Upload folder using huggingface_hub

README.md

@@ -0,0 +1,78 @@
+---
+license: other
+base_model: meta-llama/Llama-2-7b-hf
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: hyporadise
+  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. -->
+
+# hyporadise
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the hyporadise dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3419
+
+## 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-05
+- train_batch_size: 8
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.3436        | 0.21  | 100  | 0.3495          |
+| 0.3306        | 0.42  | 200  | 0.3352          |
+| 0.3417        | 0.63  | 300  | 0.3245          |
+| 0.3154        | 0.84  | 400  | 0.3160          |
+| 0.1577        | 1.05  | 500  | 0.3239          |
+| 0.159         | 1.26  | 600  | 0.3230          |
+| 0.1493        | 1.48  | 700  | 0.3176          |
+| 0.1498        | 1.69  | 800  | 0.3158          |
+| 0.147         | 1.9   | 900  | 0.3104          |
+| 0.0583        | 2.11  | 1000 | 0.3452          |
+| 0.0547        | 2.32  | 1100 | 0.3395          |
+| 0.0589        | 2.53  | 1200 | 0.3417          |
+| 0.0593        | 2.74  | 1300 | 0.3414          |
+| 0.0624        | 2.95  | 1400 | 0.3420          |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.3418794870376587,
+    "eval_runtime": 47.7981,
+    "eval_samples_per_second": 282.25,
+    "eval_steps_per_second": 8.829,
+    "train_loss": 0.18191866144936128,
+    "train_runtime": 7053.867,
+    "train_samples_per_second": 51.639,
+    "train_steps_per_second": 0.202
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.3418794870376587,
+    "eval_runtime": 47.7981,
+    "eval_samples_per_second": 282.25,
+    "eval_steps_per_second": 8.829
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836ace6bd72e251e82ca37883d8a66e2d27f33641a7a7c7fd55e7fbc807cc728
+size 4938985352

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:827286d347c6f9acf296e2f21015464569cb792e281d1f3b7f6c1c434e6c7d70
+size 4947390880

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:420d9bdebad5206f8f2c3d7801f254cb070639096ea6090111c58cdd89c14d72
+size 3590488816

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13476831232
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

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": "</s>",
+  "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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.18191866144936128,
+    "train_runtime": 7053.867,
+    "train_samples_per_second": 51.639,
+    "train_steps_per_second": 0.202
+}

trainer_log.jsonl

@@ -0,0 +1,158 @@
+{"current_steps": 10, "total_steps": 1422, "loss": 0.681, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5e-05, "epoch": 0.02, "percentage": 0.7, "elapsed_time": "0:00:39", "remaining_time": "1:33:21"}
+{"current_steps": 20, "total_steps": 1422, "loss": 0.3735, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 0.04, "percentage": 1.41, "elapsed_time": "0:01:18", "remaining_time": "1:31:19"}
+{"current_steps": 30, "total_steps": 1422, "loss": 0.3481, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9993723817567996e-05, "epoch": 0.06, "percentage": 2.11, "elapsed_time": "0:01:56", "remaining_time": "1:30:16"}
+{"current_steps": 40, "total_steps": 1422, "loss": 0.3733, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.997489842150924e-05, "epoch": 0.08, "percentage": 2.81, "elapsed_time": "0:02:36", "remaining_time": "1:29:49"}
+{"current_steps": 50, "total_steps": 1422, "loss": 0.3561, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.994353326395334e-05, "epoch": 0.11, "percentage": 3.52, "elapsed_time": "0:03:15", "remaining_time": "1:29:33"}
+{"current_steps": 60, "total_steps": 1422, "loss": 0.355, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.989964409317637e-05, "epoch": 0.13, "percentage": 4.22, "elapsed_time": "0:03:55", "remaining_time": "1:29:15"}
+{"current_steps": 70, "total_steps": 1422, "loss": 0.3444, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.984325294569372e-05, "epoch": 0.15, "percentage": 4.92, "elapsed_time": "0:04:37", "remaining_time": "1:29:18"}
+{"current_steps": 80, "total_steps": 1422, "loss": 0.3373, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.977438813519574e-05, "epoch": 0.17, "percentage": 5.63, "elapsed_time": "0:05:16", "remaining_time": "1:28:22"}
+{"current_steps": 90, "total_steps": 1422, "loss": 0.3602, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.969308423833152e-05, "epoch": 0.19, "percentage": 6.33, "elapsed_time": "0:05:56", "remaining_time": "1:27:48"}
+{"current_steps": 100, "total_steps": 1422, "loss": 0.3436, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9599382077348205e-05, "epoch": 0.21, "percentage": 7.03, "elapsed_time": "0:06:35", "remaining_time": "1:27:04"}
+{"current_steps": 100, "total_steps": 1422, "loss": null, "eval_loss": 0.34954115748405457, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.21, "percentage": 7.03, "elapsed_time": "0:06:35", "remaining_time": "1:27:04"}
+{"current_steps": 110, "total_steps": 1422, "loss": 0.352, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.949332869959432e-05, "epoch": 0.23, "percentage": 7.74, "elapsed_time": "0:08:48", "remaining_time": "1:45:09"}
+{"current_steps": 120, "total_steps": 1422, "loss": 0.3426, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9374977353897566e-05, "epoch": 0.25, "percentage": 8.44, "elapsed_time": "0:09:32", "remaining_time": "1:43:29"}
+{"current_steps": 130, "total_steps": 1422, "loss": 0.3422, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9244387463828876e-05, "epoch": 0.27, "percentage": 9.14, "elapsed_time": "0:10:14", "remaining_time": "1:41:47"}
+{"current_steps": 140, "total_steps": 1422, "loss": 0.3378, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.910162459786617e-05, "epoch": 0.3, "percentage": 9.85, "elapsed_time": "0:10:56", "remaining_time": "1:40:10"}
+{"current_steps": 150, "total_steps": 1422, "loss": 0.3381, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.894676043647274e-05, "epoch": 0.32, "percentage": 10.55, "elapsed_time": "0:11:38", "remaining_time": "1:38:41"}
+{"current_steps": 160, "total_steps": 1422, "loss": 0.3214, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8779872736106916e-05, "epoch": 0.34, "percentage": 11.25, "elapsed_time": "0:12:16", "remaining_time": "1:36:52"}
+{"current_steps": 170, "total_steps": 1422, "loss": 0.3372, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8601045290180946e-05, "epoch": 0.36, "percentage": 11.95, "elapsed_time": "0:12:57", "remaining_time": "1:35:24"}
+{"current_steps": 180, "total_steps": 1422, "loss": 0.3378, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.84103678869888e-05, "epoch": 0.38, "percentage": 12.66, "elapsed_time": "0:13:37", "remaining_time": "1:34:03"}
+{"current_steps": 190, "total_steps": 1422, "loss": 0.3218, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.820793626462391e-05, "epoch": 0.4, "percentage": 13.36, "elapsed_time": "0:14:16", "remaining_time": "1:32:35"}
+{"current_steps": 200, "total_steps": 1422, "loss": 0.3306, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.799385206290965e-05, "epoch": 0.42, "percentage": 14.06, "elapsed_time": "0:14:56", "remaining_time": "1:31:19"}
+{"current_steps": 200, "total_steps": 1422, "loss": null, "eval_loss": 0.33515387773513794, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.42, "percentage": 14.06, "elapsed_time": "0:14:56", "remaining_time": "1:31:19"}
+{"current_steps": 210, "total_steps": 1422, "loss": 0.3288, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7768222772366466e-05, "epoch": 0.44, "percentage": 14.77, "elapsed_time": "0:17:14", "remaining_time": "1:39:31"}
+{"current_steps": 220, "total_steps": 1422, "loss": 0.3052, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.753116168024153e-05, "epoch": 0.46, "percentage": 15.47, "elapsed_time": "0:17:56", "remaining_time": "1:37:59"}
