Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:632bb0d4617b2c38c939eb2706a12c41de2855fff1c02f3afb319d04d68344b8
+oid sha256:4b8e84687e588a0d61f75a4c7644c43363c1083550056e5c25ef9a46d93b395a
 size 498612824

run-aoq0iqgi/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-aoq0iqgi/checkpoint-10168/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b8e84687e588a0d61f75a4c7644c43363c1083550056e5c25ef9a46d93b395a
+size 498612824

run-aoq0iqgi/checkpoint-10168/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4726b14b495a54ae41c81e5d6a2f4d24905c4fe83876ae5d850b64202557674f
+size 997345530

run-aoq0iqgi/checkpoint-10168/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c68f3b55e02ab12602ce34fbaf912752082e3519389804f239b41191e9da9eee
+size 14180

run-aoq0iqgi/checkpoint-10168/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c46a90ef17901633bdbde15be4509b2f4e279f8f35a328ff99d877a46c5efa
+size 1064

run-aoq0iqgi/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-aoq0iqgi/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-aoq0iqgi/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": 4.198366641998291,
+      "learning_rate": 4.7541306058221875e-05,
+      "loss": 0.3438,
+      "step": 500
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 6.5167412757873535,
+      "learning_rate": 4.508261211644375e-05,
+      "loss": 0.2899,
+      "step": 1000
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 8.44621753692627,
+      "learning_rate": 4.262391817466562e-05,
+      "loss": 0.2836,
+      "step": 1500
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 5.728306293487549,
+      "learning_rate": 4.016522423288749e-05,
+      "loss": 0.2707,
+      "step": 2000
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 21.944625854492188,
+      "learning_rate": 3.7706530291109365e-05,
+      "loss": 0.2555,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_Accuracy": 0.908118475895393,
+      "eval_F1": 0.8677321722508363,
+      "eval_Precision": 0.9054742907801419,
+      "eval_Recall": 0.8330105005607096,
+      "eval_loss": 0.2431253343820572,
+      "eval_runtime": 89.7162,
+      "eval_samples_per_second": 302.186,
+      "eval_steps_per_second": 37.775,
+      "step": 2542
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 6.02112340927124,
+      "learning_rate": 3.524783634933124e-05,
+      "loss": 0.2034,
+      "step": 3000
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 5.231555938720703,
+      "learning_rate": 3.278914240755311e-05,
+      "loss": 0.1878,
+      "step": 3500
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 11.2307767868042,
+      "learning_rate": 3.033044846577498e-05,
+      "loss": 0.1821,
+      "step": 4000
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 6.832123279571533,
+      "learning_rate": 2.7871754523996855e-05,
+      "loss": 0.1765,
+      "step": 4500
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 5.67682409286499,
+      "learning_rate": 2.5413060582218728e-05,
+      "loss": 0.1673,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_Accuracy": 0.9325366087565933,
+      "eval_F1": 0.9067074725835246,
+      "eval_Precision": 0.907309105757452,
+      "eval_Recall": 0.9061066367621572,
+      "eval_loss": 0.18651607632637024,
+      "eval_runtime": 88.3981,
+      "eval_samples_per_second": 306.692,
+      "eval_steps_per_second": 38.338,
+      "step": 5084
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 4.083110809326172,
+      "learning_rate": 2.29543666404406e-05,
+      "loss": 0.1275,
+      "step": 5500
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.7959149479866028,
+      "learning_rate": 2.0495672698662473e-05,
+      "loss": 0.1222,
+      "step": 6000
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 17.33026123046875,
+      "learning_rate": 1.8036978756884342e-05,
+      "loss": 0.114,
+      "step": 6500
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 6.551443099975586,
+      "learning_rate": 1.5578284815106218e-05,
+      "loss": 0.1033,
+      "step": 7000
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 4.966001510620117,
+      "learning_rate": 1.3119590873328089e-05,
+      "loss": 0.1079,
+      "step": 7500
+    },
+    {
+      "epoch": 3.0,
+      "eval_Accuracy": 0.9464792888495445,
+      "eval_F1": 0.9272645245375708,
+      "eval_Precision": 0.9121301775147929,
+      "eval_Recall": 0.9429095728412682,
+      "eval_loss": 0.1950514316558838,
+      "eval_runtime": 87.4698,
+      "eval_samples_per_second": 309.947,
+      "eval_steps_per_second": 38.745,
+      "step": 7626
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 8.118966102600098,
+      "learning_rate": 1.0660896931549961e-05,
+      "loss": 0.0719,
+      "step": 8000
+    },
+    {
+      "epoch": 3.34,
+      "grad_norm": 12.746671676635742,
+      "learning_rate": 8.202202989771832e-06,
+      "loss": 0.0694,
+      "step": 8500
+    },
+    {
+      "epoch": 3.54,
+      "grad_norm": 1.7363771200180054,
+      "learning_rate": 5.743509047993706e-06,
+      "loss": 0.0693,
+      "step": 9000
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 54.89155960083008,
+      "learning_rate": 3.284815106215578e-06,
+      "loss": 0.0701,
+      "step": 9500
+    },
+    {
+      "epoch": 3.93,
+      "grad_norm": 0.0783783346414566,
+      "learning_rate": 8.261211644374508e-07,
+      "loss": 0.0676,
+      "step": 10000
+    },
+    {
+      "epoch": 4.0,
+      "eval_Accuracy": 0.9551842425583711,
+      "eval_F1": 0.9375930967178592,
+      "eval_Precision": 0.944824016563147,
+      "eval_Recall": 0.9304720154959731,
+      "eval_loss": 0.19617860019207,
+      "eval_runtime": 89.2256,
+      "eval_samples_per_second": 303.848,
+      "eval_steps_per_second": 37.982,
+      "step": 10168
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10168,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1.81645320538599e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 5e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32
+  }
+}

run-aoq0iqgi/checkpoint-10168/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067eb0971eb3b96cb048c7ac33c2509754b49b327b0fd134c6c87269d7f1e94a
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2bc76c4f5af8e353c06a15a8bc6c53dcf9c785c8d8f93b0aeacc87982180064
+oid sha256:067eb0971eb3b96cb048c7ac33c2509754b49b327b0fd134c6c87269d7f1e94a
 size 4920