Upload folder using huggingface_hub

README.md

@@ -1,3 +1,60 @@
----
-license: apache-2.0
----
+---
+library_name: transformers
+license: other
+base_model: Yhhhhhhhhh/final-tc-deepseek-coder-1.3b-instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: nopy_DEC_final_sft_deepseek-coder-1.3b-instruct
+  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. -->
+
+# nopy_DEC_final_sft_deepseek-coder-1.3b-instruct
+
+This model is a fine-tuned version of [/content/drive/MyDrive/Effi-Code/LLaMA-Factory/saves/nopy_tc_final_sft_deepseek-coder-1.3b-instruct](https://huggingface.co//content/drive/MyDrive/Effi-Code/LLaMA-Factory/saves/nopy_tc_final_sft_deepseek-coder-1.3b-instruct) on the output dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4482
+
+## 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: 5e-06
+- train_batch_size: 8
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 4.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 0.4481600522994995,
+    "eval_runtime": 0.9382,
+    "eval_samples_per_second": 1.066,
+    "eval_steps_per_second": 1.066,
+    "total_flos": 1.573815416315904e+17,
+    "train_loss": 0.29322911118125095,
+    "train_runtime": 2500.7039,
+    "train_samples_per_second": 5.936,
+    "train_steps_per_second": 0.371
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/Effi-Code/LLaMA-Factory/saves/nopy_tc_final_sft_deepseek-coder-1.3b-instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32013,
+  "eos_token_id": 32021,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "rope_type": "linear",
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 32256
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 0.4481600522994995,
+    "eval_runtime": 0.9382,
+    "eval_samples_per_second": 1.066,
+    "eval_steps_per_second": 1.066
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32021,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91da8237fa4cf90ae4b154c934e187d9353b9be575040d3879cbdad4ad11e426
+size 4986380064

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7169f1c209571d3322d3ef83a316b008c544ccc120bed8f7905437f71a4b721a
+size 399532808

model.safetensors.index.json

@@ -0,0 +1,226 @@
+{
+  "metadata": {
+    "total_size": 5385887744
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

runs/Oct31_17-18-17_59165d74727b/events.out.tfevents.1730395113.59165d74727b.48870.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d5612d54b3c366dde8005fe243b658d9824f53b37499f46d5da168bbfd7ba98
+size 25116

runs/Oct31_17-18-17_59165d74727b/events.out.tfevents.1730397639.59165d74727b.48870.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bd627a0af6d917245997f08a5c79265b50d029fdc8cf710119f93ce1e78cf09
+size 359

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|EOT|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Please continue to complete the function. You are not allowed to modify the given code and do the completion only. Please return all completed function in a codeblock. Here is the given code to do completion:\n```python\n' + content + '\n' }}{% elif message['role'] == 'assistant' %}{{ '\n' + content + '\n```<|EOT|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 1.573815416315904e+17,
+    "train_loss": 0.29322911118125095,
+    "train_runtime": 2500.7039,
+    "train_samples_per_second": 5.936,
+    "train_steps_per_second": 0.371
+}

trainer_log.jsonl

@@ -0,0 +1,93 @@
+{"current_steps": 10, "total_steps": 928, "loss": 0.7126, "learning_rate": 1.7857142857142859e-06, "epoch": 0.04310344827586207, "percentage": 1.08, "elapsed_time": "0:00:37", "remaining_time": "0:57:10"}
+{"current_steps": 20, "total_steps": 928, "loss": 0.6662, "learning_rate": 3.5714285714285718e-06, "epoch": 0.08620689655172414, "percentage": 2.16, "elapsed_time": "0:01:09", "remaining_time": "0:52:53"}
+{"current_steps": 30, "total_steps": 928, "loss": 0.5303, "learning_rate": 4.999939076763487e-06, "epoch": 0.12931034482758622, "percentage": 3.23, "elapsed_time": "0:01:45", "remaining_time": "0:52:43"}
+{"current_steps": 40, "total_steps": 928, "loss": 0.453, "learning_rate": 4.997807075247147e-06, "epoch": 0.1724137931034483, "percentage": 4.31, "elapsed_time": "0:02:14", "remaining_time": "0:49:37"}
+{"current_steps": 50, "total_steps": 928, "loss": 0.4192, "learning_rate": 4.992631880567301e-06, "epoch": 0.21551724137931033, "percentage": 5.39, "elapsed_time": "0:02:43", "remaining_time": "0:47:53"}
+{"current_steps": 60, "total_steps": 928, "loss": 0.418, "learning_rate": 4.984419797901491e-06, "epoch": 0.25862068965517243, "percentage": 6.47, "elapsed_time": "0:03:09", "remaining_time": "0:45:42"}
+{"current_steps": 70, "total_steps": 928, "loss": 0.4118, "learning_rate": 4.973180832407471e-06, "epoch": 0.3017241379310345, "percentage": 7.54, "elapsed_time": "0:03:38", "remaining_time": "0:44:39"}
