Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,70 @@
+---
+license: gemma
+base_model: google/gemma-2b
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: zephyr-2b-gemma-sft
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://zebra.wandb.io/cto/distillm/runs/38yxv4re)
+# zephyr-2b-gemma-sft
+
+This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0529
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9699        | 0.9983 | 299  | 1.0448          |
+| 0.8939        | 2.0    | 599  | 1.0375          |
+| 0.8191        | 2.9950 | 897  | 1.0529          |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.994991652754591,
+    "total_flos": 106879455854592.0,
+    "train_loss": 0.9405513189841008,
+    "train_runtime": 1810.6389,
+    "train_samples": 9500,
+    "train_samples_per_second": 63.501,
+    "train_steps_per_second": 0.495
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "google/gemma-2b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a04274f12c058fb2915cb4235aadd2642fdcab9dc94c02a362d65db1c44366cb
+size 4945242264

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0ebcee8026716ca6c5fdcb43baa6d9d3d3ffd078a0b3004ad44f31485744c81
+size 67121608

model.safetensors.index.json

@@ -0,0 +1,171 @@
+{
+  "metadata": {
+    "total_size": 5012344832
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

runs/Jul11_10-06-29_ale-distillm-8-0-0/events.out.tfevents.1720689278.ale-distillm-8-0-0.1206.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caaa52517f17fd897f67a61fcf78cd38126c8736b95ea966e34c24e8c273c698
+size 9435

runs/Jul11_10-19-42_ale-distillm-8-0-0/events.out.tfevents.1720689602.ale-distillm-8-0-0.2700.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18597910fe8436b032558a75527997b4cbc692d96440672282184137f5416b3e
+size 44131

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322a5f52ab5cab196761ab397a022d6fa3a2e1418585e532bb6efb2fedd2ae94
+size 17477501

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.994991652754591,
+    "total_flos": 106879455854592.0,
+    "train_loss": 0.9405513189841008,
+    "train_runtime": 1810.6389,
+    "train_samples": 9500,
+    "train_samples_per_second": 63.501,
+    "train_steps_per_second": 0.495
+}

trainer_state.json

@@ -0,0 +1,1326 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.994991652754591,
+  "eval_steps": 500,
+  "global_step": 897,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00333889816360601,
+      "grad_norm": 15.957291352883223,
+      "learning_rate": 2.2222222222222224e-07,
+      "loss": 1.659,
+      "step": 1
+    },
+    {
+      "epoch": 0.01669449081803005,
+      "grad_norm": 20.82554498626078,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 1.6865,
+      "step": 5
+    },
+    {
+      "epoch": 0.0333889816360601,
+      "grad_norm": 86.6993488709915,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.6197,
+      "step": 10
+    },
+    {
+      "epoch": 0.05008347245409015,
+      "grad_norm": 14.254925959501568,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.5486,
+      "step": 15
+    },
+    {
+      "epoch": 0.0667779632721202,
+      "grad_norm": 13.342089213956086,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 1.4139,
+      "step": 20
+    },
+    {
+      "epoch": 0.08347245409015025,
+      "grad_norm": 4.153939027731178,
+      "learning_rate": 5.555555555555557e-06,
+      "loss": 1.3362,
+      "step": 25
+    },
+    {
+      "epoch": 0.1001669449081803,
+      "grad_norm": 3.6584133983100555,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.2915,
+      "step": 30
+    },
+    {
+      "epoch": 0.11686143572621036,
+      "grad_norm": 1.7065592509714724,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 1.2528,
+      "step": 35
+    },
+    {
+      "epoch": 0.1335559265442404,
+      "grad_norm": 1.2120527319735446,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 1.1931,
+      "step": 40
+    },
+    {
+      "epoch": 0.15025041736227046,
+      "grad_norm": 0.9282324284674316,
+      "learning_rate": 1e-05,
+      "loss": 1.2201,
+      "step": 45
+    },
+    {
+      "epoch": 0.1669449081803005,
+      "grad_norm": 1.0951455236906156,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 1.1159,
+      "step": 50
+    },
+    {
+      "epoch": 0.18363939899833054,
+      "grad_norm": 1.2930034758923397,
+      "learning_rate": 1.2222222222222224e-05,
+      "loss": 1.1869,
+      "step": 55
+    },
+    {
