Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2480afe618f2232958e9c3418c6ae29896dedf6b79966b9dfef2ac809bfa2064
+oid sha256:a7b34459a6587b2bfedb04b29b2b2cf03b1626d1802247853e1e2fcc82d31d55
 size 498612824

run-2pm2ctug/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-2pm2ctug/checkpoint-10168/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f24807caefb1a10157226d70357043103d5792ebc40bf7baa531c8e6b8007f9
+size 498612824

run-2pm2ctug/checkpoint-10168/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8533169322f458d720d0cb100f621275b723fe3e0b5c73afbaf1e479a4b51071
+size 997345530

run-2pm2ctug/checkpoint-10168/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2faa6142e89c05a2547dfd3a0529e787b545123af3ce4d4793952f1da9d33c5
+size 14244

run-2pm2ctug/checkpoint-10168/scheduler.pt

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

run-2pm2ctug/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-2pm2ctug/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-2pm2ctug/checkpoint-10168/trainer_state.json

@@ -0,0 +1,192 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 10168,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 8.952469825744629,
+      "learning_rate": 4.7541306058221875e-05,
+      "loss": 0.374,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.356359958648682,
+      "learning_rate": 4.508261211644375e-05,
+      "loss": 0.3127,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 10.497965812683105,
+      "learning_rate": 4.262391817466562e-05,
+      "loss": 0.3057,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.5229237079620361,
+      "learning_rate": 4.016522423288749e-05,
+      "loss": 0.3009,
+      "step": 2000
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 5.804162979125977,
+      "learning_rate": 3.7706530291109365e-05,
+      "loss": 0.2774,
+      "step": 2500
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 24.477081298828125,
+      "learning_rate": 3.524783634933124e-05,
+      "loss": 0.2932,
+      "step": 3000
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 2.478816270828247,
+      "learning_rate": 3.278914240755311e-05,
+      "loss": 0.2819,
+      "step": 3500
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 6.592701435089111,
+      "learning_rate": 3.033044846577498e-05,
+      "loss": 0.2704,
+      "step": 4000
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.1151834726333618,
+      "learning_rate": 2.7871754523996855e-05,
+      "loss": 0.2685,
+      "step": 4500
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 5.545079231262207,
+      "learning_rate": 2.5413060582218728e-05,
+      "loss": 0.2596,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0,
+      "eval_Accuracy": 0.906016008262329,
+      "eval_F1": 0.8705284552845529,
+      "eval_Precision": 0.8677945496910141,
+      "eval_Recall": 0.8732796411458864,
+      "eval_loss": 0.2526940703392029,
+      "eval_runtime": 102.0206,
+      "eval_samples_per_second": 265.74,
+      "eval_steps_per_second": 33.219,
+      "step": 5084
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 15.355692863464355,
+      "learning_rate": 2.29543666404406e-05,
+      "loss": 0.2172,
+      "step": 5500
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 3.923316717147827,
+      "learning_rate": 2.0495672698662473e-05,
+      "loss": 0.2099,
+      "step": 6000
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 4.595956802368164,
+      "learning_rate": 1.8036978756884342e-05,
+      "loss": 0.2023,
+      "step": 6500
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 12.429964065551758,
+      "learning_rate": 1.5578284815106218e-05,
+      "loss": 0.199,
+      "step": 7000
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 2.73836088180542,
+      "learning_rate": 1.3119590873328089e-05,
+      "loss": 0.1911,
+      "step": 7500
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 1.6286685466766357,
+      "learning_rate": 1.0660896931549961e-05,
+      "loss": 0.1894,
+      "step": 8000
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 11.347786903381348,
+      "learning_rate": 8.202202989771832e-06,
+      "loss": 0.1897,
+      "step": 8500
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 15.639930725097656,
+      "learning_rate": 5.743509047993706e-06,
+      "loss": 0.1756,
+      "step": 9000
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.3368394374847412,
+      "learning_rate": 3.284815106215578e-06,
+      "loss": 0.1703,
+      "step": 9500
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.2661483585834503,
+      "learning_rate": 8.261211644374508e-07,
+      "loss": 0.1562,
+      "step": 10000
+    },
+    {
+      "epoch": 2.0,
+      "eval_Accuracy": 0.9305816827118144,
+      "eval_F1": 0.9034277504105089,
+      "eval_Precision": 0.9094947825188553,
+      "eval_Recall": 0.8974411254969925,
+      "eval_loss": 0.23381005227565765,
+      "eval_runtime": 102.4467,
+      "eval_samples_per_second": 264.635,
+      "eval_steps_per_second": 33.081,
+      "step": 10168
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10168,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 8059213417317660.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 5e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16
+  }
+}

run-2pm2ctug/checkpoint-10168/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38aa6eaab112efcf4cce54af8cfefe98ef03eff8152b57158c5921cfacf9ff1d
+size 4920

run-s53o2mei/checkpoint-2542/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-s53o2mei/checkpoint-2542/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac826e5400166d9b1e11fb948c4fda78d15f1effd4a15abc4f24cb0087b0f49
+size 498612824

run-s53o2mei/checkpoint-2542/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f345c23664883c2aba653f7335c7bf16ccd8d7e50e5d251d8e72e12298cec4a
+size 997345530