+{"current_steps": 230, "total_steps": 1422, "loss": 0.3329, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.728278781362777e-05, "epoch": 0.48, "percentage": 16.17, "elapsed_time": "0:18:33", "remaining_time": "1:36:11"}
+{"current_steps": 240, "total_steps": 1422, "loss": 0.3305, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.702322587970104e-05, "epoch": 0.51, "percentage": 16.88, "elapsed_time": "0:19:14", "remaining_time": "1:34:43"}
+{"current_steps": 250, "total_steps": 1422, "loss": 0.3293, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6752606203105314e-05, "epoch": 0.53, "percentage": 17.58, "elapsed_time": "0:19:55", "remaining_time": "1:33:25"}
+{"current_steps": 260, "total_steps": 1422, "loss": 0.3276, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.647106466051741e-05, "epoch": 0.55, "percentage": 18.28, "elapsed_time": "0:20:33", "remaining_time": "1:31:54"}
+{"current_steps": 270, "total_steps": 1422, "loss": 0.3148, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.617874261242399e-05, "epoch": 0.57, "percentage": 18.99, "elapsed_time": "0:21:13", "remaining_time": "1:30:34"}
+{"current_steps": 280, "total_steps": 1422, "loss": 0.3131, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5875786832145287e-05, "epoch": 0.59, "percentage": 19.69, "elapsed_time": "0:21:53", "remaining_time": "1:29:16"}
+{"current_steps": 290, "total_steps": 1422, "loss": 0.3222, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.556234943214095e-05, "epoch": 0.61, "percentage": 20.39, "elapsed_time": "0:22:32", "remaining_time": "1:28:00"}
+{"current_steps": 300, "total_steps": 1422, "loss": 0.3417, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.523858778763528e-05, "epoch": 0.63, "percentage": 21.1, "elapsed_time": "0:23:11", "remaining_time": "1:26:45"}
+{"current_steps": 300, "total_steps": 1422, "loss": null, "eval_loss": 0.32445600628852844, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.63, "percentage": 21.1, "elapsed_time": "0:23:11", "remaining_time": "1:26:45"}
+{"current_steps": 310, "total_steps": 1422, "loss": 0.3152, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.490466445759988e-05, "epoch": 0.65, "percentage": 21.8, "elapsed_time": "0:25:37", "remaining_time": "1:31:56"}
+{"current_steps": 320, "total_steps": 1422, "loss": 0.3038, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.456074710313378e-05, "epoch": 0.67, "percentage": 22.5, "elapsed_time": "0:26:16", "remaining_time": "1:30:28"}
+{"current_steps": 330, "total_steps": 1422, "loss": 0.3082, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.420700840328162e-05, "epoch": 0.7, "percentage": 23.21, "elapsed_time": "0:26:57", "remaining_time": "1:29:13"}
+{"current_steps": 340, "total_steps": 1422, "loss": 0.3174, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.38436259683325e-05, "epoch": 0.72, "percentage": 23.91, "elapsed_time": "0:27:36", "remaining_time": "1:27:50"}
+{"current_steps": 350, "total_steps": 1422, "loss": 0.3238, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.347078225064276e-05, "epoch": 0.74, "percentage": 24.61, "elapsed_time": "0:28:14", "remaining_time": "1:26:31"}
+{"current_steps": 360, "total_steps": 1422, "loss": 0.3036, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.308866445302766e-05, "epoch": 0.76, "percentage": 25.32, "elapsed_time": "0:28:54", "remaining_time": "1:25:18"}
+{"current_steps": 370, "total_steps": 1422, "loss": 0.3053, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.269746443476787e-05, "epoch": 0.78, "percentage": 26.02, "elapsed_time": "0:29:34", "remaining_time": "1:24:04"}
+{"current_steps": 380, "total_steps": 1422, "loss": 0.3082, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.2297378615277935e-05, "epoch": 0.8, "percentage": 26.72, "elapsed_time": "0:30:15", "remaining_time": "1:22:57"}
+{"current_steps": 390, "total_steps": 1422, "loss": 0.3126, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.188860787548522e-05, "epoch": 0.82, "percentage": 27.43, "elapsed_time": "0:30:56", "remaining_time": "1:21:52"}
+{"current_steps": 400, "total_steps": 1422, "loss": 0.3154, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1471357456968556e-05, "epoch": 0.84, "percentage": 28.13, "elapsed_time": "0:31:36", "remaining_time": "1:20:44"}
+{"current_steps": 400, "total_steps": 1422, "loss": null, "eval_loss": 0.31601378321647644, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.84, "percentage": 28.13, "elapsed_time": "0:31:36", "remaining_time": "1:20:44"}
+{"current_steps": 410, "total_steps": 1422, "loss": 0.3144, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1045836858907676e-05, "epoch": 0.86, "percentage": 28.83, "elapsed_time": "0:33:53", "remaining_time": "1:23:39"}
+{"current_steps": 420, "total_steps": 1422, "loss": 0.3054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.061225973289473e-05, "epoch": 0.89, "percentage": 29.54, "elapsed_time": "0:34:32", "remaining_time": "1:22:24"}
+{"current_steps": 430, "total_steps": 1422, "loss": 0.3132, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.0170843775661025e-05, "epoch": 0.91, "percentage": 30.24, "elapsed_time": "0:35:13", "remaining_time": "1:21:15"}
+{"current_steps": 440, "total_steps": 1422, "loss": 0.3096, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9721810619772636e-05, "epoch": 0.93, "percentage": 30.94, "elapsed_time": "0:35:51", "remaining_time": "1:20:01"}
+{"current_steps": 450, "total_steps": 1422, "loss": 0.3112, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.926538572234991e-05, "epoch": 0.95, "percentage": 31.65, "elapsed_time": "0:36:29", "remaining_time": "1:18:50"}
+{"current_steps": 460, "total_steps": 1422, "loss": 0.32, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.880179825186667e-05, "epoch": 0.97, "percentage": 32.35, "elapsed_time": "0:37:09", "remaining_time": "1:17:42"}
+{"current_steps": 470, "total_steps": 1422, "loss": 0.2963, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.833128097308594e-05, "epoch": 0.99, "percentage": 33.05, "elapsed_time": "0:37:50", "remaining_time": "1:16:39"}
+{"current_steps": 480, "total_steps": 1422, "loss": 0.2216, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.785407013019006e-05, "epoch": 1.01, "percentage": 33.76, "elapsed_time": "0:38:28", "remaining_time": "1:15:31"}
+{"current_steps": 490, "total_steps": 1422, "loss": 0.1707, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.73704053281637e-05, "epoch": 1.03, "percentage": 34.46, "elapsed_time": "0:39:08", "remaining_time": "1:14:26"}
+{"current_steps": 500, "total_steps": 1422, "loss": 0.1577, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.688052941248956e-05, "epoch": 1.05, "percentage": 35.16, "elapsed_time": "0:39:46", "remaining_time": "1:13:20"}
+{"current_steps": 500, "total_steps": 1422, "loss": null, "eval_loss": 0.3239268660545349, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.05, "percentage": 35.16, "elapsed_time": "0:39:46", "remaining_time": "1:13:20"}
+{"current_steps": 510, "total_steps": 1422, "loss": 0.1549, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6384688347216875e-05, "epoch": 1.07, "percentage": 35.86, "elapsed_time": "0:41:58", "remaining_time": "1:15:04"}
+{"current_steps": 520, "total_steps": 1422, "loss": 0.1597, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.58831310914643e-05, "epoch": 1.1, "percentage": 36.57, "elapsed_time": "0:42:38", "remaining_time": "1:13:58"}
+{"current_steps": 530, "total_steps": 1422, "loss": 0.1492, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.53761094744188e-05, "epoch": 1.12, "percentage": 37.27, "elapsed_time": "0:43:20", "remaining_time": "1:12:57"}
+{"current_steps": 540, "total_steps": 1422, "loss": 0.1576, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.4863878068893625e-05, "epoch": 1.14, "percentage": 37.97, "elapsed_time": "0:44:01", "remaining_time": "1:11:53"}
+{"current_steps": 550, "total_steps": 1422, "loss": 0.152, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.434669406350866e-05, "epoch": 1.16, "percentage": 38.68, "elapsed_time": "0:44:40", "remaining_time": "1:10:50"}
