upload files

almanach_camembert-base-ft-BUILD/checkpoint-1900/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "almanach/camembert-base",
+  "architectures": [
+    "CamembertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Entr\u00e9e",
+    "1": "Plat principal",
+    "2": "Dessert"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Dessert": 2,
+    "Entr\u00e9e": 0,
+    "Plat principal": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

almanach_camembert-base-ft-BUILD/checkpoint-1900/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:547f6bbbfbdec5c26b9fae54085d97b05f9add010448783a119bf4832337d8d0
+size 442521180

almanach_camembert-base-ft-BUILD/checkpoint-1900/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6244963faf15355ec722b8b1504dee14543fac52fe45b755bf00889f44726c0
+size 885164986

almanach_camembert-base-ft-BUILD/checkpoint-1900/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc70bdba96a91a98d0c8557b720997868da04e77653ee36b0a38eac210abd15e
+size 14244

almanach_camembert-base-ft-BUILD/checkpoint-1900/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcb72089611643c8b1e0da4e340a983f7f65be10078fcd26180415c3d8850bac
+size 1064

almanach_camembert-base-ft-BUILD/checkpoint-1900/trainer_state.json

@@ -0,0 +1,344 @@
+{
+  "best_metric": 0.878238119025816,
+  "best_model_checkpoint": "./models/camembert-base-naive-weights-/almanach_camembert-base-ft-BUILD/checkpoint-1900",
+  "epoch": 3.0448717948717947,
+  "eval_steps": 100,
+  "global_step": 1900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 1e-05,
+      "loss": 1.0573,
+      "step": 100
+    },
+    {
+      "epoch": 0.16,
+      "eval_f1": 0.7181262892296706,
+      "eval_loss": 0.8446577787399292,
+      "eval_p": 0.7713467932594631,
+      "eval_r": 0.7760416666666666,
+      "eval_runtime": 17.9743,
+      "eval_samples_per_second": 138.865,
+      "eval_steps_per_second": 8.679,
+      "step": 100
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2e-05,
+      "loss": 0.6581,
+      "step": 200
+    },
+    {
+      "epoch": 0.32,
+      "eval_f1": 0.8247575651992449,
+      "eval_loss": 0.498252809047699,
+      "eval_p": 0.8263731375750148,
+      "eval_r": 0.8305288461538461,
+      "eval_runtime": 17.6825,
+      "eval_samples_per_second": 141.156,
+      "eval_steps_per_second": 8.822,
+      "step": 200
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 3e-05,
+      "loss": 0.442,
+      "step": 300
+    },
+    {
+      "epoch": 0.48,
+      "eval_f1": 0.8461570920982805,
+      "eval_loss": 0.4266268014907837,
+      "eval_p": 0.845950710738389,
+      "eval_r": 0.8469551282051282,
+      "eval_runtime": 17.6628,
+      "eval_samples_per_second": 141.314,
+      "eval_steps_per_second": 8.832,
+      "step": 300
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 4e-05,
+      "loss": 0.3953,
+      "step": 400
+    },
+    {
+      "epoch": 0.64,
+      "eval_f1": 0.8373930528837824,
+      "eval_loss": 0.37538591027259827,
+      "eval_p": 0.8615924077023979,
+      "eval_r": 0.8325320512820513,
+      "eval_runtime": 17.7216,
+      "eval_samples_per_second": 140.845,
+      "eval_steps_per_second": 8.803,
+      "step": 400
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5e-05,
+      "loss": 0.3967,
+      "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "eval_f1": 0.8597057450718358,
+      "eval_loss": 0.37563666701316833,
+      "eval_p": 0.8679186256164589,
+      "eval_r": 0.8569711538461539,
+      "eval_runtime": 17.6917,
+      "eval_samples_per_second": 141.083,
+      "eval_steps_per_second": 8.818,
+      "step": 500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.9128919860627184e-05,
+      "loss": 0.3706,
+      "step": 600
+    },
+    {
+      "epoch": 0.96,
+      "eval_f1": 0.8670503688483537,
+      "eval_loss": 0.3591344654560089,
+      "eval_p": 0.8746353616433462,
+      "eval_r": 0.8645833333333334,
+      "eval_runtime": 17.4959,
+      "eval_samples_per_second": 142.662,
+      "eval_steps_per_second": 8.916,
+      "step": 600
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 4.825783972125435e-05,
+      "loss": 0.3505,
+      "step": 700
+    },
+    {
+      "epoch": 1.12,
+      "eval_f1": 0.8689141924456363,
+      "eval_loss": 0.347836434841156,
+      "eval_p": 0.871340517431561,
+      "eval_r": 0.8677884615384616,
+      "eval_runtime": 17.4911,
+      "eval_samples_per_second": 142.701,
+      "eval_steps_per_second": 8.919,
+      "step": 700
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 4.7386759581881534e-05,
+      "loss": 0.3418,
+      "step": 800
+    },
+    {
+      "epoch": 1.28,
+      "eval_f1": 0.8721428193709895,
+      "eval_loss": 0.3746407926082611,
+      "eval_p": 0.8722147363786865,
+      "eval_r": 0.8729967948717948,
+      "eval_runtime": 17.5366,
+      "eval_samples_per_second": 142.331,
+      "eval_steps_per_second": 8.896,
+      "step": 800
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 4.6515679442508716e-05,
+      "loss": 0.2908,
+      "step": 900
+    },
+    {
+      "epoch": 1.44,
+      "eval_f1": 0.8219523564010185,
+      "eval_loss": 0.4078001081943512,
