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:dccee95091b4b69072f7ccc7b907673e22c418cc12e3a6e6d53db181cd39d29b
+oid sha256:65d2bbd89dadf4bf84de5227731ba3f1723e0bb02a3ac0ceb56cfdda9365d216
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5401dec28ec3298bbeed387f8b366f2d96589a7302aadd4f902ab6b8572d4e6a
+oid sha256:e213ecb822c0f88a65f9444b688b80afc3b48208d730f0d58cf9d1ec742a6ea1
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e52918a71203f8db26aa1a6286ae7e080cb3279416ee85a0671bfd3d695051b1
+oid sha256:4ca573846cad2d7cebefa900e9820081f01d5362b1ea5249ad8bfe9652068bed
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5835d771ca7dd658542af3b8fa4832b06470f92322c7d42246147c558973249a
+oid sha256:f40d30fb9c7a7604dc9d546726a10677063a36b28e9b0c26d9587dbf7bea5ca5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0fa4c7fee56eb5c4c4dc54b32c42ecb83ba53c7e21399e467b67c1c3fb7537e
+oid sha256:14fe391495256980c5c03dee8eff8b80dfe611000fc0da9dcf947763bb6afd17
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:849ce287c8079b33ad37d14b9d37f5717524d73a51092b85f6b14580c43a607a
+oid sha256:3819e642a9056110482f8944c199c4369510a86050d3711d7bdd28d98c45ffab
 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": 1.9534236192703247,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06902502157031924,
+  "best_metric": 1.8351699113845825,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13805004314063848,
   "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": 109.99,
       "eval_steps_per_second": 13.749,
       "step": 25
+    },
+    {
+      "epoch": 0.07178602243313201,
+      "grad_norm": 11.875720024108887,
+      "learning_rate": 5e-05,
+      "loss": 2.4916,
+      "step": 26
+    },
+    {
+      "epoch": 0.07454702329594479,
+      "grad_norm": 5.627650260925293,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.7081,
+      "step": 27
+    },
+    {
+      "epoch": 0.07730802415875755,
+      "grad_norm": 4.874751567840576,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.6722,
+      "step": 28
+    },
+    {
+      "epoch": 0.08006902502157032,
+      "grad_norm": 4.535109043121338,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.6553,
+      "step": 29
+    },
+    {
+      "epoch": 0.08283002588438308,
+      "grad_norm": 3.0000500679016113,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.6382,
+      "step": 30
+    },
+    {
+      "epoch": 0.08559102674719586,
+      "grad_norm": 0.9891252517700195,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.6092,
+      "step": 31
+    },
+    {
+      "epoch": 0.08835202761000863,
+      "grad_norm": 3.292105197906494,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.5993,
+      "step": 32
+    },
+    {
+      "epoch": 0.09111302847282139,
+      "grad_norm": 2.8137319087982178,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.6062,
+      "step": 33
+    },
+    {
+      "epoch": 0.09387402933563417,
+      "grad_norm": 0.6060113906860352,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.5763,
+      "step": 34
+    },
+    {
+      "epoch": 0.09663503019844694,
+      "grad_norm": 1.3685656785964966,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.5971,
+      "step": 35
+    },
+    {
+      "epoch": 0.0993960310612597,
+      "grad_norm": 3.1901323795318604,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.6005,
+      "step": 36
+    },
+    {
+      "epoch": 0.10215703192407248,
+      "grad_norm": 27.733556747436523,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.9088,
+      "step": 37
+    },
+    {
+      "epoch": 0.10491803278688525,
+      "grad_norm": 16.257993698120117,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.3302,
+      "step": 38
+    },
+    {
+      "epoch": 0.10767903364969801,
+      "grad_norm": 2.6833341121673584,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.6092,
+      "step": 39
+    },
+    {
+      "epoch": 0.11044003451251079,
+      "grad_norm": 2.7292048931121826,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.5974,
+      "step": 40
+    },
+    {
+      "epoch": 0.11320103537532356,
+      "grad_norm": 1.0176692008972168,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.5762,
+      "step": 41
+    },
+    {
+      "epoch": 0.11596203623813632,
+      "grad_norm": 2.5920333862304688,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.5751,
+      "step": 42
+    },
+    {
+      "epoch": 0.1187230371009491,
+      "grad_norm": 2.3291893005371094,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.5899,
+      "step": 43
+    },
+    {
+      "epoch": 0.12148403796376187,
+      "grad_norm": 0.8562758564949036,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.5714,
+      "step": 44
+    },
+    {
+      "epoch": 0.12424503882657463,
+      "grad_norm": 3.0587594509124756,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.5834,
+      "step": 45
+    },
+    {
+      "epoch": 0.1270060396893874,
+      "grad_norm": 0.6108625531196594,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.5768,
+      "step": 46
+    },
+    {
+      "epoch": 0.12976704055220017,
+      "grad_norm": 0.5593339800834656,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.5774,
+      "step": 47
+    },
+    {
+      "epoch": 0.13252804141501295,
+      "grad_norm": 0.6090744733810425,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.5771,
+      "step": 48
+    },
+    {
+      "epoch": 0.1352890422778257,
+      "grad_norm": 14.088340759277344,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.6429,
+      "step": 49
+    },
+    {
+      "epoch": 0.13805004314063848,
+      "grad_norm": 26.365188598632812,
+      "learning_rate": 0.0,
+      "loss": 3.5791,
+      "step": 50
+    },
+    {
+      "epoch": 0.13805004314063848,
+      "eval_loss": 1.8351699113845825,
+      "eval_runtime": 22.1791,
+      "eval_samples_per_second": 110.013,
+      "eval_steps_per_second": 13.752,
+      "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": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null