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:bf560e2e7409ddf57d7ece644e9c5c5de3de77ff038555623e5ed727dd996576
+oid sha256:365102aeac295d570316a3d304754637495a72ebff69a3c5cd18a8c4571438c7
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2894ce984c995455e3b887217a0a9fdda861e79e4e087afaccfb156df7bc0814
+oid sha256:41f6580e5f500544cf8f6bb5a9a9699e5c79375248d1b0b715e16f1bb0775e69
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17d0114118a73d0c78c6ee6ba2c843a465438f82ae4124e160457df34227e45c
+oid sha256:9dfb87d696a1e1b6e15531275e3e3d8c6c5b39e0511dcfb3af572a36dc6ee094
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91a2cc6c3f4b5622fd61d3c3d8da364dc88572b89922595f444ca0cc114fd554
+oid sha256:4528bb37182b6d5098d1bc3455182c55e3779bfb579da0a357bbf4cc50bd1ef2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:087769dfbc3dfd8ff58bd1931d796cd62e6fecc41a7f95d6351abf3a6517b5d6
+oid sha256:2c144fa557bcf59053261912e1e2d9c43b420e8ccb8032c986e410a5d7229741
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10c5b295715e6407c221523b83719dea8bd6190b79d90c3e281dcc095feee92a
+oid sha256:0ea0fc2a6839efccdda8288ced6e835749b8fc64d38f9ccb873a3e08c0b6e7d1
 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": 0.5616207122802734,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1607717041800643,
+  "best_metric": 0.4051450192928314,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3215434083601286,
   "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": 76.564,
       "eval_steps_per_second": 9.57,
       "step": 25
+    },
+    {
+      "epoch": 0.16720257234726688,
+      "grad_norm": 0.32802271842956543,
+      "learning_rate": 5e-05,
+      "loss": 0.2042,
+      "step": 26
+    },
+    {
+      "epoch": 0.17363344051446947,
+      "grad_norm": 0.3432858884334564,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.1963,
+      "step": 27
+    },
+    {
+      "epoch": 0.18006430868167203,
+      "grad_norm": 0.47117841243743896,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1536,
+      "step": 28
+    },
+    {
+      "epoch": 0.1864951768488746,
+      "grad_norm": 0.7523587346076965,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1858,
+      "step": 29
+    },
+    {
+      "epoch": 0.19292604501607716,
+      "grad_norm": 1.9443529844284058,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5641,
+      "step": 30
+    },
+    {
+      "epoch": 0.19935691318327975,
+      "grad_norm": 1.7204391956329346,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8415,
+      "step": 31
+    },
+    {
+      "epoch": 0.2057877813504823,
+      "grad_norm": 1.6888691186904907,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8393,
+      "step": 32
+    },
+    {
+      "epoch": 0.21221864951768488,
+      "grad_norm": 1.8478753566741943,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.7366,
+      "step": 33
+    },
+    {
+      "epoch": 0.21864951768488747,
+      "grad_norm": 1.4996860027313232,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6738,
+      "step": 34
+    },
+    {
+      "epoch": 0.22508038585209003,
+      "grad_norm": 1.2945411205291748,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.6364,
+      "step": 35
+    },
+    {
+      "epoch": 0.2315112540192926,
+      "grad_norm": 1.1487884521484375,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.5501,
+      "step": 36
+    },
+    {
+      "epoch": 0.2379421221864952,
+      "grad_norm": 0.9475870728492737,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3431,
+      "step": 37
+    },
+    {
+      "epoch": 0.24437299035369775,
+      "grad_norm": 0.3858092725276947,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2235,
+      "step": 38
+    },
+    {
+      "epoch": 0.2508038585209003,
+      "grad_norm": 0.3695223927497864,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.1923,
+      "step": 39
+    },
+    {
+      "epoch": 0.2572347266881029,
+      "grad_norm": 0.3529227674007416,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1856,
+      "step": 40
+    },
+    {
+      "epoch": 0.26366559485530544,
+      "grad_norm": 0.6777685284614563,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1207,
+      "step": 41
+    },
+    {
+      "epoch": 0.27009646302250806,
+      "grad_norm": 0.6900791525840759,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1935,
+      "step": 42
+    },
+    {
+      "epoch": 0.2765273311897106,
+      "grad_norm": 1.5598366260528564,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6328,
+      "step": 43
+    },
+    {
+      "epoch": 0.2829581993569132,
+      "grad_norm": 1.3518791198730469,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6282,
+      "step": 44
+    },
+    {
+      "epoch": 0.28938906752411575,
+      "grad_norm": 1.361425518989563,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6111,
+      "step": 45
+    },
+    {
+      "epoch": 0.2958199356913183,
+      "grad_norm": 1.2370153665542603,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.488,
+      "step": 46
+    },
+    {
+      "epoch": 0.3022508038585209,
+      "grad_norm": 1.0256456136703491,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.5618,
+      "step": 47
+    },
+    {
+      "epoch": 0.3086816720257235,
+      "grad_norm": 0.8804541826248169,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4539,
+      "step": 48
+    },
+    {
+      "epoch": 0.31511254019292606,
+      "grad_norm": 0.9141364693641663,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4084,
+      "step": 49
+    },
+    {
+      "epoch": 0.3215434083601286,
+      "grad_norm": 0.9475950598716736,
+      "learning_rate": 0.0,
+      "loss": 0.3759,
+      "step": 50
+    },
+    {
+      "epoch": 0.3215434083601286,
+      "eval_loss": 0.4051450192928314,
+      "eval_runtime": 13.6625,
+      "eval_samples_per_second": 76.707,
+      "eval_steps_per_second": 9.588,
+      "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": 7.94731890081792e+16,
+  "total_flos": 1.589463780163584e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null