+      "eval_p": 0.8720701363497414,
+      "eval_r": 0.8173076923076923,
+      "eval_runtime": 17.4499,
+      "eval_samples_per_second": 143.038,
+      "eval_steps_per_second": 8.94,
+      "step": 900
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.564459930313589e-05,
+      "loss": 0.3348,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6,
+      "eval_f1": 0.8648309479972653,
+      "eval_loss": 0.33482280373573303,
+      "eval_p": 0.8723716947662293,
+      "eval_r": 0.8625801282051282,
+      "eval_runtime": 17.4381,
+      "eval_samples_per_second": 143.135,
+      "eval_steps_per_second": 8.946,
+      "step": 1000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 4.4773519163763066e-05,
+      "loss": 0.2938,
+      "step": 1100
+    },
+    {
+      "epoch": 1.76,
+      "eval_f1": 0.8724294245473613,
+      "eval_loss": 0.38330796360969543,
+      "eval_p": 0.8741132178400003,
+      "eval_r": 0.8713942307692307,
+      "eval_runtime": 17.7534,
+      "eval_samples_per_second": 140.593,
+      "eval_steps_per_second": 8.787,
+      "step": 1100
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 4.390243902439025e-05,
+      "loss": 0.3086,
+      "step": 1200
+    },
+    {
+      "epoch": 1.92,
+      "eval_f1": 0.861950088740092,
+      "eval_loss": 0.44666504859924316,
+      "eval_p": 0.8676684596002215,
+      "eval_r": 0.8673878205128205,
+      "eval_runtime": 17.7841,
+      "eval_samples_per_second": 140.35,
+      "eval_steps_per_second": 8.772,
+      "step": 1200
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 4.303135888501742e-05,
+      "loss": 0.2838,
+      "step": 1300
+    },
+    {
+      "epoch": 2.08,
+      "eval_f1": 0.8556130076768697,
+      "eval_loss": 0.4276644289493561,
+      "eval_p": 0.861887082795119,
+      "eval_r": 0.8525641025641025,
+      "eval_runtime": 17.7988,
+      "eval_samples_per_second": 140.234,
+      "eval_steps_per_second": 8.765,
+      "step": 1300
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 4.21602787456446e-05,
+      "loss": 0.2677,
+      "step": 1400
+    },
+    {
+      "epoch": 2.24,
+      "eval_f1": 0.8733882441796467,
+      "eval_loss": 0.42381784319877625,
+      "eval_p": 0.8734263329753387,
+      "eval_r": 0.8733974358974359,
+      "eval_runtime": 17.8297,
+      "eval_samples_per_second": 139.991,
+      "eval_steps_per_second": 8.749,
+      "step": 1400
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 4.128919860627178e-05,
+      "loss": 0.2538,
+      "step": 1500
+    },
+    {
+      "epoch": 2.4,
+      "eval_f1": 0.867629952103172,
+      "eval_loss": 0.39002811908721924,
+      "eval_p": 0.8702966102264474,
+      "eval_r": 0.8661858974358975,
+      "eval_runtime": 17.806,
+      "eval_samples_per_second": 140.178,
+      "eval_steps_per_second": 8.761,
+      "step": 1500
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 4.0418118466898954e-05,
+      "loss": 0.2613,
+      "step": 1600
+    },
+    {
+      "epoch": 2.56,
+      "eval_f1": 0.8681936230677955,
+      "eval_loss": 0.37953686714172363,
+      "eval_p": 0.8713033389783905,
+      "eval_r": 0.8669871794871795,
+      "eval_runtime": 20.4414,
+      "eval_samples_per_second": 122.105,
+      "eval_steps_per_second": 7.632,
+      "step": 1600
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 3.9547038327526136e-05,
+      "loss": 0.2443,
+      "step": 1700
+    },
+    {
+      "epoch": 2.72,
+      "eval_f1": 0.8728885802238776,
+      "eval_loss": 0.3882499933242798,
+      "eval_p": 0.8743747661401656,
+      "eval_r": 0.8717948717948718,
+      "eval_runtime": 18.0771,
+      "eval_samples_per_second": 138.075,
+      "eval_steps_per_second": 8.63,
+      "step": 1700
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 3.867595818815331e-05,
+      "loss": 0.2738,
+      "step": 1800
+    },
+    {
+      "epoch": 2.88,
+      "eval_f1": 0.8781093591941508,
+      "eval_loss": 0.3620370924472809,
+      "eval_p": 0.879086535191297,
+      "eval_r": 0.8774038461538461,
+      "eval_runtime": 17.7891,
+      "eval_samples_per_second": 140.311,
+      "eval_steps_per_second": 8.769,
+      "step": 1800
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 3.780487804878049e-05,
+      "loss": 0.2293,
+      "step": 1900
+    },
+    {
+      "epoch": 3.04,
+      "eval_f1": 0.878238119025816,
+      "eval_loss": 0.42100784182548523,
+      "eval_p": 0.8787634832998302,
+      "eval_r": 0.8806089743589743,
+      "eval_runtime": 17.8166,
+      "eval_samples_per_second": 140.094,
+      "eval_steps_per_second": 8.756,
+      "step": 1900
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 6240,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 7993122517158912.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

almanach_camembert-base-ft-BUILD/checkpoint-1900/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75331ca2e87d59e9845aaf1e64eda5dda7022fe47bbfe178295bfc616811eee6
+size 4856

almanach_camembert-base-ft-BUILD/logs/events.out.tfevents.1710517532.DESKTOP-VOM7ARG.17936.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:035a5f83e70cf2ffab8c0188076fb37a8277db6f2b9da5c7cfef4cf90a64f4cd
+size 25619