
+      "grad_norm": 0.4596008360385895,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.7676,
+      "step": 47
+    },
+    {
+      "epoch": 0.6597938144329897,
+      "grad_norm": 0.4760560691356659,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.6652,
+      "step": 48
+    },
+    {
+      "epoch": 0.6735395189003437,
+      "grad_norm": 0.6931067109107971,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.59,
+      "step": 49
+    },
+    {
+      "epoch": 0.6872852233676976,
+      "grad_norm": 1.223355770111084,
+      "learning_rate": 0.0,
+      "loss": 2.7209,
+      "step": 50
+    },
+    {
+      "epoch": 0.6872852233676976,
+      "eval_loss": 2.7374379634857178,
+      "eval_runtime": 30.5331,
+      "eval_samples_per_second": 16.048,
+      "eval_steps_per_second": 2.031,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null