+{"current_steps": 560, "total_steps": 1422, "loss": 0.1581, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.382481713355738e-05, "epoch": 1.18, "percentage": 39.38, "elapsed_time": "0:45:23", "remaining_time": "1:09:52"}
+{"current_steps": 570, "total_steps": 1422, "loss": 0.1574, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3298509310625363e-05, "epoch": 1.2, "percentage": 40.08, "elapsed_time": "0:46:04", "remaining_time": "1:08:51"}
+{"current_steps": 580, "total_steps": 1422, "loss": 0.1578, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.276803485102557e-05, "epoch": 1.22, "percentage": 40.79, "elapsed_time": "0:46:44", "remaining_time": "1:07:51"}
+{"current_steps": 590, "total_steps": 1422, "loss": 0.1514, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.223366010311671e-05, "epoch": 1.24, "percentage": 41.49, "elapsed_time": "0:47:22", "remaining_time": "1:06:48"}
+{"current_steps": 600, "total_steps": 1422, "loss": 0.159, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.1695653373571196e-05, "epoch": 1.26, "percentage": 42.19, "elapsed_time": "0:48:03", "remaining_time": "1:05:50"}
+{"current_steps": 600, "total_steps": 1422, "loss": null, "eval_loss": 0.32300886511802673, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.26, "percentage": 42.19, "elapsed_time": "0:48:03", "remaining_time": "1:05:50"}
+{"current_steps": 610, "total_steps": 1422, "loss": 0.1527, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.115428479265975e-05, "epoch": 1.29, "percentage": 42.9, "elapsed_time": "0:50:17", "remaining_time": "1:06:57"}
+{"current_steps": 620, "total_steps": 1422, "loss": 0.1542, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.060982617862053e-05, "epoch": 1.31, "percentage": 43.6, "elapsed_time": "0:50:58", "remaining_time": "1:05:56"}
+{"current_steps": 630, "total_steps": 1422, "loss": 0.1574, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.006255090118059e-05, "epoch": 1.33, "percentage": 44.3, "elapsed_time": "0:51:37", "remaining_time": "1:04:54"}
+{"current_steps": 640, "total_steps": 1422, "loss": 0.1599, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9512733744298482e-05, "epoch": 1.35, "percentage": 45.01, "elapsed_time": "0:52:15", "remaining_time": "1:03:51"}
+{"current_steps": 650, "total_steps": 1422, "loss": 0.1527, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8960650768196672e-05, "epoch": 1.37, "percentage": 45.71, "elapsed_time": "0:52:56", "remaining_time": "1:02:52"}
+{"current_steps": 660, "total_steps": 1422, "loss": 0.1555, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8406579170753205e-05, "epoch": 1.39, "percentage": 46.41, "elapsed_time": "0:53:39", "remaining_time": "1:01:56"}
+{"current_steps": 670, "total_steps": 1422, "loss": 0.1503, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.785079714832216e-05, "epoch": 1.41, "percentage": 47.12, "elapsed_time": "0:54:18", "remaining_time": "1:00:57"}
+{"current_steps": 680, "total_steps": 1422, "loss": 0.1615, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7293583756052755e-05, "epoch": 1.43, "percentage": 47.82, "elapsed_time": "0:54:58", "remaining_time": "0:59:59"}
+{"current_steps": 690, "total_steps": 1422, "loss": 0.1527, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.673521876777727e-05, "epoch": 1.45, "percentage": 48.52, "elapsed_time": "0:55:38", "remaining_time": "0:59:02"}
+{"current_steps": 700, "total_steps": 1422, "loss": 0.1493, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6175982535538098e-05, "epoch": 1.48, "percentage": 49.23, "elapsed_time": "0:56:17", "remaining_time": "0:58:03"}
+{"current_steps": 700, "total_steps": 1422, "loss": null, "eval_loss": 0.3175669312477112, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.48, "percentage": 49.23, "elapsed_time": "0:56:17", "remaining_time": "0:58:03"}
+{"current_steps": 710, "total_steps": 1422, "loss": 0.1607, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.561615584882453e-05, "epoch": 1.5, "percentage": 49.93, "elapsed_time": "0:58:31", "remaining_time": "0:58:41"}
+{"current_steps": 720, "total_steps": 1422, "loss": 0.1492, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5056019793589858e-05, "epoch": 1.52, "percentage": 50.63, "elapsed_time": "0:59:08", "remaining_time": "0:57:39"}
+{"current_steps": 730, "total_steps": 1422, "loss": 0.1324, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.449585561111965e-05, "epoch": 1.54, "percentage": 51.34, "elapsed_time": "0:59:50", "remaining_time": "0:56:43"}
+{"current_steps": 740, "total_steps": 1422, "loss": 0.1555, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3935944556821966e-05, "epoch": 1.56, "percentage": 52.04, "elapsed_time": "1:00:31", "remaining_time": "0:55:46"}
+{"current_steps": 750, "total_steps": 1422, "loss": 0.1528, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3376567759010614e-05, "epoch": 1.58, "percentage": 52.74, "elapsed_time": "1:01:11", "remaining_time": "0:54:50"}
+{"current_steps": 760, "total_steps": 1422, "loss": 0.152, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.281800607775211e-05, "epoch": 1.6, "percentage": 53.45, "elapsed_time": "1:01:53", "remaining_time": "0:53:54"}
+{"current_steps": 770, "total_steps": 1422, "loss": 0.1534, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2260539963847317e-05, "epoch": 1.62, "percentage": 54.15, "elapsed_time": "1:02:32", "remaining_time": "0:52:57"}
+{"current_steps": 780, "total_steps": 1422, "loss": 0.1592, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1704449318018692e-05, "epoch": 1.64, "percentage": 54.85, "elapsed_time": "1:03:13", "remaining_time": "0:52:02"}
+{"current_steps": 790, "total_steps": 1422, "loss": 0.1426, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1150013350373594e-05, "epoch": 1.66, "percentage": 55.56, "elapsed_time": "1:03:55", "remaining_time": "0:51:08"}
+{"current_steps": 800, "total_steps": 1422, "loss": 0.1498, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.059751044021441e-05, "epoch": 1.69, "percentage": 56.26, "elapsed_time": "1:04:34", "remaining_time": "0:50:12"}
+{"current_steps": 800, "total_steps": 1422, "loss": null, "eval_loss": 0.31580981612205505, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.69, "percentage": 56.26, "elapsed_time": "1:04:34", "remaining_time": "0:50:12"}
+{"current_steps": 810, "total_steps": 1422, "loss": 0.1437, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.00472179962658e-05, "epoch": 1.71, "percentage": 56.96, "elapsed_time": "1:06:49", "remaining_time": "0:50:29"}
+{"current_steps": 820, "total_steps": 1422, "loss": 0.156, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9499412317389305e-05, "epoch": 1.73, "percentage": 57.67, "elapsed_time": "1:07:31", "remaining_time": "0:49:34"}
+{"current_steps": 830, "total_steps": 1422, "loss": 0.1496, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.895436845385516e-05, "epoch": 1.75, "percentage": 58.37, "elapsed_time": "1:08:11", "remaining_time": "0:48:38"}
+{"current_steps": 840, "total_steps": 1422, "loss": 0.1454, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8412360069241034e-05, "epoch": 1.77, "percentage": 59.07, "elapsed_time": "1:08:52", "remaining_time": "0:47:43"}
+{"current_steps": 850, "total_steps": 1422, "loss": 0.1492, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7873659303027052e-05, "epoch": 1.79, "percentage": 59.77, "elapsed_time": "1:09:33", "remaining_time": "0:46:48"}
+{"current_steps": 860, "total_steps": 1422, "loss": 0.1535, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.733853663395602e-05, "epoch": 1.81, "percentage": 60.48, "elapsed_time": "1:10:13", "remaining_time": "0:45:53"}
+{"current_steps": 870, "total_steps": 1422, "loss": 0.1479, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6807260744227513e-05, "epoch": 1.83, "percentage": 61.18, "elapsed_time": "1:10:55", "remaining_time": "0:44:59"}
+{"current_steps": 880, "total_steps": 1422, "loss": 0.1452, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6280098384593966e-05, "epoch": 1.85, "percentage": 61.88, "elapsed_time": "1:11:35", "remaining_time": "0:44:05"}
