Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2594313111e477594a91648cde226a4cb30800bf4e3cd3b785ff702f9e4a3af6
+oid sha256:152481e37c52a8adc035db1d81d71d3da40df87ef7ef5e63fe8fe4fb331f2474
 size 498612824

run-abl7jl8d/checkpoint-10168/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "FacebookAI/roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "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,
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-abl7jl8d/checkpoint-10168/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:152481e37c52a8adc035db1d81d71d3da40df87ef7ef5e63fe8fe4fb331f2474
+size 498612824

run-abl7jl8d/checkpoint-10168/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b5caba9a21fc8e77c7c276570e818a7ab21bed468ff7caa612d3b66c737cca7
+size 997345530

run-abl7jl8d/checkpoint-10168/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e44f253103df3e137112212c9524f8377e5d37a4496d441b00f3295569ccf5
+size 14180

run-abl7jl8d/checkpoint-10168/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3cbc92f19f4176221a173e5f93e35f3c999adf13240fbaa0646f4e8c3f3dfda
+size 1064

run-abl7jl8d/checkpoint-10168/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-abl7jl8d/checkpoint-10168/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "unk_token": "<unk>"
+}

run-abl7jl8d/checkpoint-10168/trainer_state.json

@@ -0,0 +1,216 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 10168,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.194170951843262,
+      "learning_rate": 2.8524783634933124e-05,
+      "loss": 0.3088,
+      "step": 500
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 6.946930408477783,
+      "learning_rate": 2.7049567269866248e-05,
+      "loss": 0.2727,
+      "step": 1000
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 6.29566764831543,
+      "learning_rate": 2.557435090479937e-05,
+      "loss": 0.2493,
+      "step": 1500
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 2.268385171890259,
+      "learning_rate": 2.4099134539732495e-05,
+      "loss": 0.233,
+      "step": 2000
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 10.843997955322266,
+      "learning_rate": 2.262391817466562e-05,
+      "loss": 0.2186,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_Accuracy": 0.9149422743535834,
+      "eval_F1": 0.8761679733648372,
+      "eval_Precision": 0.9256779757176897,
+      "eval_Recall": 0.8316851870730961,
+      "eval_loss": 0.21612036228179932,
+      "eval_runtime": 100.741,
+      "eval_samples_per_second": 269.116,
+      "eval_steps_per_second": 33.641,
+      "step": 2542
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 3.7359442710876465,
+      "learning_rate": 2.1148701809598742e-05,
+      "loss": 0.1707,
+      "step": 3000
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 7.295307636260986,
+      "learning_rate": 1.9673485444531865e-05,
+      "loss": 0.1571,
+      "step": 3500
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 6.433475971221924,
+      "learning_rate": 1.819826907946499e-05,
+      "loss": 0.1538,
+      "step": 4000
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 12.596657752990723,
+      "learning_rate": 1.6723052714398112e-05,
+      "loss": 0.1467,
+      "step": 4500
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 8.3139066696167,
+      "learning_rate": 1.5247836349331236e-05,
+      "loss": 0.1379,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_Accuracy": 0.9450776437608351,
+      "eval_F1": 0.9234801377254742,
+      "eval_Precision": 0.9310880829015544,
+      "eval_Recall": 0.9159955143235804,
+      "eval_loss": 0.171908438205719,
+      "eval_runtime": 103.7269,
+      "eval_samples_per_second": 261.369,
+      "eval_steps_per_second": 32.672,
+      "step": 5084
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 3.9494094848632812,
+      "learning_rate": 1.377261998426436e-05,
+      "loss": 0.1029,
+      "step": 5500
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 14.299867630004883,
+      "learning_rate": 1.2297403619197483e-05,
+      "loss": 0.0989,
+      "step": 6000
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 23.562984466552734,
+      "learning_rate": 1.0822187254130605e-05,
+      "loss": 0.0932,
+      "step": 6500
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 31.26663589477539,
+      "learning_rate": 9.34697088906373e-06,
+      "loss": 0.0888,
+      "step": 7000
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 42.10767364501953,
+      "learning_rate": 7.871754523996854e-06,
+      "loss": 0.0938,
+      "step": 7500
+    },
+    {
+      "epoch": 3.0,
+      "eval_Accuracy": 0.9524178377780237,
+      "eval_F1": 0.9330774019506123,
+      "eval_Precision": 0.949931340445759,
+      "eval_Recall": 0.9168110918544194,
+      "eval_loss": 0.1916985958814621,
+      "eval_runtime": 103.9471,
+      "eval_samples_per_second": 260.815,
+      "eval_steps_per_second": 32.603,
+      "step": 7626
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 19.0760498046875,
+      "learning_rate": 6.396538158929977e-06,
+      "loss": 0.0713,
+      "step": 8000
+    },
+    {
+      "epoch": 3.34,
+      "grad_norm": 0.10520514100790024,
+      "learning_rate": 4.9213217938631e-06,
+      "loss": 0.0631,
+      "step": 8500
+    },
+    {
+      "epoch": 3.54,
+      "grad_norm": 17.626262664794922,
+      "learning_rate": 3.4461054287962234e-06,
+      "loss": 0.0666,
+      "step": 9000
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 20.675457000732422,
+      "learning_rate": 1.970889063729347e-06,
+      "loss": 0.0538,
+      "step": 9500
+    },
+    {
+      "epoch": 3.93,
+      "grad_norm": 0.32099175453186035,
+      "learning_rate": 4.956726986624704e-07,
+      "loss": 0.0572,
+      "step": 10000
+    },
+    {
+      "epoch": 4.0,
+      "eval_Accuracy": 0.9545940762052304,
+      "eval_F1": 0.9374587207234669,
+      "eval_Precision": 0.9343731010735264,
+      "eval_Recall": 0.9405647874401061,
+      "eval_loss": 0.235666885972023,
+      "eval_runtime": 103.2623,
+      "eval_samples_per_second": 262.545,
+      "eval_steps_per_second": 32.819,
+      "step": 10168
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10168,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1.821254930757432e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 3e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32
+  }
+}

run-abl7jl8d/checkpoint-10168/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dde10c28a53365df9182bc3888d1f202abddeabc74f43518071c9ce1357949d
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:067eb0971eb3b96cb048c7ac33c2509754b49b327b0fd134c6c87269d7f1e94a
+oid sha256:7dde10c28a53365df9182bc3888d1f202abddeabc74f43518071c9ce1357949d
 size 4920