+{"current_steps": 80, "total_steps": 928, "loss": 0.4065, "learning_rate": 4.958928677033465e-06, "epoch": 0.3448275862068966, "percentage": 8.62, "elapsed_time": "0:04:04", "remaining_time": "0:43:07"}
+{"current_steps": 90, "total_steps": 928, "loss": 0.3819, "learning_rate": 4.9416806958354206e-06, "epoch": 0.3879310344827586, "percentage": 9.7, "elapsed_time": "0:04:28", "remaining_time": "0:41:42"}
+{"current_steps": 100, "total_steps": 928, "loss": 0.399, "learning_rate": 4.921457902821578e-06, "epoch": 0.43103448275862066, "percentage": 10.78, "elapsed_time": "0:04:55", "remaining_time": "0:40:42"}
+{"current_steps": 110, "total_steps": 928, "loss": 0.3962, "learning_rate": 4.898284936350144e-06, "epoch": 0.47413793103448276, "percentage": 11.85, "elapsed_time": "0:05:23", "remaining_time": "0:40:03"}
+{"current_steps": 120, "total_steps": 928, "loss": 0.3818, "learning_rate": 4.8721900291112415e-06, "epoch": 0.5172413793103449, "percentage": 12.93, "elapsed_time": "0:05:49", "remaining_time": "0:39:15"}
+{"current_steps": 130, "total_steps": 928, "loss": 0.3901, "learning_rate": 4.84320497372973e-06, "epoch": 0.5603448275862069, "percentage": 14.01, "elapsed_time": "0:06:16", "remaining_time": "0:38:29"}
+{"current_steps": 140, "total_steps": 928, "loss": 0.3867, "learning_rate": 4.811365084030784e-06, "epoch": 0.603448275862069, "percentage": 15.09, "elapsed_time": "0:06:43", "remaining_time": "0:37:49"}
+{"current_steps": 150, "total_steps": 928, "loss": 0.3882, "learning_rate": 4.776709152015443e-06, "epoch": 0.646551724137931, "percentage": 16.16, "elapsed_time": "0:07:09", "remaining_time": "0:37:09"}
+{"current_steps": 160, "total_steps": 928, "loss": 0.3739, "learning_rate": 4.7392794005985324e-06, "epoch": 0.6896551724137931, "percentage": 17.24, "elapsed_time": "0:07:33", "remaining_time": "0:36:17"}
+{"current_steps": 170, "total_steps": 928, "loss": 0.3733, "learning_rate": 4.699121432166542e-06, "epoch": 0.7327586206896551, "percentage": 18.32, "elapsed_time": "0:07:59", "remaining_time": "0:35:39"}
+{"current_steps": 180, "total_steps": 928, "loss": 0.3625, "learning_rate": 4.656284173018144e-06, "epoch": 0.7758620689655172, "percentage": 19.4, "elapsed_time": "0:08:24", "remaining_time": "0:34:55"}
+{"current_steps": 190, "total_steps": 928, "loss": 0.3698, "learning_rate": 4.610819813755038e-06, "epoch": 0.8189655172413793, "percentage": 20.47, "elapsed_time": "0:08:49", "remaining_time": "0:34:18"}
+{"current_steps": 200, "total_steps": 928, "loss": 0.3471, "learning_rate": 4.562783745695738e-06, "epoch": 0.8620689655172413, "percentage": 21.55, "elapsed_time": "0:09:15", "remaining_time": "0:33:41"}
+{"current_steps": 210, "total_steps": 928, "loss": 0.3712, "learning_rate": 4.512234493389785e-06, "epoch": 0.9051724137931034, "percentage": 22.63, "elapsed_time": "0:09:41", "remaining_time": "0:33:09"}
+{"current_steps": 220, "total_steps": 928, "loss": 0.3651, "learning_rate": 4.4592336433146e-06, "epoch": 0.9482758620689655, "percentage": 23.71, "elapsed_time": "0:10:08", "remaining_time": "0:32:38"}
+{"current_steps": 230, "total_steps": 928, "loss": 0.3641, "learning_rate": 4.403845768841842e-06, "epoch": 0.9913793103448276, "percentage": 24.78, "elapsed_time": "0:10:34", "remaining_time": "0:32:05"}
+{"current_steps": 240, "total_steps": 928, "loss": 0.3057, "learning_rate": 4.346138351564711e-06, "epoch": 1.0344827586206897, "percentage": 25.86, "elapsed_time": "0:11:00", "remaining_time": "0:31:34"}
+{"current_steps": 250, "total_steps": 928, "loss": 0.3045, "learning_rate": 4.286181699082008e-06, "epoch": 1.0775862068965518, "percentage": 26.94, "elapsed_time": "0:11:26", "remaining_time": "0:31:01"}
+{"current_steps": 260, "total_steps": 928, "loss": 0.301, "learning_rate": 4.224048859339175e-06, "epoch": 1.1206896551724137, "percentage": 28.02, "elapsed_time": "0:11:49", "remaining_time": "0:30:23"}
+{"current_steps": 270, "total_steps": 928, "loss": 0.3236, "learning_rate": 4.159815531630604e-06, "epoch": 1.1637931034482758, "percentage": 29.09, "elapsed_time": "0:12:13", "remaining_time": "0:29:47"}
+{"current_steps": 280, "total_steps": 928, "loss": 0.3078, "learning_rate": 4.093559974371725e-06, "epoch": 1.206896551724138, "percentage": 30.17, "elapsed_time": "0:12:38", "remaining_time": "0:29:15"}
+{"current_steps": 290, "total_steps": 928, "loss": 0.3145, "learning_rate": 4.02536290975317e-06, "epoch": 1.25, "percentage": 31.25, "elapsed_time": "0:13:02", "remaining_time": "0:28:42"}
+{"current_steps": 300, "total_steps": 928, "loss": 0.3018, "learning_rate": 3.955307425393224e-06, "epoch": 1.293103448275862, "percentage": 32.33, "elapsed_time": "0:13:26", "remaining_time": "0:28:08"}
+{"current_steps": 310, "total_steps": 928, "loss": 0.3215, "learning_rate": 3.88347887310836e-06, "epoch": 1.3362068965517242, "percentage": 33.41, "elapsed_time": "0:13:50", "remaining_time": "0:27:35"}
