Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a78a5ad316c5ae20ffd1c4f1e70be6d0da9fbc807f6a32df3b80b985513826d
+oid sha256:5fa0b5cf64cebf94328d779e0a4c2eb1fe4b55453c5f3a7e208d770a8883ad05
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61e9ad38d6ea3a1b286dfe685bf743457ba0f49db452b8cab91f016fbd14a1ef
+oid sha256:ffc0ecdeed3b4a3bfd247a8e06afdd94da4461e9f641b4403336bbb4b2d73ae0
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935604650dca2ec2062875f4f6b20f3d920ea3cf54e5d7adc62b1c5a1bcb0085
+oid sha256:1e62997b340ea554f0c085d4706675af0fdd3f840ee95db67bb3bd111da36090
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27b5ed9f561b329a9af046537d5fa67d4cb080cdf9fa3320a318ff433589c516
+oid sha256:2ac08e050a45a101724df5d3a448c62b78ab2f06a3ac735e9c1e5e24eacbd336
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:610ddc7c96deb5b5592d78f865e5b2bfc55e16f00d50ff462f3dc52240a2c4fb
+oid sha256:f088b6e9880d8bbd93ca79ae1325012d5e81ecd914db9fe0ec1f47f9c0a29a3a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c6e5e1fce48789c9d9d84ee3d4c44a6efd527cce45698ef199a81aa9fed1bd3
+oid sha256:2c635e03a2dd13aaab1d736f055f8ee9bcd3ad0191820234f15fa38aaf06a555
 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": 10.362049102783203,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.008180628272251309,
+  "best_metric": 10.360050201416016,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.016361256544502618,
   "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": 1048.008,
       "eval_steps_per_second": 131.026,
       "step": 25
+    },
+    {
+      "epoch": 0.008507853403141362,
+      "grad_norm": 0.0465715155005455,
+      "learning_rate": 5e-05,
+      "loss": 10.3673,
+      "step": 26
+    },
+    {
+      "epoch": 0.008835078534031414,
+      "grad_norm": 0.0531485453248024,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3679,
+      "step": 27
+    },
+    {
+      "epoch": 0.009162303664921465,
+      "grad_norm": 0.04927300289273262,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.367,
+      "step": 28
+    },
+    {
+      "epoch": 0.009489528795811518,
+      "grad_norm": 0.053813155740499496,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3641,
+      "step": 29
+    },
+    {
+      "epoch": 0.00981675392670157,
+      "grad_norm": 0.05822814628481865,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3658,
+      "step": 30
+    },
+    {
+      "epoch": 0.010143979057591623,
+      "grad_norm": 0.07245771586894989,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3648,
+      "step": 31
+    },
+    {
+      "epoch": 0.010471204188481676,
+      "grad_norm": 0.06997586041688919,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3608,
+      "step": 32
+    },
+    {
+      "epoch": 0.010798429319371727,
+      "grad_norm": 0.0739465206861496,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3633,
+      "step": 33
+    },
+    {
+      "epoch": 0.01112565445026178,
+      "grad_norm": 0.08442109823226929,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3608,
+      "step": 34
+    },
+    {
+      "epoch": 0.011452879581151832,
+      "grad_norm": 0.08695055544376373,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3621,
+      "step": 35
+    },
+    {
+      "epoch": 0.011780104712041885,
+      "grad_norm": 0.09437209367752075,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3534,
+      "step": 36
+    },
+    {
+      "epoch": 0.012107329842931938,
+      "grad_norm": 0.10353465378284454,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3544,
+      "step": 37
+    },
+    {
+      "epoch": 0.012434554973821989,
+      "grad_norm": 0.06279531121253967,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3637,
+      "step": 38
+    },
+    {
+      "epoch": 0.012761780104712041,
+      "grad_norm": 0.060497626662254333,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3668,
+      "step": 39
+    },
+    {
+      "epoch": 0.013089005235602094,
+      "grad_norm": 0.05795399472117424,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3645,
+      "step": 40
+    },
+    {
+      "epoch": 0.013416230366492147,
+      "grad_norm": 0.05940159037709236,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3635,
+      "step": 41
+    },
+    {
+      "epoch": 0.0137434554973822,
+      "grad_norm": 0.061443179845809937,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3669,
+      "step": 42
+    },
+    {
+      "epoch": 0.01407068062827225,
+      "grad_norm": 0.0652313157916069,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3625,
+      "step": 43
+    },
+    {
+      "epoch": 0.014397905759162303,
+      "grad_norm": 0.06856326758861542,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3601,
+      "step": 44
+    },
+    {
+      "epoch": 0.014725130890052356,
+      "grad_norm": 0.06705807894468307,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3607,
+      "step": 45
+    },
+    {
+      "epoch": 0.015052356020942409,
+      "grad_norm": 0.07734378427267075,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3589,
+      "step": 46
+    },
+    {
+      "epoch": 0.015379581151832461,
+      "grad_norm": 0.0883852019906044,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3599,
+      "step": 47
+    },
+    {
+      "epoch": 0.015706806282722512,
+      "grad_norm": 0.08160966634750366,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3601,
+      "step": 48
+    },
+    {
+      "epoch": 0.016034031413612565,
+      "grad_norm": 0.09474560618400574,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3526,
+      "step": 49
+    },
+    {
+      "epoch": 0.016361256544502618,
+      "grad_norm": 0.1311928927898407,
+      "learning_rate": 0.0,
+      "loss": 10.3484,
+      "step": 50
+    },
+    {
+      "epoch": 0.016361256544502618,
+      "eval_loss": 10.360050201416016,
+      "eval_runtime": 19.6493,
+      "eval_samples_per_second": 1047.772,
+      "eval_steps_per_second": 130.997,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null