+{"current_steps": 890, "total_steps": 1422, "loss": 0.1417, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5757314240426613e-05, "epoch": 1.88, "percentage": 62.59, "elapsed_time": "1:12:15", "remaining_time": "0:43:11"}
+{"current_steps": 900, "total_steps": 1422, "loss": 0.147, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5239170798818381e-05, "epoch": 1.9, "percentage": 63.29, "elapsed_time": "1:12:54", "remaining_time": "0:42:17"}
+{"current_steps": 900, "total_steps": 1422, "loss": null, "eval_loss": 0.3103533089160919, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.9, "percentage": 63.29, "elapsed_time": "1:12:54", "remaining_time": "0:42:17"}
+{"current_steps": 910, "total_steps": 1422, "loss": 0.1599, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.472592821679048e-05, "epoch": 1.92, "percentage": 63.99, "elapsed_time": "1:15:08", "remaining_time": "0:42:16"}
+{"current_steps": 920, "total_steps": 1422, "loss": 0.1413, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4217844190669058e-05, "epoch": 1.94, "percentage": 64.7, "elapsed_time": "1:15:50", "remaining_time": "0:41:22"}
+{"current_steps": 930, "total_steps": 1422, "loss": 0.1575, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3715173826697209e-05, "epoch": 1.96, "percentage": 65.4, "elapsed_time": "1:16:31", "remaining_time": "0:40:28"}
+{"current_steps": 940, "total_steps": 1422, "loss": 0.1368, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3218169512947542e-05, "epoch": 1.98, "percentage": 66.1, "elapsed_time": "1:17:10", "remaining_time": "0:39:34"}
+{"current_steps": 950, "total_steps": 1422, "loss": 0.1356, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2727080792599455e-05, "epoch": 2.0, "percentage": 66.81, "elapsed_time": "1:17:51", "remaining_time": "0:38:41"}
+{"current_steps": 960, "total_steps": 1422, "loss": 0.0618, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2242154238644879e-05, "epoch": 2.02, "percentage": 67.51, "elapsed_time": "1:18:31", "remaining_time": "0:37:47"}
+{"current_steps": 970, "total_steps": 1422, "loss": 0.0638, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1763633330085325e-05, "epoch": 2.04, "percentage": 68.21, "elapsed_time": "1:19:10", "remaining_time": "0:36:53"}
+{"current_steps": 980, "total_steps": 1422, "loss": 0.0611, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1291758329682358e-05, "epoch": 2.07, "percentage": 68.92, "elapsed_time": "1:19:50", "remaining_time": "0:36:00"}
+{"current_steps": 990, "total_steps": 1422, "loss": 0.0575, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0826766163322982e-05, "epoch": 2.09, "percentage": 69.62, "elapsed_time": "1:20:30", "remaining_time": "0:35:07"}
+{"current_steps": 1000, "total_steps": 1422, "loss": 0.0583, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0368890301060457e-05, "epoch": 2.11, "percentage": 70.32, "elapsed_time": "1:21:09", "remaining_time": "0:34:14"}
+{"current_steps": 1000, "total_steps": 1422, "loss": null, "eval_loss": 0.34516656398773193, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.11, "percentage": 70.32, "elapsed_time": "1:21:09", "remaining_time": "0:34:14"}
+{"current_steps": 1010, "total_steps": 1422, "loss": 0.0601, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.918360639890187e-06, "epoch": 2.13, "percentage": 71.03, "elapsed_time": "1:23:26", "remaining_time": "0:34:02"}
+{"current_steps": 1020, "total_steps": 1422, "loss": 0.0562, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.475403388319752e-06, "epoch": 2.15, "percentage": 71.73, "elapsed_time": "1:24:03", "remaining_time": "0:33:07"}
+{"current_steps": 1030, "total_steps": 1422, "loss": 0.06, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.040240952790765e-06, "epoch": 2.17, "percentage": 72.43, "elapsed_time": "1:24:41", "remaining_time": "0:32:14"}
+{"current_steps": 1040, "total_steps": 1422, "loss": 0.0586, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.613091826009884e-06, "epoch": 2.19, "percentage": 73.14, "elapsed_time": "1:25:22", "remaining_time": "0:31:21"}
+{"current_steps": 1050, "total_steps": 1422, "loss": 0.0555, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.194170477244729e-06, "epoch": 2.21, "percentage": 73.84, "elapsed_time": "1:26:04", "remaining_time": "0:30:29"}
+{"current_steps": 1060, "total_steps": 1422, "loss": 0.0586, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.783687244640048e-06, "epoch": 2.23, "percentage": 74.54, "elapsed_time": "1:26:43", "remaining_time": "0:29:37"}
+{"current_steps": 1070, "total_steps": 1422, "loss": 0.0563, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.38184822960811e-06, "epoch": 2.26, "percentage": 75.25, "elapsed_time": "1:27:23", "remaining_time": "0:28:45"}
+{"current_steps": 1080, "total_steps": 1422, "loss": 0.0591, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.988855193346236e-06, "epoch": 2.28, "percentage": 75.95, "elapsed_time": "1:28:03", "remaining_time": "0:27:53"}
+{"current_steps": 1090, "total_steps": 1422, "loss": 0.0581, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.604905455533625e-06, "epoch": 2.3, "percentage": 76.65, "elapsed_time": "1:28:43", "remaining_time": "0:27:01"}
+{"current_steps": 1100, "total_steps": 1422, "loss": 0.0547, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.230191795258228e-06, "epoch": 2.32, "percentage": 77.36, "elapsed_time": "1:29:24", "remaining_time": "0:26:10"}
+{"current_steps": 1100, "total_steps": 1422, "loss": null, "eval_loss": 0.3394644260406494, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.32, "percentage": 77.36, "elapsed_time": "1:29:24", "remaining_time": "0:26:10"}
+{"current_steps": 1110, "total_steps": 1422, "loss": 0.0647, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.864902354223384e-06, "epoch": 2.34, "percentage": 78.06, "elapsed_time": "1:31:42", "remaining_time": "0:25:46"}
+{"current_steps": 1120, "total_steps": 1422, "loss": 0.0579, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.509220542282864e-06, "epoch": 2.36, "percentage": 78.76, "elapsed_time": "1:32:22", "remaining_time": "0:24:54"}
+{"current_steps": 1130, "total_steps": 1422, "loss": 0.0547, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.163324945351841e-06, "epoch": 2.38, "percentage": 79.47, "elapsed_time": "1:33:01", "remaining_time": "0:24:02"}
+{"current_steps": 1140, "total_steps": 1422, "loss": 0.0522, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.82738923573983e-06, "epoch": 2.4, "percentage": 80.17, "elapsed_time": "1:33:42", "remaining_time": "0:23:10"}
+{"current_steps": 1150, "total_steps": 1422, "loss": 0.0546, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.501582084950715e-06, "epoch": 2.42, "percentage": 80.87, "elapsed_time": "1:34:24", "remaining_time": "0:22:19"}
+{"current_steps": 1160, "total_steps": 1422, "loss": 0.0549, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.186067078993794e-06, "epoch": 2.44, "percentage": 81.58, "elapsed_time": "1:35:06", "remaining_time": "0:21:28"}
+{"current_steps": 1170, "total_steps": 1422, "loss": 0.0587, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.8810026362480684e-06, "epoch": 2.47, "percentage": 82.28, "elapsed_time": "1:35:47", "remaining_time": "0:20:37"}
+{"current_steps": 1180, "total_steps": 1422, "loss": 0.0581, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.586541927921222e-06, "epoch": 2.49, "percentage": 82.98, "elapsed_time": "1:36:27", "remaining_time": "0:19:46"}
+{"current_steps": 1190, "total_steps": 1422, "loss": 0.0575, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3028328011432157e-06, "epoch": 2.51, "percentage": 83.68, "elapsed_time": "1:37:06", "remaining_time": "0:18:55"}
+{"current_steps": 1200, "total_steps": 1422, "loss": 0.0589, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.030017704733043e-06, "epoch": 2.53, "percentage": 84.39, "elapsed_time": "1:37:45", "remaining_time": "0:18:05"}