+{"current_steps": 320, "total_steps": 928, "loss": 0.2973, "learning_rate": 3.8099647649251984e-06, "epoch": 1.3793103448275863, "percentage": 34.48, "elapsed_time": "0:14:15", "remaining_time": "0:27:04"}
+{"current_steps": 330, "total_steps": 928, "loss": 0.3095, "learning_rate": 3.7348546664605777e-06, "epoch": 1.4224137931034484, "percentage": 35.56, "elapsed_time": "0:14:38", "remaining_time": "0:26:32"}
+{"current_steps": 340, "total_steps": 928, "loss": 0.3172, "learning_rate": 3.658240087799655e-06, "epoch": 1.4655172413793103, "percentage": 36.64, "elapsed_time": "0:15:03", "remaining_time": "0:26:02"}
+{"current_steps": 350, "total_steps": 928, "loss": 0.2923, "learning_rate": 3.5802143720049565e-06, "epoch": 1.5086206896551724, "percentage": 37.72, "elapsed_time": "0:15:28", "remaining_time": "0:25:34"}
+{"current_steps": 360, "total_steps": 928, "loss": 0.3032, "learning_rate": 3.5008725813922383e-06, "epoch": 1.5517241379310345, "percentage": 38.79, "elapsed_time": "0:15:54", "remaining_time": "0:25:05"}
+{"current_steps": 370, "total_steps": 928, "loss": 0.3113, "learning_rate": 3.4203113817116955e-06, "epoch": 1.5948275862068966, "percentage": 39.87, "elapsed_time": "0:16:17", "remaining_time": "0:24:34"}
+{"current_steps": 380, "total_steps": 928, "loss": 0.3122, "learning_rate": 3.338628924375638e-06, "epoch": 1.6379310344827587, "percentage": 40.95, "elapsed_time": "0:16:40", "remaining_time": "0:24:03"}
+{"current_steps": 390, "total_steps": 928, "loss": 0.2986, "learning_rate": 3.2559247268761117e-06, "epoch": 1.6810344827586206, "percentage": 42.03, "elapsed_time": "0:17:05", "remaining_time": "0:23:34"}
+{"current_steps": 400, "total_steps": 928, "loss": 0.2969, "learning_rate": 3.1722995515381644e-06, "epoch": 1.7241379310344827, "percentage": 43.1, "elapsed_time": "0:17:30", "remaining_time": "0:23:06"}
+{"current_steps": 410, "total_steps": 928, "loss": 0.294, "learning_rate": 3.087855282756475e-06, "epoch": 1.7672413793103448, "percentage": 44.18, "elapsed_time": "0:17:54", "remaining_time": "0:22:38"}
+{"current_steps": 420, "total_steps": 928, "loss": 0.2987, "learning_rate": 3.002694802864912e-06, "epoch": 1.8103448275862069, "percentage": 45.26, "elapsed_time": "0:18:18", "remaining_time": "0:22:08"}
+{"current_steps": 430, "total_steps": 928, "loss": 0.3087, "learning_rate": 2.9169218667902562e-06, "epoch": 1.853448275862069, "percentage": 46.34, "elapsed_time": "0:18:42", "remaining_time": "0:21:39"}
+{"current_steps": 440, "total_steps": 928, "loss": 0.2945, "learning_rate": 2.8306409756428067e-06, "epoch": 1.896551724137931, "percentage": 47.41, "elapsed_time": "0:19:07", "remaining_time": "0:21:12"}
+{"current_steps": 450, "total_steps": 928, "loss": 0.3036, "learning_rate": 2.743957249397874e-06, "epoch": 1.9396551724137931, "percentage": 48.49, "elapsed_time": "0:19:32", "remaining_time": "0:20:45"}
+{"current_steps": 460, "total_steps": 928, "loss": 0.3119, "learning_rate": 2.6569762988232838e-06, "epoch": 1.9827586206896552, "percentage": 49.57, "elapsed_time": "0:19:56", "remaining_time": "0:20:17"}
+{"current_steps": 470, "total_steps": 928, "loss": 0.2789, "learning_rate": 2.569804096808923e-06, "epoch": 2.0258620689655173, "percentage": 50.65, "elapsed_time": "0:20:19", "remaining_time": "0:19:48"}
+{"current_steps": 480, "total_steps": 928, "loss": 0.2435, "learning_rate": 2.482546849255096e-06, "epoch": 2.0689655172413794, "percentage": 51.72, "elapsed_time": "0:20:44", "remaining_time": "0:19:21"}
+{"current_steps": 490, "total_steps": 928, "loss": 0.2475, "learning_rate": 2.3953108656770018e-06, "epoch": 2.1120689655172415, "percentage": 52.8, "elapsed_time": "0:21:06", "remaining_time": "0:18:52"}
+{"current_steps": 500, "total_steps": 928, "loss": 0.2384, "learning_rate": 2.3082024296829538e-06, "epoch": 2.1551724137931036, "percentage": 53.88, "elapsed_time": "0:21:30", "remaining_time": "0:18:24"}
+{"current_steps": 510, "total_steps": 928, "loss": 0.2356, "learning_rate": 2.2213276694841866e-06, "epoch": 2.1982758620689653, "percentage": 54.96, "elapsed_time": "0:22:48", "remaining_time": "0:18:41"}
+{"current_steps": 520, "total_steps": 928, "loss": 0.2466, "learning_rate": 2.134792428593971e-06, "epoch": 2.2413793103448274, "percentage": 56.03, "elapsed_time": "0:23:12", "remaining_time": "0:18:12"}
+{"current_steps": 530, "total_steps": 928, "loss": 0.2456, "learning_rate": 2.0487021368736002e-06, "epoch": 2.2844827586206895, "percentage": 57.11, "elapsed_time": "0:23:36", "remaining_time": "0:17:43"}
+{"current_steps": 540, "total_steps": 928, "loss": 0.2406, "learning_rate": 1.963161682082342e-06, "epoch": 2.3275862068965516, "percentage": 58.19, "elapsed_time": "0:24:00", "remaining_time": "0:17:15"}
+{"current_steps": 550, "total_steps": 928, "loss": 0.2225, "learning_rate": 1.8782752820878636e-06, "epoch": 2.3706896551724137, "percentage": 59.27, "elapsed_time": "0:24:25", "remaining_time": "0:16:47"}
