init model

README.md

@@ -1,3 +1,86 @@
 ---
-license: cc-by-nc-4.0
+tags:
+- generated_from_trainer
+datasets:
+- BramVanroy/alpaca-dolly-dutch
+model-index:
+- name: 1e-3lr+512tbs@4n4gpus80
+  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. -->
+
+# 1e-3lr+512tbs@4n4gpus80
+
+This model is a fine-tuned version of [ybelkada/falcon-7b-sharded-bf16](https://huggingface.co/ybelkada/falcon-7b-sharded-bf16) on the BramVanroy/alpaca-dolly-dutch dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2612
+
+## 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: 0.001
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- total_train_batch_size: 512
+- total_eval_batch_size: 512
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.8677        | 0.16  | 20   | 1.6766          |
+| 1.5635        | 0.32  | 40   | 1.5643          |
+| 1.6353        | 0.48  | 60   | 1.4980          |
+| 1.5166        | 0.65  | 80   | 1.4516          |
+| 1.4287        | 0.81  | 100  | 1.4096          |
+| 1.5791        | 0.97  | 120  | 1.3802          |
+| 1.3911        | 1.13  | 140  | 1.3633          |
+| 1.356         | 1.29  | 160  | 1.3419          |
+| 1.2524        | 1.45  | 180  | 1.3263          |
+| 1.4224        | 1.61  | 200  | 1.3056          |
+| 1.2266        | 1.77  | 220  | 1.2897          |
+| 1.3242        | 1.94  | 240  | 1.2785          |
+| 1.03          | 2.1   | 260  | 1.2957          |
+| 1.1643        | 2.26  | 280  | 1.2970          |
+| 1.1492        | 2.42  | 300  | 1.2779          |
+| 1.0679        | 2.58  | 320  | 1.2770          |
+| 1.2695        | 2.74  | 340  | 1.2658          |
+| 1.0439        | 2.9   | 360  | 1.2612          |
+| 0.9453        | 3.06  | 380  | 1.3157          |
+| 0.8494        | 3.23  | 400  | 1.3189          |
+| 1.0745        | 3.39  | 420  | 1.3073          |
+| 0.8679        | 3.55  | 440  | 1.3019          |
+| 1.0569        | 3.71  | 460  | 1.2955          |
+| 1.0186        | 3.87  | 480  | 1.2890          |
+| 0.8413        | 4.03  | 500  | 1.3445          |
+
+
+### Framework versions
+
+- Transformers 4.30.1
+- Pytorch 2.0.1+cu117
+- Datasets 2.13.1
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.03,
+    "eval_loss": 1.2611794471740723,
+    "eval_runtime": 25.4151,
+    "eval_samples": 3332,
+    "eval_samples_per_second": 131.103,
+    "eval_steps_per_second": 0.275,
+    "perplexity": 3.5295819888396176,
+    "train_loss": 1.25592919921875,
+    "train_runtime": 8163.1704,
+    "train_samples": 63101,
+    "train_samples_per_second": 154.599,
+    "train_steps_per_second": 0.304
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "RWForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-7b--configuration_RW.RWConfig",
+    "AutoModel": "tiiuae/falcon-7b--modelling_RW.RWModel",
+    "AutoModelForCausalLM": "tiiuae/falcon-7b--modelling_RW.RWForCausalLM",
+    "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modelling_RW.RWForQuestionAnswering",
+    "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modelling_RW.RWForSequenceClassification",
+    "AutoModelForTokenClassification": "tiiuae/falcon-7b--modelling_RW.RWForTokenClassification"
+  },
+  "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,
+  "model_type": "RefinedWebModel",
+  "multi_query": true,
+  "n_head": 71,
+  "n_layer": 32,
+  "parallel_attn": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.30.1",
+  "use_cache": true,
+  "vocab_size": 65024
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.03,
+    "eval_loss": 1.2611794471740723,
+    "eval_runtime": 25.4151,
+    "eval_samples": 3332,
+    "eval_samples_per_second": 131.103,
+    "eval_steps_per_second": 0.275,
+    "perplexity": 3.5295819888396176
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.30.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4e3738b284ef25022b8e199f3679c551c395d23dc7f2b12cbf0f6454bdccc05
+size 9950994832

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72f95161dc905c3ca4814d3bc158aea416daeba422ff52087251d89d3688c0ef
+size 3892469920

model.safetensors.index.json

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

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,7 @@
+{
+  "add_prefix_space": false,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.03,
+    "train_loss": 1.25592919921875,
+    "train_runtime": 8163.1704,
+    "train_samples": 63101,
+    "train_samples_per_second": 154.599,
+    "train_steps_per_second": 0.304
+}

trainer_state.json

@@ -0,0 +1,3225 @@
+{
+  "best_metric": 1.2611794471740723,
+  "best_model_checkpoint": "/dodrio/scratch/projects/2023_005/llm-finetuning/instruct-tuning/results/falcon-7b-ft-alpaca-dolly-dutch/1e-3lr+512tbs@4n4gpus80/checkpoint-360",
+  "epoch": 4.032258064516129,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0,
+      "loss": 2.188,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016054408543402142,
+      "loss": 1.9531,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00025445635512549755,
+      "loss": 1.9692,
+      "step": 3
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00032108817086804283,
+      "loss": 1.9897,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00037277182243725126,
+      "loss": 2.0171,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.000415000440559519,
+      "loss": 1.8857,
+      "step": 6
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00045070422845043653,
+      "loss": 2.022,
+      "step": 7
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0004816322563020642,
+      "loss": 1.8857,
+      "step": 8
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0005089127102509951,
+      "loss": 1.8364,
+      "step": 9
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0005333159078712729,
+      "loss": 1.9458,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0005553912853356613,
+      "loss": 1.8647,
+      "step": 11
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0005755445259935404,
+      "loss": 1.7886,
+      "step": 12
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0005940837102526897,
+      "loss": 1.813,
+      "step": 13
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0006112483138844579,
+      "loss": 1.8379,
+      "step": 14
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0006272281775627489,
+      "loss": 1.7515,
+      "step": 15
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0006421763417360857,
+      "loss": 1.8223,
+      "step": 16
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0006562179835940824,
+      "loss": 1.8599,
+      "step": 17
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0006694567956850165,
+      "loss": 1.6924,
+      "step": 18
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0006819796376358172,
+      "loss": 1.7749,
+      "step": 19
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0006938599933052941,
+      "loss": 1.8677,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 1.676583170890808,
+      "eval_runtime": 24.1848,
+      "eval_samples_per_second": 137.773,
+      "eval_steps_per_second": 0.289,
+      "step": 20
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000705160583575934,
+      "loss": 1.7212,
+      "step": 21
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0007159353707696828,
+      "loss": 1.707,
+      "step": 22
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0007262311171393061,
+      "loss": 1.8433,
+      "step": 23
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0007360886114275618,
+      "loss": 1.6592,
+      "step": 24
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0007455436448745025,
+      "loss": 1.6602,
+      "step": 25
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0007546277956867112,
+      "loss": 1.8247,
