Upload folder using huggingface_hub

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:472918c43ff26020e0403a9d61f6609a5f1b34293635ad117d90c5a71150fd82
+oid sha256:8945b643153235916bf7633b75f652080229cb16f684035410e93ef1e1cb0a99
 size 437975176

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19ac66615e26422c3800c360a0fbc80cdf8675d7c95e64d525550df445268d4c
+size 876075403

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b610f2cb3689e09e66dc65865af018594c349cf8159efd976d36d73dad10850
+size 14645

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a4f4a80b978dd2a9920d4ebc79158f6d1353f6a66461fece2188f23076c4fed
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed2b9f21a4594ec5f1a7c0c98d4ee49f8bb7789fbc9b3cce6505b7d8b83a0bd8
+size 1465

trainer_state.json

@@ -0,0 +1,190 @@
+{
+  "best_global_step": 2188,
+  "best_metric": 0.8126,
+  "best_model_checkpoint": "/ceph/home/student.aau.dk/uo02pm/exam_m4/final_assignment/results_final/checkpoint-2188",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2188,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04570383912248629,
+      "grad_norm": 1.4680031538009644,
+      "learning_rate": 9.04109589041096e-06,
+      "loss": 0.6659906005859375,
+      "step": 100
+    },
+    {
+      "epoch": 0.09140767824497258,
+      "grad_norm": 3.0468764305114746,
+      "learning_rate": 1.8173515981735163e-05,
+      "loss": 0.5402507400512695,
+      "step": 200
+    },
+    {
+      "epoch": 0.13711151736745886,
+      "grad_norm": 3.0381736755371094,
+      "learning_rate": 1.9187404773996955e-05,
+      "loss": 0.500119514465332,
+      "step": 300
+    },
+    {
+      "epoch": 0.18281535648994515,
+      "grad_norm": 3.2309110164642334,
+      "learning_rate": 1.8171660741493145e-05,
+      "loss": 0.4982530975341797,
+      "step": 400
+    },
+    {
+      "epoch": 0.22851919561243145,
+      "grad_norm": 3.3481152057647705,
+      "learning_rate": 1.7155916708989335e-05,
+      "loss": 0.4839456939697266,
+      "step": 500
+    },
+    {
+      "epoch": 0.2742230347349177,
+      "grad_norm": 1.9908303022384644,
+      "learning_rate": 1.6140172676485525e-05,
+      "loss": 0.48401123046875,
+      "step": 600
+    },
+    {
+      "epoch": 0.31992687385740404,
+      "grad_norm": 4.413586616516113,
+      "learning_rate": 1.5124428643981718e-05,
+      "loss": 0.4505374145507812,
+      "step": 700
+    },
+    {
+      "epoch": 0.3656307129798903,
+      "grad_norm": 3.1499385833740234,
+      "learning_rate": 1.410868461147791e-05,
+      "loss": 0.4597699737548828,
+      "step": 800
+    },
+    {
+      "epoch": 0.4113345521023766,
+      "grad_norm": 3.83247447013855,
+      "learning_rate": 1.30929405789741e-05,
+      "loss": 0.41371593475341795,
+      "step": 900
+    },
+    {
+      "epoch": 0.4570383912248629,
+      "grad_norm": 2.611191749572754,
+      "learning_rate": 1.2077196546470291e-05,
+      "loss": 0.45951534271240235,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5027422303473492,
+      "grad_norm": 4.901726245880127,
+      "learning_rate": 1.1061452513966481e-05,
+      "loss": 0.4458449935913086,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5484460694698354,
+      "grad_norm": 2.2019906044006348,
+      "learning_rate": 1.0045708481462673e-05,
+      "loss": 0.4343938446044922,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5941499085923218,
+      "grad_norm": 4.241252899169922,
+      "learning_rate": 9.029964448958863e-06,
+      "loss": 0.424683952331543,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6398537477148081,
+      "grad_norm": 2.6701462268829346,
+      "learning_rate": 8.014220416455055e-06,
+      "loss": 0.4311076736450195,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6855575868372943,
+      "grad_norm": 2.7700655460357666,
+      "learning_rate": 6.998476383951245e-06,
+      "loss": 0.4267000961303711,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7312614259597806,
+      "grad_norm": 4.248820781707764,
+      "learning_rate": 5.9827323514474355e-06,
+      "loss": 0.43855819702148435,
+      "step": 1600
+    },
+    {
+      "epoch": 0.7769652650822669,
+      "grad_norm": 2.6922144889831543,
+      "learning_rate": 4.966988318943627e-06,
+      "loss": 0.42610862731933596,
+      "step": 1700
+    },
+    {
+      "epoch": 0.8226691042047533,
+      "grad_norm": 2.1052846908569336,
+      "learning_rate": 3.951244286439818e-06,
+      "loss": 0.41606285095214846,
+      "step": 1800
+    },
+    {
+      "epoch": 0.8683729433272395,
+      "grad_norm": 4.449422359466553,
+      "learning_rate": 2.9355002539360083e-06,
+      "loss": 0.4456697082519531,
+      "step": 1900
+    },
+    {
+      "epoch": 0.9140767824497258,
+      "grad_norm": 3.9595413208007812,
+      "learning_rate": 1.9197562214321996e-06,
+      "loss": 0.4376623916625977,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9597806215722121,
+      "grad_norm": 4.138005256652832,
+      "learning_rate": 9.040121889283901e-07,
+      "loss": 0.41156463623046874,
+      "step": 2100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8126,
+      "eval_loss": 0.40674716234207153,
+      "eval_runtime": 26.549,
+      "eval_samples_per_second": 188.331,
+      "eval_steps_per_second": 5.914,
+      "step": 2188
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2188,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4604443468800000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8eae8d9fad20d62bd1bc23a993cae62e4e4729ca8d7fcf47de9a8de0a7be258
+size 5329