+{"current_steps": 560, "total_steps": 928, "loss": 0.2312, "learning_rate": 1.7941463578928088e-06, "epoch": 2.413793103448276, "percentage": 60.34, "elapsed_time": "0:24:49", "remaining_time": "0:16:19"}
+{"current_steps": 570, "total_steps": 928, "loss": 0.2415, "learning_rate": 1.7108774076322443e-06, "epoch": 2.456896551724138, "percentage": 61.42, "elapsed_time": "0:25:13", "remaining_time": "0:15:50"}
+{"current_steps": 580, "total_steps": 928, "loss": 0.2487, "learning_rate": 1.6285698816954626e-06, "epoch": 2.5, "percentage": 62.5, "elapsed_time": "0:25:38", "remaining_time": "0:15:23"}
+{"current_steps": 590, "total_steps": 928, "loss": 0.2378, "learning_rate": 1.547324059124315e-06, "epoch": 2.543103448275862, "percentage": 63.58, "elapsed_time": "0:26:02", "remaining_time": "0:14:55"}
+{"current_steps": 600, "total_steps": 928, "loss": 0.2765, "learning_rate": 1.467238925438646e-06, "epoch": 2.586206896551724, "percentage": 64.66, "elapsed_time": "0:26:25", "remaining_time": "0:14:26"}
+{"current_steps": 610, "total_steps": 928, "loss": 0.2584, "learning_rate": 1.388412052037682e-06, "epoch": 2.6293103448275863, "percentage": 65.73, "elapsed_time": "0:26:49", "remaining_time": "0:13:59"}
+{"current_steps": 620, "total_steps": 928, "loss": 0.2323, "learning_rate": 1.3109394773243117e-06, "epoch": 2.6724137931034484, "percentage": 66.81, "elapsed_time": "0:27:15", "remaining_time": "0:13:32"}
+{"current_steps": 630, "total_steps": 928, "loss": 0.2384, "learning_rate": 1.234915589697091e-06, "epoch": 2.7155172413793105, "percentage": 67.89, "elapsed_time": "0:27:38", "remaining_time": "0:13:04"}
+{"current_steps": 640, "total_steps": 928, "loss": 0.2382, "learning_rate": 1.160433012552508e-06, "epoch": 2.7586206896551726, "percentage": 68.97, "elapsed_time": "0:28:03", "remaining_time": "0:12:37"}
+{"current_steps": 650, "total_steps": 928, "loss": 0.2303, "learning_rate": 1.0875824914376555e-06, "epoch": 2.8017241379310347, "percentage": 70.04, "elapsed_time": "0:28:28", "remaining_time": "0:12:10"}
+{"current_steps": 660, "total_steps": 928, "loss": 0.2423, "learning_rate": 1.0164527834907468e-06, "epoch": 2.844827586206897, "percentage": 71.12, "elapsed_time": "0:28:50", "remaining_time": "0:11:42"}
+{"current_steps": 670, "total_steps": 928, "loss": 0.2426, "learning_rate": 9.471305493042243e-07, "epoch": 2.887931034482759, "percentage": 72.2, "elapsed_time": "0:29:15", "remaining_time": "0:11:15"}
+{"current_steps": 680, "total_steps": 928, "loss": 0.2494, "learning_rate": 8.797002473421729e-07, "epoch": 2.9310344827586206, "percentage": 73.28, "elapsed_time": "0:29:38", "remaining_time": "0:10:48"}
+{"current_steps": 690, "total_steps": 928, "loss": 0.2407, "learning_rate": 8.142440310406923e-07, "epoch": 2.9741379310344827, "percentage": 74.35, "elapsed_time": "0:30:03", "remaining_time": "0:10:21"}
+{"current_steps": 700, "total_steps": 928, "loss": 0.2254, "learning_rate": 7.508416487165862e-07, "epoch": 3.0172413793103448, "percentage": 75.43, "elapsed_time": "0:30:28", "remaining_time": "0:09:55"}
+{"current_steps": 710, "total_steps": 928, "loss": 0.2015, "learning_rate": 6.895703464063319e-07, "epoch": 3.060344827586207, "percentage": 76.51, "elapsed_time": "0:30:55", "remaining_time": "0:09:29"}
+{"current_steps": 720, "total_steps": 928, "loss": 0.1952, "learning_rate": 6.305047737536707e-07, "epoch": 3.103448275862069, "percentage": 77.59, "elapsed_time": "0:31:18", "remaining_time": "0:09:02"}
+{"current_steps": 730, "total_steps": 928, "loss": 0.1967, "learning_rate": 5.737168930605272e-07, "epoch": 3.146551724137931, "percentage": 78.66, "elapsed_time": "0:31:44", "remaining_time": "0:08:36"}
+{"current_steps": 740, "total_steps": 928, "loss": 0.2128, "learning_rate": 5.192758916120236e-07, "epoch": 3.189655172413793, "percentage": 79.74, "elapsed_time": "0:32:08", "remaining_time": "0:08:09"}
+{"current_steps": 750, "total_steps": 928, "loss": 0.1907, "learning_rate": 4.672480973824312e-07, "epoch": 3.2327586206896552, "percentage": 80.82, "elapsed_time": "0:32:32", "remaining_time": "0:07:43"}
+{"current_steps": 760, "total_steps": 928, "loss": 0.2046, "learning_rate": 4.1769689822475147e-07, "epoch": 3.2758620689655173, "percentage": 81.9, "elapsed_time": "0:32:56", "remaining_time": "0:07:16"}
+{"current_steps": 770, "total_steps": 928, "loss": 0.1973, "learning_rate": 3.7068266464238085e-07, "epoch": 3.3189655172413794, "percentage": 82.97, "elapsed_time": "0:33:18", "remaining_time": "0:06:50"}
+{"current_steps": 780, "total_steps": 928, "loss": 0.2107, "learning_rate": 3.262626762369525e-07, "epoch": 3.3620689655172415, "percentage": 84.05, "elapsed_time": "0:33:42", "remaining_time": "0:06:23"}
+{"current_steps": 790, "total_steps": 928, "loss": 0.2055, "learning_rate": 2.844910519219632e-07, "epoch": 3.405172413793103, "percentage": 85.13, "elapsed_time": "0:34:06", "remaining_time": "0:05:57"}
