Training in progress, step 15000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a650c90512a42dd4683e8a973d7b2a127d961133cf781e96a2f0bedbf19c86ff
+oid sha256:fb2c6c1cadce7ce52b13a926bfbafa64e446b86e5b4b7ec3eba9dfd5cad410f6
 size 962707376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9968735e9e258ea0ca015e23b0b8b0c42c3599f8a7328f83e1fd380c91894e9b
+oid sha256:b855713affff09aec742fce2d37ecba061f0936159fdaf7e21c3bd0641619255
 size 61870586

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70a8bad0a644766abc3efe2e19d0f0855eb6b4e5b56ecabe95af68e9bc0f2d75
+oid sha256:e255daa5ad5f11069df3a999246b0ccdc09247bd43432e7fdcd3a70ab5d06348
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab7cf4dee40cabd63b41ea11b2d5474174351dcc28ca3f8824100288377df3d5
+oid sha256:9fba2973ecba0f00ec98a89ba1c3d4441c0d63876f4e6205a3677f60062c512c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bcb873a9c3fc793985c939b6c1983b22259cb938f5837ad9557e8686e8fb37e
+oid sha256:995a7178a2eebf115a7587c3e6c91ed487a1801369e20d9a59c790e542ab8b74
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7d663db8d609f40e7f1b8517b937f6ab700284f01dc91d7fd7acdf1e743e492
+oid sha256:8acf023b229f8625b4ebc78e4ac75d24c6c079231c7dd2b05ff59df4dcb92a3f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2eeebb1ff1345658711a7b947405ee1bda725b6384a44aad58e2e369e255d2
+oid sha256:ac3a306a2182134e3345739eaf8e920ee1bbaf2cd67b334a1c9dd75d75464588
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.457188218832016,
-  "best_model_checkpoint": "/workspace/plateer_classifier_v0.1_result/checkpoint-10000",
-  "epoch": 0.05856078096657497,
+  "best_metric": 0.4201970100402832,
+  "best_model_checkpoint": "/workspace/plateer_classifier_v0.1_result/checkpoint-15000",
+  "epoch": 0.08784117144986245,
   "eval_steps": 5000,
-  "global_step": 10000,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,155 @@
       "eval_samples_per_second": 210.492,
       "eval_steps_per_second": 6.578,
       "step": 10000
+    },
+    {
+      "epoch": 0.06002480049073934,
+      "grad_norm": 13.643828392028809,
+      "learning_rate": 0.0001997014219778306,
+      "loss": 0.456,
+      "step": 10250
+    },
+    {
+      "epoch": 0.06148882001490372,
+      "grad_norm": 13.211404800415039,
+      "learning_rate": 0.00019939040320473745,
+      "loss": 0.4666,
+      "step": 10500
+    },
+    {
+      "epoch": 0.06295283953906809,
+      "grad_norm": 11.1001615524292,
+      "learning_rate": 0.00019907938443164432,
+      "loss": 0.4495,
+      "step": 10750
+    },
+    {
+      "epoch": 0.06441685906323247,
+      "grad_norm": 8.222249984741211,
+      "learning_rate": 0.00019876836565855117,
+      "loss": 0.4483,
+      "step": 11000
+    },
+    {
+      "epoch": 0.06588087858739684,
+      "grad_norm": 13.589752197265625,
+      "learning_rate": 0.0001984585909605504,
+      "loss": 0.4438,
+      "step": 11250
+    },
+    {
+      "epoch": 0.06734489811156122,
+      "grad_norm": 9.988068580627441,
+      "learning_rate": 0.00019814757218745724,
+      "loss": 0.447,
+      "step": 11500
+    },
+    {
+      "epoch": 0.0688089176357256,
+      "grad_norm": 8.311960220336914,
+      "learning_rate": 0.0001978365534143641,
+      "loss": 0.4476,
+      "step": 11750
+    },
+    {
+      "epoch": 0.07027293715988997,
+      "grad_norm": 8.099685668945312,
+      "learning_rate": 0.00019752553464127094,
+      "loss": 0.4477,
+      "step": 12000
+    },
+    {
+      "epoch": 0.07173695668405435,
+      "grad_norm": 8.23130989074707,
+      "learning_rate": 0.00019721451586817782,
+      "loss": 0.4385,
+      "step": 12250
+    },
+    {
+      "epoch": 0.07320097620821871,
+      "grad_norm": 10.875362396240234,
+      "learning_rate": 0.00019690349709508467,
+      "loss": 0.4345,
+      "step": 12500
+    },
+    {
+      "epoch": 0.07466499573238308,
+      "grad_norm": 9.479572296142578,
+      "learning_rate": 0.00019659247832199152,
+      "loss": 0.4345,
+      "step": 12750
+    },
+    {
+      "epoch": 0.07612901525654746,
+      "grad_norm": 11.883151054382324,
+      "learning_rate": 0.0001962814595488984,
+      "loss": 0.4241,
+      "step": 13000
+    },
+    {
+      "epoch": 0.07759303478071183,
+      "grad_norm": 8.15208911895752,
+      "learning_rate": 0.00019597044077580524,
+      "loss": 0.4335,
+      "step": 13250
+    },
+    {
+      "epoch": 0.07905705430487621,
+      "grad_norm": 9.323240280151367,
+      "learning_rate": 0.0001956594220027121,
+      "loss": 0.4396,
+      "step": 13500
+    },
+    {
+      "epoch": 0.08052107382904058,
+      "grad_norm": 7.250824928283691,
+      "learning_rate": 0.00019534840322961897,
+      "loss": 0.4376,
+      "step": 13750
+    },
+    {
+      "epoch": 0.08198509335320496,
+      "grad_norm": 12.220071792602539,
+      "learning_rate": 0.0001950373844565258,
+      "loss": 0.4323,
+      "step": 14000
+    },
+    {
+      "epoch": 0.08344911287736934,
+      "grad_norm": 8.460916519165039,
+      "learning_rate": 0.00019472636568343266,
+      "loss": 0.4271,
+      "step": 14250
+    },
+    {
+      "epoch": 0.08491313240153371,
+      "grad_norm": 6.110500812530518,
+      "learning_rate": 0.0001944153469103395,
+      "loss": 0.4253,
+      "step": 14500
+    },
+    {
+      "epoch": 0.08637715192569809,
+      "grad_norm": 10.618386268615723,
+      "learning_rate": 0.00019410432813724636,
+      "loss": 0.427,
+      "step": 14750
+    },
+    {
+      "epoch": 0.08784117144986245,
+      "grad_norm": 9.827556610107422,
+      "learning_rate": 0.00019379330936415324,
+      "loss": 0.4254,
+      "step": 15000
+    },
+    {
+      "epoch": 0.08784117144986245,
+      "eval_accuracy": 0.877075711565186,
+      "eval_loss": 0.4201970100402832,
+      "eval_runtime": 11537.2443,
+      "eval_samples_per_second": 210.503,
+      "eval_steps_per_second": 6.578,
+      "step": 15000
     }
   ],
   "logging_steps": 250,
@@ -324,7 +473,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.591444624862085e+18,
+  "total_flos": 3.8871669372931277e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null