Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b78619eda998519a199cc8e23c331f1080acf463b56b80eae6b96c1ecb73b3e
+oid sha256:a274017ddb8e7d303b923aa459a0149415ae77954f912b7b1848917a31b0b814
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2181a59153700861a5ce31641342be66e7821fb0ee6ddba2ea456b477ce89b9
+oid sha256:429a5d19d42f1ff558db39a5c1f446d3bbf43bfcba5ddf9101b3127aa737689d
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4adadb7508cda3750b14fd3de56449df4339bc5ee936843dbf64efac4dde705c
+oid sha256:2cc093135f1febf674ec04d7b375433036a258b6dd9c2b30adc950c37a64bfaf
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85898d2b80bcb758882e644d3f3bcbb41a9e1f47561079123d1ea697d6637391
+oid sha256:ae3c7e75cd1edc48b7817465ee80b8a9853238f5ffba89b56eb5db7de5ded312
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6459f985ebaf9621304e576ca303a98f751af016838e78dcc2fcd2bbe8d8b52e
+oid sha256:fb20925872f4c5aad08cb970bac659e7f101948cbc83d7d4ad616a07d55a076b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:450b5f4de24a59b1fe37ba63ca3909d1d723cc52cf06f4fa8377ff3f69082fab
+oid sha256:7cc904e167e4d81c7bf5707e9ae4166fb9844428b9b27c6f744bb4b2036067e0
 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": 11.929275512695312,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.20964360587002095,
+  "best_metric": 11.928146362304688,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4192872117400419,
   "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": 462.955,
       "eval_steps_per_second": 58.157,
       "step": 25
+    },
+    {
+      "epoch": 0.2180293501048218,
+      "grad_norm": 0.0470016710460186,
+      "learning_rate": 5e-05,
+      "loss": 11.9248,
+      "step": 26
+    },
+    {
+      "epoch": 0.22641509433962265,
+      "grad_norm": 0.047832075506448746,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.9269,
+      "step": 27
+    },
+    {
+      "epoch": 0.2348008385744235,
+      "grad_norm": 0.054423995316028595,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.9269,
+      "step": 28
+    },
+    {
+      "epoch": 0.2431865828092243,
+      "grad_norm": 0.059153150767087936,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.9256,
+      "step": 29
+    },
+    {
+      "epoch": 0.25157232704402516,
+      "grad_norm": 0.05590154230594635,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.927,
+      "step": 30
+    },
+    {
+      "epoch": 0.259958071278826,
+      "grad_norm": 0.058628544211387634,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.9266,
+      "step": 31
+    },
+    {
+      "epoch": 0.26834381551362685,
+      "grad_norm": 0.06399206817150116,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9272,
+      "step": 32
+    },
+    {
+      "epoch": 0.27672955974842767,
+      "grad_norm": 0.06347686797380447,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.9286,
+      "step": 33
+    },
+    {
+      "epoch": 0.2851153039832285,
+      "grad_norm": 0.06550882756710052,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.9276,
+      "step": 34
+    },
+    {
+      "epoch": 0.29350104821802936,
+      "grad_norm": 0.059900153428316116,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.9315,
+      "step": 35
+    },
+    {
+      "epoch": 0.3018867924528302,
+      "grad_norm": 0.07278956472873688,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.9284,
+      "step": 36
+    },
+    {
+      "epoch": 0.31027253668763105,
+      "grad_norm": 0.0694255456328392,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.9324,
+      "step": 37
+    },
+    {
+      "epoch": 0.31865828092243187,
+      "grad_norm": 0.053817711770534515,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9236,
+      "step": 38
+    },
+    {
+      "epoch": 0.3270440251572327,
+      "grad_norm": 0.066506028175354,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.9231,
+      "step": 39
+    },
+    {
+      "epoch": 0.33542976939203356,
+      "grad_norm": 0.06306684017181396,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.9245,
+      "step": 40
+    },
+    {
+      "epoch": 0.3438155136268344,
+      "grad_norm": 0.06684385240077972,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.9263,
+      "step": 41
+    },
+    {
+      "epoch": 0.3522012578616352,
+      "grad_norm": 0.06455033272504807,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.9278,
+      "step": 42
+    },
+    {
+      "epoch": 0.36058700209643607,
+      "grad_norm": 0.06546949595212936,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.9259,
+      "step": 43
+    },
+    {
+      "epoch": 0.3689727463312369,
+      "grad_norm": 0.07471216470003128,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9258,
+      "step": 44
+    },
+    {
+      "epoch": 0.37735849056603776,
+      "grad_norm": 0.0686088502407074,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.9275,
+      "step": 45
+    },
+    {
+      "epoch": 0.3857442348008386,
+      "grad_norm": 0.07394406944513321,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.929,
+      "step": 46
+    },
+    {
+      "epoch": 0.3941299790356394,
+      "grad_norm": 0.06964340806007385,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.9301,
+      "step": 47
+    },
+    {
+      "epoch": 0.4025157232704403,
+      "grad_norm": 0.06854347884654999,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 11.9288,
+      "step": 48
+    },
+    {
+      "epoch": 0.4109014675052411,
+      "grad_norm": 0.07059460133314133,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.929,
+      "step": 49
+    },
+    {
+      "epoch": 0.4192872117400419,
+      "grad_norm": 0.07417823374271393,
+      "learning_rate": 0.0,
+      "loss": 11.9308,
+      "step": 50
+    },
+    {
+      "epoch": 0.4192872117400419,
+      "eval_loss": 11.928146362304688,
+      "eval_runtime": 1.7255,
+      "eval_samples_per_second": 465.963,
+      "eval_steps_per_second": 58.535,
+      "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": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null