+{"current_steps": 800, "total_steps": 928, "loss": 0.2083, "learning_rate": 2.454186839872158e-07, "epoch": 3.4482758620689653, "percentage": 86.21, "elapsed_time": "0:34:32", "remaining_time": "0:05:31"}
+{"current_steps": 810, "total_steps": 928, "loss": 0.1973, "learning_rate": 2.0909317609440093e-07, "epoch": 3.4913793103448274, "percentage": 87.28, "elapsed_time": "0:34:56", "remaining_time": "0:05:05"}
+{"current_steps": 820, "total_steps": 928, "loss": 0.2336, "learning_rate": 1.7555878527937164e-07, "epoch": 3.5344827586206895, "percentage": 88.36, "elapsed_time": "0:35:21", "remaining_time": "0:04:39"}
+{"current_steps": 830, "total_steps": 928, "loss": 0.2028, "learning_rate": 1.4485636803175828e-07, "epoch": 3.5775862068965516, "percentage": 89.44, "elapsed_time": "0:35:46", "remaining_time": "0:04:13"}
+{"current_steps": 840, "total_steps": 928, "loss": 0.1897, "learning_rate": 1.1702333051763271e-07, "epoch": 3.6206896551724137, "percentage": 90.52, "elapsed_time": "0:36:11", "remaining_time": "0:03:47"}
+{"current_steps": 850, "total_steps": 928, "loss": 0.2053, "learning_rate": 9.209358300585474e-08, "epoch": 3.663793103448276, "percentage": 91.59, "elapsed_time": "0:36:34", "remaining_time": "0:03:21"}
+{"current_steps": 860, "total_steps": 928, "loss": 0.2019, "learning_rate": 7.009749855363457e-08, "epoch": 3.706896551724138, "percentage": 92.67, "elapsed_time": "0:36:57", "remaining_time": "0:02:55"}
+{"current_steps": 870, "total_steps": 928, "loss": 0.2012, "learning_rate": 5.106187600163987e-08, "epoch": 3.75, "percentage": 93.75, "elapsed_time": "0:37:21", "remaining_time": "0:02:29"}
+{"current_steps": 880, "total_steps": 928, "loss": 0.2041, "learning_rate": 3.5009907323737826e-08, "epoch": 3.793103448275862, "percentage": 94.83, "elapsed_time": "0:37:45", "remaining_time": "0:02:03"}
+{"current_steps": 890, "total_steps": 928, "loss": 0.2157, "learning_rate": 2.1961149371145795e-08, "epoch": 3.836206896551724, "percentage": 95.91, "elapsed_time": "0:38:08", "remaining_time": "0:01:37"}
+{"current_steps": 900, "total_steps": 928, "loss": 0.2124, "learning_rate": 1.193150004542204e-08, "epoch": 3.8793103448275863, "percentage": 96.98, "elapsed_time": "0:38:32", "remaining_time": "0:01:11"}
+{"current_steps": 910, "total_steps": 928, "loss": 0.2164, "learning_rate": 4.933178929321103e-09, "epoch": 3.9224137931034484, "percentage": 98.06, "elapsed_time": "0:38:57", "remaining_time": "0:00:46"}
+{"current_steps": 920, "total_steps": 928, "loss": 0.209, "learning_rate": 9.747123991141193e-10, "epoch": 3.9655172413793105, "percentage": 99.14, "elapsed_time": "0:39:21", "remaining_time": "0:00:20"}
+{"current_steps": 928, "total_steps": 928, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "0:40:35", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,686 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 50000,
+  "global_step": 928,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04310344827586207,
+      "grad_norm": 5.7193193435668945,
+      "learning_rate": 1.7857142857142859e-06,
+      "loss": 0.7126,
+      "step": 10
+    },
+    {
+      "epoch": 0.08620689655172414,
+      "grad_norm": 2.6962673664093018,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 0.6662,
+      "step": 20
+    },
+    {
+      "epoch": 0.12931034482758622,
+      "grad_norm": 1.6143770217895508,
+      "learning_rate": 4.999939076763487e-06,
+      "loss": 0.5303,
+      "step": 30
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 1.3705445528030396,
+      "learning_rate": 4.997807075247147e-06,
+      "loss": 0.453,
+      "step": 40
+    },
+    {
+      "epoch": 0.21551724137931033,
+      "grad_norm": 1.129184603691101,
+      "learning_rate": 4.992631880567301e-06,
+      "loss": 0.4192,
+      "step": 50
+    },
+    {
+      "epoch": 0.25862068965517243,
+      "grad_norm": 1.3925697803497314,
+      "learning_rate": 4.984419797901491e-06,
+      "loss": 0.418,
+      "step": 60
+    },
+    {
+      "epoch": 0.3017241379310345,
+      "grad_norm": 1.4394880533218384,
+      "learning_rate": 4.973180832407471e-06,
+      "loss": 0.4118,
+      "step": 70
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 1.3788193464279175,
+      "learning_rate": 4.958928677033465e-06,
+      "loss": 0.4065,
+      "step": 80
+    },
+    {
+      "epoch": 0.3879310344827586,
+      "grad_norm": 1.1382204294204712,
+      "learning_rate": 4.9416806958354206e-06,
+      "loss": 0.3819,
+      "step": 90
+    },
+    {
+      "epoch": 0.43103448275862066,
+      "grad_norm": 1.081235647201538,
+      "learning_rate": 4.921457902821578e-06,
+      "loss": 0.399,
+      "step": 100
+    },
+    {
+      "epoch": 0.47413793103448276,
+      "grad_norm": 1.21293044090271,
+      "learning_rate": 4.898284936350144e-06,
+      "loss": 0.3962,
+      "step": 110
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 1.3453164100646973,
+      "learning_rate": 4.8721900291112415e-06,
