End of training

README.md

@@ -0,0 +1,56 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: mistral-7b-300k-10k-a100-6e-valid
+  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. -->
+
+# mistral-7b-300k-10k-a100-6e-valid
+
+This model was trained from scratch on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 512
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 6.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "models/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.34.1"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1a35cfb271f0563208fdd86b8a81647fec29bc4429d2373b089de0e7a855a0c
+size 9943028531

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b999fee8ee473a653b9834808af15b39e3e045c0d30c7f284e1f3585cca4122c
+size 4540536134

pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
+    "model.norm.weight": "pytorch_model-00002-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,712 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.955918367346939,
+  "eval_steps": 50.0,
+  "global_step": 114,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.8797,
+      "step": 1
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.0534,
+      "step": 2
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 5e-06,
+      "loss": 0.8717,
+      "step": 3
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.7959,
+      "step": 4
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 3.2059,
+      "step": 5
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1e-05,
+      "loss": 0.8372,
+      "step": 6
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 1.1969,
+      "step": 7
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.254,
+      "step": 8
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.1179,
+      "step": 9
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.1814,
+      "step": 10
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 1.347,
+      "step": 11
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 2e-05,
+      "loss": 1.7794,
+      "step": 12
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.999525719713366e-05,
+      "loss": 1.8954,
+      "step": 13
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.9981033287370443e-05,
+      "loss": 2.2458,
+      "step": 14
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.9957341762950346e-05,
+      "loss": 3.2685,
+      "step": 15
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.992420509671936e-05,
+      "loss": 0.7298,
+      "step": 16
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.9881654720812594e-05,
+      "loss": 0.9609,
+      "step": 17
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.982973099683902e-05,
+      "loss": 1.4588,
+      "step": 18
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.9768483177596008e-05,
+      "loss": 2.8982,
+      "step": 19
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.9697969360350098e-05,
+      "loss": 2.4402,
+      "step": 20
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.961825643172819e-05,
+      "loss": 1.1163,
+      "step": 21
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.9529420004271568e-05,
+      "loss": 0.8707,
+      "step": 22
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.9431544344712776e-05,
+      "loss": 1.7509,
+      "step": 23
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.932472229404356e-05,
+      "loss": 2.3267,
+      "step": 24
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.920905517944954e-05,
+      "loss": 0.9076,
+      "step": 25
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.9084652718195237e-05,
+      "loss": 1.1937,
+      "step": 26
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.8951632913550625e-05,
+      "loss": 1.3822,
+      "step": 27
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.8810121942857848e-05,
+      "loss": 0.9578,
+      "step": 28
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.866025403784439e-05,
+      "loss": 1.2731,
+      "step": 29
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.8502171357296144e-05,
+      "loss": 1.0392,
+      "step": 30
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.8336023852211197e-05,
+      "loss": 1.1563,
+      "step": 31
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.816196912356222e-05,
+      "loss": 2.1663,
+      "step": 32
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.7980172272802398e-05,
+      "loss": 0.902,
+      "step": 33
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.7790805745256703e-05,
+      "loss": 3.3316,
+      "step": 34
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.7594049166547073e-05,
+      "loss": 0.6502,
+      "step": 35
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.7390089172206594e-05,
+      "loss": 0.8059,
+      "step": 36