+      "epoch": 0.2003338898163606,
+      "grad_norm": 1.0326836881864259,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.1471,
+      "step": 60
+    },
+    {
+      "epoch": 0.21702838063439064,
+      "grad_norm": 1.3171962712550565,
+      "learning_rate": 1.4444444444444446e-05,
+      "loss": 1.1128,
+      "step": 65
+    },
+    {
+      "epoch": 0.2337228714524207,
+      "grad_norm": 1.0884778593805544,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 1.1264,
+      "step": 70
+    },
+    {
+      "epoch": 0.25041736227045075,
+      "grad_norm": 0.9392194413455617,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.0988,
+      "step": 75
+    },
+    {
+      "epoch": 0.2671118530884808,
+      "grad_norm": 1.9552115109721053,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 1.1021,
+      "step": 80
+    },
+    {
+      "epoch": 0.2838063439065108,
+      "grad_norm": 3.0360726960980946,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 1.0973,
+      "step": 85
+    },
+    {
+      "epoch": 0.3005008347245409,
+      "grad_norm": 4.983883252794476,
+      "learning_rate": 2e-05,
+      "loss": 1.1114,
+      "step": 90
+    },
+    {
+      "epoch": 0.31719532554257096,
+      "grad_norm": 2.3180149380481923,
+      "learning_rate": 1.9998105699049984e-05,
+      "loss": 1.0802,
+      "step": 95
+    },
+    {
+      "epoch": 0.333889816360601,
+      "grad_norm": 2.319946130765325,
+      "learning_rate": 1.9992423513875158e-05,
+      "loss": 1.0662,
+      "step": 100
+    },
+    {
+      "epoch": 0.35058430717863104,
+      "grad_norm": 3.3442318487800233,
+      "learning_rate": 1.9982955597229275e-05,
+      "loss": 1.0806,
+      "step": 105
+    },
+    {
+      "epoch": 0.3672787979966611,
+      "grad_norm": 2.142182950971819,
+      "learning_rate": 1.9969705536129033e-05,
+      "loss": 1.0649,
+      "step": 110
+    },
+    {
+      "epoch": 0.38397328881469117,
+      "grad_norm": 0.6856937250318401,
+      "learning_rate": 1.9952678350495104e-05,
+      "loss": 1.0447,
+      "step": 115
+    },
+    {
+      "epoch": 0.4006677796327212,
+      "grad_norm": 0.7829500151676976,
+      "learning_rate": 1.9931880491250263e-05,
+      "loss": 1.0597,
+      "step": 120
+    },
+    {
+      "epoch": 0.41736227045075125,
+      "grad_norm": 0.7638616840316438,
+      "learning_rate": 1.990731983787542e-05,
+      "loss": 1.0531,
+      "step": 125
+    },
+    {
+      "epoch": 0.4340567612687813,
+      "grad_norm": 2.040636856622385,
+      "learning_rate": 1.987900569542438e-05,
+      "loss": 1.0477,
+      "step": 130
+    },
+    {
+      "epoch": 0.4507512520868113,
+      "grad_norm": 2.3786229682426097,
+      "learning_rate": 1.9846948790998532e-05,
+      "loss": 1.0269,
+      "step": 135
+    },
+    {
+      "epoch": 0.4674457429048414,
+      "grad_norm": 2.1337859327827924,
+      "learning_rate": 1.9811161269682776e-05,
+      "loss": 1.0433,
+      "step": 140
+    },
+    {
+      "epoch": 0.48414023372287146,
+      "grad_norm": 1.1867114123037232,
+      "learning_rate": 1.9771656689944238e-05,
+      "loss": 1.0553,
+      "step": 145
+    },
+    {
+      "epoch": 0.5008347245409015,
+      "grad_norm": 0.7895227440440761,
+      "learning_rate": 1.9728450018495506e-05,
+      "loss": 1.0324,
+      "step": 150
+    },
+    {
+      "epoch": 0.5175292153589316,
+      "grad_norm": 1.0628554871553173,
+      "learning_rate": 1.968155762462433e-05,
+      "loss": 1.0328,
+      "step": 155
+    },
+    {
+      "epoch": 0.5342237061769616,
+      "grad_norm": 0.6995453797111978,
+      "learning_rate": 1.9630997273991964e-05,
+      "loss": 1.0464,
+      "step": 160
+    },
+    {
+      "epoch": 0.5509181969949917,
+      "grad_norm": 0.8920498995880328,
+      "learning_rate": 1.9576788121902457e-05,
+      "loss": 1.0387,
+      "step": 165
+    },
+    {
+      "epoch": 0.5676126878130217,
+      "grad_norm": 0.5794791237069282,
+      "learning_rate": 1.951895070604547e-05,
+      "loss": 1.0344,
+      "step": 170
+    },
+    {
+      "epoch": 0.5843071786310517,
+      "grad_norm": 0.812865125617091,
+      "learning_rate": 1.9457506938715357e-05,
+      "loss": 1.0334,
+      "step": 175
+    },
+    {
+      "epoch": 0.6010016694490818,
+      "grad_norm": 0.6221536202120724,
+      "learning_rate": 1.9392480098509488e-05,
+      "loss": 1.0174,
+      "step": 180
+    },
+    {
+      "epoch": 0.6176961602671118,