+      "loss": 0.3818,
+      "step": 120
+    },
+    {
+      "epoch": 0.5603448275862069,
+      "grad_norm": 1.2487531900405884,
+      "learning_rate": 4.84320497372973e-06,
+      "loss": 0.3901,
+      "step": 130
+    },
+    {
+      "epoch": 0.603448275862069,
+      "grad_norm": 1.1610265970230103,
+      "learning_rate": 4.811365084030784e-06,
+      "loss": 0.3867,
+      "step": 140
+    },
+    {
+      "epoch": 0.646551724137931,
+      "grad_norm": 1.0656601190567017,
+      "learning_rate": 4.776709152015443e-06,
+      "loss": 0.3882,
+      "step": 150
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 1.2680625915527344,
+      "learning_rate": 4.7392794005985324e-06,
+      "loss": 0.3739,
+      "step": 160
+    },
+    {
+      "epoch": 0.7327586206896551,
+      "grad_norm": 1.3623387813568115,
+      "learning_rate": 4.699121432166542e-06,
+      "loss": 0.3733,
+      "step": 170
+    },
+    {
+      "epoch": 0.7758620689655172,
+      "grad_norm": 1.096368432044983,
+      "learning_rate": 4.656284173018144e-06,
+      "loss": 0.3625,
+      "step": 180
+    },
+    {
+      "epoch": 0.8189655172413793,
+      "grad_norm": 0.9958175420761108,
+      "learning_rate": 4.610819813755038e-06,
+      "loss": 0.3698,
+      "step": 190
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 1.023909091949463,
+      "learning_rate": 4.562783745695738e-06,
+      "loss": 0.3471,
+      "step": 200
+    },
+    {
+      "epoch": 0.9051724137931034,
+      "grad_norm": 1.061679482460022,
+      "learning_rate": 4.512234493389785e-06,
+      "loss": 0.3712,
+      "step": 210
+    },
+    {
+      "epoch": 0.9482758620689655,
+      "grad_norm": 1.3929497003555298,
+      "learning_rate": 4.4592336433146e-06,
+      "loss": 0.3651,
+      "step": 220
+    },
+    {
+      "epoch": 0.9913793103448276,
+      "grad_norm": 0.8806857466697693,
+      "learning_rate": 4.403845768841842e-06,
+      "loss": 0.3641,
+      "step": 230
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 0.9649218916893005,
+      "learning_rate": 4.346138351564711e-06,
+      "loss": 0.3057,
+      "step": 240
+    },
+    {
+      "epoch": 1.0775862068965518,
+      "grad_norm": 1.1328972578048706,
+      "learning_rate": 4.286181699082008e-06,
+      "loss": 0.3045,
+      "step": 250
+    },
+    {
+      "epoch": 1.1206896551724137,
+      "grad_norm": 1.1146079301834106,
+      "learning_rate": 4.224048859339175e-06,
+      "loss": 0.301,
+      "step": 260
+    },
+    {
+      "epoch": 1.1637931034482758,
+      "grad_norm": 1.1736148595809937,
+      "learning_rate": 4.159815531630604e-06,
+      "loss": 0.3236,
+      "step": 270
+    },
+    {
+      "epoch": 1.206896551724138,
+      "grad_norm": 1.1570653915405273,
+      "learning_rate": 4.093559974371725e-06,
+      "loss": 0.3078,
+      "step": 280
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.335072636604309,
+      "learning_rate": 4.02536290975317e-06,
+      "loss": 0.3145,
+      "step": 290
+    },
+    {
+      "epoch": 1.293103448275862,
+      "grad_norm": 1.0565122365951538,
+      "learning_rate": 3.955307425393224e-06,
+      "loss": 0.3018,
+      "step": 300
+    },
+    {
+      "epoch": 1.3362068965517242,
+      "grad_norm": 1.3002219200134277,
+      "learning_rate": 3.88347887310836e-06,
+      "loss": 0.3215,
+      "step": 310
+    },
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 1.0199170112609863,
+      "learning_rate": 3.8099647649251984e-06,
+      "loss": 0.2973,
+      "step": 320
+    },
+    {
+      "epoch": 1.4224137931034484,
+      "grad_norm": 1.118922233581543,
+      "learning_rate": 3.7348546664605777e-06,
+      "loss": 0.3095,
+      "step": 330
+    },
+    {
+      "epoch": 1.4655172413793103,
+      "grad_norm": 1.080239176750183,
+      "learning_rate": 3.658240087799655e-06,
+      "loss": 0.3172,
+      "step": 340
+    },
+    {
+      "epoch": 1.5086206896551724,
+      "grad_norm": 0.9963559508323669,
+      "learning_rate": 3.5802143720049565e-06,
+      "loss": 0.2923,
+      "step": 350
+    },
+    {
+      "epoch": 1.5517241379310345,
+      "grad_norm": 1.1155935525894165,
+      "learning_rate": 3.5008725813922383e-06,
+      "loss": 0.3032,
+      "step": 360
+    },
+    {
+      "epoch": 1.5948275862068966,
+      "grad_norm": 1.4892568588256836,
+      "learning_rate": 3.4203113817116955e-06,
+      "loss": 0.3113,
+      "step": 370
+    },
+    {
+      "epoch": 1.6379310344827587,
+      "grad_norm": 1.1873013973236084,
+      "learning_rate": 3.338628924375638e-06,
+      "loss": 0.3122,
+      "step": 380
+    },
+    {
+      "epoch": 1.6810344827586206,
+      "grad_norm": 1.215104103088379,
+      "learning_rate": 3.2559247268761117e-06,
+      "loss": 0.2986,
+      "step": 390
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 1.2356464862823486,
+      "learning_rate": 3.1722995515381644e-06,