+{"current_steps": 1200, "total_steps": 1422, "loss": null, "eval_loss": 0.34168508648872375, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.53, "percentage": 84.39, "elapsed_time": "1:37:45", "remaining_time": "0:18:05"}
+{"current_steps": 1210, "total_steps": 1422, "loss": 0.0581, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7682336176759195e-06, "epoch": 2.55, "percentage": 85.09, "elapsed_time": "1:40:05", "remaining_time": "0:17:32"}
+{"current_steps": 1220, "total_steps": 1422, "loss": 0.0546, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.51761198034689e-06, "epoch": 2.57, "percentage": 85.79, "elapsed_time": "1:40:47", "remaining_time": "0:16:41"}
+{"current_steps": 1230, "total_steps": 1422, "loss": 0.0546, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.278278628515354e-06, "epoch": 2.59, "percentage": 86.5, "elapsed_time": "1:41:29", "remaining_time": "0:15:50"}
+{"current_steps": 1240, "total_steps": 1422, "loss": 0.0587, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.050353730163554e-06, "epoch": 2.61, "percentage": 87.2, "elapsed_time": "1:42:09", "remaining_time": "0:14:59"}
+{"current_steps": 1250, "total_steps": 1422, "loss": 0.0591, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8339517251509146e-06, "epoch": 2.63, "percentage": 87.9, "elapsed_time": "1:42:50", "remaining_time": "0:14:09"}
+{"current_steps": 1260, "total_steps": 1422, "loss": 0.0565, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6291812677544121e-06, "epoch": 2.66, "percentage": 88.61, "elapsed_time": "1:43:30", "remaining_time": "0:13:18"}
+{"current_steps": 1270, "total_steps": 1422, "loss": 0.0621, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.436145172113834e-06, "epoch": 2.68, "percentage": 89.31, "elapsed_time": "1:44:11", "remaining_time": "0:12:28"}
+{"current_steps": 1280, "total_steps": 1422, "loss": 0.0585, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2549403606093525e-06, "epoch": 2.7, "percentage": 90.01, "elapsed_time": "1:44:52", "remaining_time": "0:11:38"}
+{"current_steps": 1290, "total_steps": 1422, "loss": 0.0551, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0856578151973246e-06, "epoch": 2.72, "percentage": 90.72, "elapsed_time": "1:45:32", "remaining_time": "0:10:47"}
+{"current_steps": 1300, "total_steps": 1422, "loss": 0.0593, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.283825317287692e-07, "epoch": 2.74, "percentage": 91.42, "elapsed_time": "1:46:11", "remaining_time": "0:09:57"}
+{"current_steps": 1300, "total_steps": 1422, "loss": null, "eval_loss": 0.34135544300079346, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.74, "percentage": 91.42, "elapsed_time": "1:46:11", "remaining_time": "0:09:57"}
+{"current_steps": 1310, "total_steps": 1422, "loss": 0.063, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.83193477273364e-07, "epoch": 2.76, "percentage": 92.12, "elapsed_time": "1:48:27", "remaining_time": "0:09:16"}
+{"current_steps": 1320, "total_steps": 1422, "loss": 0.0556, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.501635504705422e-07, "epoch": 2.78, "percentage": 92.83, "elapsed_time": "1:49:06", "remaining_time": "0:08:25"}
+{"current_steps": 1330, "total_steps": 1422, "loss": 0.0578, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.293595449274685e-07, "epoch": 2.8, "percentage": 93.53, "elapsed_time": "1:49:45", "remaining_time": "0:07:35"}
+{"current_steps": 1340, "total_steps": 1422, "loss": 0.0621, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.208421156823239e-07, "epoch": 2.82, "percentage": 94.23, "elapsed_time": "1:50:25", "remaining_time": "0:06:45"}
+{"current_steps": 1350, "total_steps": 1422, "loss": 0.0615, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2466574874975565e-07, "epoch": 2.85, "percentage": 94.94, "elapsed_time": "1:51:05", "remaining_time": "0:05:55"}
+{"current_steps": 1360, "total_steps": 1422, "loss": 0.0563, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.408787337637164e-07, "epoch": 2.87, "percentage": 95.64, "elapsed_time": "1:51:44", "remaining_time": "0:05:05"}
+{"current_steps": 1370, "total_steps": 1422, "loss": 0.0557, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6952313973152834e-07, "epoch": 2.89, "percentage": 96.34, "elapsed_time": "1:52:22", "remaining_time": "0:04:15"}
+{"current_steps": 1380, "total_steps": 1422, "loss": 0.0519, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1063479391124898e-07, "epoch": 2.91, "percentage": 97.05, "elapsed_time": "1:53:00", "remaining_time": "0:03:26"}
+{"current_steps": 1390, "total_steps": 1422, "loss": 0.0569, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.424326382299394e-08, "epoch": 2.93, "percentage": 97.75, "elapsed_time": "1:53:41", "remaining_time": "0:02:37"}
+{"current_steps": 1400, "total_steps": 1422, "loss": 0.0624, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.037184240325397e-08, "epoch": 2.95, "percentage": 98.45, "elapsed_time": "1:54:21", "remaining_time": "0:01:47"}
+{"current_steps": 1400, "total_steps": 1422, "loss": null, "eval_loss": 0.34196367859840393, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.95, "percentage": 98.45, "elapsed_time": "1:54:21", "remaining_time": "0:01:47"}
+{"current_steps": 1410, "total_steps": 1422, "loss": 0.0549, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.037536309636218e-09, "epoch": 2.97, "percentage": 99.16, "elapsed_time": "1:56:36", "remaining_time": "0:00:59"}
+{"current_steps": 1420, "total_steps": 1422, "loss": 0.0564, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5105738190867033e-10, "epoch": 2.99, "percentage": 99.86, "elapsed_time": "1:57:15", "remaining_time": "0:00:09"}
+{"current_steps": 1422, "total_steps": 1422, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:57:24", "remaining_time": "0:00:00"}
+{"current_steps": 422, "total_steps": 422, "loss": null, "eval_loss": 0.3418794870376587, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:58:25", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1136 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9968387776606953,
+  "eval_steps": 100,
+  "global_step": 1422,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.8102548576192377,
+      "learning_rate": 2.5e-05,
+      "loss": 0.681,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.6409873968033384,
+      "learning_rate": 5e-05,
+      "loss": 0.3735,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.4241968146548056,
+      "learning_rate": 4.9993723817567996e-05,
+      "loss": 0.3481,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.5192149828819788,
+      "learning_rate": 4.997489842150924e-05,
+      "loss": 0.3733,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.3829364414625014,
+      "learning_rate": 4.994353326395334e-05,
+      "loss": 0.3561,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.6320786389820312,
+      "learning_rate": 4.989964409317637e-05,
+      "loss": 0.355,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.4596195084848897,
+      "learning_rate": 4.984325294569372e-05,
+      "loss": 0.3444,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.4431914548343205,
+      "learning_rate": 4.977438813519574e-05,
+      "loss": 0.3373,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 2.498892153458844,
+      "learning_rate": 4.969308423833152e-05,
+      "loss": 0.3602,
+      "step": 90
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.6601234439104857,
+      "learning_rate": 4.9599382077348205e-05,
+      "loss": 0.3436,
+      "step": 100
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.34954115748405457,
+      "eval_runtime": 46.7928,
+      "eval_samples_per_second": 288.314,
+      "eval_steps_per_second": 9.018,
+      "step": 100
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.0930800520190758,
+      "learning_rate": 4.949332869959432e-05,
+      "loss": 0.352,
+      "step": 110
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.5471349397538547,
+      "learning_rate": 4.9374977353897566e-05,
+      "loss": 0.3426,
+      "step": 120
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 1.2518152452620943,