+      "grad_norm": 1.183734025560333,
+      "learning_rate": 1.93238948215089e-05,
+      "loss": 1.0419,
+      "step": 185
+    },
+    {
+      "epoch": 0.6343906510851419,
+      "grad_norm": 0.9014792857328605,
+      "learning_rate": 1.9251777091944665e-05,
+      "loss": 1.0379,
+      "step": 190
+    },
+    {
+      "epoch": 0.6510851419031719,
+      "grad_norm": 0.6277333718665531,
+      "learning_rate": 1.9176154232353513e-05,
+      "loss": 1.048,
+      "step": 195
+    },
+    {
+      "epoch": 0.667779632721202,
+      "grad_norm": 0.7852268352013753,
+      "learning_rate": 1.9097054893226395e-05,
+      "loss": 1.0036,
+      "step": 200
+    },
+    {
+      "epoch": 0.6844741235392321,
+      "grad_norm": 0.7644282091895362,
+      "learning_rate": 1.9014509042153964e-05,
+      "loss": 1.0185,
+      "step": 205
+    },
+    {
+      "epoch": 0.7011686143572621,
+      "grad_norm": 1.155642192053512,
+      "learning_rate": 1.8928547952473037e-05,
+      "loss": 1.031,
+      "step": 210
+    },
+    {
+      "epoch": 0.7178631051752922,
+      "grad_norm": 0.8244257339118122,
+      "learning_rate": 1.8839204191418386e-05,
+      "loss": 0.9993,
+      "step": 215
+    },
+    {
+      "epoch": 0.7345575959933222,
+      "grad_norm": 1.277466050359365,
+      "learning_rate": 1.8746511607784298e-05,
+      "loss": 1.0109,
+      "step": 220
+    },
+    {
+      "epoch": 0.7512520868113522,
+      "grad_norm": 1.5066052003680952,
+      "learning_rate": 1.865050531910062e-05,
+      "loss": 1.023,
+      "step": 225
+    },
+    {
+      "epoch": 0.7679465776293823,
+      "grad_norm": 0.9113854901116754,
+      "learning_rate": 1.855122169832813e-05,
+      "loss": 1.0242,
+      "step": 230
+    },
+    {
+      "epoch": 0.7846410684474123,
+      "grad_norm": 1.2402339775346432,
+      "learning_rate": 1.844869836007825e-05,
+      "loss": 1.0286,
+      "step": 235
+    },
+    {
+      "epoch": 0.8013355592654424,
+      "grad_norm": 0.6049851988239257,
+      "learning_rate": 1.8342974146362397e-05,
+      "loss": 1.0186,
+      "step": 240
+    },
+    {
+      "epoch": 0.8180300500834724,
+      "grad_norm": 1.3277263188043547,
+      "learning_rate": 1.8234089111876256e-05,
+      "loss": 0.9915,
+      "step": 245
+    },
+    {
+      "epoch": 0.8347245409015025,
+      "grad_norm": 1.1833581547921075,
+      "learning_rate": 1.8122084508824692e-05,
+      "loss": 0.9774,
+      "step": 250
+    },
+    {
+      "epoch": 0.8514190317195326,
+      "grad_norm": 0.7893966735725576,
+      "learning_rate": 1.80070027712929e-05,
+      "loss": 0.9796,
+      "step": 255
+    },
+    {
+      "epoch": 0.8681135225375626,
+      "grad_norm": 0.6376249393560345,
+      "learning_rate": 1.7888887499169816e-05,
+      "loss": 1.0042,
+      "step": 260
+    },
+    {
+      "epoch": 0.8848080133555927,
+      "grad_norm": 0.5190419036120189,
+      "learning_rate": 1.7767783441629883e-05,
+      "loss": 1.0154,
+      "step": 265
+    },
+    {
+      "epoch": 0.9015025041736227,
+      "grad_norm": 1.1818796423028393,
+      "learning_rate": 1.7643736480179353e-05,
+      "loss": 1.0011,
+      "step": 270
+    },
+    {
+      "epoch": 0.9181969949916527,
+      "grad_norm": 1.1796026630847036,
+      "learning_rate": 1.7516793611273614e-05,
+      "loss": 1.028,
+      "step": 275
+    },
+    {
+      "epoch": 0.9348914858096828,
+      "grad_norm": 1.439445951878622,
+      "learning_rate": 1.7387002928512093e-05,
+      "loss": 0.9978,
+      "step": 280
+    },
+    {
+      "epoch": 0.9515859766277128,
+      "grad_norm": 0.8419035609125706,
+      "learning_rate": 1.725441360441752e-05,
+      "loss": 0.9684,
+      "step": 285
+    },
+    {
+      "epoch": 0.9682804674457429,
+      "grad_norm": 0.5556776261573866,
+      "learning_rate": 1.711907587180642e-05,
+      "loss": 1.0063,
+      "step": 290
+    },
+    {
+      "epoch": 0.9849749582637729,
+      "grad_norm": 0.5859264166409325,
+      "learning_rate": 1.698104100475788e-05,
+      "loss": 0.9699,
+      "step": 295
+    },
+    {
+      "epoch": 0.998330550918197,
+      "eval_loss": 1.0447537899017334,
+      "eval_runtime": 8.3378,
+      "eval_samples_per_second": 229.437,
+      "eval_steps_per_second": 7.196,
+      "step": 299
+    },
+    {
+      "epoch": 1.001669449081803,
+      "grad_norm": 0.684116955981944,
+      "learning_rate": 1.684036129918786e-05,
+      "loss": 0.994,
+      "step": 300
