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:a3e8b83c16c3deac16425f11f510907c939d03b8c1db73501696f9afac6af921
+oid sha256:23a65ee166e7b692e428f19d3228f2820235b1ebecff32cd59e8853c516fae7c
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf17221d0d4f8d688ba91e306d83be82453b36aafd121332cda2bf9d70b94f6b
+oid sha256:c5f6c52589b64676d3f0a36d956d59fbf7bac6ec26ea2f410327eeaf38f441c9
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96b4da2986de8077d21e29ad12a2f57545dc290b7560a34ea93e5e222d65f69f
+oid sha256:f586c6c7c8836b0a1b0f2eb8bf3da5b730a0edb64c504738c42f06560b5be8f5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6659cff124862fca68af8e63f92f33b5a8ef4521f37d1ff4a1256968e0b1634
+oid sha256:fc24f6fed1ec931b8736c04fce9b03e023b5545cee0b100a23018b1131e2cf90
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:909417e31f38a0d0c7dea3d0c22d78a77c86a77697576912f62ec9b68dc8b13d
+oid sha256:670308ce7659289a93953875f9dab10d2ea98aff83c99e89ac5cde13f9037faa
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87adff1ee5066ccd11f7876be5604e785511e161363a3ef2266033e17139fc4a
+oid sha256:64c23623495f9df8dbba2c6d63933a443eb2b2b51791012c349af9bea56c1cfb
 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": 0.12119682133197784,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.1485714285714286,
+  "best_metric": 0.06591447442770004,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.297142857142857,
   "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": 29.351,
       "eval_steps_per_second": 3.768,
       "step": 25
+    },
+    {
+      "epoch": 1.1942857142857144,
+      "grad_norm": 1.4274019002914429,
+      "learning_rate": 5e-05,
+      "loss": 0.0741,
+      "step": 26
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 3.5917248725891113,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0649,
+      "step": 27
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 2.621929407119751,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0699,
+      "step": 28
+    },
+    {
+      "epoch": 1.3314285714285714,
+      "grad_norm": 7.4172587394714355,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0814,
+      "step": 29
+    },
+    {
+      "epoch": 1.3771428571428572,
+      "grad_norm": 1.105510950088501,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0542,
+      "step": 30
+    },
+    {
+      "epoch": 1.4228571428571428,
+      "grad_norm": 6.01181697845459,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0764,
+      "step": 31
+    },
+    {
+      "epoch": 1.4685714285714286,
+      "grad_norm": 6.905984401702881,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0955,
+      "step": 32
+    },
+    {
+      "epoch": 1.5142857142857142,
+      "grad_norm": 3.86792254447937,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0608,
+      "step": 33
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 2.1256277561187744,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0715,
+      "step": 34
+    },
+    {
+      "epoch": 1.6057142857142859,
+      "grad_norm": 1.1592352390289307,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0806,
+      "step": 35
+    },
+    {
+      "epoch": 1.6514285714285715,
+      "grad_norm": 2.9074413776397705,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0529,
+      "step": 36
+    },
+    {
+      "epoch": 1.697142857142857,
+      "grad_norm": 0.9467344880104065,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0506,
+      "step": 37
+    },
+    {
+      "epoch": 1.7428571428571429,
+      "grad_norm": 1.4687691926956177,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.044,
+      "step": 38
+    },
+    {
+      "epoch": 1.7885714285714287,
+      "grad_norm": 3.692380905151367,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0465,
+      "step": 39
+    },
+    {
+      "epoch": 1.8342857142857143,
+      "grad_norm": 1.5593693256378174,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0521,
+      "step": 40
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 3.5100090503692627,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0833,
+      "step": 41
+    },
+    {
+      "epoch": 1.9257142857142857,
+      "grad_norm": 2.3228797912597656,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0879,
+      "step": 42
+    },
+    {
+      "epoch": 1.9714285714285715,
+      "grad_norm": 1.710174560546875,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0463,
+      "step": 43
+    },
+    {
+      "epoch": 2.0228571428571427,
+      "grad_norm": 0.9889352321624756,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0852,
+      "step": 44
+    },
+    {
+      "epoch": 2.0685714285714285,
+      "grad_norm": 0.7676489949226379,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.03,
+      "step": 45
+    },
+    {
+      "epoch": 2.1142857142857143,
+      "grad_norm": 1.2411009073257446,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0414,
+      "step": 46
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 1.7227236032485962,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0425,
+      "step": 47
+    },
+    {
+      "epoch": 2.2057142857142855,
+      "grad_norm": 3.282838821411133,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0347,
+      "step": 48
+    },
+    {
+      "epoch": 2.2514285714285713,
+      "grad_norm": 1.625943899154663,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0295,
+      "step": 49
+    },
+    {
+      "epoch": 2.297142857142857,
+      "grad_norm": 0.8124039769172668,
+      "learning_rate": 0.0,
+      "loss": 0.0367,
+      "step": 50
+    },
+    {
+      "epoch": 2.297142857142857,
+      "eval_loss": 0.06591447442770004,
+      "eval_runtime": 5.04,
+      "eval_samples_per_second": 29.365,
+      "eval_steps_per_second": 3.77,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null