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.717911923064442e-05,
+      "loss": 1.1848,
+      "step": 37
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.696133945962927e-05,
+      "loss": 2.206,
+      "step": 38
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.6736956436465573e-05,
+      "loss": 2.4701,
+      "step": 39
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1.650618300204242e-05,
+      "loss": 0.6776,
+      "step": 40
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.626923805894107e-05,
+      "loss": 0.7389,
+      "step": 41
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 1.6026346363792565e-05,
+      "loss": 1.3054,
+      "step": 42
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.5777738314082514e-05,
+      "loss": 1.8761,
+      "step": 43
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.552364972960506e-05,
+      "loss": 0.6992,
+      "step": 44
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 1.526432162877356e-05,
+      "loss": 0.9598,
+      "step": 45
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.915,
+      "step": 46
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 1.4730935568360103e-05,
+      "loss": 0.6342,
+      "step": 47
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.4457383557765385e-05,
+      "loss": 1.183,
+      "step": 48
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.4179603448867836e-05,
+      "loss": 0.4343,
+      "step": 49
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 1.3897858732926794e-05,
+      "loss": 1.1305,
+      "step": 50
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 1.3612416661871532e-05,
+      "loss": 1.8615,
+      "step": 51
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 1.3323547994796597e-05,
+      "loss": 0.4561,
+      "step": 52
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 1.3031526741130435e-05,
+      "loss": 1.5047,
+      "step": 53
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.2736629900720832e-05,
+      "loss": 0.4501,
+      "step": 54
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 1.2439137201083772e-05,
+      "loss": 0.5707,
+      "step": 55
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.2139330832064975e-05,
+      "loss": 0.6563,
+      "step": 56
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.1837495178165706e-05,
+      "loss": 2.1239,
+      "step": 57
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 1.1533916548786856e-05,
+      "loss": 1.5156,
+      "step": 58
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 1.1228882906647142e-05,
+      "loss": 0.4064,
+      "step": 59
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 1.092268359463302e-05,
+      "loss": 0.4697,
+      "step": 60
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 1.0615609061339431e-05,
+      "loss": 0.6203,
+      "step": 61
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 1.0307950585561705e-05,
+      "loss": 1.0488,
+      "step": 62
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 1e-05,
+      "loss": 0.5809,
+      "step": 63
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 9.692049414438298e-06,
+      "loss": 0.5637,
+      "step": 64
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 9.384390938660572e-06,
+      "loss": 0.6708,
+      "step": 65
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 9.07731640536698e-06,
+      "loss": 0.4084,
+      "step": 66
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 8.771117093352861e-06,
+      "loss": 0.6342,
+      "step": 67
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 8.466083451213145e-06,
+      "loss": 0.3105,
+      "step": 68
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 8.162504821834296e-06,
+      "loss": 0.7767,
+      "step": 69
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 7.860669167935028e-06,
+      "loss": 1.0683,
+      "step": 70
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 7.560862798916229e-06,
+      "loss": 0.3493,
+      "step": 71
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 7.263370099279173e-06,
+      "loss": 0.7215,
+      "step": 72
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 6.968473258869566e-06,
+      "loss": 0.364,
+      "step": 73
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 6.6764520052034054e-06,
+      "loss": 0.3022,
+      "step": 74
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 6.387583338128471e-06,
+      "loss": 0.2838,
+      "step": 75
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 6.102141267073207e-06,
+      "loss": 1.0471,
+      "step": 76
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 5.82039655113217e-06,
+      "loss": 1.0706,
+      "step": 77
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 5.542616442234618e-06,
+      "loss": 0.2637,
+      "step": 78
+    },