+      "step": 26
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0007633690653764926,
+      "loss": 1.6953,
+      "step": 27
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0007717923993184793,
+      "loss": 1.6763,
+      "step": 28
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0007799201159186134,
+      "loss": 1.8345,
+      "step": 29
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0007877722629967703,
+      "loss": 1.6792,
+      "step": 30
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0007953669157116642,
+      "loss": 1.6304,
+      "step": 31
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.000802720427170107,
+      "loss": 1.7705,
+      "step": 32
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0008098476404611588,
+      "loss": 1.7578,
+      "step": 33
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0008167620690281039,
+      "loss": 1.5894,
+      "step": 34
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0008234760508876878,
+      "loss": 1.7002,
+      "step": 35
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.000830000881119038,
+      "loss": 1.7217,
+      "step": 36
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0008363469261960845,
+      "loss": 1.5684,
+      "step": 37
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0008425237230698386,
+      "loss": 1.7104,
+      "step": 38
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0008485400653781872,
+      "loss": 1.6812,
+      "step": 39
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0008544040787393155,
+      "loss": 1.5635,
+      "step": 40
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 1.564281940460205,
+      "eval_runtime": 24.7371,
+      "eval_samples_per_second": 134.697,
+      "eval_steps_per_second": 0.283,
+      "step": 40
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0008601232867466185,
+      "loss": 1.6558,
+      "step": 41
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0008657046690099555,
+      "loss": 1.7666,
+      "step": 42
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0008711547123665129,
+      "loss": 1.5806,
+      "step": 43
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.000876479456203704,
+      "loss": 1.6216,
+      "step": 44
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0008816845326882464,
+      "loss": 1.708,
+      "step": 45
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0008867752025733276,
+      "loss": 1.564,
+      "step": 46
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0008917563871545975,
+      "loss": 1.5454,
+      "step": 47
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0008966326968615833,
+      "loss": 1.7354,
+      "step": 48
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0009014084569008731,
+      "loss": 1.6152,
+      "step": 49
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.000906087730308524,
+      "loss": 1.5288,
+      "step": 50
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0009106743387195799,
+      "loss": 1.7051,
+      "step": 51
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0009151718811207326,
+      "loss": 1.5562,
+      "step": 52
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0009195837508166731,
+      "loss": 1.5249,
+      "step": 53
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0009239131508105141,
+      "loss": 1.6948,
+      "step": 54
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0009281631077729125,
+      "loss": 1.6055,
+      "step": 55
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0009323364847525009,
+      "loss": 1.5146,
+      "step": 56
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0009364359927613148,
+      "loss": 1.5801,
+      "step": 57
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0009404642013526347,
+      "loss": 1.624,
+      "step": 58
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0009444235482945997,
+      "loss": 1.4819,
+      "step": 59
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0009483163484307916,
+      "loss": 1.6353,
+      "step": 60
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 1.4979554414749146,
+      "eval_runtime": 24.0342,
+      "eval_samples_per_second": 138.636,
+      "eval_steps_per_second": 0.291,
+      "step": 60
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0009521448018084367,
+      "loss": 1.645,
+      "step": 61
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0009559110011456856,
+      "loss": 1.4971,
+      "step": 62
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0009596169387014316,
+      "loss": 1.5503,
+      "step": 63
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0009632645126041284,
+      "loss": 1.7114,
+      "step": 64
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0009668555326899408,
+      "loss": 1.5264,
+      "step": 65
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0009703917258951801,
+      "loss": 1.6533,
+      "step": 66
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0009738747412432464,
+      "loss": 1.5928,
+      "step": 67
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0009773061544621254,
+      "loss": 1.501,
+      "step": 68
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0009806874722648037,
+      "loss": 1.543,
+      "step": 69
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0009840201363217093,
+      "loss": 1.7285,
+      "step": 70
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0009873055269513868,
+      "loss": 1.5205,
+      "step": 71
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0009905449665530593,
+      "loss": 1.5073,
+      "step": 72
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0009937397228024375,
+      "loss": 1.5635,
+      "step": 73
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0009968910116301061,
+      "loss": 1.4424,
+      "step": 74
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.001,
+      "loss": 1.498,
+      "step": 75
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.001,
+      "loss": 1.7285,
+      "step": 76
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.001,
+      "loss": 1.5024,
+      "step": 77
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.001,
+      "loss": 1.4243,
+      "step": 78
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.001,
+      "loss": 1.6143,
+      "step": 79
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.001,
+      "loss": 1.5166,
+      "step": 80
+    },
+    {
+      "epoch": 0.65,
+      "eval_loss": 1.4516056776046753,
+      "eval_runtime": 24.3249,
+      "eval_samples_per_second": 136.979,
+      "eval_steps_per_second": 0.288,
+      "step": 80
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.001,
+      "loss": 1.417,
+      "step": 81
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.001,
+      "loss": 1.604,
+      "step": 82
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.001,
+      "loss": 1.5,
+      "step": 83
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.001,
+      "loss": 1.4702,
+      "step": 84
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.001,
+      "loss": 1.6206,
+      "step": 85
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.001,
+      "loss": 1.5986,
+      "step": 86
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.001,
+      "loss": 1.4194,
+      "step": 87
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.001,
+      "loss": 1.5752,
+      "step": 88
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.001,
+      "loss": 1.5435,
+      "step": 89
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.001,
+      "loss": 1.4448,
+      "step": 90
