Upload 7 files

checkpoint-21000/config.json

@@ -0,0 +1,207 @@
+{
+  "_commit_hash": null,
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "gpt2",
+    "activation_function": "gelu_new",
+    "add_cross_attention": true,
+    "architectures": [
+      "GPT2LMHeadModel"
+    ],
+    "attn_pdrop": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 50256,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "embd_pdrop": 0.1,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 50256,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "gpt2",
+    "n_ctx": 1024,
+    "n_embd": 768,
+    "n_head": 12,
+    "n_inner": null,
+    "n_layer": 12,
+    "n_positions": 1024,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "reorder_and_upcast_attn": false,
+    "repetition_penalty": 1.0,
+    "resid_pdrop": 0.1,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_attn_by_inverse_layer_idx": false,
+    "scale_attn_weights": true,
+    "sep_token_id": null,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "suppress_tokens": null,
+    "task_specific_params": {
+      "text-generation": {
+        "do_sample": true,
+        "max_length": 50
+      }
+    },
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.24.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50257
+  },
+  "decoder_start_token_id": 50256,
+  "encoder": {
+    "_name_or_path": "microsoft/swin-large-patch4-window7-224",
+    "add_cross_attention": false,
+    "architectures": [
+      "SwinForImageClassification"
+    ],
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "depths": [
+      2,
+      2,
+      18,
+      2
+    ],
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.1,
+    "early_stopping": false,
+    "embed_dim": 192,
+    "encoder_no_repeat_ngram_size": 0,
+    "encoder_stride": 32,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1536,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "mlp_ratio": 4.0,
+    "model_type": "swin",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_heads": [
+      6,
+      12,
+      24,
+      48
+    ],
+    "num_layers": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 4,
+    "path_norm": true,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "transformers_version": "4.24.0",
+    "typical_p": 1.0,
+    "use_absolute_embeddings": false,
+    "use_bfloat16": false,
+    "window_size": 7
+  },
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 50256,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": null
+}

checkpoint-21000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b3e10d000f20a9a0c40cc0760a3232d22bbb10bf9de55199359e72ac9e05554
+size 1421809655

checkpoint-21000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:511685412bc1112cfbfc048209401c538552e3a3d43331c5e056951d4b4b684f
+size 14503

checkpoint-21000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c25d2250ccfcbfeb9ce1554127f5362a2dd904ef51e0b94eefe137957129a79
+size 559

checkpoint-21000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad98a991bac38e8a07b98a0da1f66f38cebadfb748b1c8ab9817f9872ffcca1
+size 623

checkpoint-21000/trainer_state.json

@@ -0,0 +1,114 @@
+{
+  "best_metric": 0.03351227194070816,
+  "best_model_checkpoint": "/content/drive/MyDrive/Doutorado/Experimentos/colabs/trainer/checkpoint-21000",
+  "epoch": 7.18439958946288,
+  "global_step": 21000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.91811152925077e-05,
+      "loss": 0.1619,
+      "step": 3000
+    },
+    {
+      "epoch": 1.03,
+      "eval_loss": 0.05028245225548744,
+      "eval_runtime": 27.6275,
+      "eval_samples_per_second": 33.445,
+      "eval_steps_per_second": 4.199,
+      "step": 3000
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.836004105371194e-05,
+      "loss": 0.0548,
+      "step": 6000
+    },
+    {
+      "epoch": 2.05,
+      "eval_loss": 0.04163406416773796,
+      "eval_runtime": 27.2823,
+      "eval_samples_per_second": 33.868,
+      "eval_steps_per_second": 4.252,
+      "step": 6000
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 1.753896681491618e-05,
+      "loss": 0.0441,
+      "step": 9000
+    },
+    {
+      "epoch": 3.08,
+      "eval_loss": 0.037465475499629974,
+      "eval_runtime": 26.8832,
+      "eval_samples_per_second": 34.371,
+      "eval_steps_per_second": 4.315,
+      "step": 9000
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 1.6717892576120426e-05,
+      "loss": 0.0391,
+      "step": 12000
+    },
+    {
+      "epoch": 4.11,
+      "eval_loss": 0.03538713976740837,
+      "eval_runtime": 28.4361,
+      "eval_samples_per_second": 32.494,
+      "eval_steps_per_second": 4.079,
+      "step": 12000
+    },
+    {
+      "epoch": 5.13,
+      "learning_rate": 1.589681833732467e-05,
+      "loss": 0.0335,
+      "step": 15000
+    },
+    {
+      "epoch": 5.13,
+      "eval_loss": 0.03461988642811775,
+      "eval_runtime": 28.0681,
+      "eval_samples_per_second": 32.92,
+      "eval_steps_per_second": 4.133,
+      "step": 15000
+    },
+    {
+      "epoch": 6.16,
+      "learning_rate": 1.5075744098528911e-05,
+      "loss": 0.0304,
+      "step": 18000
+    },
+    {
+      "epoch": 6.16,
+      "eval_loss": 0.033533450216054916,
+      "eval_runtime": 27.7618,
+      "eval_samples_per_second": 33.283,
+      "eval_steps_per_second": 4.178,
+      "step": 18000
+    },
+    {
+      "epoch": 7.18,
+      "learning_rate": 1.4254943551146082e-05,
+      "loss": 0.0273,
+      "step": 21000
+    },
+    {
+      "epoch": 7.18,
+      "eval_loss": 0.03351227194070816,
+      "eval_runtime": 27.8867,
+      "eval_samples_per_second": 33.134,
+      "eval_steps_per_second": 4.16,
+      "step": 21000
+    }
+  ],
+  "max_steps": 73075,
+  "num_train_epochs": 25,
+  "total_flos": 3.523012168812466e+19,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-21000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4573672c7313f2dc99708ae0234ccaea4f5d5d1bcbd2de34545b740c8496b9e7
+size 3439