Upload folder using huggingface_hub

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48ee1c52efa36b1ddbf25bc4e4ed55d0578291857b8b679332606fbc3fb85339
+oid sha256:1780b264366447965d82a1ff26d8bbc1d6b9db6fa345791f12a94b630ed3320b
 size 4991037968

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b18e90d4d7e18d06da89e473f5961ddfb78ace4047b02033b3bcfdd13e431ab
+oid sha256:9516d1ac25e339e5d92064c18054b82148dec67e44b80999621ec4892c5a09f9
 size 1610725592

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e96ea5fa62813d9d6515dbcec2df5fe94ddafe752d31554765323bbd9612682
+oid sha256:aa866c7589021a83baaeab8023d7f3e747b22b1c43b3a6585cff333fac7aca55
 size 13203690391

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a804dd9b4962bc1e7c8e5b51c83ce95f04ab0a366340b47fc4849e7d4ecffd6d
+oid sha256:8bd75f3b287b15c92e6927ee3d2a9e3e9a7c2ea768e141eb8d1ab87cfbf9392a
 size 14645

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d4e59b60cb34c3dcef59040cbee17beefe5c2b969d4d9004a66e12c73ae4898
+oid sha256:c2994ac6b75a3e5e5a6b01d6da8955b44535bb0896dc728ab36a422e8d44ebdf
 size 1465

trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 3500,
-  "best_metric": 1.2014065980911255,
-  "best_model_checkpoint": "./orpheus-turkish-emotion-finetune/checkpoint-3500",
-  "epoch": 17.418691588785048,
+  "best_global_step": 4500,
+  "best_metric": 1.2012678384780884,
+  "best_model_checkpoint": "./orpheus-turkish-emotion-finetune/checkpoint-4500",
+  "epoch": 22.393769470404983,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -554,6 +554,162 @@
       "eval_samples_per_second": 11.474,
       "eval_steps_per_second": 1.474,
       "step": 3500
+    },
+    {
+      "epoch": 17.66791277258567,
+      "grad_norm": 1.046875,
+      "learning_rate": 2.4063399404745724e-06,
+      "loss": 1.2199,
+      "step": 3550
+    },
+    {
+      "epoch": 17.917133956386294,
+      "grad_norm": 1.625,
+      "learning_rate": 2.2594457607888917e-06,
+      "loss": 1.217,
+      "step": 3600
+    },
+    {
+      "epoch": 18.16448598130841,
+      "grad_norm": 1.3515625,
+      "learning_rate": 2.115858117971553e-06,
+      "loss": 1.2021,
+      "step": 3650
+    },
+    {
+      "epoch": 18.413707165109034,
+      "grad_norm": 1.484375,
+      "learning_rate": 1.9757502535618137e-06,
+      "loss": 1.2159,
+      "step": 3700
+    },
+    {
+      "epoch": 18.662928348909656,
+      "grad_norm": 1.015625,
+      "learning_rate": 1.839291210672407e-06,
+      "loss": 1.2117,
+      "step": 3750
+    },
+    {
+      "epoch": 18.91214953271028,
+      "grad_norm": 1.234375,
+      "learning_rate": 1.7066456300354462e-06,
+      "loss": 1.225,
+      "step": 3800
+    },
+    {
+      "epoch": 19.1595015576324,
+      "grad_norm": 1.390625,
+      "learning_rate": 1.577973551359877e-06,
+      "loss": 1.2239,
+      "step": 3850
+    },
+    {
+      "epoch": 19.40872274143302,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.453430220240178e-06,
+      "loss": 1.209,
+      "step": 3900
+    },
+    {
+      "epoch": 19.657943925233646,
+      "grad_norm": 1.203125,
+      "learning_rate": 1.333165900849255e-06,
+      "loss": 1.2148,
+      "step": 3950
+    },
+    {
+      "epoch": 19.907165109034267,
+      "grad_norm": 1.1484375,
+      "learning_rate": 1.2173256946415214e-06,
+      "loss": 1.2024,
+      "step": 4000
+    },
+    {
+      "epoch": 19.907165109034267,
+      "eval_loss": 1.2013256549835205,
+      "eval_runtime": 15.5958,
+      "eval_samples_per_second": 11.477,
+      "eval_steps_per_second": 1.475,
+      "step": 4000
+    },
+    {
+      "epoch": 20.154517133956386,
+      "grad_norm": 1.1328125,
+      "learning_rate": 1.106049365284918e-06,
+      "loss": 1.2362,
+      "step": 4050
+    },
+    {
+      "epoch": 20.40373831775701,
+      "grad_norm": 1.0078125,
+      "learning_rate": 9.994711700330779e-07,
+      "loss": 1.2212,
+      "step": 4100
+    },
+    {
+      "epoch": 20.652959501557632,
+      "grad_norm": 1.5078125,
+      "learning_rate": 8.97719697741104e-07,
+      "loss": 1.1908,
+      "step": 4150
+    },
+    {
+      "epoch": 20.902180685358257,
+      "grad_norm": 1.0390625,
+      "learning_rate": 8.009177137203794e-07,
+      "loss": 1.2261,
+      "step": 4200
+    },
+    {
+      "epoch": 21.149532710280372,
+      "grad_norm": 1.046875,
+      "learning_rate": 7.091820116196152e-07,
+      "loss": 1.1987,
+      "step": 4250
+    },
+    {
+      "epoch": 21.398753894080997,
+      "grad_norm": 1.46875,
+      "learning_rate": 6.2262327251084e-07,
+      "loss": 1.2089,
+      "step": 4300
+    },
+    {
+      "epoch": 21.64797507788162,
+      "grad_norm": 1.1796875,
+      "learning_rate": 5.413459313503272e-07,
+      "loss": 1.2162,
+      "step": 4350
+    },
+    {
+      "epoch": 21.897196261682243,
+      "grad_norm": 1.0859375,
+      "learning_rate": 4.654480509756082e-07,
+      "loss": 1.216,
+      "step": 4400
+    },
+    {
+      "epoch": 22.144548286604362,
+      "grad_norm": 1.484375,
+      "learning_rate": 3.9502120379057764e-07,
+      "loss": 1.2089,
+      "step": 4450
+    },
+    {
+      "epoch": 22.393769470404983,
+      "grad_norm": 1.171875,
+      "learning_rate": 3.301503612814444e-07,
+      "loss": 1.2161,
+      "step": 4500
+    },
+    {
+      "epoch": 22.393769470404983,
+      "eval_loss": 1.2012678384780884,
+      "eval_runtime": 15.6175,
+      "eval_samples_per_second": 11.462,
+      "eval_steps_per_second": 1.473,
+      "step": 4500
     }
   ],
   "logging_steps": 50,
@@ -573,7 +729,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.686172158027366e+17,
+  "total_flos": 1.2451918079066112e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null