Upload folder using huggingface_hub

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33a77d12adc3c90a6d03d30b2ebb684027e4f21c9ca19ce87864192c1cbdd7b8
+oid sha256:12b20d2726037c98f2ce4ae7731f490bd4c05574f16b52fedf610ca2f299fbf8
 size 4991037968

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16b197f53c7eb5f953acb0917626be62d881b989a1678589016fddbdd2e620b8
+oid sha256:338de36ed0bd740de5ef2e61b137c64e2bd91321bb50de1a705521395bcfd53b
 size 1610725592

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:709540f11f094ab7fcb18f525b097ef780a66646213b0f225b0cec2172f4c781
+oid sha256:e2bac92613552e39b1793e6ae133fd0d27096b237be00533069cc8a7dbcb0bb3
 size 13203690391

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8e2011629d8bed3ef560fa11175cac55684c4e12a72634bb24abf767b6c7399
+oid sha256:f196323d7423b60f8e4ceb7dbf8715ee326c0d068e5ff164f13c63b279b9f1a0
 size 14645

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3159b8255e3ba63ecfbf9ad9882d37c8b55d7643e07b70fee54fef23e5ee0ce
+oid sha256:3e92a7052d2a7c01a1b09ea2ba38f44479d548f97aef62e831f459b08d633005
 size 1465

trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 500,
-  "best_metric": 1.3274219036102295,
-  "best_model_checkpoint": "./orpheus-turkish-emotion-finetune/checkpoint-500",
-  "epoch": 2.4884735202492214,
+  "best_global_step": 1000,
+  "best_metric": 1.2828963994979858,
+  "best_model_checkpoint": "./orpheus-turkish-emotion-finetune/checkpoint-1000",
+  "epoch": 4.976947040498443,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -86,6 +86,84 @@
       "eval_samples_per_second": 11.532,
       "eval_steps_per_second": 1.482,
       "step": 500
+    },
+    {
+      "epoch": 2.7376947040498445,
+      "grad_norm": 0.87109375,
+      "learning_rate": 9.95932312693483e-06,
+      "loss": 1.2695,
+      "step": 550
+    },
+    {
+      "epoch": 2.986915887850467,
+      "grad_norm": 1.3984375,
+      "learning_rate": 9.927024711991988e-06,
+      "loss": 1.2801,
+      "step": 600
+    },
+    {
+      "epoch": 3.2342679127725855,
+      "grad_norm": 0.91015625,
+      "learning_rate": 9.885440500813695e-06,
+      "loss": 1.2495,
+      "step": 650
+    },
+    {
+      "epoch": 3.4834890965732086,
+      "grad_norm": 0.9375,
+      "learning_rate": 9.834648865751254e-06,
+      "loss": 1.2456,
+      "step": 700
+    },
+    {
+      "epoch": 3.7327102803738317,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.774745532075235e-06,
+      "loss": 1.2472,
+      "step": 750
+    },
+    {
+      "epoch": 3.9819314641744548,
+      "grad_norm": 0.89453125,
+      "learning_rate": 9.705843397565304e-06,
+      "loss": 1.2243,
+      "step": 800
+    },
+    {
+      "epoch": 4.229283489096574,
+      "grad_norm": 1.1484375,
+      "learning_rate": 9.628072319735607e-06,
+      "loss": 1.2273,
+      "step": 850
+    },
+    {
+      "epoch": 4.478504672897197,
+      "grad_norm": 1.0,
+      "learning_rate": 9.541578871096728e-06,
+      "loss": 1.2192,
+      "step": 900
+    },
+    {
+      "epoch": 4.72772585669782,
+      "grad_norm": 0.85546875,
+      "learning_rate": 9.446526062915449e-06,
+      "loss": 1.2295,
+      "step": 950
+    },
+    {
+      "epoch": 4.976947040498443,
+      "grad_norm": 1.2265625,
+      "learning_rate": 9.343093037992946e-06,
+      "loss": 1.2226,
+      "step": 1000
+    },
+    {
+      "epoch": 4.976947040498443,
+      "eval_loss": 1.2828963994979858,
+      "eval_runtime": 15.5322,
+      "eval_samples_per_second": 11.524,
+      "eval_steps_per_second": 1.481,
+      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -105,7 +183,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3833925120386662e+17,
+  "total_flos": 2.7667850240773325e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null