+    },
+    {
+      "epoch": 1.018363939899833,
+      "grad_norm": 0.636525659695419,
+      "learning_rate": 1.6697090053036344e-05,
+      "loss": 0.9265,
+      "step": 305
+    },
+    {
+      "epoch": 1.0350584307178632,
+      "grad_norm": 0.6445403739585581,
+      "learning_rate": 1.6551281546074863e-05,
+      "loss": 0.9375,
+      "step": 310
+    },
+    {
+      "epoch": 1.0517529215358932,
+      "grad_norm": 0.5637049176444268,
+      "learning_rate": 1.6402991019342073e-05,
+      "loss": 0.8965,
+      "step": 315
+    },
+    {
+      "epoch": 1.0684474123539232,
+      "grad_norm": 1.4378688957966754,
+      "learning_rate": 1.625227465421511e-05,
+      "loss": 0.9485,
+      "step": 320
+    },
+    {
+      "epoch": 1.0851419031719534,
+      "grad_norm": 0.9003525847557393,
+      "learning_rate": 1.60991895511247e-05,
+      "loss": 0.9224,
+      "step": 325
+    },
+    {
+      "epoch": 1.1018363939899833,
+      "grad_norm": 1.3901582427227526,
+      "learning_rate": 1.5943793707922086e-05,
+      "loss": 0.8996,
+      "step": 330
+    },
+    {
+      "epoch": 1.1185308848080133,
+      "grad_norm": 0.6502172371002246,
+      "learning_rate": 1.5786145997905952e-05,
+      "loss": 0.8986,
+      "step": 335
+    },
+    {
+      "epoch": 1.1352253756260433,
+      "grad_norm": 0.7409388125111871,
+      "learning_rate": 1.5626306147517665e-05,
+      "loss": 0.9041,
+      "step": 340
+    },
+    {
+      "epoch": 1.1519198664440735,
+      "grad_norm": 0.7699617044708045,
+      "learning_rate": 1.5464334713713312e-05,
+      "loss": 0.9105,
+      "step": 345
+    },
+    {
+      "epoch": 1.1686143572621035,
+      "grad_norm": 0.482173835799333,
+      "learning_rate": 1.5300293061021084e-05,
+      "loss": 0.9284,
+      "step": 350
+    },
+    {
+      "epoch": 1.1853088480801335,
+      "grad_norm": 0.6661684757723031,
+      "learning_rate": 1.5134243338292686e-05,
+      "loss": 0.9138,
+      "step": 355
+    },
+    {
+      "epoch": 1.2020033388981637,
+      "grad_norm": 0.6181201510230905,
+      "learning_rate": 1.4966248455157622e-05,
+      "loss": 0.9133,
+      "step": 360
+    },
+    {
+      "epoch": 1.2186978297161937,
+      "grad_norm": 0.6932256442185771,
+      "learning_rate": 1.4796372058189235e-05,
+      "loss": 0.8791,
+      "step": 365
+    },
+    {
+      "epoch": 1.2353923205342237,
+      "grad_norm": 0.8467977250421432,
+      "learning_rate": 1.4624678506791556e-05,
+      "loss": 0.9125,
+      "step": 370
+    },
+    {
+      "epoch": 1.2520868113522536,
+      "grad_norm": 0.5242049477951446,
+      "learning_rate": 1.445123284881609e-05,
+      "loss": 0.88,
+      "step": 375
+    },
+    {
+      "epoch": 1.2687813021702838,
+      "grad_norm": 1.1383635594624812,
+      "learning_rate": 1.4276100795917777e-05,
+      "loss": 0.906,
+      "step": 380
+    },
+    {
+      "epoch": 1.2854757929883138,
+      "grad_norm": 0.7300479274157736,
+      "learning_rate": 1.409934869865945e-05,
+      "loss": 0.9329,
+      "step": 385
+    },
+    {
+      "epoch": 1.302170283806344,
+      "grad_norm": 0.6241250631319742,
+      "learning_rate": 1.392104352137426e-05,
+      "loss": 0.91,
+      "step": 390
+    },
+    {
+      "epoch": 1.318864774624374,
+      "grad_norm": 0.5314621726495606,
+      "learning_rate": 1.3741252816795552e-05,
+      "loss": 0.9082,
+      "step": 395
+    },
+    {
+      "epoch": 1.335559265442404,
+      "grad_norm": 0.5158076915249926,
+      "learning_rate": 1.3560044700463824e-05,
+      "loss": 0.9071,
+      "step": 400
+    },
+    {
+      "epoch": 1.352253756260434,
+      "grad_norm": 0.6440319283841749,
+      "learning_rate": 1.3377487824920459e-05,
+      "loss": 0.9222,
+      "step": 405
+    },
+    {
+      "epoch": 1.3689482470784642,
+      "grad_norm": 0.6783380289367208,
+      "learning_rate": 1.3193651353698012e-05,
+      "loss": 0.9047,
+      "step": 410
+    },
+    {
+      "epoch": 1.3856427378964942,
+      "grad_norm": 0.5351014013897331,
+      "learning_rate": 1.30086049351169e-05,
+      "loss": 0.9222,
+      "step": 415
+    },
+    {
+      "epoch": 1.4023372287145242,
+      "grad_norm": 0.6007683835319969,
+      "learning_rate": 1.2822418675898428e-05,
+      "loss": 0.9233,
+      "step": 420
+    },
+    {
+      "epoch": 1.4190317195325544,
+      "grad_norm": 0.6163929600226291,
+      "learning_rate": 1.2635163114604131e-05,