+      "learning_rate": 4.9244387463828876e-05,
+      "loss": 0.3422,
+      "step": 130
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.0687037118070535,
+      "learning_rate": 4.910162459786617e-05,
+      "loss": 0.3378,
+      "step": 140
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.2965517147404728,
+      "learning_rate": 4.894676043647274e-05,
+      "loss": 0.3381,
+      "step": 150
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.077453296704333,
+      "learning_rate": 4.8779872736106916e-05,
+      "loss": 0.3214,
+      "step": 160
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.1426693406130142,
+      "learning_rate": 4.8601045290180946e-05,
+      "loss": 0.3372,
+      "step": 170
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 1.0178221568525938,
+      "learning_rate": 4.84103678869888e-05,
+      "loss": 0.3378,
+      "step": 180
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.228896746635447,
+      "learning_rate": 4.820793626462391e-05,
+      "loss": 0.3218,
+      "step": 190
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 1.7376473974923927,
+      "learning_rate": 4.799385206290965e-05,
+      "loss": 0.3306,
+      "step": 200
+    },
+    {
+      "epoch": 0.42,
+      "eval_loss": 0.33515387773513794,
+      "eval_runtime": 47.1074,
+      "eval_samples_per_second": 286.388,
+      "eval_steps_per_second": 8.958,
+      "step": 200
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 1.1779458621544412,
+      "learning_rate": 4.7768222772366466e-05,
+      "loss": 0.3288,
+      "step": 210
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.0719044164695737,
+      "learning_rate": 4.753116168024153e-05,
+      "loss": 0.3052,
+      "step": 220
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.3092426623376585,
+      "learning_rate": 4.728278781362777e-05,
+      "loss": 0.3329,
+      "step": 230
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 1.3613973232931833,
+      "learning_rate": 4.702322587970104e-05,
+      "loss": 0.3305,
+      "step": 240
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 1.379957402090315,
+      "learning_rate": 4.6752606203105314e-05,
+      "loss": 0.3293,
+      "step": 250
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 1.2064354059145495,
+      "learning_rate": 4.647106466051741e-05,
+      "loss": 0.3276,
+      "step": 260
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.9407218615903679,
+      "learning_rate": 4.617874261242399e-05,
+      "loss": 0.3148,
+      "step": 270
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 1.102895278969822,
+      "learning_rate": 4.5875786832145287e-05,
+      "loss": 0.3131,
+      "step": 280
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 1.1283794552904691,
+      "learning_rate": 4.556234943214095e-05,
+      "loss": 0.3222,
+      "step": 290
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 1.3966644012679954,
+      "learning_rate": 4.523858778763528e-05,
+      "loss": 0.3417,
+      "step": 300
+    },
+    {
+      "epoch": 0.63,
+      "eval_loss": 0.32445600628852844,
+      "eval_runtime": 47.1805,
+      "eval_samples_per_second": 285.945,
+      "eval_steps_per_second": 8.944,
+      "step": 300
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.0630493028269177,
+      "learning_rate": 4.490466445759988e-05,
+      "loss": 0.3152,
+      "step": 310
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 1.0652057869610336,
+      "learning_rate": 4.456074710313378e-05,
+      "loss": 0.3038,
+      "step": 320
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.2341586090990317,
+      "learning_rate": 4.420700840328162e-05,
+      "loss": 0.3082,
+      "step": 330
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.9252822939526227,
+      "learning_rate": 4.38436259683325e-05,
+      "loss": 0.3174,
+      "step": 340
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 1.1914450398759333,
+      "learning_rate": 4.347078225064276e-05,
+      "loss": 0.3238,
+      "step": 350
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 1.0380458098458347,
+      "learning_rate": 4.308866445302766e-05,
+      "loss": 0.3036,
+      "step": 360
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 1.1100397252938874,
+      "learning_rate": 4.269746443476787e-05,
+      "loss": 0.3053,
+      "step": 370
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.0584951830825808,
+      "learning_rate": 4.2297378615277935e-05,
+      "loss": 0.3082,
+      "step": 380
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.1192502727228961,
+      "learning_rate": 4.188860787548522e-05,
+      "loss": 0.3126,
+      "step": 390
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 1.0566732730775144,
+      "learning_rate": 4.1471357456968556e-05,
+      "loss": 0.3154,
+      "step": 400
+    },
+    {
+      "epoch": 0.84,
+      "eval_loss": 0.31601378321647644,
+      "eval_runtime": 47.231,
+      "eval_samples_per_second": 285.639,
+      "eval_steps_per_second": 8.935,
+      "step": 400
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.1380881980287134,
+      "learning_rate": 4.1045836858907676e-05,
+      "loss": 0.3144,
+      "step": 410
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.9239785068723881,
+      "learning_rate": 4.061225973289473e-05,
+      "loss": 0.3054,
+      "step": 420
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 1.1226362379499772,
+      "learning_rate": 4.0170843775661025e-05,
+      "loss": 0.3132,
+      "step": 430
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.055418877421314,
+      "learning_rate": 3.9721810619772636e-05,
+      "loss": 0.3096,
+      "step": 440
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.260485940528199,
+      "learning_rate": 3.926538572234991e-05,
+      "loss": 0.3112,
+      "step": 450
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.8290208161083492,
+      "learning_rate": 3.880179825186667e-05,
+      "loss": 0.32,
+      "step": 460
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.9894500964017104,
+      "learning_rate": 3.833128097308594e-05,
+      "loss": 0.2963,
+      "step": 470
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.8202492183589537,
+      "learning_rate": 3.785407013019006e-05,
+      "loss": 0.2216,
+      "step": 480
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.8958874625557091,
+      "learning_rate": 3.73704053281637e-05,
+      "loss": 0.1707,
+      "step": 490
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.7913123522777149,
+      "learning_rate": 3.688052941248956e-05,
+      "loss": 0.1577,
+      "step": 500
+    },
+    {
+      "epoch": 1.05,
+      "eval_loss": 0.3239268660545349,
+      "eval_runtime": 47.1856,
+      "eval_samples_per_second": 285.913,
+      "eval_steps_per_second": 8.943,
+      "step": 500
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.6951457322398226,
+      "learning_rate": 3.6384688347216875e-05,
+      "loss": 0.1549,
+      "step": 510
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 3.3614607662338507,
+      "learning_rate": 3.58831310914643e-05,
+      "loss": 0.1597,
+      "step": 520
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.8448116369901294,
+      "learning_rate": 3.53761094744188e-05,
+      "loss": 0.1492,
+      "step": 530
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.9188827386043135,
+      "learning_rate": 3.4863878068893625e-05,
+      "loss": 0.1576,
+      "step": 540
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.8781597082892243,
+      "learning_rate": 3.434669406350866e-05,
+      "loss": 0.152,
+      "step": 550
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.6881353088868859,
+      "learning_rate": 3.382481713355738e-05,
+      "loss": 0.1581,
+      "step": 560
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.2684676365868262,
+      "learning_rate": 3.3298509310625363e-05,
+      "loss": 0.1574,
+      "step": 570
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.6337141659864904,
