Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: TR_10000_41
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# TR_10000_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.3289
+- Accuracy: 0.2970
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0006
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 41
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 10.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 869  | 5.5504          | 0.1968   |
+| 1.4286        | 2.0   | 1738 | 5.2647          | 0.2070   |
+| 1.2405        | 3.0   | 2607 | 5.0152          | 0.2232   |
+| 1.1718        | 4.0   | 3476 | 4.8169          | 0.2414   |
+| 1.1158        | 5.0   | 4345 | 4.6747          | 0.2555   |
+| 1.0736        | 6.0   | 5214 | 4.5662          | 0.2683   |
+| 1.0394        | 7.0   | 6083 | 4.4812          | 0.2789   |
+| 1.0394        | 8.0   | 6952 | 4.4101          | 0.2872   |
+| 1.0081        | 9.0   | 7821 | 4.3540          | 0.2938   |
+| 0.9826        | 10.0  | 8690 | 4.3289          | 0.2970   |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.5.1+cu121
+- Datasets 3.6.0
+- Tokenizers 0.21.1

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.2970094807440199,
+    "eval_loss": 4.328894138336182,
+    "eval_runtime": 4.6814,
+    "eval_samples": 206,
+    "eval_samples_per_second": 44.003,
+    "eval_steps_per_second": 1.495,
+    "perplexity": 75.86034911424535,
+    "total_flos": 7.262873321472e+16,
+    "train_loss": 1.1195150886772691,
+    "train_runtime": 8063.5745,
+    "train_samples": 27796,
+    "train_samples_per_second": 34.471,
+    "train_steps_per_second": 1.078
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "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": 512,
+  "pad_token_id": 0,
+  "prefix": "<|endoftext|>",
+  "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": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 10000
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.2970094807440199,
+    "eval_loss": 4.328894138336182,
+    "eval_runtime": 4.6814,
+    "eval_samples": 206,
+    "eval_samples_per_second": 44.003,
+    "eval_steps_per_second": 1.495,
+    "perplexity": 75.86034911424535
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24084f5112a8a1ebb6023e82b5212dd43e1187d3c501a93f4ccc29a18cc85f14
+size 372531840

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<pad>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 7.262873321472e+16,
+    "train_loss": 1.1195150886772691,
+    "train_runtime": 8063.5745,
+    "train_samples": 27796,
+    "train_samples_per_second": 34.471,
+    "train_steps_per_second": 1.078
+}

trainer_state.json

@@ -0,0 +1,189 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 8690,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.19677768700245094,
+      "eval_loss": 5.550434589385986,
+      "eval_runtime": 5.714,
+      "eval_samples_per_second": 36.052,
+      "eval_steps_per_second": 1.225,
+      "step": 869
+    },
+    {
+      "epoch": 1.1507479861910241,
+      "grad_norm": 11300.1083984375,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 1.4286,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.2070469097334372,
+      "eval_loss": 5.264675140380859,
+      "eval_runtime": 4.7535,
+      "eval_samples_per_second": 43.336,
+      "eval_steps_per_second": 1.473,
+      "step": 1738
+    },
+    {
+      "epoch": 2.3014959723820483,
+      "grad_norm": 9430.6962890625,
+      "learning_rate": 0.0005220546163849154,
+      "loss": 1.2405,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.223224972925731,
+      "eval_loss": 5.015192985534668,
+      "eval_runtime": 4.6951,
+      "eval_samples_per_second": 43.875,
+      "eval_steps_per_second": 1.491,
+      "step": 2607
+    },
+    {
+      "epoch": 3.4522439585730726,
+      "grad_norm": 10195.8359375,
+      "learning_rate": 0.0004440312093628088,
+      "loss": 1.1718,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.24135998328045144,
+      "eval_loss": 4.8169026374816895,
+      "eval_runtime": 4.4691,
+      "eval_samples_per_second": 46.095,
+      "eval_steps_per_second": 1.566,
+      "step": 3476
+    },
+    {
+      "epoch": 4.602991944764097,
+      "grad_norm": 10352.796875,
+      "learning_rate": 0.00036600780234070213,
+      "loss": 1.1158,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.25547660213174245,
+      "eval_loss": 4.674685001373291,
+      "eval_runtime": 4.5251,
+      "eval_samples_per_second": 45.524,
+      "eval_steps_per_second": 1.547,
+      "step": 4345
+    },
+    {
+      "epoch": 5.7537399309551205,
+      "grad_norm": 10494.6123046875,
+      "learning_rate": 0.00028798439531859554,
+      "loss": 1.0736,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.26832025535310544,
+      "eval_loss": 4.56621789932251,
+      "eval_runtime": 4.6891,
+      "eval_samples_per_second": 43.932,
+      "eval_steps_per_second": 1.493,
+      "step": 5214
+    },
+    {
+      "epoch": 6.904487917146145,
+      "grad_norm": 11196.5615234375,
+      "learning_rate": 0.00020996098829648892,
+      "loss": 1.0394,
+      "step": 6000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.27890296961982025,
+      "eval_loss": 4.481164932250977,
+      "eval_runtime": 4.6581,
+      "eval_samples_per_second": 44.224,
+      "eval_steps_per_second": 1.503,
+      "step": 6083
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.28719624570136604,
+      "eval_loss": 4.410129547119141,
+      "eval_runtime": 4.8018,
+      "eval_samples_per_second": 42.901,
+      "eval_steps_per_second": 1.458,
+      "step": 6952
+    },
+    {
+      "epoch": 8.055235903337168,
+      "grad_norm": 11843.2666015625,
+      "learning_rate": 0.0001319375812743823,
+      "loss": 1.0081,
+      "step": 7000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.2938080671821861,
+      "eval_loss": 4.353987216949463,
+      "eval_runtime": 4.5523,
+      "eval_samples_per_second": 45.252,
+      "eval_steps_per_second": 1.538,
+      "step": 7821
+    },
+    {
+      "epoch": 9.205983889528193,
+      "grad_norm": 12118.0166015625,
+      "learning_rate": 5.391417425227568e-05,
+      "loss": 0.9826,
+      "step": 8000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.2970094807440199,
+      "eval_loss": 4.328894138336182,
+      "eval_runtime": 4.5667,
+      "eval_samples_per_second": 45.109,
+      "eval_steps_per_second": 1.533,
+      "step": 8690
+    },
+    {
+      "epoch": 10.0,
+      "step": 8690,
+      "total_flos": 7.262873321472e+16,
+      "train_loss": 1.1195150886772691,
+      "train_runtime": 8063.5745,
+      "train_samples_per_second": 34.471,
+      "train_steps_per_second": 1.078
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 8690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.262873321472e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa423dfea91604ebdaddfdab82ec584b91f3a9d7e88a06a8da10891880a1daea
+size 5304