+      "loss": 0.9055,
+      "step": 425
+    },
+    {
+      "epoch": 1.4357262103505843,
+      "grad_norm": 0.49834894870770663,
+      "learning_rate": 1.2446909194911552e-05,
+      "loss": 0.9218,
+      "step": 430
+    },
+    {
+      "epoch": 1.4524207011686143,
+      "grad_norm": 0.5385307548828243,
+      "learning_rate": 1.2257728238736468e-05,
+      "loss": 0.892,
+      "step": 435
+    },
+    {
+      "epoch": 1.4691151919866443,
+      "grad_norm": 0.5517156095572195,
+      "learning_rate": 1.2067691919211879e-05,
+      "loss": 0.8929,
+      "step": 440
+    },
+    {
+      "epoch": 1.4858096828046745,
+      "grad_norm": 0.7153685327652367,
+      "learning_rate": 1.1876872233533909e-05,
+      "loss": 0.923,
+      "step": 445
+    },
+    {
+      "epoch": 1.5025041736227045,
+      "grad_norm": 0.7676764132245686,
+      "learning_rate": 1.1685341475684935e-05,
+      "loss": 0.9045,
+      "step": 450
+    },
+    {
+      "epoch": 1.5191986644407347,
+      "grad_norm": 0.5222423769515294,
+      "learning_rate": 1.1493172209044259e-05,
+      "loss": 0.8796,
+      "step": 455
+    },
+    {
+      "epoch": 1.5358931552587647,
+      "grad_norm": 0.6572944121034952,
+      "learning_rate": 1.1300437238896758e-05,
+      "loss": 0.8864,
+      "step": 460
+    },
+    {
+      "epoch": 1.5525876460767947,
+      "grad_norm": 0.5696483456027143,
+      "learning_rate": 1.1107209584849845e-05,
+      "loss": 0.9003,
+      "step": 465
+    },
+    {
+      "epoch": 1.5692821368948247,
+      "grad_norm": 0.6111254138799543,
+      "learning_rate": 1.0913562453169241e-05,
+      "loss": 0.9148,
+      "step": 470
+    },
+    {
+      "epoch": 1.5859766277128546,
+      "grad_norm": 0.5948615420574401,
+      "learning_rate": 1.0719569209044047e-05,
+      "loss": 0.886,
+      "step": 475
+    },
+    {
+      "epoch": 1.6026711185308848,
+      "grad_norm": 0.5708947368895286,
+      "learning_rate": 1.0525303348791599e-05,
+      "loss": 0.9145,
+      "step": 480
+    },
+    {
+      "epoch": 1.6193656093489148,
+      "grad_norm": 0.5425313255069921,
+      "learning_rate": 1.0330838472012617e-05,
+      "loss": 0.9145,
+      "step": 485
+    },
+    {
+      "epoch": 1.636060100166945,
+      "grad_norm": 0.5410656168164641,
+      "learning_rate": 1.0136248253707267e-05,
+      "loss": 0.9009,
+      "step": 490
+    },
+    {
+      "epoch": 1.652754590984975,
+      "grad_norm": 0.6530203724837228,
+      "learning_rate": 9.94160641636263e-06,
+      "loss": 0.8822,
+      "step": 495
+    },
+    {
+      "epoch": 1.669449081803005,
+      "grad_norm": 0.4919274312787223,
+      "learning_rate": 9.74698670202218e-06,
+      "loss": 0.9086,
+      "step": 500
+    },
+    {
+      "epoch": 1.686143572621035,
+      "grad_norm": 0.5238976053781923,
+      "learning_rate": 9.552462844347883e-06,
+      "loss": 0.9035,
+      "step": 505
+    },
+    {
+      "epoch": 1.702838063439065,
+      "grad_norm": 0.523434772533601,
+      "learning_rate": 9.358108540685406e-06,
+      "loss": 0.8863,
+      "step": 510
+    },
+    {
+      "epoch": 1.7195325542570952,
+      "grad_norm": 0.5475333278586838,
+      "learning_rate": 9.163997424143167e-06,
+      "loss": 0.8931,
+      "step": 515
+    },
+    {
+      "epoch": 1.7362270450751254,
+      "grad_norm": 0.5167332021656158,
+      "learning_rate": 8.970203035695662e-06,
+      "loss": 0.8994,
+      "step": 520
+    },
+    {
+      "epoch": 1.7529215358931554,
+      "grad_norm": 0.5326685781863387,
+      "learning_rate": 8.776798796321715e-06,
+      "loss": 0.8926,
+      "step": 525
+    },
+    {
+      "epoch": 1.7696160267111853,
+      "grad_norm": 0.5863957550550153,
+      "learning_rate": 8.583857979188203e-06,
+      "loss": 0.8838,
+      "step": 530
+    },
+    {
+      "epoch": 1.7863105175292153,
+      "grad_norm": 0.628416420944202,
+      "learning_rate": 8.391453681889772e-06,
+      "loss": 0.9048,
+      "step": 535
+    },
+    {
+      "epoch": 1.8030050083472453,
+      "grad_norm": 0.5843287954680072,
+      "learning_rate": 8.199658798755048e-06,
+      "loss": 0.9497,
+      "step": 540
+    },
+    {
+      "epoch": 1.8196994991652755,
+      "grad_norm": 0.45288053121542915,
+      "learning_rate": 8.008545993229897e-06,
+      "loss": 0.8966,
+      "step": 545
+    },
+    {
+      "epoch": 1.8363939899833055,
+      "grad_norm": 0.5590037561540859,
+      "learning_rate": 7.818187670348133e-06,