+      "loss": 0.2969,
+      "step": 400
+    },
+    {
+      "epoch": 1.7672413793103448,
+      "grad_norm": 1.217281699180603,
+      "learning_rate": 3.087855282756475e-06,
+      "loss": 0.294,
+      "step": 410
+    },
+    {
+      "epoch": 1.8103448275862069,
+      "grad_norm": 1.3647332191467285,
+      "learning_rate": 3.002694802864912e-06,
+      "loss": 0.2987,
+      "step": 420
+    },
+    {
+      "epoch": 1.853448275862069,
+      "grad_norm": 1.295482873916626,
+      "learning_rate": 2.9169218667902562e-06,
+      "loss": 0.3087,
+      "step": 430
+    },
+    {
+      "epoch": 1.896551724137931,
+      "grad_norm": 1.1709827184677124,
+      "learning_rate": 2.8306409756428067e-06,
+      "loss": 0.2945,
+      "step": 440
+    },
+    {
+      "epoch": 1.9396551724137931,
+      "grad_norm": 1.2571437358856201,
+      "learning_rate": 2.743957249397874e-06,
+      "loss": 0.3036,
+      "step": 450
+    },
+    {
+      "epoch": 1.9827586206896552,
+      "grad_norm": 1.7302639484405518,
+      "learning_rate": 2.6569762988232838e-06,
+      "loss": 0.3119,
+      "step": 460
+    },
+    {
+      "epoch": 2.0258620689655173,
+      "grad_norm": 0.9986317157745361,
+      "learning_rate": 2.569804096808923e-06,
+      "loss": 0.2789,
+      "step": 470
+    },
+    {
+      "epoch": 2.0689655172413794,
+      "grad_norm": 1.130508303642273,
+      "learning_rate": 2.482546849255096e-06,
+      "loss": 0.2435,
+      "step": 480
+    },
+    {
+      "epoch": 2.1120689655172415,
+      "grad_norm": 1.446877121925354,
+      "learning_rate": 2.3953108656770018e-06,
+      "loss": 0.2475,
+      "step": 490
+    },
+    {
+      "epoch": 2.1551724137931036,
+      "grad_norm": 1.60965096950531,
+      "learning_rate": 2.3082024296829538e-06,
+      "loss": 0.2384,
+      "step": 500
+    },
+    {
+      "epoch": 2.1982758620689653,
+      "grad_norm": 1.383519172668457,
+      "learning_rate": 2.2213276694841866e-06,
+      "loss": 0.2356,
+      "step": 510
+    },
+    {
+      "epoch": 2.2413793103448274,
+      "grad_norm": 1.3211714029312134,
+      "learning_rate": 2.134792428593971e-06,
+      "loss": 0.2466,
+      "step": 520
+    },
+    {
+      "epoch": 2.2844827586206895,
+      "grad_norm": 1.302563190460205,
+      "learning_rate": 2.0487021368736002e-06,
+      "loss": 0.2456,
+      "step": 530
+    },
+    {
+      "epoch": 2.3275862068965516,
+      "grad_norm": 1.30355703830719,
+      "learning_rate": 1.963161682082342e-06,
+      "loss": 0.2406,
+      "step": 540
+    },
+    {
+      "epoch": 2.3706896551724137,
+      "grad_norm": 1.1259819269180298,
+      "learning_rate": 1.8782752820878636e-06,
+      "loss": 0.2225,
+      "step": 550
+    },
+    {
+      "epoch": 2.413793103448276,
+      "grad_norm": 1.2397651672363281,
+      "learning_rate": 1.7941463578928088e-06,
+      "loss": 0.2312,
+      "step": 560
+    },
+    {
+      "epoch": 2.456896551724138,
+      "grad_norm": 1.3761606216430664,
+      "learning_rate": 1.7108774076322443e-06,
+      "loss": 0.2415,
+      "step": 570
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.3666378259658813,
+      "learning_rate": 1.6285698816954626e-06,
+      "loss": 0.2487,
+      "step": 580
+    },
+    {
+      "epoch": 2.543103448275862,
+      "grad_norm": 1.183164119720459,
+      "learning_rate": 1.547324059124315e-06,
+      "loss": 0.2378,
+      "step": 590
+    },
+    {
+      "epoch": 2.586206896551724,
+      "grad_norm": 1.4499019384384155,
+      "learning_rate": 1.467238925438646e-06,
+      "loss": 0.2765,
+      "step": 600
+    },
+    {
+      "epoch": 2.6293103448275863,
+      "grad_norm": 1.447636604309082,
+      "learning_rate": 1.388412052037682e-06,
+      "loss": 0.2584,
+      "step": 610
+    },
+    {
+      "epoch": 2.6724137931034484,
+      "grad_norm": 1.449857473373413,
+      "learning_rate": 1.3109394773243117e-06,
+      "loss": 0.2323,
+      "step": 620
+    },
+    {
+      "epoch": 2.7155172413793105,
+      "grad_norm": 1.3404827117919922,
+      "learning_rate": 1.234915589697091e-06,
+      "loss": 0.2384,
+      "step": 630
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 1.3379237651824951,
+      "learning_rate": 1.160433012552508e-06,
+      "loss": 0.2382,
+      "step": 640
+    },
+    {
+      "epoch": 2.8017241379310347,
+      "grad_norm": 1.4709217548370361,
+      "learning_rate": 1.0875824914376555e-06,
+      "loss": 0.2303,
+      "step": 650
+    },
+    {
+      "epoch": 2.844827586206897,
+      "grad_norm": 1.3744317293167114,
+      "learning_rate": 1.0164527834907468e-06,
+      "loss": 0.2423,
+      "step": 660
+    },
+    {
+      "epoch": 2.887931034482759,
+      "grad_norm": 1.7406655550003052,
+      "learning_rate": 9.471305493042243e-07,
+      "loss": 0.2426,
+      "step": 670
+    },
+    {
+      "epoch": 2.9310344827586206,