+    {
+      "epoch": 4.13,
+      "learning_rate": 5.269064431639901e-06,
+      "loss": 0.2863,
+      "step": 79
+    },
+    {
+      "epoch": 4.18,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.427,
+      "step": 80
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 4.7356783712264405e-06,
+      "loss": 0.8951,
+      "step": 81
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 4.476350270394942e-06,
+      "loss": 0.4509,
+      "step": 82
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 4.222261685917489e-06,
+      "loss": 0.4164,
+      "step": 83
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 3.973653636207437e-06,
+      "loss": 0.4345,
+      "step": 84
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 3.730761941058938e-06,
+      "loss": 0.2924,
+      "step": 85
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 3.493816997957582e-06,
+      "loss": 0.5268,
+      "step": 86
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 3.2630435635344283e-06,
+      "loss": 0.2499,
+      "step": 87
+    },
+    {
+      "epoch": 4.6,
+      "learning_rate": 3.0386605403707347e-06,
+      "loss": 0.5463,
+      "step": 88
+    },
+    {
+      "epoch": 4.65,
+      "learning_rate": 2.820880769355582e-06,
+      "loss": 0.8528,
+      "step": 89
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 2.6099108277934105e-06,
+      "loss": 0.2086,
+      "step": 90
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 2.405950833452928e-06,
+      "loss": 0.5901,
+      "step": 91
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 2.209194254743295e-06,
+      "loss": 0.3309,
+      "step": 92
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 2.019827727197605e-06,
+      "loss": 0.2144,
+      "step": 93
+    },
+    {
+      "epoch": 4.91,
+      "learning_rate": 1.8380308764377841e-06,
+      "loss": 0.208,
+      "step": 94
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 1.663976147788806e-06,
+      "loss": 0.9179,
+      "step": 95
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 1.4978286427038602e-06,
+      "loss": 0.384,
+      "step": 96
+    },
+    {
+      "epoch": 5.07,
+      "learning_rate": 1.339745962155613e-06,
+      "loss": 0.2262,
+      "step": 97
+    },
+    {
+      "epoch": 5.12,
+      "learning_rate": 1.1898780571421554e-06,
+      "loss": 0.2064,
+      "step": 98
+    },
+    {
+      "epoch": 5.17,
+      "learning_rate": 1.0483670864493777e-06,
+      "loss": 0.2237,
+      "step": 99
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 9.153472818047627e-07,
+      "loss": 0.3679,
+      "step": 100
+    },
+    {
+      "epoch": 5.28,
+      "learning_rate": 7.909448205504633e-07,
+      "loss": 0.3021,
+      "step": 101
+    },
+    {
+      "epoch": 5.33,
+      "learning_rate": 6.752777059564431e-07,
+      "loss": 0.3259,
+      "step": 102
+    },
+    {
+      "epoch": 5.38,
+      "learning_rate": 5.684556552872256e-07,
+      "loss": 0.2477,
+      "step": 103
+    },
+    {
+      "epoch": 5.43,
+      "learning_rate": 4.7057999572843516e-07,
+      "loss": 0.1951,
+      "step": 104
+    },
+    {
+      "epoch": 5.49,
+      "learning_rate": 3.817435682718096e-07,
+      "loss": 0.3738,
+      "step": 105
+    },
+    {
+      "epoch": 5.54,
+      "learning_rate": 3.020306396499062e-07,
+      "loss": 0.2194,
+      "step": 106
+    },
+    {
+      "epoch": 5.59,
+      "learning_rate": 2.315168224039932e-07,
+      "loss": 0.4283,
+      "step": 107
+    },
+    {
+      "epoch": 5.64,
+      "learning_rate": 1.7026900316098217e-07,
+      "loss": 0.86,
+      "step": 108
+    },
+    {
+      "epoch": 5.69,
+      "learning_rate": 1.1834527918740624e-07,
+      "loss": 0.1774,
+      "step": 109
+    },
+    {
+      "epoch": 5.75,
+      "learning_rate": 7.579490328064265e-08,
+      "loss": 0.2705,
+      "step": 110
+    },
+    {
+      "epoch": 5.8,
+      "learning_rate": 4.2658237049655325e-08,
+      "loss": 0.3743,
+      "step": 111
+    },
+    {
+      "epoch": 5.85,
+      "learning_rate": 1.896671262955896e-08,
+      "loss": 0.1744,
+      "step": 112
+    },
+    {
+      "epoch": 5.9,
+      "learning_rate": 4.74280286634099e-09,
+      "loss": 0.1446,
+      "step": 113
+    },
+    {
+      "epoch": 5.96,
+      "learning_rate": 0.0,
+      "loss": 0.6711,
+      "step": 114
+    },
+    {
+      "epoch": 5.96,
+      "step": 114,
+      "total_flos": 5.099950184243134e+18,
+      "train_loss": 0.9367022931314352,
+      "train_runtime": 10489.7515,
+      "train_samples_per_second": 5.605,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 114,
+  "num_train_epochs": 6,
+  "save_steps": 100,
+  "total_flos": 5.099950184243134e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff712400c5bcdc839e3a24f63bd9dbd285160537bf97a6c2d13204da5c91fcbe
+size 6072