Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63bf4f7ba16bfc84fb42c5f7df8f1186f72e16f01a1251771aba5c22adeac580
+oid sha256:56002553fb08df97f53c84d92766a1c9e2344c77de9e235f84cb74dc250c5ffb
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdf6f815010065e49d96b8e0e004406df5172d5393eeaf19ecd49acc0325194a
+oid sha256:1ccf0dde441827c0ba6a024f4183ea26d1db3e54929b312e4ee101c470cdf64c
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04b6378962e1cb87b9fa22b102df776f42b39ae40ff6ca9b2463503b1fbc6ebb
+oid sha256:c60d45f07efabd19a5df6731c45399735a811b04a1d2a7e02767e37190d625a6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d551fbd33ebe57f40bfb6264dab769ac9ac3db53e237b17c93830519f4c77f63
+oid sha256:f3e897a3ec9e4693591d9723834bcfbfdf021d5eaf5b7706bf59606a750b6684
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d0dd76eea6c12dbf3342fe3ee52a052328fe36616f874bb6185411dc7017797
+oid sha256:5000c5a9021efa5c0d12444d0d0ef8987db915bd41ac72095c4de626561d85c8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efd80eeefedfacb6bd307f810ad94f706811b6f481f1c7c3e3f3f2410bfe25bc
+oid sha256:75b05e3e5f3c4603f91ddb29b75c8e3b9e69abcdd793fd2ff817c28efdcbc2be
 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": 0.03923076018691063,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.17006802721088435,
+  "best_metric": 0.006335424259305,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3401360544217687,
   "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": 55.066,
       "eval_steps_per_second": 6.897,
       "step": 25
+    },
+    {
+      "epoch": 0.17687074829931973,
+      "grad_norm": 0.8757835030555725,
+      "learning_rate": 5e-05,
+      "loss": 0.0741,
+      "step": 26
+    },
+    {
+      "epoch": 0.1836734693877551,
+      "grad_norm": 0.6202448010444641,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0278,
+      "step": 27
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 0.2728913724422455,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0152,
+      "step": 28
+    },
+    {
+      "epoch": 0.19727891156462585,
+      "grad_norm": 0.35162627696990967,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0054,
+      "step": 29
+    },
+    {
+      "epoch": 0.20408163265306123,
+      "grad_norm": 0.26197877526283264,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0038,
+      "step": 30
+    },
+    {
+      "epoch": 0.2108843537414966,
+      "grad_norm": 0.02254539169371128,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0002,
+      "step": 31
+    },
+    {
+      "epoch": 0.21768707482993196,
+      "grad_norm": 0.5768834948539734,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0592,
+      "step": 32
+    },
+    {
+      "epoch": 0.22448979591836735,
+      "grad_norm": 0.03499084711074829,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0004,
+      "step": 33
+    },
+    {
+      "epoch": 0.23129251700680273,
+      "grad_norm": 0.11083720624446869,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.001,
+      "step": 34
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 0.09705158323049545,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0009,
+      "step": 35
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "grad_norm": 0.25740352272987366,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0076,
+      "step": 36
+    },
+    {
+      "epoch": 0.25170068027210885,
+      "grad_norm": 0.5679620504379272,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0165,
+      "step": 37
+    },
+    {
+      "epoch": 0.2585034013605442,
+      "grad_norm": 0.4646860659122467,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0172,
+      "step": 38
+    },
+    {
+      "epoch": 0.2653061224489796,
+      "grad_norm": 0.19410698115825653,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.004,
+      "step": 39
+    },
+    {
+      "epoch": 0.272108843537415,
+      "grad_norm": 0.2193833589553833,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0106,
+      "step": 40
+    },
+    {
+      "epoch": 0.2789115646258503,
+      "grad_norm": 0.6219828724861145,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.014,
+      "step": 41
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.018709324300289154,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0003,
+      "step": 42
+    },
+    {
+      "epoch": 0.2925170068027211,
+      "grad_norm": 0.037566523998975754,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0003,
+      "step": 43
+    },
+    {
+      "epoch": 0.29931972789115646,
+      "grad_norm": 0.37556684017181396,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0064,
+      "step": 44
+    },
+    {
+      "epoch": 0.30612244897959184,
+      "grad_norm": 0.027847126126289368,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0002,
+      "step": 45
+    },
+    {
+      "epoch": 0.3129251700680272,
+      "grad_norm": 0.015570895746350288,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0003,
+      "step": 46
+    },
+    {
+      "epoch": 0.3197278911564626,
+      "grad_norm": 0.3432367146015167,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.005,
+      "step": 47
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 0.11973174661397934,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0015,
+      "step": 48
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.04032721742987633,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0005,
+      "step": 49
+    },
+    {
+      "epoch": 0.3401360544217687,
+      "grad_norm": 0.1603790819644928,
+      "learning_rate": 0.0,
+      "loss": 0.0019,
+      "step": 50
+    },
+    {
+      "epoch": 0.3401360544217687,
+      "eval_loss": 0.006335424259305,
+      "eval_runtime": 18.3293,
+      "eval_samples_per_second": 54.012,
+      "eval_steps_per_second": 6.765,
+      "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": 1.1167160802790605e+17,
+  "total_flos": 2.234825437211525e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null