Model save

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+base_model: tiiuae/falcon-7b
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: falcon-lima
+  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. -->
+
+# falcon-lima
+
+This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4276
+
+## 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: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.0634        | 0.91  | 5    | 1.9126          |
+| 1.9281        | 2.0   | 11   | 1.8793          |
+| 1.7541        | 2.91  | 16   | 2.2713          |
+| 1.5669        | 4.0   | 22   | 2.2287          |
+| 1.3976        | 4.91  | 27   | 2.2656          |
+| 1.2434        | 6.0   | 33   | 2.3438          |
+| 1.1083        | 6.91  | 38   | 2.3551          |
+| 1.0215        | 8.0   | 44   | 2.4332          |
+| 0.9556        | 8.91  | 49   | 2.4332          |
+| 0.9465        | 9.09  | 50   | 2.4276          |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.2
+- Datasets 2.14.6
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.09,
+    "train_loss": 1.39877197265625,
+    "train_runtime": 578.7401,
+    "train_samples": 1030,
+    "train_samples_per_second": 11.629,
+    "train_steps_per_second": 0.086
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "tiiuae/falcon-7b",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-7b--configuration_falcon.FalconConfig",
+    "AutoModel": "tiiuae/falcon-7b--modeling_falcon.FalconModel",
+    "AutoModelForCausalLM": "tiiuae/falcon-7b--modeling_falcon.FalconForCausalLM",
+    "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "tiiuae/falcon-7b--modeling_falcon.FalconForTokenClassification"
+  },
+  "bias": false,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4544,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "falcon",
+  "multi_query": true,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 71,
+  "num_hidden_layers": 32,
+  "num_kv_heads": 71,
+  "parallel_attn": true,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86a9460943698d7869d58e037fffb74930184403b9f317008926f27dd5a864b8
+size 4981285848

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f387bc374c492f9a5d5567d45733531d69a810f47c02b99cf90873d138c57171
+size 4969690568

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92eae49853ef8c4dbc1a1bd0fe7c623c2772f6631a2896517bac3674dc30ca4d
+size 3892488296

model.safetensors.index.json

@@ -0,0 +1,202 @@
+{
+  "metadata": {
+    "total_size": 13843441408
+  },
+  "weight_map": {
+    "transformer.h.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.10.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.11.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.11.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.12.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.13.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.14.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.15.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.16.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.17.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.18.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.19.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.20.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
+    "transformer.h.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.21.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.self_attention.dense.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.22.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
+    "transformer.h.23.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.23.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.23.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.24.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.25.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.26.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.27.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.28.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.29.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.30.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.30.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
+    "transformer.h.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.self_attention.dense.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.31.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
+    "transformer.h.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.8.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
+    "transformer.h.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.self_attention.dense.weight": "model-00001-of-00003.safetensors",
+    "transformer.h.9.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
+    "transformer.ln_f.bias": "model-00003-of-00003.safetensors",
+    "transformer.ln_f.weight": "model-00003-of-00003.safetensors",
+    "transformer.word_embeddings.weight": "model-00001-of-00003.safetensors"
+  }
+}

runs/Apr27_01-54-02_aga39/events.out.tfevents.1714200940.aga39.1542291.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae38a5bc47f262b625bfe3023193b6ad2c469cc8cde9d90df3c891d5e47ea5fc
+size 10583

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,124 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": ">>TITLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": ">>ABSTRACT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": ">>INTRODUCTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": ">>SUMMARY<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": ">>COMMENT<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": ">>ANSWER<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": ">>QUESTION<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": ">>DOMAIN<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": ">>PREFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": ">>SUFFIX<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": ">>MIDDLE<<",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '### Human\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '### System\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '### Assistant\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '### Assistant' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.09,
+    "train_loss": 1.39877197265625,
+    "train_runtime": 578.7401,
+    "train_samples": 1030,
+    "train_samples_per_second": 11.629,
+    "train_steps_per_second": 0.086
+}

trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.090909090909092,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.9203362743829422,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.0754,
+      "step": 1
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 2.2522979550420272,
+      "learning_rate": 2e-05,
+      "loss": 2.0634,
+      "step": 5
+    },
+    {
+      "epoch": 0.91,
+      "eval_loss": 1.912642002105713,
+      "eval_runtime": 2.1098,
+      "eval_samples_per_second": 5.214,
+      "eval_steps_per_second": 0.474,
+      "step": 5
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 1.0376267934668848,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 1.9281,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8792613744735718,
+      "eval_runtime": 2.0802,
+      "eval_samples_per_second": 5.288,
+      "eval_steps_per_second": 0.481,
+      "step": 11
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 0.807859290768886,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 1.7541,
+      "step": 15
+    },
+    {
+      "epoch": 2.91,
+      "eval_loss": 2.2713067531585693,
+      "eval_runtime": 1.9404,
+      "eval_samples_per_second": 5.669,
+      "eval_steps_per_second": 0.515,
+      "step": 16
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 0.6587224869045021,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.5669,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.2286932468414307,
+      "eval_runtime": 2.057,
+      "eval_samples_per_second": 5.348,
+      "eval_steps_per_second": 0.486,
+      "step": 22
+    },
+    {
+      "epoch": 4.55,
+      "grad_norm": 0.6858567432222655,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 1.3976,
+      "step": 25
+    },
+    {
+      "epoch": 4.91,
+      "eval_loss": 2.265625,
+      "eval_runtime": 1.934,
+      "eval_samples_per_second": 5.688,
+      "eval_steps_per_second": 0.517,
+      "step": 27
+    },
+    {
+      "epoch": 5.45,
+      "grad_norm": 0.8265868923051504,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 1.2434,
+      "step": 30
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.34375,
+      "eval_runtime": 2.0742,
+      "eval_samples_per_second": 5.303,
+      "eval_steps_per_second": 0.482,
+      "step": 33
+    },
+    {
+      "epoch": 6.36,
+      "grad_norm": 0.7945639183231874,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 1.1083,
+      "step": 35
+    },
+    {
+      "epoch": 6.91,
+      "eval_loss": 2.3551137447357178,
+      "eval_runtime": 1.9306,
+      "eval_samples_per_second": 5.698,
+      "eval_steps_per_second": 0.518,
+      "step": 38
+    },
+    {
+      "epoch": 7.27,
+      "grad_norm": 0.5788791207539581,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 1.0215,
+      "step": 40
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.4332387447357178,
+      "eval_runtime": 2.0639,
+      "eval_samples_per_second": 5.33,
+      "eval_steps_per_second": 0.485,
+      "step": 44
+    },
+    {
+      "epoch": 8.18,
+      "grad_norm": 0.515743831937742,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.9556,
+      "step": 45
+    },
+    {
+      "epoch": 8.91,
+      "eval_loss": 2.4332387447357178,
+      "eval_runtime": 1.9298,
+      "eval_samples_per_second": 5.7,
+      "eval_steps_per_second": 0.518,
+      "step": 49
+    },
+    {
+      "epoch": 9.09,
+      "grad_norm": 0.5703656649999668,
+      "learning_rate": 0.0,
+      "loss": 0.9465,
+      "step": 50
+    },
+    {
+      "epoch": 9.09,
+      "eval_loss": 2.4275567531585693,
+      "eval_runtime": 2.0663,
+      "eval_samples_per_second": 5.324,
+      "eval_steps_per_second": 0.484,
+      "step": 50
+    },
+    {
+      "epoch": 9.09,
+      "step": 50,
+      "total_flos": 11674778075136.0,
+      "train_loss": 1.39877197265625,
+      "train_runtime": 578.7401,
+      "train_samples_per_second": 11.629,
+      "train_steps_per_second": 0.086
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 1000000000,
+  "total_flos": 11674778075136.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59be15529ce960f6eb9ef4346694550467d1c0f2e89d1eb6e49e7e595b8dcbf
+size 6072