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.001,
+      "loss": 1.5337,
+      "step": 91
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.001,
+      "loss": 1.5547,
+      "step": 92
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.001,
+      "loss": 1.4829,
+      "step": 93
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.001,
+      "loss": 1.4834,
+      "step": 94
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.001,
+      "loss": 1.561,
+      "step": 95
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.001,
+      "loss": 1.4536,
+      "step": 96
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.001,
+      "loss": 1.5151,
+      "step": 97
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.001,
+      "loss": 1.7051,
+      "step": 98
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.001,
+      "loss": 1.4521,
+      "step": 99
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.001,
+      "loss": 1.4287,
+      "step": 100
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 1.4096169471740723,
+      "eval_runtime": 26.3405,
+      "eval_samples_per_second": 126.497,
+      "eval_steps_per_second": 0.266,
+      "step": 100
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.001,
+      "loss": 1.6558,
+      "step": 101
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.001,
+      "loss": 1.4482,
+      "step": 102
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.001,
+      "loss": 1.4409,
+      "step": 103
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.001,
+      "loss": 1.5991,
+      "step": 104
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.001,
+      "loss": 1.5435,
+      "step": 105
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.001,
+      "loss": 1.3647,
+      "step": 106
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.001,
+      "loss": 1.5928,
+      "step": 107
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.001,
+      "loss": 1.5244,
+      "step": 108
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.001,
+      "loss": 1.4141,
+      "step": 109
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.001,
+      "loss": 1.4819,
+      "step": 110
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.001,
+      "loss": 1.4995,
+      "step": 111
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.001,
+      "loss": 1.3999,
+      "step": 112
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.001,
+      "loss": 1.4883,
+      "step": 113
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.001,
+      "loss": 1.5132,
+      "step": 114
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.001,
+      "loss": 1.3804,
+      "step": 115
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.001,
+      "loss": 1.4854,
+      "step": 116
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.001,
+      "loss": 1.5962,
+      "step": 117
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.001,
+      "loss": 1.394,
+      "step": 118
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.001,
+      "loss": 1.4629,
+      "step": 119
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.001,
+      "loss": 1.5791,
+      "step": 120
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 1.3802427053451538,
+      "eval_runtime": 24.4976,
+      "eval_samples_per_second": 136.014,
+      "eval_steps_per_second": 0.286,
+      "step": 120
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.001,
+      "loss": 1.3711,
+      "step": 121
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.001,
+      "loss": 1.3843,
+      "step": 122
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.001,
+      "loss": 1.5171,
+      "step": 123
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.001,
+      "loss": 1.4922,
+      "step": 124
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.001,
+      "loss": 1.5166,
+      "step": 125
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.001,
+      "loss": 1.3613,
+      "step": 126
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.001,
+      "loss": 1.3135,
+      "step": 127
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.001,
+      "loss": 1.437,
+      "step": 128
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.001,
+      "loss": 1.4111,
+      "step": 129
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.001,
+      "loss": 1.2817,
+      "step": 130
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.001,
+      "loss": 1.4141,
+      "step": 131
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.001,
+      "loss": 1.5527,
+      "step": 132
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.001,
+      "loss": 1.2939,
+      "step": 133
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.001,
+      "loss": 1.3945,
+      "step": 134
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.001,
+      "loss": 1.4224,
+      "step": 135
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.001,
+      "loss": 1.3032,
+      "step": 136
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.001,
+      "loss": 1.4395,
+      "step": 137
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.001,
+      "loss": 1.3862,
+      "step": 138
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.001,
+      "loss": 1.2554,
+      "step": 139
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.001,
+      "loss": 1.3911,
+      "step": 140
+    },
+    {
+      "epoch": 1.13,
+      "eval_loss": 1.3633328676223755,
+      "eval_runtime": 24.0035,
+      "eval_samples_per_second": 138.813,
+      "eval_steps_per_second": 0.292,
+      "step": 140
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.001,
+      "loss": 1.4424,
+      "step": 141
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.001,
+      "loss": 1.2134,
+      "step": 142
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.001,
+      "loss": 1.3359,
+      "step": 143
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.001,
+      "loss": 1.4165,
+      "step": 144
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.001,
+      "loss": 1.2524,
+      "step": 145
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.001,
+      "loss": 1.3276,
+      "step": 146
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.001,
+      "loss": 1.4663,
+      "step": 147
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.001,
+      "loss": 1.2729,
+      "step": 148
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.001,
+      "loss": 1.2524,
+      "step": 149
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.001,
+      "loss": 1.4224,
+      "step": 150
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.001,
+      "loss": 1.3154,
+      "step": 151
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.001,
+      "loss": 1.2686,
+      "step": 152
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.001,
+      "loss": 1.4751,
+      "step": 153
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.001,
+      "loss": 1.3906,
+      "step": 154
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.001,
+      "loss": 1.2861,
+      "step": 155
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.001,
+      "loss": 1.4839,
+      "step": 156
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.001,
+      "loss": 1.356,
+      "step": 157
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.001,
+      "loss": 1.2783,
+      "step": 158
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.001,
+      "loss": 1.4194,
+      "step": 159
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.001,
+      "loss": 1.356,
+      "step": 160
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 1.341939926147461,
+      "eval_runtime": 23.8746,