+      "learning_rate": 3.276803485102557e-05,
+      "loss": 0.1578,
+      "step": 580
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.704714314928959,
+      "learning_rate": 3.223366010311671e-05,
+      "loss": 0.1514,
+      "step": 590
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.6460825296146832,
+      "learning_rate": 3.1695653373571196e-05,
+      "loss": 0.159,
+      "step": 600
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 0.32300886511802673,
+      "eval_runtime": 47.067,
+      "eval_samples_per_second": 286.634,
+      "eval_steps_per_second": 8.966,
+      "step": 600
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.8717091665319785,
+      "learning_rate": 3.115428479265975e-05,
+      "loss": 0.1527,
+      "step": 610
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.8221409439379637,
+      "learning_rate": 3.060982617862053e-05,
+      "loss": 0.1542,
+      "step": 620
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.7676631827886251,
+      "learning_rate": 3.006255090118059e-05,
+      "loss": 0.1574,
+      "step": 630
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.8176603071255903,
+      "learning_rate": 2.9512733744298482e-05,
+      "loss": 0.1599,
+      "step": 640
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.8478701648849646,
+      "learning_rate": 2.8960650768196672e-05,
+      "loss": 0.1527,
+      "step": 650
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.8105241966593794,
+      "learning_rate": 2.8406579170753205e-05,
+      "loss": 0.1555,
+      "step": 660
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.7341788063465178,
+      "learning_rate": 2.785079714832216e-05,
+      "loss": 0.1503,
+      "step": 670
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 1.1238252352545457,
+      "learning_rate": 2.7293583756052755e-05,
+      "loss": 0.1615,
+      "step": 680
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.7793278106904632,
+      "learning_rate": 2.673521876777727e-05,
+      "loss": 0.1527,
+      "step": 690
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.7257177280067018,
+      "learning_rate": 2.6175982535538098e-05,
+      "loss": 0.1493,
+      "step": 700
+    },
+    {
+      "epoch": 1.48,
+      "eval_loss": 0.3175669312477112,
+      "eval_runtime": 47.0992,
+      "eval_samples_per_second": 286.438,
+      "eval_steps_per_second": 8.96,
+      "step": 700
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.801964046142728,
+      "learning_rate": 2.561615584882453e-05,
+      "loss": 0.1607,
+      "step": 710
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.7155830027665171,
+      "learning_rate": 2.5056019793589858e-05,
+      "loss": 0.1492,
+      "step": 720
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.7264384440518477,
+      "learning_rate": 2.449585561111965e-05,
+      "loss": 0.1324,
+      "step": 730
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 0.8168302855335549,
+      "learning_rate": 2.3935944556821966e-05,
+      "loss": 0.1555,
+      "step": 740
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.7446449421109613,
+      "learning_rate": 2.3376567759010614e-05,
+      "loss": 0.1528,
+      "step": 750
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6027586148022397,
+      "learning_rate": 2.281800607775211e-05,
+      "loss": 0.152,
+      "step": 760
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.8554567150163206,
+      "learning_rate": 2.2260539963847317e-05,
+      "loss": 0.1534,
+      "step": 770
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.7383522990234253,
+      "learning_rate": 2.1704449318018692e-05,
+      "loss": 0.1592,
+      "step": 780
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.7958490328944942,
+      "learning_rate": 2.1150013350373594e-05,
+      "loss": 0.1426,
+      "step": 790
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 0.9825338160992358,
+      "learning_rate": 2.059751044021441e-05,
+      "loss": 0.1498,
+      "step": 800
+    },
+    {
+      "epoch": 1.69,
+      "eval_loss": 0.31580981612205505,
+      "eval_runtime": 49.0093,
+      "eval_samples_per_second": 275.274,
+      "eval_steps_per_second": 8.611,
+      "step": 800
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.7301707840582428,
+      "learning_rate": 2.00472179962658e-05,
+      "loss": 0.1437,
+      "step": 810
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.9685123461176025,
+      "learning_rate": 1.9499412317389305e-05,
+      "loss": 0.156,
+      "step": 820
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 2.10442864010648,
+      "learning_rate": 1.895436845385516e-05,
+      "loss": 0.1496,
+      "step": 830
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.9146649049632373,
+      "learning_rate": 1.8412360069241034e-05,
+      "loss": 0.1454,
+      "step": 840
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 1.4265670270210795,
+      "learning_rate": 1.7873659303027052e-05,
+      "loss": 0.1492,
+      "step": 850
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.7559717203281935,
+      "learning_rate": 1.733853663395602e-05,
+      "loss": 0.1535,
+      "step": 860
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 1.3311913559020063,
+      "learning_rate": 1.6807260744227513e-05,
+      "loss": 0.1479,
+      "step": 870
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 0.7863355556565459,
+      "learning_rate": 1.6280098384593966e-05,
+      "loss": 0.1452,
+      "step": 880
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.6405600189189222,
+      "learning_rate": 1.5757314240426613e-05,
+      "loss": 0.1417,
+      "step": 890
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.9800841015815575,
+      "learning_rate": 1.5239170798818381e-05,
+      "loss": 0.147,
+      "step": 900
+    },
+    {
+      "epoch": 1.9,
+      "eval_loss": 0.3103533089160919,
+      "eval_runtime": 47.2326,
+      "eval_samples_per_second": 285.629,
+      "eval_steps_per_second": 8.935,
+      "step": 900
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.8072145902479386,
+      "learning_rate": 1.472592821679048e-05,
+      "loss": 0.1599,
+      "step": 910
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.7396163055843903,
+      "learning_rate": 1.4217844190669058e-05,
+      "loss": 0.1413,
+      "step": 920
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.7609487598644061,
+      "learning_rate": 1.3715173826697209e-05,
+      "loss": 0.1575,
+      "step": 930
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.899248106175493,
+      "learning_rate": 1.3218169512947542e-05,
+      "loss": 0.1368,
+      "step": 940
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5492609472889338,
+      "learning_rate": 1.2727080792599455e-05,
+      "loss": 0.1356,
+      "step": 950
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 0.5155984048617979,
+      "learning_rate": 1.2242154238644879e-05,
+      "loss": 0.0618,
+      "step": 960
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.6456926556116795,
+      "learning_rate": 1.1763633330085325e-05,
+      "loss": 0.0638,
+      "step": 970
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 0.6205542344499085,
+      "learning_rate": 1.1291758329682358e-05,
+      "loss": 0.0611,
+      "step": 980
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 0.4847483179925426,
+      "learning_rate": 1.0826766163322982e-05,
+      "loss": 0.0575,
+      "step": 990
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 0.5413371468713811,
+      "learning_rate": 1.0368890301060457e-05,
+      "loss": 0.0583,
+      "step": 1000
+    },
+    {
+      "epoch": 2.11,
+      "eval_loss": 0.34516656398773193,
+      "eval_runtime": 47.23,
+      "eval_samples_per_second": 285.645,
+      "eval_steps_per_second": 8.935,
+      "step": 1000
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 0.5404171416731017,
+      "learning_rate": 9.918360639890187e-06,
+      "loss": 0.0601,
