e

Browse files

Files changed (9) hide show

all_results.json +19 -0
config.json +42 -0
post-training eval_results.json +8 -0
pre-training eval_results.json +7 -0
prediction_output.jsonl +1 -0
pytorch_model.bin +3 -0
train_results.json +8 -0
trainer_state.json +178 -0
training_args.bin +3 -0

all_results.json ADDED Viewed

	@@ -0,0 +1,19 @@

+{
+    "epoch": 3.0,
+    "eval_f1": 0.09061488673139159,
+    "eval_loss": 0.6903448541319821,
+    "eval_runtime": 1.8447,
+    "eval_samples": 72,
+    "eval_samples_per_second": 39.03,
+    "eval_steps_per_second": 39.03,
+    "test_f1": 0.8675598506479244,
+    "test_loss": 0.3880781803951334,
+    "test_runtime": 1.86,
+    "test_samples_per_second": 38.71,
+    "test_steps_per_second": 38.71,
+    "train_loss": 0.3420516606757191,
+    "train_runtime": 138.2139,
+    "train_samples": 516,
+    "train_samples_per_second": 11.2,
+    "train_steps_per_second": 11.2
+}

config.json ADDED Viewed

	@@ -0,0 +1,42 @@

+{
+  "architectures": [
+    "SentenceClassificationModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classification_head": {
+    "num_labels": 1,
+    "pooling_method": "average"
+  },
+  "classifier_dropout": null,
+  "context_layer": null,
+  "eos_token_id": 2,
+  "frozen_layers": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8
+  ],
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.12.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

post-training eval_results.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "eval_samples": 72,
+    "test_f1": 0.8675598506479244,
+    "test_loss": 0.3880781803951334,
+    "test_runtime": 1.86,
+    "test_samples_per_second": 38.71,
+    "test_steps_per_second": 38.71
+}

pre-training eval_results.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+    "eval_f1": 0.09061488673139159,
+    "eval_loss": 0.6903448541319821,
+    "eval_runtime": 1.8447,
+    "eval_samples_per_second": 39.03,
+    "eval_steps_per_second": 39.03
+}