+      "eval_samples_per_second": 139.562,
+      "eval_steps_per_second": 0.293,
+      "step": 160
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.001,
+      "loss": 1.2544,
+      "step": 161
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.001,
+      "loss": 1.3643,
+      "step": 162
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.001,
+      "loss": 1.4229,
+      "step": 163
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.001,
+      "loss": 1.2627,
+      "step": 164
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.001,
+      "loss": 1.3892,
+      "step": 165
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.001,
+      "loss": 1.5151,
+      "step": 166
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.001,
+      "loss": 1.2168,
+      "step": 167
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.001,
+      "loss": 1.3306,
+      "step": 168
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.001,
+      "loss": 1.4424,
+      "step": 169
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.001,
+      "loss": 1.2183,
+      "step": 170
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.001,
+      "loss": 1.2798,
+      "step": 171
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.001,
+      "loss": 1.5454,
+      "step": 172
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.001,
+      "loss": 1.2725,
+      "step": 173
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.001,
+      "loss": 1.2222,
+      "step": 174
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.001,
+      "loss": 1.3862,
+      "step": 175
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.001,
+      "loss": 1.2637,
+      "step": 176
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.001,
+      "loss": 1.2256,
+      "step": 177
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.001,
+      "loss": 1.439,
+      "step": 178
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.001,
+      "loss": 1.2974,
+      "step": 179
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.001,
+      "loss": 1.2524,
+      "step": 180
+    },
+    {
+      "epoch": 1.45,
+      "eval_loss": 1.326296091079712,
+      "eval_runtime": 23.9696,
+      "eval_samples_per_second": 139.009,
+      "eval_steps_per_second": 0.292,
+      "step": 180
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.001,
+      "loss": 1.3242,
+      "step": 181
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.001,
+      "loss": 1.3345,
+      "step": 182
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.001,
+      "loss": 1.2563,
+      "step": 183
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.001,
+      "loss": 1.4194,
+      "step": 184
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.001,
+      "loss": 1.3213,
+      "step": 185
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.001,
+      "loss": 1.2412,
+      "step": 186
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.001,
+      "loss": 1.3003,
+      "step": 187
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.001,
+      "loss": 1.3892,
+      "step": 188
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.001,
+      "loss": 1.2295,
+      "step": 189
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.001,
+      "loss": 1.27,
+      "step": 190
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.001,
+      "loss": 1.3984,
+      "step": 191
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.001,
+      "loss": 1.2236,
+      "step": 192
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.001,
+      "loss": 1.3335,
+      "step": 193
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.001,
+      "loss": 1.3965,
+      "step": 194
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.001,
+      "loss": 1.2295,
+      "step": 195
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.001,
+      "loss": 1.2939,
+      "step": 196
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.001,
+      "loss": 1.3872,
+      "step": 197
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.001,
+      "loss": 1.2891,
+      "step": 198
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.001,
+      "loss": 1.2827,
+      "step": 199
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.001,
+      "loss": 1.4224,
+      "step": 200
+    },
+    {
+      "epoch": 1.61,
+      "eval_loss": 1.305644154548645,
+      "eval_runtime": 23.9951,
+      "eval_samples_per_second": 138.862,
+      "eval_steps_per_second": 0.292,
+      "step": 200
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.001,
+      "loss": 1.2891,
+      "step": 201
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.001,
+      "loss": 1.2495,
+      "step": 202
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.001,
+      "loss": 1.4082,
+      "step": 203
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.001,
+      "loss": 1.3306,
+      "step": 204
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.001,
+      "loss": 1.248,
+      "step": 205
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.001,
+      "loss": 1.3462,
+      "step": 206
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.001,
+      "loss": 1.3633,
+      "step": 207
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.001,
+      "loss": 1.2339,
+      "step": 208
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.001,
+      "loss": 1.4131,
+      "step": 209
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.001,
+      "loss": 1.4395,
+      "step": 210
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.001,
+      "loss": 1.1953,
+      "step": 211
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.001,
+      "loss": 1.3569,
+      "step": 212
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.001,
+      "loss": 1.3804,
+      "step": 213
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.001,
+      "loss": 1.2354,
+      "step": 214
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.001,
+      "loss": 1.2998,
+      "step": 215
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.001,
+      "loss": 1.4072,
+      "step": 216
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.001,
+      "loss": 1.2261,
+      "step": 217
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.001,
+      "loss": 1.2988,
+      "step": 218
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.001,
+      "loss": 1.4756,
+      "step": 219
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.001,
+      "loss": 1.2266,
+      "step": 220
+    },
+    {
+      "epoch": 1.77,
+      "eval_loss": 1.2897284030914307,
+      "eval_runtime": 23.6772,
+      "eval_samples_per_second": 140.726,
+      "eval_steps_per_second": 0.296,
+      "step": 220
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.001,
+      "loss": 1.3101,
+      "step": 221
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.001,
+      "loss": 1.4614,
+      "step": 222
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.001,
+      "loss": 1.2827,
+      "step": 223
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.001,
+      "loss": 1.2476,
+      "step": 224
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.001,
+      "loss": 1.3916,
+      "step": 225
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.001,
+      "loss": 1.2935,
+      "step": 226
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.001,
+      "loss": 1.2173,
+      "step": 227
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.001,
+      "loss": 1.3789,
+      "step": 228
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.001,
+      "loss": 1.2949,
+      "step": 229
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.001,
+      "loss": 1.2227,
+      "step": 230