+      "step": 1010
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.5620072184000532,
+      "learning_rate": 9.475403388319752e-06,
+      "loss": 0.0562,
+      "step": 1020
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 0.5612527587767797,
+      "learning_rate": 9.040240952790765e-06,
+      "loss": 0.06,
+      "step": 1030
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 0.556109347253415,
+      "learning_rate": 8.613091826009884e-06,
+      "loss": 0.0586,
+      "step": 1040
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 0.526323377202855,
+      "learning_rate": 8.194170477244729e-06,
+      "loss": 0.0555,
+      "step": 1050
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 0.4839147527811038,
+      "learning_rate": 7.783687244640048e-06,
+      "loss": 0.0586,
+      "step": 1060
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 0.5384902556315007,
+      "learning_rate": 7.38184822960811e-06,
+      "loss": 0.0563,
+      "step": 1070
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 0.5487199740187843,
+      "learning_rate": 6.988855193346236e-06,
+      "loss": 0.0591,
+      "step": 1080
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.558830265761421,
+      "learning_rate": 6.604905455533625e-06,
+      "loss": 0.0581,
+      "step": 1090
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.5905937756559718,
+      "learning_rate": 6.230191795258228e-06,
+      "loss": 0.0547,
+      "step": 1100
+    },
+    {
+      "epoch": 2.32,
+      "eval_loss": 0.3394644260406494,
+      "eval_runtime": 47.3785,
+      "eval_samples_per_second": 284.75,
+      "eval_steps_per_second": 8.907,
+      "step": 1100
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.5552812370662581,
+      "learning_rate": 5.864902354223384e-06,
+      "loss": 0.0647,
+      "step": 1110
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.5583176961830797,
+      "learning_rate": 5.509220542282864e-06,
+      "loss": 0.0579,
+      "step": 1120
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.527577115010199,
+      "learning_rate": 5.163324945351841e-06,
+      "loss": 0.0547,
+      "step": 1130
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.5723382741785656,
+      "learning_rate": 4.82738923573983e-06,
+      "loss": 0.0522,
+      "step": 1140
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 0.6612580191515155,
+      "learning_rate": 4.501582084950715e-06,
+      "loss": 0.0546,
+      "step": 1150
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.5398335429013659,
+      "learning_rate": 4.186067078993794e-06,
+      "loss": 0.0549,
+      "step": 1160
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 0.5344699336645098,
+      "learning_rate": 3.8810026362480684e-06,
+      "loss": 0.0587,
+      "step": 1170
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 0.5444597939849882,
+      "learning_rate": 3.586541927921222e-06,
+      "loss": 0.0581,
+      "step": 1180
+    },
+    {
+      "epoch": 2.51,
+      "grad_norm": 0.5463988615566789,
+      "learning_rate": 3.3028328011432157e-06,
+      "loss": 0.0575,
+      "step": 1190
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 1.0764210232146447,
+      "learning_rate": 3.030017704733043e-06,
+      "loss": 0.0589,
+      "step": 1200
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 0.34168508648872375,
+      "eval_runtime": 47.2752,
+      "eval_samples_per_second": 285.372,
+      "eval_steps_per_second": 8.926,
+      "step": 1200
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 0.4953517170839006,
+      "learning_rate": 2.7682336176759195e-06,
+      "loss": 0.0581,
+      "step": 1210
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.5541503548086418,
+      "learning_rate": 2.51761198034689e-06,
+      "loss": 0.0546,
+      "step": 1220
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 0.49468890807169186,
+      "learning_rate": 2.278278628515354e-06,
+      "loss": 0.0546,
+      "step": 1230
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 0.5409541969627151,
+      "learning_rate": 2.050353730163554e-06,
+      "loss": 0.0587,
+      "step": 1240
+    },
+    {
+      "epoch": 2.63,
+      "grad_norm": 0.5627631577280182,
+      "learning_rate": 1.8339517251509146e-06,
+      "loss": 0.0591,
+      "step": 1250
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 0.6303369184474236,
+      "learning_rate": 1.6291812677544121e-06,
+      "loss": 0.0565,
+      "step": 1260
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.5950168840485455,
+      "learning_rate": 1.436145172113834e-06,
+      "loss": 0.0621,
+      "step": 1270
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.6169520124840763,
+      "learning_rate": 1.2549403606093525e-06,
+      "loss": 0.0585,
+      "step": 1280
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 0.6215760879408516,
+      "learning_rate": 1.0856578151973246e-06,
+      "loss": 0.0551,
+      "step": 1290
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 0.5481992179891889,
+      "learning_rate": 9.283825317287692e-07,
+      "loss": 0.0593,
+      "step": 1300
+    },
+    {
+      "epoch": 2.74,
+      "eval_loss": 0.34135544300079346,
+      "eval_runtime": 47.2086,
+      "eval_samples_per_second": 285.774,
+      "eval_steps_per_second": 8.939,
+      "step": 1300
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.5600873628791802,
+      "learning_rate": 7.83193477273364e-07,
+      "loss": 0.063,
+      "step": 1310
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 0.47881555590847813,
+      "learning_rate": 6.501635504705422e-07,
+      "loss": 0.0556,
+      "step": 1320
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.5702498469737556,
+      "learning_rate": 5.293595449274685e-07,
+      "loss": 0.0578,
+      "step": 1330
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 0.6344603201355465,
+      "learning_rate": 4.208421156823239e-07,
+      "loss": 0.0621,
+      "step": 1340
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.4557995262356338,
+      "learning_rate": 3.2466574874975565e-07,
+      "loss": 0.0615,
+      "step": 1350
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 0.60731847293474,
+      "learning_rate": 2.408787337637164e-07,
+      "loss": 0.0563,
+      "step": 1360
+    },
+    {
+      "epoch": 2.89,
+      "grad_norm": 0.5748533793418215,
+      "learning_rate": 1.6952313973152834e-07,
+      "loss": 0.0557,
+      "step": 1370
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 0.5805376198014929,
+      "learning_rate": 1.1063479391124898e-07,
+      "loss": 0.0519,
+      "step": 1380
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 0.5744481873667274,
+      "learning_rate": 6.424326382299394e-08,
+      "loss": 0.0569,
+      "step": 1390
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.6568824061735796,
+      "learning_rate": 3.037184240325397e-08,
+      "loss": 0.0624,
+      "step": 1400
+    },
+    {
+      "epoch": 2.95,
+      "eval_loss": 0.34196367859840393,
+      "eval_runtime": 47.1898,
+      "eval_samples_per_second": 285.888,
+      "eval_steps_per_second": 8.943,
+      "step": 1400
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 0.5396314216567086,
+      "learning_rate": 9.037536309636218e-09,
+      "loss": 0.0549,
+      "step": 1410
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 0.6363488595941399,
+      "learning_rate": 2.5105738190867033e-10,
+      "loss": 0.0564,
+      "step": 1420
+    },
+    {
+      "epoch": 3.0,
+      "step": 1422,
+      "total_flos": 3.6498441825094205e+18,
+      "train_loss": 0.18191866144936128,
+      "train_runtime": 7053.867,
+      "train_samples_per_second": 51.639,
+      "train_steps_per_second": 0.202
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1422,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 3.6498441825094205e+18,
+  "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 sha256:4d07123eed52c93df0c49bc2df3962ce21c10e826eb16555bb917a1f87b586c0
+size 6328