Training in progress, step 10000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f17723ea2dc8d07eec950ce6661a040e4a2bf91a0a1310fde192975a612831b
+oid sha256:a650c90512a42dd4683e8a973d7b2a127d961133cf781e96a2f0bedbf19c86ff
 size 962707376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b2d310cc85410edafa6b19e0fb8e40f731b33476548775abce57515155f9f4f
+oid sha256:9968735e9e258ea0ca015e23b0b8b0c42c3599f8a7328f83e1fd380c91894e9b
 size 61870586

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf520f9e4f91c0f6fdff915bd23ec6d457ff663156e78e10369951a31dec58a7
+oid sha256:70a8bad0a644766abc3efe2e19d0f0855eb6b4e5b56ecabe95af68e9bc0f2d75
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6728d29a0b06760da0481c2ca2a495c6b194e450ebfb9817990e46d2e1aa2a23
+oid sha256:ab7cf4dee40cabd63b41ea11b2d5474174351dcc28ca3f8824100288377df3d5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07669cde176c75c081c4da15e4ae6a7b6eda38633d16631cc31f97d7433b5d62
+oid sha256:9bcb873a9c3fc793985c939b6c1983b22259cb938f5837ad9557e8686e8fb37e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38aa191ab0e5668c9cb71e6a9b193a01b9b7f5021ef11b8b75e2b040b7b6c3a0
+oid sha256:d7d663db8d609f40e7f1b8517b937f6ab700284f01dc91d7fd7acdf1e743e492
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3fdc1907a2f4143bc0e898e77db3a36296150c8c0c843a6c9c3db4c1bcad112
+oid sha256:ff2eeebb1ff1345658711a7b947405ee1bda725b6384a44aad58e2e369e255d2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5044249296188354,
-  "best_model_checkpoint": "/workspace/plateer_classifier_v0.1_result/checkpoint-5000",
-  "epoch": 0.029280390483287486,
+  "best_metric": 0.457188218832016,
+  "best_model_checkpoint": "/workspace/plateer_classifier_v0.1_result/checkpoint-10000",
+  "epoch": 0.05856078096657497,
   "eval_steps": 5000,
-  "global_step": 5000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -156,6 +156,155 @@
       "eval_samples_per_second": 210.432,
       "eval_steps_per_second": 6.576,
       "step": 5000
+    },
+    {
+      "epoch": 0.03074441000745186,
+      "grad_norm": 24.74563217163086,
+      "learning_rate": 0.00010484,
+      "loss": 0.5073,
+      "step": 5250
+    },
+    {
+      "epoch": 0.032208429531616234,
+      "grad_norm": 17.229019165039062,
+      "learning_rate": 0.00010984,
+      "loss": 0.4932,
+      "step": 5500
+    },
+    {
+      "epoch": 0.03367244905578061,
+      "grad_norm": 23.318979263305664,
+      "learning_rate": 0.00011484000000000002,
+      "loss": 0.504,
+      "step": 5750
+    },
+    {
+      "epoch": 0.035136468579944985,
+      "grad_norm": 22.271846771240234,
+      "learning_rate": 0.00011983999999999999,
+      "loss": 0.4817,
+      "step": 6000
+    },
+    {
+      "epoch": 0.036600488104109354,
+      "grad_norm": 24.304887771606445,
+      "learning_rate": 0.00012484,
+      "loss": 0.4966,
+      "step": 6250
+    },
+    {
+      "epoch": 0.03806450762827373,
+      "grad_norm": 23.76158905029297,
+      "learning_rate": 0.00012984000000000002,
+      "loss": 0.4899,
+      "step": 6500
+    },
+    {
+      "epoch": 0.039528527152438105,
+      "grad_norm": 20.765274047851562,
+      "learning_rate": 0.00013484,
+      "loss": 0.4773,
+      "step": 6750
+    },
+    {
+      "epoch": 0.04099254667660248,
+      "grad_norm": 12.793950080871582,
+      "learning_rate": 0.00013982000000000003,
+      "loss": 0.4781,
+      "step": 7000
+    },
+    {
+      "epoch": 0.042456566200766856,
+      "grad_norm": 14.128210067749023,
+      "learning_rate": 0.00014482,
+      "loss": 0.4687,
+      "step": 7250
+    },
+    {
+      "epoch": 0.043920585724931224,
+      "grad_norm": 22.348928451538086,
+      "learning_rate": 0.00014982,
+      "loss": 0.4722,
+      "step": 7500
+    },
+    {
+      "epoch": 0.0453846052490956,
+      "grad_norm": 17.29800796508789,
+      "learning_rate": 0.00015480000000000002,
+      "loss": 0.4692,
+      "step": 7750
+    },
+    {
+      "epoch": 0.046848624773259975,
+      "grad_norm": 11.0147066116333,
+      "learning_rate": 0.0001598,
+      "loss": 0.4689,
+      "step": 8000
+    },
+    {
+      "epoch": 0.04831264429742435,
+      "grad_norm": 11.713265419006348,
+      "learning_rate": 0.0001648,
+      "loss": 0.4788,
+      "step": 8250
+    },
+    {
+      "epoch": 0.049776663821588726,
+      "grad_norm": 12.367693901062012,
+      "learning_rate": 0.0001698,
+      "loss": 0.4697,
+      "step": 8500
+    },
+    {
+      "epoch": 0.0512406833457531,
+      "grad_norm": 8.11889934539795,
+      "learning_rate": 0.00017480000000000002,
+      "loss": 0.4696,
+      "step": 8750
+    },
+    {
+      "epoch": 0.05270470286991747,
+      "grad_norm": 12.321019172668457,
+      "learning_rate": 0.0001798,
+      "loss": 0.461,
+      "step": 9000
+    },
+    {
+      "epoch": 0.054168722394081846,
+      "grad_norm": 15.612183570861816,
+      "learning_rate": 0.00018480000000000002,
+      "loss": 0.4646,
+      "step": 9250
+    },
+    {
+      "epoch": 0.05563274191824622,
+      "grad_norm": 10.72978687286377,
+      "learning_rate": 0.0001898,
+      "loss": 0.4673,
+      "step": 9500
+    },
+    {
+      "epoch": 0.0570967614424106,
+      "grad_norm": 8.815441131591797,
+      "learning_rate": 0.0001948,
+      "loss": 0.4472,
+      "step": 9750
+    },
+    {
+      "epoch": 0.05856078096657497,
+      "grad_norm": 8.681705474853516,
+      "learning_rate": 0.0001998,
+      "loss": 0.4629,
+      "step": 10000
+    },
+    {
+      "epoch": 0.05856078096657497,
+      "eval_accuracy": 0.8688706572649133,
+      "eval_loss": 0.457188218832016,
+      "eval_runtime": 11537.8227,
+      "eval_samples_per_second": 210.492,
+      "eval_steps_per_second": 6.578,
+      "step": 10000
     }
   ],
   "logging_steps": 250,
@@ -175,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2957223124310426e+18,
+  "total_flos": 2.591444624862085e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null