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.001,
+      "loss": 1.3623,
+      "step": 231
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.001,
+      "loss": 1.3252,
+      "step": 232
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.001,
+      "loss": 1.249,
+      "step": 233
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.001,
+      "loss": 1.3735,
+      "step": 234
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.001,
+      "loss": 1.3267,
+      "step": 235
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.001,
+      "loss": 1.2441,
+      "step": 236
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.001,
+      "loss": 1.2886,
+      "step": 237
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.001,
+      "loss": 1.3623,
+      "step": 238
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.001,
+      "loss": 1.2324,
+      "step": 239
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.001,
+      "loss": 1.3242,
+      "step": 240
+    },
+    {
+      "epoch": 1.94,
+      "eval_loss": 1.278455138206482,
+      "eval_runtime": 23.9196,
+      "eval_samples_per_second": 139.3,
+      "eval_steps_per_second": 0.293,
+      "step": 240
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.001,
+      "loss": 1.4194,
+      "step": 241
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.001,
+      "loss": 1.2461,
+      "step": 242
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.001,
+      "loss": 1.2886,
+      "step": 243
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.001,
+      "loss": 1.4292,
+      "step": 244
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.001,
+      "loss": 1.2231,
+      "step": 245
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.001,
+      "loss": 1.2627,
+      "step": 246
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.001,
+      "loss": 1.3315,
+      "step": 247
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.001,
+      "loss": 1.1792,
+      "step": 248
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.001,
+      "loss": 1.2563,
+      "step": 249
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.001,
+      "loss": 1.051,
+      "step": 250
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 0.001,
+      "loss": 1.052,
+      "step": 251
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.001,
+      "loss": 1.1621,
+      "step": 252
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.001,
+      "loss": 1.188,
+      "step": 253
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 0.001,
+      "loss": 1.0442,
+      "step": 254
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.001,
+      "loss": 1.2251,
+      "step": 255
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.001,
+      "loss": 1.1899,
+      "step": 256
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 0.001,
+      "loss": 1.0444,
+      "step": 257
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 0.001,
+      "loss": 1.1858,
+      "step": 258
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.001,
+      "loss": 1.1958,
+      "step": 259
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 0.001,
+      "loss": 1.03,
+      "step": 260
+    },
+    {
+      "epoch": 2.1,
+      "eval_loss": 1.295693278312683,
+      "eval_runtime": 23.7743,
+      "eval_samples_per_second": 140.151,
+      "eval_steps_per_second": 0.294,
+      "step": 260
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 0.001,
+      "loss": 1.144,
+      "step": 261
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.001,
+      "loss": 1.2034,
+      "step": 262
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 0.001,
+      "loss": 1.0547,
+      "step": 263
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.001,
+      "loss": 1.0669,
+      "step": 264
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 0.001,
+      "loss": 1.1838,
+      "step": 265
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 0.001,
+      "loss": 1.0349,
+      "step": 266
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 0.001,
+      "loss": 1.1018,
+      "step": 267
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 0.001,
+      "loss": 1.2759,
+      "step": 268
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 0.001,
+      "loss": 1.0559,
+      "step": 269
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 0.001,
+      "loss": 1.0703,
+      "step": 270
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.001,
+      "loss": 1.2087,
+      "step": 271
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.001,
+      "loss": 1.0957,
+      "step": 272
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 0.001,
+      "loss": 1.0356,
+      "step": 273
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 0.001,
+      "loss": 1.2476,
+      "step": 274
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.001,
+      "loss": 1.0591,
+      "step": 275
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 0.001,
+      "loss": 1.0166,
+      "step": 276
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 0.001,
+      "loss": 1.2988,
+      "step": 277
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 0.001,
+      "loss": 1.1099,
+      "step": 278
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 0.001,
+      "loss": 1.033,
+      "step": 279
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.001,
+      "loss": 1.1643,
+      "step": 280
+    },
+    {
+      "epoch": 2.26,
+      "eval_loss": 1.29701566696167,
+      "eval_runtime": 24.0606,
+      "eval_samples_per_second": 138.484,
+      "eval_steps_per_second": 0.291,
+      "step": 280
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.001,
+      "loss": 1.123,
+      "step": 281
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 0.001,
+      "loss": 1.0576,
+      "step": 282
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 0.001,
+      "loss": 1.2297,
+      "step": 283
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 0.001,
+      "loss": 1.2073,
+      "step": 284
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 0.001,
+      "loss": 1.0713,
+      "step": 285
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.001,
+      "loss": 1.1284,
+      "step": 286
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.001,
+      "loss": 1.1682,
+      "step": 287
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 0.001,
+      "loss": 1.019,
+      "step": 288
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 0.001,
+      "loss": 1.1343,
+      "step": 289
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 0.001,
+      "loss": 1.2163,
+      "step": 290
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 0.001,
+      "loss": 1.033,
+      "step": 291
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 0.001,
+      "loss": 1.082,
+      "step": 292
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 0.001,
+      "loss": 1.3159,
+      "step": 293
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 0.001,
+      "loss": 0.9993,
+      "step": 294
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 0.001,
+      "loss": 1.1074,
+      "step": 295
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 0.001,
+      "loss": 1.2188,
+      "step": 296
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.001,
+      "loss": 1.0862,
+      "step": 297
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.001,
+      "loss": 1.0276,
+      "step": 298
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 0.001,
+      "loss": 1.1821,
+      "step": 299
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 0.001,
+      "loss": 1.1492,
+      "step": 300
+    },
+    {
+      "epoch": 2.42,
