Upload folder using huggingface_hub

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:563ad1a53ff9968c23e661fbde0971b00547c40f4d286b6a81f100ad3a953090
+oid sha256:3245d78a13e7ddea92cfe2329a3cd9082ce81c727a2cc2606ce1f900c202e0a6
 size 4991037968

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cae00f32d5364a2e287e59819cabad01b83cc639d9fa338d8f4a929c62f6b094
+oid sha256:f0c547788cdb8c419c8cb9f5d95e756653d92acc015aa99d43bf59eb40ae716f
 size 1610725592

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c768a039ece165c81adc7ffc56067dfc1c0ba40916bd4dd23a66b7db5284ff5
+oid sha256:60cec7fca8de21c83b496fb8b64d9ea7326c87883c23fc24097cace6df9ef4fe
 size 13203690391

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9445552595536daf5bd8731be4eabb308bd26e76a3f4f0c20c4aa55fcf9ea202
+oid sha256:12d8b6c71ec5842a7f720763e6312f0db9384dc999ad47a74f64d26d1c1cb7ce
 size 14645

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5db160d0d863329e76a33fba4aeedbc2d728eee05bd8deed47128275fa20fabd
+oid sha256:ec90f171ad210047003950ef1fd5a4adde21307241897cd52f196d25f3f85ab7
 size 1465

trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 2500,
   "best_metric": 1.2259057760238647,
   "best_model_checkpoint": "./orpheus-turkish-emotion-finetune/checkpoint-2500",
-  "epoch": 12.44361370716511,
+  "epoch": 14.93208722741433,
   "eval_steps": 500,
-  "global_step": 2500,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -398,6 +398,84 @@
       "eval_samples_per_second": 11.596,
       "eval_steps_per_second": 1.49,
       "step": 2500
+    },
+    {
+      "epoch": 12.692834890965733,
+      "grad_norm": 1.40625,
+      "learning_rate": 3.55351105100606e-06,
+      "loss": 1.1879,
+      "step": 2550
+    },
+    {
+      "epoch": 12.942056074766356,
+      "grad_norm": 0.89453125,
+      "learning_rate": 3.3471412060573944e-06,
+      "loss": 1.215,
+      "step": 2600
+    },
+    {
+      "epoch": 13.189408099688473,
+      "grad_norm": 1.15625,
+      "learning_rate": 3.1438864479742693e-06,
+      "loss": 1.2105,
+      "step": 2650
+    },
+    {
+      "epoch": 13.438629283489096,
+      "grad_norm": 1.2109375,
+      "learning_rate": 2.9441298441001165e-06,
+      "loss": 1.1956,
+      "step": 2700
+    },
+    {
+      "epoch": 13.687850467289719,
+      "grad_norm": 1.15625,
+      "learning_rate": 2.7482478689258733e-06,
+      "loss": 1.2139,
+      "step": 2750
+    },
+    {
+      "epoch": 13.937071651090342,
+      "grad_norm": 1.640625,
+      "learning_rate": 2.556609694561273e-06,
+      "loss": 1.1846,
+      "step": 2800
+    },
+    {
+      "epoch": 14.184423676012461,
+      "grad_norm": 0.98828125,
+      "learning_rate": 2.3695764949687234e-06,
+      "loss": 1.1978,
+      "step": 2850
+    },
+    {
+      "epoch": 14.433644859813084,
+      "grad_norm": 1.2890625,
+      "learning_rate": 2.1875007652709768e-06,
+      "loss": 1.199,
+      "step": 2900
+    },
+    {
+      "epoch": 14.682866043613707,
+      "grad_norm": 0.9140625,
+      "learning_rate": 2.0107256574155564e-06,
+      "loss": 1.2097,
+      "step": 2950
+    },
+    {
+      "epoch": 14.93208722741433,
+      "grad_norm": 1.0625,
+      "learning_rate": 1.8395843334479125e-06,
+      "loss": 1.2051,
+      "step": 3000
+    },
+    {
+      "epoch": 14.93208722741433,
+      "eval_loss": 1.2260087728500366,
+      "eval_runtime": 15.4261,
+      "eval_samples_per_second": 11.604,
+      "eval_steps_per_second": 1.491,
+      "step": 3000
     }
   ],
   "logging_steps": 50,
@@ -417,7 +495,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.917655295552389e+17,
+  "total_flos": 8.301047807591055e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null