+      "loss": 0.894,
+      "step": 550
+    },
+    {
+      "epoch": 1.8530884808013357,
+      "grad_norm": 0.4833538496147019,
+      "learning_rate": 7.628655949300133e-06,
+      "loss": 0.9073,
+      "step": 555
+    },
+    {
+      "epoch": 1.8697829716193657,
+      "grad_norm": 0.5876142408674571,
+      "learning_rate": 7.440022636109742e-06,
+      "loss": 0.9323,
+      "step": 560
+    },
+    {
+      "epoch": 1.8864774624373957,
+      "grad_norm": 0.5308705244707532,
+      "learning_rate": 7.2523591964298345e-06,
+      "loss": 0.8729,
+      "step": 565
+    },
+    {
+      "epoch": 1.9031719532554257,
+      "grad_norm": 0.5518206549230582,
+      "learning_rate": 7.065736728466832e-06,
+      "loss": 0.8941,
+      "step": 570
+    },
+    {
+      "epoch": 1.9198664440734556,
+      "grad_norm": 0.5663164888037011,
+      "learning_rate": 6.880225936044402e-06,
+      "loss": 0.8969,
+      "step": 575
+    },
+    {
+      "epoch": 1.9365609348914858,
+      "grad_norm": 0.7716989331300791,
+      "learning_rate": 6.695897101816606e-06,
+      "loss": 0.889,
+      "step": 580
+    },
+    {
+      "epoch": 1.9532554257095158,
+      "grad_norm": 0.4854407441914746,
+      "learning_rate": 6.512820060640608e-06,
+      "loss": 0.9096,
+      "step": 585
+    },
+    {
+      "epoch": 1.969949916527546,
+      "grad_norm": 0.5964300371902113,
+      "learning_rate": 6.331064173119008e-06,
+      "loss": 0.9019,
+      "step": 590
+    },
+    {
+      "epoch": 1.986644407345576,
+      "grad_norm": 0.6395862090435611,
+      "learning_rate": 6.150698299321889e-06,
+      "loss": 0.8939,
+      "step": 595
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.0374501943588257,
+      "eval_runtime": 8.2489,
+      "eval_samples_per_second": 231.909,
+      "eval_steps_per_second": 7.274,
+      "step": 599
+    },
+    {
+      "epoch": 2.003338898163606,
+      "grad_norm": 1.1426098029417433,
+      "learning_rate": 5.971790772698467e-06,
+      "loss": 0.8679,
+      "step": 600
+    },
+    {
+      "epoch": 2.020033388981636,
+      "grad_norm": 0.5981322500928512,
+      "learning_rate": 5.794409374188272e-06,
+      "loss": 0.8143,
+      "step": 605
+    },
+    {
+      "epoch": 2.036727879799666,
+      "grad_norm": 2.0693984258723956,
+      "learning_rate": 5.61862130654165e-06,
+      "loss": 0.8096,
+      "step": 610
+    },
+    {
+      "epoch": 2.053422370617696,
+      "grad_norm": 0.5390665268645869,
+      "learning_rate": 5.444493168859304e-06,
+      "loss": 0.7971,
+      "step": 615
+    },
+    {
+      "epoch": 2.0701168614357264,
+      "grad_norm": 0.5206821850461111,
+      "learning_rate": 5.272090931360564e-06,
+      "loss": 0.8068,
+      "step": 620
+    },
+    {
+      "epoch": 2.0868113522537564,
+      "grad_norm": 0.4396188787285125,
+      "learning_rate": 5.101479910389888e-06,
+      "loss": 0.8178,
+      "step": 625
+    },
+    {
+      "epoch": 2.1035058430717863,
+      "grad_norm": 0.48916345255937493,
+      "learning_rate": 4.932724743671089e-06,
+      "loss": 0.8474,
+      "step": 630
+    },
+    {
+      "epoch": 2.1202003338898163,
+      "grad_norm": 0.4681540498427145,
+      "learning_rate": 4.765889365818708e-06,
+      "loss": 0.8171,
+      "step": 635
+    },
+    {
+      "epoch": 2.1368948247078463,
+      "grad_norm": 0.46734523192627164,
+      "learning_rate": 4.601036984115684e-06,
+      "loss": 0.8417,
+      "step": 640
+    },
+    {
+      "epoch": 2.1535893155258763,
+      "grad_norm": 0.4848107575518711,
+      "learning_rate": 4.438230054566678e-06,
+      "loss": 0.7979,
+      "step": 645
+    },
+    {
+      "epoch": 2.1702838063439067,
+      "grad_norm": 0.5080508354482104,
+      "learning_rate": 4.277530258235955e-06,
+      "loss": 0.8318,
+      "step": 650
+    },
+    {
+      "epoch": 2.1869782971619367,
+      "grad_norm": 0.4773573845484071,
+      "learning_rate": 4.118998477878879e-06,
+      "loss": 0.8369,
+      "step": 655
+    },
+    {
+      "epoch": 2.2036727879799667,
+      "grad_norm": 0.48182311371778996,
+      "learning_rate": 3.96269477487588e-06,
+      "loss": 0.858,
+      "step": 660
+    },
+    {
+      "epoch": 2.2203672787979967,
+      "grad_norm": 0.465215050189049,
+      "learning_rate": 3.8086783664775827e-06,
+      "loss": 0.7989,
+      "step": 665
+    },
+    {
+      "epoch": 2.2370617696160267,
+      "grad_norm": 0.46077400437834526,