+      "eval_loss": 1.2779204845428467,
+      "eval_runtime": 24.1558,
+      "eval_samples_per_second": 137.938,
+      "eval_steps_per_second": 0.29,
+      "step": 300
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 0.001,
+      "loss": 1.0618,
+      "step": 301
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 0.001,
+      "loss": 1.25,
+      "step": 302
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 0.001,
+      "loss": 1.1101,
+      "step": 303
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 0.001,
+      "loss": 1.073,
+      "step": 304
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 0.001,
+      "loss": 1.2202,
+      "step": 305
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 0.001,
+      "loss": 1.1765,
+      "step": 306
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 0.001,
+      "loss": 1.0349,
+      "step": 307
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 0.001,
+      "loss": 1.1387,
+      "step": 308
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 0.001,
+      "loss": 1.1799,
+      "step": 309
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 0.001,
+      "loss": 1.062,
+      "step": 310
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 0.001,
+      "loss": 1.0908,
+      "step": 311
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 0.001,
+      "loss": 1.21,
+      "step": 312
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 0.001,
+      "loss": 1.0945,
+      "step": 313
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.001,
+      "loss": 1.1582,
+      "step": 314
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 0.001,
+      "loss": 1.1777,
+      "step": 315
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 0.001,
+      "loss": 1.0696,
+      "step": 316
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 0.001,
+      "loss": 1.1179,
+      "step": 317
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 0.001,
+      "loss": 1.2627,
+      "step": 318
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 0.001,
+      "loss": 1.0361,
+      "step": 319
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 0.001,
+      "loss": 1.0679,
+      "step": 320
+    },
+    {
+      "epoch": 2.58,
+      "eval_loss": 1.2769920825958252,
+      "eval_runtime": 23.8067,
+      "eval_samples_per_second": 139.961,
+      "eval_steps_per_second": 0.294,
+      "step": 320
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 0.001,
+      "loss": 1.2393,
+      "step": 321
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 0.001,
+      "loss": 1.0154,
+      "step": 322
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 0.001,
+      "loss": 1.0388,
+      "step": 323
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 0.001,
+      "loss": 1.2422,
+      "step": 324
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 0.001,
+      "loss": 1.0452,
+      "step": 325
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 0.001,
+      "loss": 1.0669,
+      "step": 326
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 0.001,
+      "loss": 1.2607,
+      "step": 327
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 0.001,
+      "loss": 1.1753,
+      "step": 328
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 0.001,
+      "loss": 1.075,
+      "step": 329
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 0.001,
+      "loss": 1.2183,
+      "step": 330
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.001,
+      "loss": 1.1465,
+      "step": 331
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 0.001,
+      "loss": 1.0376,
+      "step": 332
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 0.001,
+      "loss": 1.2236,
+      "step": 333
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 0.001,
+      "loss": 1.2019,
+      "step": 334
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 0.001,
+      "loss": 1.032,
+      "step": 335
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 0.001,
+      "loss": 1.1501,
+      "step": 336
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 0.001,
+      "loss": 1.2266,
+      "step": 337
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 0.001,
+      "loss": 1.0776,
+      "step": 338
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 0.001,
+      "loss": 1.1018,
+      "step": 339
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 0.001,
+      "loss": 1.2695,
+      "step": 340
+    },
+    {
+      "epoch": 2.74,
+      "eval_loss": 1.2657562494277954,
+      "eval_runtime": 27.5245,
+      "eval_samples_per_second": 121.056,
+      "eval_steps_per_second": 0.254,
+      "step": 340
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 0.001,
+      "loss": 1.0842,
+      "step": 341
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 0.001,
+      "loss": 1.1338,
+      "step": 342
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 0.001,
+      "loss": 1.1943,
+      "step": 343
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 0.001,
+      "loss": 1.064,
+      "step": 344
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 0.001,
+      "loss": 1.1348,
+      "step": 345
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 0.001,
+      "loss": 1.2854,
+      "step": 346
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.001,
+      "loss": 1.0405,
+      "step": 347
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 0.001,
+      "loss": 1.0881,
+      "step": 348
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 0.001,
+      "loss": 1.2676,
+      "step": 349
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 0.001,
+      "loss": 1.1062,
+      "step": 350
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 0.001,
+      "loss": 1.0374,
+      "step": 351
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 0.001,
+      "loss": 1.303,
+      "step": 352
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 0.001,
+      "loss": 1.1091,
+      "step": 353
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 0.001,
+      "loss": 1.0615,
+      "step": 354
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 0.001,
+      "loss": 1.2202,
+      "step": 355
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 0.001,
+      "loss": 1.1516,
+      "step": 356
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 0.001,
+      "loss": 1.0771,
+      "step": 357
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 0.001,
+      "loss": 1.2385,
+      "step": 358
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 0.001,
+      "loss": 1.177,
+      "step": 359
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 0.001,
+      "loss": 1.0439,
+      "step": 360
+    },
+    {
+      "epoch": 2.9,
+      "eval_loss": 1.2611794471740723,
+      "eval_runtime": 24.1764,
+      "eval_samples_per_second": 137.82,
+      "eval_steps_per_second": 0.29,
+      "step": 360
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 0.001,
+      "loss": 1.1562,
+      "step": 361
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 0.001,
+      "loss": 1.1904,
+      "step": 362
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.001,
+      "loss": 1.0874,
+      "step": 363
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 0.001,
+      "loss": 1.1545,
+      "step": 364
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 0.001,
+      "loss": 1.1794,
+      "step": 365
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 0.001,
+      "loss": 1.0461,
+      "step": 366
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 0.001,
+      "loss": 1.113,
+      "step": 367
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 0.001,
+      "loss": 1.2446,
