Upload folder using huggingface_hub

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b20d2726037c98f2ce4ae7731f490bd4c05574f16b52fedf610ca2f299fbf8
+oid sha256:6a0fb435857da39fb3ac4a6250cba4532cdfeca14f1ceb94ac4c0859ff87c986
 size 4991037968

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:338de36ed0bd740de5ef2e61b137c64e2bd91321bb50de1a705521395bcfd53b
+oid sha256:6a3ebf4fcc9f98c653aafde81046f3489c2c8df911dcf954681a07bda8f5ad06
 size 1610725592

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2bac92613552e39b1793e6ae133fd0d27096b237be00533069cc8a7dbcb0bb3
+oid sha256:6ab574ed84635fe62ae45a58e5af8787fc4f025fd04fcdc4fcf32df00d050037
 size 13203690391

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f196323d7423b60f8e4ceb7dbf8715ee326c0d068e5ff164f13c63b279b9f1a0
+oid sha256:ea11996454b5587fcf33ae0ab5cf14b2031bf5f53f8c2ed5a48e87de31e29c84
 size 14645

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e92a7052d2a7c01a1b09ea2ba38f44479d548f97aef62e831f459b08d633005
+oid sha256:c085c9e30c4332cb31b5d70b86d33eec0e6be6c0ce92c99e20a2795c064a4205
 size 1465

trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 1000,
-  "best_metric": 1.2828963994979858,
-  "best_model_checkpoint": "./orpheus-turkish-emotion-finetune/checkpoint-1000",
-  "epoch": 4.976947040498443,
+  "best_global_step": 1500,
+  "best_metric": 1.2759937047958374,
+  "best_model_checkpoint": "./orpheus-turkish-emotion-finetune/checkpoint-1500",
+  "epoch": 7.463551401869159,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -164,6 +164,84 @@
       "eval_samples_per_second": 11.524,
       "eval_steps_per_second": 1.481,
       "step": 1000
+    },
+    {
+      "epoch": 5.224299065420561,
+      "grad_norm": 0.92578125,
+      "learning_rate": 9.231474733040436e-06,
+      "loss": 1.2206,
+      "step": 1050
+    },
+    {
+      "epoch": 5.473520249221184,
+      "grad_norm": 0.9609375,
+      "learning_rate": 9.111881511288579e-06,
+      "loss": 1.2081,
+      "step": 1100
+    },
+    {
+      "epoch": 5.722741433021807,
+      "grad_norm": 1.0703125,
+      "learning_rate": 8.984538766023024e-06,
+      "loss": 1.2224,
+      "step": 1150
+    },
+    {
+      "epoch": 5.97196261682243,
+      "grad_norm": 1.0625,
+      "learning_rate": 8.849686495793349e-06,
+      "loss": 1.2105,
+      "step": 1200
+    },
+    {
+      "epoch": 6.219314641744548,
+      "grad_norm": 1.1015625,
+      "learning_rate": 8.707578852095928e-06,
+      "loss": 1.2096,
+      "step": 1250
+    },
+    {
+      "epoch": 6.468535825545171,
+      "grad_norm": 1.3203125,
+      "learning_rate": 8.558483660383245e-06,
+      "loss": 1.2097,
+      "step": 1300
+    },
+    {
+      "epoch": 6.717757009345794,
+      "grad_norm": 1.1875,
+      "learning_rate": 8.402681915302344e-06,
+      "loss": 1.2227,
+      "step": 1350
+    },
+    {
+      "epoch": 6.966978193146417,
+      "grad_norm": 1.2265625,
+      "learning_rate": 8.240467251113762e-06,
+      "loss": 1.2102,
+      "step": 1400
+    },
+    {
+      "epoch": 7.214330218068536,
+      "grad_norm": 1.1015625,
+      "learning_rate": 8.072145388289002e-06,
+      "loss": 1.185,
+      "step": 1450
+    },
+    {
+      "epoch": 7.463551401869159,
+      "grad_norm": 1.1953125,
+      "learning_rate": 7.898033557329536e-06,
+      "loss": 1.2051,
+      "step": 1500
+    },
+    {
+      "epoch": 7.463551401869159,
+      "eval_loss": 1.2759937047958374,
+      "eval_runtime": 15.5082,
+      "eval_samples_per_second": 11.542,
+      "eval_steps_per_second": 1.483,
+      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -183,7 +261,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7667850240773325e+17,
+  "total_flos": 4.149138433077412e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null