Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18be3ecf87d1c2d8ecb3944cfdcbe8c7c15e826d11ed2a20ba15dc741d952a98
+oid sha256:b236727556bdc10bb1b6cee6ca4eef52e2ef1b47d0fe692d13c42f5f89912887
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05750968e6f0e58e142088d69f4c5799ffae931df1970ff35c3e71e40f3d3826
+oid sha256:92eb7f3787d6e17b17cb44a5691f39667be234d3cb826c70a773979dd8b7277f
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:415a45a4d93f2b8ccf737cc657c0811ce78427a39e240e7ecceed46424a0a3f4
+oid sha256:6ff77720c7000fcedb57eb1ec371480b0ebb212bfab716f82991331a0c7724f9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a9663b15212de6a41f200ff4dff86fd3582dae2d71780683f62049da0f78687
+oid sha256:10540bf414d1124df2ec122475878457214dd0155672d6f7ac9e01d3ecd20ca2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:852499de0771bfaff715cffc05cc5e01a7fa7e082917c7454d54593b088463e2
+oid sha256:eb611bbe1b2e9540bf348ec7f2938e53fa9c2524fbc7253dcbaa38520ffa7a2e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b72faf3302f1f08a7194de2f8d4b9d5c6744d3c1bee21a2e94e6eaaa5927e50d
+oid sha256:50d841d04a7be547f1e4c333ec4a1998f3f6422457c7d4326655acad6b6ee60e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3177ea4b394d20689f047a52c65a4c736ff1c10b2534d22548525087dc2bae5a
+oid sha256:69229c49401e88b3b3378c31d82dab5bb5c4af56b04c5c6fd06f1abbc7474757
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.930004119873047,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.7420718816067653,
+  "epoch": 3.1966173361522197,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,146 @@
       "eval_samples_per_second": 309.787,
       "eval_steps_per_second": 80.545,
       "step": 25
+    },
+    {
+      "epoch": 1.809725158562368,
+      "grad_norm": 0.10472561419010162,
+      "learning_rate": 4.682634170592537e-05,
+      "loss": 11.9661,
+      "step": 26
+    },
+    {
+      "epoch": 1.8773784355179703,
+      "grad_norm": 0.10933728516101837,
+      "learning_rate": 4.3617997792374365e-05,
+      "loss": 11.9384,
+      "step": 27
+    },
+    {
+      "epoch": 1.945031712473573,
+      "grad_norm": 0.10500363260507584,
+      "learning_rate": 4.0470381785284936e-05,
+      "loss": 11.9867,
+      "step": 28
+    },
+    {
+      "epoch": 2.063424947145877,
+      "grad_norm": 0.202621728181839,
+      "learning_rate": 3.7400287577942993e-05,
+      "loss": 23.6529,
+      "step": 29
+    },
+    {
+      "epoch": 2.13107822410148,
+      "grad_norm": 0.1180591881275177,
+      "learning_rate": 3.4424095451291274e-05,
+      "loss": 11.6859,
+      "step": 30
+    },
+    {
+      "epoch": 2.1987315010570825,
+      "grad_norm": 0.1156446561217308,
+      "learning_rate": 3.155768467804314e-05,
+      "loss": 11.953,
+      "step": 31
+    },
+    {
+      "epoch": 2.266384778012685,
+      "grad_norm": 0.10630480200052261,
+      "learning_rate": 2.8816348799892133e-05,
+      "loss": 11.8165,
+      "step": 32
+    },
+    {
+      "epoch": 2.3340380549682873,
+      "grad_norm": 0.11527036130428314,
+      "learning_rate": 2.621471402984991e-05,
+      "loss": 12.0291,
+      "step": 33
+    },
+    {
+      "epoch": 2.40169133192389,
+      "grad_norm": 0.11367418617010117,
+      "learning_rate": 2.3766661215071475e-05,
+      "loss": 11.9994,
+      "step": 34
+    },
+    {
+      "epoch": 2.4693446088794926,
+      "grad_norm": 0.11251702904701233,
+      "learning_rate": 2.148525177652982e-05,
+      "loss": 12.0468,
+      "step": 35
+    },
+    {
+      "epoch": 2.536997885835095,
+      "grad_norm": 0.11068017780780792,
+      "learning_rate": 1.938265802068357e-05,
+      "loss": 12.0091,
+      "step": 36
+    },
+    {
+      "epoch": 2.604651162790698,
+      "grad_norm": 0.11702769994735718,
+      "learning_rate": 1.74700981949555e-05,
+      "loss": 11.6006,
+      "step": 37
+    },
+    {
+      "epoch": 2.6723044397463003,
+      "grad_norm": 0.12750905752182007,
+      "learning_rate": 1.5757776633528655e-05,
+      "loss": 12.0497,
+      "step": 38
+    },
+    {
+      "epoch": 2.7399577167019027,
+      "grad_norm": 0.11485005170106888,
+      "learning_rate": 1.4254829312808404e-05,
+      "loss": 11.7737,
+      "step": 39
+    },
+    {
+      "epoch": 2.807610993657505,
+      "grad_norm": 0.12216285616159439,
+      "learning_rate": 1.2969275107035345e-05,
+      "loss": 12.0644,
+      "step": 40
+    },
+    {
+      "epoch": 2.875264270613108,
+      "grad_norm": 0.11762136220932007,
+      "learning_rate": 1.1907973004121738e-05,
+      "loss": 11.9411,
+      "step": 41
+    },
+    {
+      "epoch": 2.9429175475687104,
+      "grad_norm": 0.11637993156909943,
+      "learning_rate": 1.1076585509983283e-05,
+      "loss": 12.1162,
+      "step": 42
+    },
+    {
+      "epoch": 3.061310782241015,
+      "grad_norm": 0.2240166813135147,
+      "learning_rate": 1.0479548436620041e-05,
+      "loss": 23.5234,
+      "step": 43
+    },
+    {
+      "epoch": 3.1289640591966172,
+      "grad_norm": 0.1293584406375885,
+      "learning_rate": 1.0120047235140178e-05,
+      "loss": 11.7586,
+      "step": 44
+    },
+    {
+      "epoch": 3.1966173361522197,
+      "grad_norm": 0.13719302415847778,
+      "learning_rate": 1e-05,
+      "loss": 11.948,
+      "step": 45
     }
   ],
   "logging_steps": 1,
@@ -221,12 +361,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 521247129600.0,
+  "total_flos": 938244833280.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null