+      "grad_norm": 1.6748679876327515,
+      "learning_rate": 8.797002473421729e-07,
+      "loss": 0.2494,
+      "step": 680
+    },
+    {
+      "epoch": 2.9741379310344827,
+      "grad_norm": 1.5766329765319824,
+      "learning_rate": 8.142440310406923e-07,
+      "loss": 0.2407,
+      "step": 690
+    },
+    {
+      "epoch": 3.0172413793103448,
+      "grad_norm": 1.2436530590057373,
+      "learning_rate": 7.508416487165862e-07,
+      "loss": 0.2254,
+      "step": 700
+    },
+    {
+      "epoch": 3.060344827586207,
+      "grad_norm": 1.3559637069702148,
+      "learning_rate": 6.895703464063319e-07,
+      "loss": 0.2015,
+      "step": 710
+    },
+    {
+      "epoch": 3.103448275862069,
+      "grad_norm": 1.3423281908035278,
+      "learning_rate": 6.305047737536707e-07,
+      "loss": 0.1952,
+      "step": 720
+    },
+    {
+      "epoch": 3.146551724137931,
+      "grad_norm": 1.4924376010894775,
+      "learning_rate": 5.737168930605272e-07,
+      "loss": 0.1967,
+      "step": 730
+    },
+    {
+      "epoch": 3.189655172413793,
+      "grad_norm": 1.4202907085418701,
+      "learning_rate": 5.192758916120236e-07,
+      "loss": 0.2128,
+      "step": 740
+    },
+    {
+      "epoch": 3.2327586206896552,
+      "grad_norm": 1.252336025238037,
+      "learning_rate": 4.672480973824312e-07,
+      "loss": 0.1907,
+      "step": 750
+    },
+    {
+      "epoch": 3.2758620689655173,
+      "grad_norm": 1.7021604776382446,
+      "learning_rate": 4.1769689822475147e-07,
+      "loss": 0.2046,
+      "step": 760
+    },
+    {
+      "epoch": 3.3189655172413794,
+      "grad_norm": 1.637277364730835,
+      "learning_rate": 3.7068266464238085e-07,
+      "loss": 0.1973,
+      "step": 770
+    },
+    {
+      "epoch": 3.3620689655172415,
+      "grad_norm": 1.2321523427963257,
+      "learning_rate": 3.262626762369525e-07,
+      "loss": 0.2107,
+      "step": 780
+    },
+    {
+      "epoch": 3.405172413793103,
+      "grad_norm": 1.3565343618392944,
+      "learning_rate": 2.844910519219632e-07,
+      "loss": 0.2055,
+      "step": 790
+    },
+    {
+      "epoch": 3.4482758620689653,
+      "grad_norm": 1.6926054954528809,
+      "learning_rate": 2.454186839872158e-07,
+      "loss": 0.2083,
+      "step": 800
+    },
+    {
+      "epoch": 3.4913793103448274,
+      "grad_norm": 1.5500190258026123,
+      "learning_rate": 2.0909317609440093e-07,
+      "loss": 0.1973,
+      "step": 810
+    },
+    {
+      "epoch": 3.5344827586206895,
+      "grad_norm": 1.4574564695358276,
+      "learning_rate": 1.7555878527937164e-07,
+      "loss": 0.2336,
+      "step": 820
+    },
+    {
+      "epoch": 3.5775862068965516,
+      "grad_norm": 1.371783971786499,
+      "learning_rate": 1.4485636803175828e-07,
+      "loss": 0.2028,
+      "step": 830
+    },
+    {
+      "epoch": 3.6206896551724137,
+      "grad_norm": 1.5117493867874146,
+      "learning_rate": 1.1702333051763271e-07,
+      "loss": 0.1897,
+      "step": 840
+    },
+    {
+      "epoch": 3.663793103448276,
+      "grad_norm": 1.4221725463867188,
+      "learning_rate": 9.209358300585474e-08,
+      "loss": 0.2053,
+      "step": 850
+    },
+    {
+      "epoch": 3.706896551724138,
+      "grad_norm": 1.3613110780715942,
+      "learning_rate": 7.009749855363457e-08,
+      "loss": 0.2019,
+      "step": 860
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 1.6522403955459595,
+      "learning_rate": 5.106187600163987e-08,
+      "loss": 0.2012,
+      "step": 870
+    },
+    {
+      "epoch": 3.793103448275862,
+      "grad_norm": 1.1785835027694702,
+      "learning_rate": 3.5009907323737826e-08,
+      "loss": 0.2041,
+      "step": 880
+    },
+    {
+      "epoch": 3.836206896551724,
+      "grad_norm": 1.3110618591308594,
+      "learning_rate": 2.1961149371145795e-08,
+      "loss": 0.2157,
+      "step": 890
+    },
+    {
+      "epoch": 3.8793103448275863,
+      "grad_norm": 1.1076109409332275,
+      "learning_rate": 1.193150004542204e-08,
+      "loss": 0.2124,
+      "step": 900
+    },
+    {
+      "epoch": 3.9224137931034484,
+      "grad_norm": 1.5730844736099243,
+      "learning_rate": 4.933178929321103e-09,
+      "loss": 0.2164,
+      "step": 910
+    },
+    {
+      "epoch": 3.9655172413793105,
+      "grad_norm": 1.6986498832702637,
+      "learning_rate": 9.747123991141193e-10,
+      "loss": 0.209,
+      "step": 920
+    },
+    {
+      "epoch": 4.0,
+      "step": 928,
+      "total_flos": 1.573815416315904e+17,
+      "train_loss": 0.29322911118125095,
+      "train_runtime": 2500.7039,
+      "train_samples_per_second": 5.936,
+      "train_steps_per_second": 0.371
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 928,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.573815416315904e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3907bf358792242e7b9ce20ebff1364e258adb65e9e98abfe9c0cf966b762f23
+size 5432