+      "step": 368
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 0.001,
+      "loss": 1.114,
+      "step": 369
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 0.001,
+      "loss": 1.1172,
+      "step": 370
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 0.001,
+      "loss": 1.1323,
+      "step": 371
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.001,
+      "loss": 1.0107,
+      "step": 372
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 0.001,
+      "loss": 1.0625,
+      "step": 373
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.001,
+      "loss": 0.9075,
+      "step": 374
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.001,
+      "loss": 0.8528,
+      "step": 375
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 0.001,
+      "loss": 1.0195,
+      "step": 376
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 0.001,
+      "loss": 0.9307,
+      "step": 377
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 0.001,
+      "loss": 0.8521,
+      "step": 378
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 0.001,
+      "loss": 0.95,
+      "step": 379
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 0.001,
+      "loss": 0.9453,
+      "step": 380
+    },
+    {
+      "epoch": 3.06,
+      "eval_loss": 1.3157168626785278,
+      "eval_runtime": 23.9413,
+      "eval_samples_per_second": 139.173,
+      "eval_steps_per_second": 0.292,
+      "step": 380
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 0.001,
+      "loss": 0.8691,
+      "step": 381
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 0.001,
+      "loss": 0.9417,
+      "step": 382
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 0.001,
+      "loss": 0.96,
+      "step": 383
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 0.001,
+      "loss": 0.8535,
+      "step": 384
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 0.001,
+      "loss": 0.9141,
+      "step": 385
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 0.001,
+      "loss": 0.9688,
+      "step": 386
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 0.001,
+      "loss": 0.8442,
+      "step": 387
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 0.001,
+      "loss": 0.9053,
+      "step": 388
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 0.001,
+      "loss": 0.9668,
+      "step": 389
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 0.001,
+      "loss": 0.8594,
+      "step": 390
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 0.001,
+      "loss": 0.8752,
+      "step": 391
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 0.001,
+      "loss": 1.0249,
+      "step": 392
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 0.001,
+      "loss": 0.8672,
+      "step": 393
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 0.001,
+      "loss": 0.8552,
+      "step": 394
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 0.001,
+      "loss": 1.0466,
+      "step": 395
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 0.001,
+      "loss": 0.896,
+      "step": 396
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 0.001,
+      "loss": 0.8523,
+      "step": 397
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 0.001,
+      "loss": 1.0496,
+      "step": 398
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 0.001,
+      "loss": 0.887,
+      "step": 399
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 0.001,
+      "loss": 0.8494,
+      "step": 400
+    },
+    {
+      "epoch": 3.23,
+      "eval_loss": 1.3189338445663452,
+      "eval_runtime": 24.0968,
+      "eval_samples_per_second": 138.275,
+      "eval_steps_per_second": 0.29,
+      "step": 400
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 0.001,
+      "loss": 0.9949,
+      "step": 401
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 0.001,
+      "loss": 0.9177,
+      "step": 402
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 0.001,
+      "loss": 0.8572,
+      "step": 403
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 0.001,
+      "loss": 1.0159,
+      "step": 404
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 0.001,
+      "loss": 0.9636,
+      "step": 405
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 0.001,
+      "loss": 0.8542,
+      "step": 406
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 0.001,
+      "loss": 0.9805,
+      "step": 407
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 0.001,
+      "loss": 1.0212,
+      "step": 408
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 0.001,
+      "loss": 0.8584,
+      "step": 409
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 0.001,
+      "loss": 1.0181,
+      "step": 410
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 0.001,
+      "loss": 1.0093,
+      "step": 411
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 0.001,
+      "loss": 0.8245,
+      "step": 412
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 0.001,
+      "loss": 0.9023,
+      "step": 413
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 0.001,
+      "loss": 1.0261,
+      "step": 414
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 0.001,
+      "loss": 0.8452,
+      "step": 415
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 0.001,
+      "loss": 0.9272,
+      "step": 416
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 0.001,
+      "loss": 1.0024,
+      "step": 417
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 0.001,
+      "loss": 0.8479,
+      "step": 418
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 0.001,
+      "loss": 0.8906,
+      "step": 419
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 0.001,
+      "loss": 1.0745,
+      "step": 420
+    },
+    {
+      "epoch": 3.39,
+      "eval_loss": 1.3072948455810547,
+      "eval_runtime": 23.9409,
+      "eval_samples_per_second": 139.176,
+      "eval_steps_per_second": 0.292,
+      "step": 420
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 0.001,
+      "loss": 0.887,
+      "step": 421
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 0.001,
+      "loss": 0.8589,
+      "step": 422
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 0.001,
+      "loss": 1.012,
+      "step": 423
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 0.001,
+      "loss": 0.9312,
+      "step": 424
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 0.001,
+      "loss": 0.8677,
+      "step": 425
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 0.001,
+      "loss": 1.0088,
+      "step": 426
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 0.001,
+      "loss": 0.9419,
+      "step": 427
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 0.001,
+      "loss": 0.8147,
+      "step": 428
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 0.001,
+      "loss": 1.0513,
+      "step": 429
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 0.001,
+      "loss": 0.9773,
+      "step": 430
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 0.001,
+      "loss": 0.9102,
+      "step": 431
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 0.001,
+      "loss": 0.9648,
+      "step": 432
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 0.001,
+      "loss": 0.9949,
+      "step": 433
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 0.001,
+      "loss": 0.9199,
+      "step": 434
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 0.001,
+      "loss": 0.999,
+      "step": 435
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 0.001,
+      "loss": 1.021,
+      "step": 436
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 0.001,
+      "loss": 0.8582,
+      "step": 437
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 0.001,