prediction_output.jsonl ADDED Viewed

	@@ -0,0 +1 @@

+ [{"pred": -6.710246562957764, "label": 1.0}, {"pred": -5.1076273918151855, "label": 0.0}, {"pred": -9.749329566955566, "label": 0.0}, {"pred": -1.2607908248901367, "label": 0.0}, {"pred": 7.604095935821533, "label": 1.0}, {"pred": -1.2607908248901367, "label": 0.0}, {"pred": -4.907297611236572, "label": 1.0}, {"pred": -1.8695299625396729, "label": 0.0}, {"pred": 0.5019912123680115, "label": 0.0}, {"pred": -0.48905226588249207, "label": 0.0}, {"pred": -5.786848545074463, "label": 0.0}, {"pred": 2.914689540863037, "label": 1.0}, {"pred": -1.375702977180481, "label": 1.0}, {"pred": 7.5268025398254395, "label": 1.0}, {"pred": -6.865538597106934, "label": 0.0}, {"pred": 12.414902687072754, "label": 1.0}, {"pred": -1.2607908248901367, "label": 0.0}, {"pred": 2.967189311981201, "label": 1.0}, {"pred": 3.7989327907562256, "label": 1.0}, {"pred": 2.9915523529052734, "label": 1.0}, {"pred": -1.8695299625396729, "label": 0.0}, {"pred": -4.842310428619385, "label": 0.0}, {"pred": 4.950301170349121, "label": 0.0}, {"pred": -6.229153633117676, "label": 0.0}, {"pred": -4.001574516296387, "label": 0.0}, {"pred": -6.162915229797363, "label": 0.0}, {"pred": -1.2607908248901367, "label": 0.0}, {"pred": 8.83720588684082, "label": 1.0}, {"pred": 3.091270923614502, "label": 0.0}, {"pred": -7.3006510734558105, "label": 0.0}, {"pred": -1.2607908248901367, "label": 0.0}, {"pred": 9.28825855255127, "label": 1.0}, {"pred": -1.2607908248901367, "label": 0.0}, {"pred": 6.154573440551758, "label": 1.0}, {"pred": -1.8695299625396729, "label": 0.0}, {"pred": -4.985635757446289, "label": 0.0}, {"pred": -7.502799034118652, "label": 0.0}, {"pred": -5.530549049377441, "label": 0.0}, {"pred": -1.2607908248901367, "label": 0.0}, {"pred": 7.455371379852295, "label": 1.0}, {"pred": -1.2607908248901367, "label": 0.0}, {"pred": 2.5521721839904785, "label": 1.0}, {"pred": -11.868775367736816, "label": 0.0}, {"pred": -6.8225812911987305, "label": 0.0}, {"pred": -6.335665225982666, "label": 0.0}, {"pred": -8.377745628356934, "label": 0.0}, {"pred": -8.231108665466309, "label": 0.0}, {"pred": -1.2607908248901367, "label": 0.0}, {"pred": 6.425404071807861, "label": 1.0}, {"pred": 1.8026080131530762, "label": 0.0}, {"pred": -1.2990999221801758, "label": 0.0}, {"pred": -1.2607908248901367, "label": 0.0}, {"pred": 10.405613899230957, "label": 1.0}, {"pred": 1.2829616069793701, "label": 1.0}, {"pred": 0.24396997690200806, "label": 0.0}, {"pred": -7.155792713165283, "label": 0.0}, {"pred": -4.654566287994385, "label": 0.0}, {"pred": -3.550811290740967, "label": 0.0}, {"pred": -5.170864582061768, "label": 0.0}, {"pred": -1.2607908248901367, "label": 0.0}, {"pred": 7.458619594573975, "label": 1.0}, {"pred": 2.0347001552581787, "label": 0.0}, {"pred": -2.0418667793273926, "label": 0.0}, {"pred": -1.2607908248901367, "label": 0.0}, {"pred": 5.3907904624938965, "label": 1.0}, {"pred": -3.7855145931243896, "label": 0.0}, {"pred": -6.813869953155518, "label": 0.0}, {"pred": 6.922443389892578, "label": 1.0}, {"pred": -1.2607908248901367, "label": 0.0}, {"pred": 6.170547008514404, "label": 1.0}, {"pred": -3.5350100994110107, "label": 0.0}, {"pred": -2.4522182941436768, "label": 0.0}, {"pred": -6.1690449714660645, "label": 0.0}, {"pred": -5.801476001739502, "label": 0.0}, {"pred": -1.2607908248901367, "label": 0.0}, {"pred": 5.135815620422363, "label": 1.0}, {"pred": -1.2607908248901367, "label": 0.0}, {"pred": 2.7306759357452393, "label": 1.0}, {"pred": 4.365366458892822, "label": 1.0}, {"pred": -1.8695299625396729, "label": 0.0}, {"pred": 2.536245584487915, "label": 0.0}, {"pred": -3.511805772781372, "label": 0.0}, {"pred": -0.21443864703178406, "label": 0.0}, {"pred": 0.4904942214488983, "label": 0.0}, {"pred": 0.6345910429954529, "label": 0.0}, {"pred": 0.8377909064292908, "label": 0.0}, {"pred": 4.581942558288574, "label": 0.0}]

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d8ed6a2e6fae18cdd12b0fb99b85ca49c674c6bd0e8daad6169e7d9c3c3311c0
+size 498671085

train_results.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+    "epoch": 3.0,
+    "train_loss": 0.3420516606757191,
+    "train_runtime": 138.2139,
+    "train_samples": 516,
+    "train_samples_per_second": 11.2,
+    "train_steps_per_second": 11.2
+}

