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:b6249e01d95e46a5d3ada911a87012cd2b899ddfec2d6bdeef3e353906966f8e
+oid sha256:868f646ef48a4fefdd55af6456a2b09aee2537a945a6dea98ae42c0d794fa793
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13a068ad4137c7b7501c0435c01039951b6cf65787a0fdf11be2851815a5b063
+oid sha256:afe0b0db446b4405a15aa1afac2e919671922fe87630dc3c8229d5e4dc1e2c14
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c1ca974d242ee9cf351d4bb7f9fe899af4c19713ff78f0fcad302d6b1338d27
+oid sha256:cce6a5234e51daa21eb44d10accde9ab7d56b280d8ea65755f4982b66964fe1a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7010dd82c0325d097a3914579a3a83f39331a98fc3759e463461a6cc71f2055
+oid sha256:b3f65c402f4402be64e282862dc8ecac9c6cd8d713440a6409078f77222d1f0f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebbd96ce1722be4cea34b3ea08f1931e7beab9099fa041221a21a150a4ffa319
+oid sha256:1d34df5f1ae784c1e399dcc8e983f4597d4d99f6452c377ebb019d9fdb0062a1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dedada7144b670a88a82d3122ce48b01f53bc6025c030ead8f1e7b25a7f2ce2a
+oid sha256:797344e9349c92cfe5181718cbbe23f46ec9ffbe13a9b4f095a2a0d0c19f92d8
 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": 1.598935842514038,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.20263424518743667,
+  "best_metric": 1.5668654441833496,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.40526849037487334,
   "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": 34.776,
       "eval_steps_per_second": 4.352,
       "step": 25
+    },
+    {
+      "epoch": 0.21073961499493415,
+      "grad_norm": 0.250800222158432,
+      "learning_rate": 5e-05,
+      "loss": 1.4023,
+      "step": 26
+    },
+    {
+      "epoch": 0.2188449848024316,
+      "grad_norm": 0.24198980629444122,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.3362,
+      "step": 27
+    },
+    {
+      "epoch": 0.22695035460992907,
+      "grad_norm": 0.18812240660190582,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.3514,
+      "step": 28
+    },
+    {
+      "epoch": 0.23505572441742653,
+      "grad_norm": 0.2894032597541809,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.2495,
+      "step": 29
+    },
+    {
+      "epoch": 0.24316109422492402,
+      "grad_norm": 0.21906958520412445,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.444,
+      "step": 30
+    },
+    {
+      "epoch": 0.2512664640324215,
+      "grad_norm": 0.2103070467710495,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.5269,
+      "step": 31
+    },
+    {
+      "epoch": 0.25937183383991896,
+      "grad_norm": 0.2812809646129608,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.4841,
+      "step": 32
+    },
+    {
+      "epoch": 0.2674772036474164,
+      "grad_norm": 0.24371977150440216,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.664,
+      "step": 33
+    },
+    {
+      "epoch": 0.2755825734549139,
+      "grad_norm": 0.26612022519111633,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.6387,
+      "step": 34
+    },
+    {
+      "epoch": 0.28368794326241137,
+      "grad_norm": 0.21530385315418243,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.7245,
+      "step": 35
+    },
+    {
+      "epoch": 0.2917933130699088,
+      "grad_norm": 0.2958863377571106,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.9309,
+      "step": 36
+    },
+    {
+      "epoch": 0.2998986828774063,
+      "grad_norm": 0.4526556730270386,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.8786,
+      "step": 37
+    },
+    {
+      "epoch": 0.3080040526849038,
+      "grad_norm": 0.14817576110363007,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4305,
+      "step": 38
+    },
+    {
+      "epoch": 0.3161094224924012,
+      "grad_norm": 0.12831979990005493,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.2881,
+      "step": 39
+    },
+    {
+      "epoch": 0.3242147922998987,
+      "grad_norm": 0.15420038998126984,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.2267,
+      "step": 40
+    },
+    {
+      "epoch": 0.3323201621073962,
+      "grad_norm": 0.12769393622875214,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.2373,
+      "step": 41
+    },
+    {
+      "epoch": 0.3404255319148936,
+      "grad_norm": 0.13905879855155945,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3497,
+      "step": 42
+    },
+    {
+      "epoch": 0.3485309017223911,
+      "grad_norm": 0.13880909979343414,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.3607,
+      "step": 43
+    },
+    {
+      "epoch": 0.3566362715298885,
+      "grad_norm": 0.12389617413282394,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.4539,
+      "step": 44
+    },
+    {
+      "epoch": 0.364741641337386,
+      "grad_norm": 0.1297137439250946,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.5299,
+      "step": 45
+    },
+    {
+      "epoch": 0.3728470111448835,
+      "grad_norm": 0.16556890308856964,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.6069,
+      "step": 46
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.15601517260074615,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.6373,
+      "step": 47
+    },
+    {
+      "epoch": 0.3890577507598784,
+      "grad_norm": 0.16503740847110748,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.7971,
+      "step": 48
+    },
+    {
+      "epoch": 0.3971631205673759,
+      "grad_norm": 0.21679052710533142,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.9231,
+      "step": 49
+    },
+    {
+      "epoch": 0.40526849037487334,
+      "grad_norm": 0.39398708939552307,
+      "learning_rate": 0.0,
+      "loss": 2.1675,
+      "step": 50
+    },
+    {
+      "epoch": 0.40526849037487334,
+      "eval_loss": 1.5668654441833496,
+      "eval_runtime": 23.9003,
+      "eval_samples_per_second": 34.769,
+      "eval_steps_per_second": 4.351,
+      "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": 2.652642132099072e+17,
+  "total_flos": 5.305284264198144e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null