End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0532
+- Loss: 0.0397
 - F1 Macro: 0.0
 - Exact Match: 1.0
 
@@ -49,11 +49,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1 Macro | Exact Match |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|
-| 0.263         | 1.0   | 25   | 0.1400          | 0.0      | 1.0         |
-| 0.1315        | 2.0   | 50   | 0.0867          | 0.0      | 1.0         |
-| 0.0903        | 3.0   | 75   | 0.0652          | 0.0      | 1.0         |
-| 0.0604        | 4.0   | 100  | 0.0560          | 0.0      | 1.0         |
-| 0.0556        | 5.0   | 125  | 0.0532          | 0.0      | 1.0         |
+| 0.3138        | 1.0   | 25   | 0.0876          | 0.0      | 1.0         |
+| 0.0895        | 2.0   | 50   | 0.0536          | 0.0      | 1.0         |
+| 0.0625        | 3.0   | 75   | 0.0448          | 0.0      | 1.0         |
+| 0.0486        | 4.0   | 100  | 0.0408          | 0.0      | 1.0         |
+| 0.0462        | 5.0   | 125  | 0.0397          | 0.0      | 1.0         |
 
 
 ### Framework versions

config.json

@@ -1,82 +1,59 @@
 {
-  "architectures": [
-    "MultiLabelClassificationModel"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "id2label": {
-    "0": "1025",
-    "1": "1071",
-    "2": "131",
-    "3": "138",
-    "4": "284",
-    "5": "285",
-    "6": "435",
-    "7": "436",
-    "8": "595",
-    "9": "657",
-    "10": "664",
-    "11": "682",
-    "12": "684",
-    "13": "691",
-    "14": "693",
-    "15": "697",
-    "16": "703",
-    "17": "706",
-    "18": "707",
-    "19": "710",
-    "20": "74",
-    "21": "754",
-    "22": "829",
-    "23": "862",
-    "24": "913",
-    "25": "94"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "1025": 0,
-    "1071": 1,
-    "131": 2,
-    "138": 3,
-    "284": 4,
-    "285": 5,
-    "435": 6,
-    "436": 7,
-    "595": 8,
-    "657": 9,
-    "664": 10,
-    "682": 11,
-    "684": 12,
-    "691": 13,
-    "693": 14,
-    "697": 15,
-    "703": 16,
-    "706": 17,
-    "707": 18,
-    "710": 19,
-    "74": 20,
-    "754": 21,
-    "829": 22,
-    "862": 23,
-    "913": 24,
-    "94": 25
-  },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
-  "torch_dtype": "float32",
-  "transformers_version": "4.55.0",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 50265
-}
+    "num_labels": 26,
+    "id2label": {
+        "0": "1025",
+        "1": "1071",
+        "2": "131",
+        "3": "138",
+        "4": "284",
+        "5": "285",
+        "6": "435",
+        "7": "436",
+        "8": "595",
+        "9": "657",
+        "10": "664",
+        "11": "682",
+        "12": "684",
+        "13": "691",
+        "14": "693",
+        "15": "697",
+        "16": "703",
+        "17": "706",
+        "18": "707",
+        "19": "710",
+        "20": "74",
+        "21": "754",
+        "22": "829",
+        "23": "862",
+        "24": "913",
+        "25": "94"
+    },
+    "label2id": {
+        "1025": 0,
+        "1071": 1,
+        "131": 2,
+        "138": 3,
+        "284": 4,
+        "285": 5,
+        "435": 6,
+        "436": 7,
+        "595": 8,
+        "657": 9,
+        "664": 10,
+        "682": 11,
+        "684": 12,
+        "691": 13,
+        "693": 14,
+        "697": 15,
+        "703": 16,
+        "706": 17,
+        "707": 18,
+        "710": 19,
+        "74": 20,
+        "754": 21,
+        "829": 22,
+        "862": 23,
+        "913": 24,
+        "94": 25
+    }
+}

emissions.csv

@@ -1,2 +1,2 @@
 timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
-2025-08-27T14:50:19,codecarbon,b680ab9c-d4ee-437c-8326-9f2fe212f3d5,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,48.50631881784648,0.000662966361586643,1.3667628831539448e-05,42.5,170.99735240530177,94.34468507766725,0.0005723921319536102,0.004455213286391313,0.0012705844640130096,0.0062981898823579316,Luxembourg,LUX,luxembourg,,,Linux-6.8.0-71-generic-x86_64-with-glibc2.39,3.12.3,2.8.4,64,AMD EPYC 9124 16-Core Processor,2,2 x NVIDIA L40S,6.1294,49.6113,251.5858268737793,machine,N,1.0
+2025-08-27T15:56:42,codecarbon,3997a6b2-dbc8-4248-b049-8e0a8e2524a2,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,42.24432637006976,0.0005517388648629392,1.3060661922493051e-05,42.5,266.00938047930725,94.34468507766725,0.0004984712969778533,0.00363654790924528,0.0011065078722654056,0.005241527078488539,Luxembourg,LUX,luxembourg,,,Linux-6.8.0-71-generic-x86_64-with-glibc2.39,3.12.3,2.8.4,64,AMD EPYC 9124 16-Core Processor,2,2 x NVIDIA L40S,6.1294,49.6113,251.5858268737793,machine,N,1.0

metrics.json

@@ -1,9 +1,9 @@
 {
-    "eval_loss": 0.05322767049074173,
+    "eval_loss": 0.039671141654253006,
     "eval_f1_macro": 0.0,
     "eval_exact_match": 1.0,
-    "eval_runtime": 0.3388,
-    "eval_samples_per_second": 262.655,
-    "eval_steps_per_second": 8.854,
+    "eval_runtime": 0.263,
+    "eval_samples_per_second": 338.428,
+    "eval_steps_per_second": 11.408,
     "epoch": 5.0
 }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23f91079994b61055a2f22748cee2ca6f8abcfe57e51cd2a4b0f04c5896aecc9
+size 498747403