trainer_state.json ADDED Viewed

	@@ -0,0 +1,178 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 1548,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "eval_f1": 0.8156471077819393,
+      "eval_loss": 0.5001406967854376,
+      "eval_runtime": 1.8455,
+      "eval_samples_per_second": 39.014,
+      "eval_steps_per_second": 39.014,
+      "step": 100
+    },
+    {
+      "epoch": 0.39,
+      "eval_f1": 0.845197255574614,
+      "eval_loss": 0.43044772204015086,
+      "eval_runtime": 1.861,
+      "eval_samples_per_second": 38.689,
+      "eval_steps_per_second": 38.689,
+      "step": 200
+    },
+    {
+      "epoch": 0.58,
+      "eval_f1": 0.8558871154291001,
+      "eval_loss": 0.3699678308231637,
+      "eval_runtime": 1.936,
+      "eval_samples_per_second": 37.19,
+      "eval_steps_per_second": 37.19,
+      "step": 300
+    },
+    {
+      "epoch": 0.78,
+      "eval_f1": 0.8616740088105727,
+      "eval_loss": 0.369556456447058,
+      "eval_runtime": 1.8526,
+      "eval_samples_per_second": 38.863,
+      "eval_steps_per_second": 38.863,
+      "step": 400
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.3850129198966415e-05,
+      "loss": 0.436,
+      "step": 500
+    },
+    {
+      "epoch": 0.97,
+      "eval_f1": 0.8502024291497975,
+      "eval_loss": 0.373378759373547,
+      "eval_runtime": 1.833,
+      "eval_samples_per_second": 39.28,
+      "eval_steps_per_second": 39.28,
+      "step": 500
+    },
+    {
+      "epoch": 1.16,
+      "eval_f1": 0.8598432457353619,
+      "eval_loss": 0.3582008616675675,
+      "eval_runtime": 1.8726,
+      "eval_samples_per_second": 38.449,
+      "eval_steps_per_second": 38.449,
+      "step": 600
+    },
+    {
+      "epoch": 1.36,
+      "eval_f1": 0.859629035951454,
+      "eval_loss": 0.3990428448363048,
+      "eval_runtime": 1.8807,
+      "eval_samples_per_second": 38.285,
+      "eval_steps_per_second": 38.285,
+      "step": 700
+    },
+    {
+      "epoch": 1.55,
+      "eval_f1": 0.8534583821805394,
+      "eval_loss": 0.37220439748563994,
+      "eval_runtime": 1.8382,
+      "eval_samples_per_second": 39.17,
+      "eval_steps_per_second": 39.17,
+      "step": 800
+    },
+    {
+      "epoch": 1.74,
+      "eval_f1": 0.8621794871794872,
+      "eval_loss": 0.35221788865736653,
+      "eval_runtime": 1.8405,
+      "eval_samples_per_second": 39.12,
+      "eval_steps_per_second": 39.12,
+      "step": 900
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.7700258397932818e-05,
+      "loss": 0.3334,
+      "step": 1000
+    },
+    {
+      "epoch": 1.94,
+      "eval_f1": 0.8674911660777386,
+      "eval_loss": 0.3408658861969036,
+      "eval_runtime": 1.9849,
+      "eval_samples_per_second": 36.275,
+      "eval_steps_per_second": 36.275,
+      "step": 1000
+    },
+    {
+      "epoch": 2.13,
+      "eval_f1": 0.8700021848372296,
+      "eval_loss": 0.35975042905666804,
+      "eval_runtime": 1.8613,
+      "eval_samples_per_second": 38.683,
+      "eval_steps_per_second": 38.683,
+      "step": 1100
+    },
+    {
+      "epoch": 2.33,
+      "eval_f1": 0.8688837110781613,
+      "eval_loss": 0.4004320452740604,
+      "eval_runtime": 1.8383,
+      "eval_samples_per_second": 39.166,
+      "eval_steps_per_second": 39.166,
+      "step": 1200
+    },
+    {
+      "epoch": 2.52,
+      "eval_f1": 0.8673469387755102,
+      "eval_loss": 0.3829791264749837,
+      "eval_runtime": 1.8659,
+      "eval_samples_per_second": 38.588,
+      "eval_steps_per_second": 38.588,
+      "step": 1300
+    },
+    {
+      "epoch": 2.71,
+      "eval_f1": 0.8671735241502684,
+      "eval_loss": 0.41182099972887176,
+      "eval_runtime": 1.8382,
+      "eval_samples_per_second": 39.168,
+      "eval_steps_per_second": 39.168,
+      "step": 1400
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.550387596899225e-06,
+      "loss": 0.2619,
+      "step": 1500
+    },
+    {
+      "epoch": 2.91,
+      "eval_f1": 0.8662842012356575,
+      "eval_loss": 0.39462613421886783,
+      "eval_runtime": 1.8602,
+      "eval_samples_per_second": 38.706,
+      "eval_steps_per_second": 38.706,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "step": 1548,
+      "total_flos": 1928644274657952.0,
+      "train_loss": 0.3420516606757191,
+      "train_runtime": 138.2139,
+      "train_samples_per_second": 11.2,
+      "train_steps_per_second": 11.2
+    }
+  ],
+  "max_steps": 1548,
+  "num_train_epochs": 3,
+  "total_flos": 1928644274657952.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:293d06dccf305e51d6621ebbfd49342e7e439f29562b7423e48d65db878a2bf5
+size 2927