run-s53o2mei/checkpoint-2542/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff88cb9fe450283dfcefbdfa53ddc11a59bd05ef7b15924a2277f40a548f43a1
+size 14244

run-s53o2mei/checkpoint-2542/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a48ed8f460678336e2efbdd02764305093f3cdc6c75ad66b15cf3988c53327
+size 1064

run-s53o2mei/checkpoint-2542/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-s53o2mei/checkpoint-2542/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-s53o2mei/checkpoint-2542/trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2542,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.570998668670654,
+      "learning_rate": 4.508261211644375e-05,
+      "loss": 0.3334,
+      "step": 500
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 3.4940078258514404,
+      "learning_rate": 4.016522423288749e-05,
+      "loss": 0.2642,
+      "step": 1000
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 4.408178329467773,
+      "learning_rate": 3.524783634933124e-05,
+      "loss": 0.2613,
+      "step": 1500
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 6.658562183380127,
+      "learning_rate": 3.033044846577498e-05,
+      "loss": 0.2411,
+      "step": 2000
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 5.94639778137207,
+      "learning_rate": 2.5413060582218728e-05,
+      "loss": 0.2254,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_Accuracy": 0.9160119508686511,
+      "eval_F1": 0.8847030229378703,
+      "eval_Precision": 0.8788732394366198,
+      "eval_Recall": 0.8906106636762158,
+      "eval_loss": 0.1989465206861496,
+      "eval_runtime": 101.8667,
+      "eval_samples_per_second": 266.142,
+      "eval_steps_per_second": 33.269,
+      "step": 2542
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5084,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 4535639927823360.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 5e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 32
+  }
+}

run-s53o2mei/checkpoint-2542/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22334f807c1930b25f02dff20d5197c776aea63071cfbf22f3395438daea453c
+size 4920

run-s53o2mei/checkpoint-5084/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-s53o2mei/checkpoint-5084/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7b34459a6587b2bfedb04b29b2b2cf03b1626d1802247853e1e2fcc82d31d55
+size 498612824

run-s53o2mei/checkpoint-5084/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5406b56f931f198c8c560e5a88d024d1131d7a5156dcee5eb7f9854d10f963
+size 997345530

run-s53o2mei/checkpoint-5084/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0adc3c5e72af4442446dc86648094be9bee1b51850bd4f5d6478abbbb07bdcc
+size 14244

run-s53o2mei/checkpoint-5084/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:106c6011bda82f533c9b10827069f6a23c37dd305a54c700e865f2d284fd4da1
+size 1064

run-s53o2mei/checkpoint-5084/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-s53o2mei/checkpoint-5084/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-s53o2mei/checkpoint-5084/trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 5084,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.570998668670654,
+      "learning_rate": 4.508261211644375e-05,
+      "loss": 0.3334,
+      "step": 500
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 3.4940078258514404,
+      "learning_rate": 4.016522423288749e-05,
+      "loss": 0.2642,
+      "step": 1000
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 4.408178329467773,
+      "learning_rate": 3.524783634933124e-05,
+      "loss": 0.2613,
+      "step": 1500
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 6.658562183380127,
+      "learning_rate": 3.033044846577498e-05,
+      "loss": 0.2411,
+      "step": 2000
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 5.94639778137207,
+      "learning_rate": 2.5413060582218728e-05,
+      "loss": 0.2254,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_Accuracy": 0.9160119508686511,
+      "eval_F1": 0.8847030229378703,
+      "eval_Precision": 0.8788732394366198,
+      "eval_Recall": 0.8906106636762158,
+      "eval_loss": 0.1989465206861496,
+      "eval_runtime": 101.8667,
+      "eval_samples_per_second": 266.142,
+      "eval_steps_per_second": 33.269,
+      "step": 2542
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 7.156487464904785,
+      "learning_rate": 2.0495672698662473e-05,
+      "loss": 0.1705,
+      "step": 3000
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 15.43547248840332,
+      "learning_rate": 1.5578284815106218e-05,
+      "loss": 0.1514,
+      "step": 3500
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 12.279090881347656,
+      "learning_rate": 1.0660896931549961e-05,
+      "loss": 0.1426,
+      "step": 4000
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 13.348250389099121,
+      "learning_rate": 5.743509047993706e-06,
+      "loss": 0.1375,
+      "step": 4500
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 3.653700828552246,
+      "learning_rate": 8.261211644374508e-07,
+      "loss": 0.1259,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_Accuracy": 0.9391022094352846,
+      "eval_F1": 0.9154070810063022,
+      "eval_Precision": 0.9201689328388958,
+      "eval_Recall": 0.9106942603731267,
+      "eval_loss": 0.18230117857456207,
+      "eval_runtime": 104.2048,
+      "eval_samples_per_second": 260.17,
+      "eval_steps_per_second": 32.522,
+      "step": 5084
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5084,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 9081241075758240.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 5e-05,
+    "metric": "eval/loss",
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 32
+  }
+}

run-s53o2mei/checkpoint-5084/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22334f807c1930b25f02dff20d5197c776aea63071cfbf22f3395438daea453c
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38aa6eaab112efcf4cce54af8cfefe98ef03eff8152b57158c5921cfacf9ff1d
+oid sha256:22334f807c1930b25f02dff20d5197c776aea63071cfbf22f3395438daea453c
 size 4920