+      "loss": 0.9563,
+      "step": 438
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 0.001,
+      "loss": 1.0237,
+      "step": 439
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 0.001,
+      "loss": 0.8679,
+      "step": 440
+    },
+    {
+      "epoch": 3.55,
+      "eval_loss": 1.3019020557403564,
+      "eval_runtime": 24.1086,
+      "eval_samples_per_second": 138.208,
+      "eval_steps_per_second": 0.29,
+      "step": 440
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 0.001,
+      "loss": 0.9531,
+      "step": 441
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 0.001,
+      "loss": 1.0359,
+      "step": 442
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 0.001,
+      "loss": 0.8894,
+      "step": 443
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 0.001,
+      "loss": 0.8979,
+      "step": 444
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 0.001,
+      "loss": 1.1045,
+      "step": 445
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 0.001,
+      "loss": 0.9033,
+      "step": 446
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 0.001,
+      "loss": 0.8884,
+      "step": 447
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 0.001,
+      "loss": 1.0732,
+      "step": 448
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 0.001,
+      "loss": 0.9446,
+      "step": 449
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 0.001,
+      "loss": 0.8816,
+      "step": 450
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 0.001,
+      "loss": 1.0325,
+      "step": 451
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 0.001,
+      "loss": 0.8955,
+      "step": 452
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 0.001,
+      "loss": 0.9236,
+      "step": 453
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 0.001,
+      "loss": 1.0732,
+      "step": 454
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 0.001,
+      "loss": 0.9915,
+      "step": 455
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 0.001,
+      "loss": 0.9148,
+      "step": 456
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 0.001,
+      "loss": 1.0352,
+      "step": 457
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 0.001,
+      "loss": 0.9668,
+      "step": 458
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 0.001,
+      "loss": 0.8896,
+      "step": 459
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 0.001,
+      "loss": 1.0569,
+      "step": 460
+    },
+    {
+      "epoch": 3.71,
+      "eval_loss": 1.2955150604248047,
+      "eval_runtime": 23.8481,
+      "eval_samples_per_second": 139.718,
+      "eval_steps_per_second": 0.294,
+      "step": 460
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 0.001,
+      "loss": 1.0542,
+      "step": 461
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 0.001,
+      "loss": 0.8853,
+      "step": 462
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 0.001,
+      "loss": 1.0237,
+      "step": 463
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 0.001,
+      "loss": 1.0415,
+      "step": 464
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 0.001,
+      "loss": 0.8921,
+      "step": 465
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 0.001,
+      "loss": 0.9136,
+      "step": 466
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 0.001,
+      "loss": 1.053,
+      "step": 467
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 0.001,
+      "loss": 0.8704,
+      "step": 468
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 0.001,
+      "loss": 0.9309,
+      "step": 469
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 0.001,
+      "loss": 1.0503,
+      "step": 470
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 0.001,
+      "loss": 0.8997,
+      "step": 471
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 0.001,
+      "loss": 0.9258,
+      "step": 472
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 0.001,
+      "loss": 1.1394,
+      "step": 473
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 0.001,
+      "loss": 0.9321,
+      "step": 474
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 0.001,
+      "loss": 0.9158,
+      "step": 475
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 0.001,
+      "loss": 1.1064,
+      "step": 476
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 0.001,
+      "loss": 1.0183,
+      "step": 477
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 0.001,
+      "loss": 0.8757,
+      "step": 478
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 0.001,
+      "loss": 1.0015,
+      "step": 479
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 0.001,
+      "loss": 1.0186,
+      "step": 480
+    },
+    {
+      "epoch": 3.87,
+      "eval_loss": 1.289034366607666,
+      "eval_runtime": 24.0617,
+      "eval_samples_per_second": 138.477,
+      "eval_steps_per_second": 0.291,
+      "step": 480
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 0.001,
+      "loss": 0.928,
+      "step": 481
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 0.001,
+      "loss": 1.0051,
+      "step": 482
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 0.001,
+      "loss": 1.0334,
+      "step": 483
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 0.001,
+      "loss": 0.8867,
+      "step": 484
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 0.001,
+      "loss": 0.9609,
+      "step": 485
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 0.001,
+      "loss": 1.0813,
+      "step": 486
+    },
+    {
+      "epoch": 3.93,
+      "learning_rate": 0.001,
+      "loss": 0.9106,
+      "step": 487
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 0.001,
+      "loss": 0.9976,
+      "step": 488
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 0.001,
+      "loss": 1.0649,
+      "step": 489
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 0.001,
+      "loss": 0.8901,
+      "step": 490
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 0.001,
+      "loss": 0.9998,
+      "step": 491
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 0.001,
+      "loss": 1.0847,
+      "step": 492
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 0.001,
+      "loss": 0.9316,
+      "step": 493
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 0.001,
+      "loss": 0.9297,
+      "step": 494
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 0.001,
+      "loss": 0.9792,
+      "step": 495
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.001,
+      "loss": 0.9214,
+      "step": 496
+    },
+    {
+      "epoch": 4.01,
+      "learning_rate": 0.001,
+      "loss": 0.8428,
+      "step": 497
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 0.001,
+      "loss": 0.7185,
+      "step": 498
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 0.001,
+      "loss": 0.7046,
+      "step": 499
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 0.001,
+      "loss": 0.8413,
+      "step": 500
+    },
+    {
+      "epoch": 4.03,
+      "eval_loss": 1.3445378541946411,
+      "eval_runtime": 23.9624,
+      "eval_samples_per_second": 139.051,
+      "eval_steps_per_second": 0.292,
+      "step": 500
+    },
+    {
+      "epoch": 4.03,
+      "step": 500,
+      "total_flos": 5.239072457268134e+18,
+      "train_loss": 1.25592919921875,
+      "train_runtime": 8163.1704,
+      "train_samples_per_second": 154.599,
+      "train_steps_per_second": 0.304
+    }
+  ],
+  "max_steps": 2480,
+  "num_train_epochs": 20,
+  "total_flos": 5.239072457268134e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f13d3605bfdbc27d9ebf35276b2a39a4b0a6786b3356aee82a9f3a897c5acff
+size 5563