+      "learning_rate": 3.657007603369728e-06,
+      "loss": 0.8292,
+      "step": 670
+    },
+    {
+      "epoch": 2.2537562604340566,
+      "grad_norm": 0.4782306803989219,
+      "learning_rate": 3.5077399475664474e-06,
+      "loss": 0.8197,
+      "step": 675
+    },
+    {
+      "epoch": 2.2704507512520866,
+      "grad_norm": 0.4829460892597705,
+      "learning_rate": 3.360931950640185e-06,
+      "loss": 0.8481,
+      "step": 680
+    },
+    {
+      "epoch": 2.287145242070117,
+      "grad_norm": 0.44292881547818397,
+      "learning_rate": 3.2166392322965423e-06,
+      "loss": 0.8306,
+      "step": 685
+    },
+    {
+      "epoch": 2.303839732888147,
+      "grad_norm": 0.48932957112501885,
+      "learning_rate": 3.074916459302211e-06,
+      "loss": 0.805,
+      "step": 690
+    },
+    {
+      "epoch": 2.320534223706177,
+      "grad_norm": 0.4990000411624427,
+      "learning_rate": 2.935817324773893e-06,
+      "loss": 0.8189,
+      "step": 695
+    },
+    {
+      "epoch": 2.337228714524207,
+      "grad_norm": 0.45360783259155707,
+      "learning_rate": 2.799394527836129e-06,
+      "loss": 0.8281,
+      "step": 700
+    },
+    {
+      "epoch": 2.353923205342237,
+      "grad_norm": 0.5557178814320654,
+      "learning_rate": 2.665699753655684e-06,
+      "loss": 0.8177,
+      "step": 705
+    },
+    {
+      "epoch": 2.370617696160267,
+      "grad_norm": 0.6076004327005405,
+      "learning_rate": 2.5347836538601113e-06,
+      "loss": 0.8234,
+      "step": 710
+    },
+    {
+      "epoch": 2.3873121869782974,
+      "grad_norm": 0.6588302547775924,
+      "learning_rate": 2.406695827347848e-06,
+      "loss": 0.8301,
+      "step": 715
+    },
+    {
+      "epoch": 2.4040066777963274,
+      "grad_norm": 1.066202010754452,
+      "learning_rate": 2.281484801497186e-06,
+      "loss": 0.8218,
+      "step": 720
+    },
+    {
+      "epoch": 2.4207011686143574,
+      "grad_norm": 0.4552773887453401,
+      "learning_rate": 2.1591980137811684e-06,
+      "loss": 0.8349,
+      "step": 725
+    },
+    {
+      "epoch": 2.4373956594323873,
+      "grad_norm": 0.4798048974347353,
+      "learning_rate": 2.0398817937954275e-06,
+      "loss": 0.8291,
+      "step": 730
+    },
+    {
+      "epoch": 2.4540901502504173,
+      "grad_norm": 0.49645874059938744,
+      "learning_rate": 1.923581345705736e-06,
+      "loss": 0.7979,
+      "step": 735
+    },
+    {
+      "epoch": 2.4707846410684473,
+      "grad_norm": 0.48114179285266284,
+      "learning_rate": 1.8103407311219523e-06,
+      "loss": 0.8202,
+      "step": 740
+    },
+    {
+      "epoch": 2.4874791318864773,
+      "grad_norm": 0.5067062797156703,
+      "learning_rate": 1.7002028524048354e-06,
+      "loss": 0.818,
+      "step": 745
+    },
+    {
+      "epoch": 2.5041736227045073,
+      "grad_norm": 0.44105556646795846,
+      "learning_rate": 1.5932094364120453e-06,
+      "loss": 0.8341,
+      "step": 750
+    },
+    {
+      "epoch": 2.5208681135225377,
+      "grad_norm": 0.4877712957131641,
+      "learning_rate": 1.489401018689488e-06,
+      "loss": 0.82,
+      "step": 755
+    },
+    {
+      "epoch": 2.5375626043405677,
+      "grad_norm": 0.46677823682519043,
+      "learning_rate": 1.3888169281140284e-06,
+      "loss": 0.8254,
+      "step": 760
+    },
+    {
+      "epoch": 2.5542570951585977,
+      "grad_norm": 0.5467343146310263,
+      "learning_rate": 1.291495271993337e-06,
+      "loss": 0.8187,
+      "step": 765
+    },
+    {
+      "epoch": 2.5709515859766277,
+      "grad_norm": 0.45191390111853974,
+      "learning_rate": 1.1974729216285386e-06,
+      "loss": 0.8284,
+      "step": 770
+    },
+    {
+      "epoch": 2.5876460767946576,
+      "grad_norm": 0.4560656029244313,
+      "learning_rate": 1.1067854983451575e-06,
+      "loss": 0.8085,
+      "step": 775
+    },
+    {
+      "epoch": 2.604340567612688,
+      "grad_norm": 0.4496802766749698,
+      "learning_rate": 1.0194673599976134e-06,
+      "loss": 0.8156,
+      "step": 780
+    },
+    {
+      "epoch": 2.621035058430718,
+      "grad_norm": 0.4541891811425995,
+      "learning_rate": 9.355515879523858e-07,
+      "loss": 0.796,
+      "step": 785
+    },
+    {
+      "epoch": 2.637729549248748,
+      "grad_norm": 0.4842807068320624,
+      "learning_rate": 8.550699745548196e-07,
+      "loss": 0.8402,
+      "step": 790
+    },
+    {
+      "epoch": 2.654424040066778,
