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:cc11664fa1e9ea132e9c983bf075f5c35955d32f580e3a208377fed9d1b7746b
+oid sha256:c712e77ffd044882125f4fc79a5f776ceca1050e7c25c1a5b332e294de5a17bb
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca315e9808308f0419923de3f1778f2198fa0c7fcda73bd006ca2853b8d37e2a
+oid sha256:dc98df3ddf231fddbd1b2986ad315469c5c910bfb6f4b59a4eb8df0d63c9540c
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b62e173ffabd131504f5c6951d83cf4628b32eb4a0ffcba1b68a89bb22de4d1d
+oid sha256:e693597b5304e5d172eaa38e5ce6b71347987c5abb5e47885f50c489ebfa22e2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b3e8d74957dc1f46eb6f52f411ed2335d0153f04845643372bc9786b7745674
+oid sha256:4888dfe66cfa465db6d27b01bf7295c6d6f6d80d3a6238edb5df1b60639c46e8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bf64e12da398783c0fbfbd2a126798e22465128d786d61ff7b5caf1a5711fe7
+oid sha256:325b24f0e7c49cd99d8ce5ca5752c5c06f11b730869125fa883f5f3541c025e3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c80294c691ddcf5640d15ef7c3555adbd13f1617d7071bd45f9c498aa10e812f
+oid sha256:2f7aec81c6b983a6252aadb3c19e07f1e79f9eaf2d6535f0fbe1285b5f52376c
 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": 0.5110846757888794,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.36986301369863,
+  "best_metric": 0.47569820284843445,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.73972602739726,
   "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": 84.104,
       "eval_steps_per_second": 10.94,
       "step": 25
+    },
+    {
+      "epoch": 1.4246575342465753,
+      "grad_norm": 0.41463303565979004,
+      "learning_rate": 5e-05,
+      "loss": 0.4533,
+      "step": 26
+    },
+    {
+      "epoch": 1.4794520547945205,
+      "grad_norm": 0.38293758034706116,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4532,
+      "step": 27
+    },
+    {
+      "epoch": 1.5342465753424657,
+      "grad_norm": 0.3628367483615875,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4094,
+      "step": 28
+    },
+    {
+      "epoch": 1.589041095890411,
+      "grad_norm": 0.42759907245635986,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4622,
+      "step": 29
+    },
+    {
+      "epoch": 1.643835616438356,
+      "grad_norm": 0.36563095450401306,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4902,
+      "step": 30
+    },
+    {
+      "epoch": 1.6986301369863015,
+      "grad_norm": 0.4586554765701294,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4133,
+      "step": 31
+    },
+    {
+      "epoch": 1.7534246575342465,
+      "grad_norm": 0.32642537355422974,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3652,
+      "step": 32
+    },
+    {
+      "epoch": 1.808219178082192,
+      "grad_norm": 0.3642094135284424,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.3965,
+      "step": 33
+    },
+    {
+      "epoch": 1.8630136986301369,
+      "grad_norm": 0.36974775791168213,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.4403,
+      "step": 34
+    },
+    {
+      "epoch": 1.9178082191780823,
+      "grad_norm": 0.37709006667137146,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.4803,
+      "step": 35
+    },
+    {
+      "epoch": 1.9726027397260273,
+      "grad_norm": 0.4891318380832672,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.5114,
+      "step": 36
+    },
+    {
+      "epoch": 2.0273972602739727,
+      "grad_norm": 0.8724299073219299,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7102,
+      "step": 37
+    },
+    {
+      "epoch": 2.0821917808219177,
+      "grad_norm": 0.4001636207103729,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4218,
+      "step": 38
+    },
+    {
+      "epoch": 2.136986301369863,
+      "grad_norm": 0.3491167426109314,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4221,
+      "step": 39
+    },
+    {
+      "epoch": 2.191780821917808,
+      "grad_norm": 0.37197569012641907,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4686,
+      "step": 40
+    },
+    {
+      "epoch": 2.2465753424657535,
+      "grad_norm": 0.4310151934623718,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.3679,
+      "step": 41
+    },
+    {
+      "epoch": 2.3013698630136985,
+      "grad_norm": 0.396329790353775,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4621,
+      "step": 42
+    },
+    {
+      "epoch": 2.356164383561644,
+      "grad_norm": 0.35895678400993347,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4256,
+      "step": 43
+    },
+    {
+      "epoch": 2.410958904109589,
+      "grad_norm": 0.3557685911655426,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4232,
+      "step": 44
+    },
+    {
+      "epoch": 2.4657534246575343,
+      "grad_norm": 0.3738231658935547,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4006,
+      "step": 45
+    },
+    {
+      "epoch": 2.5205479452054793,
+      "grad_norm": 0.36462685465812683,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.395,
+      "step": 46
+    },
+    {
+      "epoch": 2.5753424657534247,
+      "grad_norm": 0.3373780846595764,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3644,
+      "step": 47
+    },
+    {
+      "epoch": 2.6301369863013697,
+      "grad_norm": 0.3781304955482483,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4711,
+      "step": 48
+    },
+    {
+      "epoch": 2.684931506849315,
+      "grad_norm": 0.3349582254886627,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4397,
+      "step": 49
+    },
+    {
+      "epoch": 2.73972602739726,
+      "grad_norm": 0.3511578440666199,
+      "learning_rate": 0.0,
+      "loss": 0.415,
+      "step": 50
+    },
+    {
+      "epoch": 2.73972602739726,
+      "eval_loss": 0.47569820284843445,
+      "eval_runtime": 1.4632,
+      "eval_samples_per_second": 84.064,
+      "eval_steps_per_second": 10.935,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null