Upload folder using huggingface_hub

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80bcd64f8b28ea0522b23c90d589da4c846b431b7b881449da4660951df57823
+oid sha256:563ad1a53ff9968c23e661fbde0971b00547c40f4d286b6a81f100ad3a953090
 size 4991037968

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d00c654b8158f6603c7785b2e8d5f47d9cb6a25204280ed8587a48e85f66172
+oid sha256:cae00f32d5364a2e287e59819cabad01b83cc639d9fa338d8f4a929c62f6b094
 size 1610725592

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:076eba10f086da4576d3906878882df2c7186b2daa7ce0f6a7f0437b019a6acc
+oid sha256:8c768a039ece165c81adc7ffc56067dfc1c0ba40916bd4dd23a66b7db5284ff5
 size 13203690391

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20ea3a198ff666cb4ace1c684b598fe43fc7c3c276b83efc553a1b787e12a304
+oid sha256:9445552595536daf5bd8731be4eabb308bd26e76a3f4f0c20c4aa55fcf9ea202
 size 14645

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:355a4437a5f06b625275e18af63d950b8d65ee72e9119d148de55df74a553f3b
+oid sha256:5db160d0d863329e76a33fba4aeedbc2d728eee05bd8deed47128275fa20fabd
 size 1465

trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 2000,
-  "best_metric": 1.2739386558532715,
-  "best_model_checkpoint": "./orpheus-turkish-emotion-finetune/checkpoint-2000",
-  "epoch": 9.95202492211838,
+  "best_global_step": 2500,
+  "best_metric": 1.2259057760238647,
+  "best_model_checkpoint": "./orpheus-turkish-emotion-finetune/checkpoint-2500",
+  "epoch": 12.44361370716511,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -320,6 +320,84 @@
       "eval_samples_per_second": 11.528,
       "eval_steps_per_second": 1.481,
       "step": 2000
+    },
+    {
+      "epoch": 10.20436137071651,
+      "grad_norm": 0.87109375,
+      "learning_rate": 5.701024361409431e-06,
+      "loss": 1.2265,
+      "step": 2050
+    },
+    {
+      "epoch": 10.453582554517133,
+      "grad_norm": 0.95703125,
+      "learning_rate": 5.485494740420431e-06,
+      "loss": 1.198,
+      "step": 2100
+    },
+    {
+      "epoch": 10.702803738317757,
+      "grad_norm": 1.7421875,
+      "learning_rate": 5.26905012397343e-06,
+      "loss": 1.2148,
+      "step": 2150
+    },
+    {
+      "epoch": 10.95202492211838,
+      "grad_norm": 1.5234375,
+      "learning_rate": 5.052098437890215e-06,
+      "loss": 1.1983,
+      "step": 2200
+    },
+    {
+      "epoch": 11.199376947040498,
+      "grad_norm": 1.15625,
+      "learning_rate": 4.835048563649499e-06,
+      "loss": 1.2025,
+      "step": 2250
+    },
+    {
+      "epoch": 11.448598130841122,
+      "grad_norm": 1.0078125,
+      "learning_rate": 4.6183095677818825e-06,
+      "loss": 1.1926,
+      "step": 2300
+    },
+    {
+      "epoch": 11.697819314641745,
+      "grad_norm": 1.4453125,
+      "learning_rate": 4.402289930916053e-06,
+      "loss": 1.2022,
+      "step": 2350
+    },
+    {
+      "epoch": 11.947040498442368,
+      "grad_norm": 1.1328125,
+      "learning_rate": 4.187396777929205e-06,
+      "loss": 1.2099,
+      "step": 2400
+    },
+    {
+      "epoch": 12.194392523364487,
+      "grad_norm": 1.625,
+      "learning_rate": 3.974035110652596e-06,
+      "loss": 1.2093,
+      "step": 2450
+    },
+    {
+      "epoch": 12.44361370716511,
+      "grad_norm": 1.0625,
+      "learning_rate": 3.762607044578357e-06,
+      "loss": 1.1972,
+      "step": 2500
+    },
+    {
+      "epoch": 12.44361370716511,
+      "eval_loss": 1.2259057760238647,
+      "eval_runtime": 15.4359,
+      "eval_samples_per_second": 11.596,
+      "eval_steps_per_second": 1.49,
+      "step": 2500
     }
   ],
   "logging_steps": 50,
@@ -339,7 +417,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.532530945116078e+17,
+  "total_flos": 6.917655295552389e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e91f58a9a988419f219f097fff3f0e1762f623e4b2b1a8cf942cacee3271dc13
+oid sha256:21019e40285276caa4e865ddd780079cee489dc246be6fcfee79f590b8e47b52
 size 5777