+      "grad_norm": 0.4825989478965968,
+      "learning_rate": 7.780530110842566e-07,
+      "loss": 0.8352,
+      "step": 795
+    },
+    {
+      "epoch": 2.671118530884808,
+      "grad_norm": 0.431656777738719,
+      "learning_rate": 7.045298762021125e-07,
+      "loss": 0.8087,
+      "step": 800
+    },
+    {
+      "epoch": 2.687813021702838,
+      "grad_norm": 0.4425844519927156,
+      "learning_rate": 6.345284248972383e-07,
+      "loss": 0.8176,
+      "step": 805
+    },
+    {
+      "epoch": 2.704507512520868,
+      "grad_norm": 0.43974863745670073,
+      "learning_rate": 5.680751779327742e-07,
+      "loss": 0.8198,
+      "step": 810
+    },
+    {
+      "epoch": 2.721202003338898,
+      "grad_norm": 0.47030660258496065,
+      "learning_rate": 5.05195311798491e-07,
+      "loss": 0.8056,
+      "step": 815
+    },
+    {
+      "epoch": 2.7378964941569284,
+      "grad_norm": 0.4413617160159506,
+      "learning_rate": 4.4591264917242195e-07,
+      "loss": 0.8061,
+      "step": 820
+    },
+    {
+      "epoch": 2.7545909849749584,
+      "grad_norm": 0.45369770612418003,
+      "learning_rate": 3.9024964989539227e-07,
+      "loss": 0.8194,
+      "step": 825
+    },
+    {
+      "epoch": 2.7712854757929883,
+      "grad_norm": 0.4491419061194818,
+      "learning_rate": 3.3822740246188477e-07,
+      "loss": 0.823,
+      "step": 830
+    },
+    {
+      "epoch": 2.7879799666110183,
+      "grad_norm": 0.46281617581131723,
+      "learning_rate": 2.8986561603044694e-07,
+      "loss": 0.8369,
+      "step": 835
+    },
+    {
+      "epoch": 2.8046744574290483,
+      "grad_norm": 0.4550289027905284,
+      "learning_rate": 2.4518261295667255e-07,
+      "loss": 0.8142,
+      "step": 840
+    },
+    {
+      "epoch": 2.8213689482470787,
+      "grad_norm": 0.509529012047999,
+      "learning_rate": 2.0419532185159796e-07,
+      "loss": 0.827,
+      "step": 845
+    },
+    {
+      "epoch": 2.8380634390651087,
+      "grad_norm": 0.49947769295928235,
+      "learning_rate": 1.6691927116812002e-07,
+      "loss": 0.8107,
+      "step": 850
+    },
+    {
+      "epoch": 2.8547579298831387,
+      "grad_norm": 0.4348773123366404,
+      "learning_rate": 1.3336858331787993e-07,
+      "loss": 0.8105,
+      "step": 855
+    },
+    {
+      "epoch": 2.8714524207011687,
+      "grad_norm": 0.5120538311262153,
+      "learning_rate": 1.0355596932085432e-07,
+      "loss": 0.8407,
+      "step": 860
+    },
+    {
+      "epoch": 2.8881469115191987,
+      "grad_norm": 0.4475268573366682,
+      "learning_rate": 7.749272398964613e-08,
+      "loss": 0.7998,
+      "step": 865
+    },
+    {
+      "epoch": 2.9048414023372287,
+      "grad_norm": 0.5489973312590801,
+      "learning_rate": 5.518872165033329e-08,
+      "loss": 0.7822,
+      "step": 870
+    },
+    {
+      "epoch": 2.9215358931552586,
+      "grad_norm": 0.4824018196136428,
+      "learning_rate": 3.6652412401478875e-08,
+      "loss": 0.8033,
+      "step": 875
+    },
+    {
+      "epoch": 2.9382303839732886,
+      "grad_norm": 0.6043350861738036,
+      "learning_rate": 2.1890818912728706e-08,
+      "loss": 0.819,
+      "step": 880
+    },
+    {
+      "epoch": 2.9549248747913186,
+      "grad_norm": 0.47649337249685186,
+      "learning_rate": 1.0909533764194013e-08,
+      "loss": 0.8066,
+      "step": 885
+    },
+    {
+      "epoch": 2.971619365609349,
+      "grad_norm": 0.4549028191201416,
+      "learning_rate": 3.7127173276563234e-09,
+      "loss": 0.8075,
+      "step": 890
+    },
+    {
+      "epoch": 2.988313856427379,
+      "grad_norm": 0.4521942548940854,
+      "learning_rate": 3.0309619035495675e-10,
+      "loss": 0.8191,
+      "step": 895
+    },
+    {
+      "epoch": 2.994991652754591,
+      "eval_loss": 1.0529426336288452,
+      "eval_runtime": 8.2524,
+      "eval_samples_per_second": 231.812,
+      "eval_steps_per_second": 7.271,
+      "step": 897
+    },
+    {
+      "epoch": 2.994991652754591,
+      "step": 897,
+      "total_flos": 106879455854592.0,
+      "train_loss": 0.9405513189841008,
+      "train_runtime": 1810.6389,
+      "train_samples_per_second": 63.501,
+      "train_steps_per_second": 0.495
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 897,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 106879455854592.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3458125092957859722de76e160166663dee5a148756de7af7b8eed58578e4bd
+size 6456