Training in progress, step 10000

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "DeepESP/gpt2-spanish",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

last-checkpoint/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "DeepESP/gpt2-spanish",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "max_length": 1024,
+  "pad_token_id": 50256,
+  "transformers_version": "4.28.1"
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79d4fa193949a1e8ccb93f801e7c758dda8058edccbb714f82055b7cb87d50a
+size 995605189

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8918b8af28267ba18d33b060c30bc163ca65c26abd0ea3193b5918ef770c45d
+size 510398013

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c520cf1bb57c2a4c42377e127df9db56f0427574ca822e986a5c3b83bd4c40b1
+size 14575

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a609d7204d71efec22c7a71c8efd13a4bc386c7339091e854dae45c249c77f63
+size 627

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,18 @@
+{
+  "additional_special_tokens": [
+    "<|talk|>",
+    "<|ax1|>",
+    "<|ax2|>",
+    "<|ax3|>",
+    "<|ax4|>",
+    "<|ax5|>",
+    "<|ax6|>",
+    "<|ax7|>",
+    "<|ax8|>",
+    "<|ax9|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "full_tokenizer_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,150 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.23676484515579127,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.913400890235818e-05,
+      "loss": 3.2516,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.907099788490072e-05,
+      "loss": 3.2746,
+      "step": 500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.900786059285918e-05,
+      "loss": 3.2966,
+      "step": 1000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 3.894472330081763e-05,
+      "loss": 3.2988,
+      "step": 1500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3.888158600877609e-05,
+      "loss": 3.2782,
+      "step": 2000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 3.8818448716734545e-05,
+      "loss": 3.2631,
+      "step": 2500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 3.8755311424693e-05,
+      "loss": 3.2792,
+      "step": 3000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 3.8692174132651456e-05,
+      "loss": 3.2848,
+      "step": 3500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3.862903684060991e-05,
+      "loss": 3.2699,
+      "step": 4000
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.8565899548568366e-05,
+      "loss": 3.2634,
+      "step": 4500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 3.8502762256526824e-05,
+      "loss": 3.276,
+      "step": 5000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.8439624964485276e-05,
+      "loss": 3.2431,
+      "step": 5500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.8376487672443735e-05,
+      "loss": 3.261,
+      "step": 6000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.8313350380402186e-05,
+      "loss": 3.2711,
+      "step": 6500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.8250213088360645e-05,
+      "loss": 3.2567,
+      "step": 7000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 3.8187075796319097e-05,
+      "loss": 3.2721,
+      "step": 7500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 3.8123938504277555e-05,
+      "loss": 3.2305,
+      "step": 8000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.806080121223601e-05,
+      "loss": 3.2749,
+      "step": 8500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.7997663920194465e-05,
+      "loss": 3.245,
+      "step": 9000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 3.7934526628152924e-05,
+      "loss": 3.251,
+      "step": 9500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 3.7871389336111375e-05,
+      "loss": 3.2401,
+      "step": 10000
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 3.248208999633789,
+      "eval_runtime": 113.4703,
+      "eval_samples_per_second": 165.435,
+      "eval_steps_per_second": 20.684,
+      "step": 10000
+    }
+  ],
+  "max_steps": 633540,
+  "num_train_epochs": 15,
+  "total_flos": 2276770162176000.0,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e13bd02ff5c40117ddbf942838af2297189fae003bd9b651003f2826488ee929
+size 4987

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8918b8af28267ba18d33b060c30bc163ca65c26abd0ea3193b5918ef770c45d
+size 510398013

special_tokens_map.json

@@ -0,0 +1,18 @@
+{
+  "additional_special_tokens": [
+    "<|talk|>",
+    "<|ax1|>",
+    "<|ax2|>",
+    "<|ax3|>",
+    "<|ax4|>",
+    "<|ax5|>",
+    "<|ax6|>",
+    "<|ax7|>",
+    "<|ax8|>",
+    "<|ax9|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "full_tokenizer_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e13bd02ff5c40117ddbf942838af2297189fae003bd9b651003f2826488ee929
+size 4987