Upload folder using huggingface_hub

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1780b264366447965d82a1ff26d8bbc1d6b9db6fa345791f12a94b630ed3320b
+oid sha256:50af6cfaef0b66eed5b89c78ecefc7b51d1d495a8ce00bfeeb711d0f5629fcb8
 size 4991037968

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9516d1ac25e339e5d92064c18054b82148dec67e44b80999621ec4892c5a09f9
+oid sha256:f2f79bba49da11c703d67f72efb455ac1f3915bbc2a61e271826791d316b3028
 size 1610725592

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa866c7589021a83baaeab8023d7f3e747b22b1c43b3a6585cff333fac7aca55
+oid sha256:1ec5d2ff5fb3d54e506057d32c3990d680339983a5fdbdd468dace5050a5a0a1
 size 13203690391

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bd75f3b287b15c92e6927ee3d2a9e3e9a7c2ea768e141eb8d1ab87cfbf9392a
+oid sha256:63aab5945fa6a4f19ef11eca5b6add2fab56216a2af2a42b2f4db10b37425e8e
 size 14645

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2994ac6b75a3e5e5a6b01d6da8955b44535bb0896dc728ab36a422e8d44ebdf
+oid sha256:cde082d406db1a89d52718af57a19af0e3b09ad5a557b076925c22776d5baf59
 size 1465

trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 4500,
   "best_metric": 1.2012678384780884,
   "best_model_checkpoint": "./orpheus-turkish-emotion-finetune/checkpoint-4500",
-  "epoch": 22.393769470404983,
+  "epoch": 24.882242990654206,
   "eval_steps": 500,
-  "global_step": 4500,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -710,6 +710,84 @@
       "eval_samples_per_second": 11.462,
       "eval_steps_per_second": 1.473,
       "step": 4500
+    },
+    {
+      "epoch": 22.642990654205608,
+      "grad_norm": 1.0625,
+      "learning_rate": 2.7091379149682683e-07,
+      "loss": 1.2239,
+      "step": 4550
+    },
+    {
+      "epoch": 22.89221183800623,
+      "grad_norm": 1.3515625,
+      "learning_rate": 2.1738296461569164e-07,
+      "loss": 1.2121,
+      "step": 4600
+    },
+    {
+      "epoch": 23.139563862928348,
+      "grad_norm": 1.2421875,
+      "learning_rate": 1.6962246671706872e-07,
+      "loss": 1.1973,
+      "step": 4650
+    },
+    {
+      "epoch": 23.388785046728973,
+      "grad_norm": 1.2578125,
+      "learning_rate": 1.2768992185557104e-07,
+      "loss": 1.2183,
+      "step": 4700
+    },
+    {
+      "epoch": 23.638006230529594,
+      "grad_norm": 1.3125,
+      "learning_rate": 9.163592253675247e-08,
+      "loss": 1.2195,
+      "step": 4750
+    },
+    {
+      "epoch": 23.88722741433022,
+      "grad_norm": 1.2109375,
+      "learning_rate": 6.15039686761748e-08,
+      "loss": 1.21,
+      "step": 4800
+    },
+    {
+      "epoch": 24.134579439252338,
+      "grad_norm": 1.2265625,
+      "learning_rate": 3.733041511583768e-08,
+      "loss": 1.2056,
+      "step": 4850
+    },
+    {
+      "epoch": 24.38380062305296,
+      "grad_norm": 1.46875,
+      "learning_rate": 1.914442776128622e-08,
+      "loss": 1.1913,
+      "step": 4900
+    },
+    {
+      "epoch": 24.633021806853584,
+      "grad_norm": 1.1796875,
+      "learning_rate": 6.9679483923318356e-09,
+      "loss": 1.2346,
+      "step": 4950
+    },
+    {
+      "epoch": 24.882242990654206,
+      "grad_norm": 1.171875,
+      "learning_rate": 8.156681898252583e-10,
+      "loss": 1.2149,
+      "step": 5000
+    },
+    {
+      "epoch": 24.882242990654206,
+      "eval_loss": 1.201310396194458,
+      "eval_runtime": 15.6169,
+      "eval_samples_per_second": 11.462,
+      "eval_steps_per_second": 1.473,
+      "step": 5000
     }
   ],
   "logging_steps": 50,
@@ -729,7 +807,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2451918079066112e+18,
+  "total_flos": 1.3835310591104778e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null