Instructions to use Phonsiri/Thai-Legal-Gemma-4B-CPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Phonsiri/Thai-Legal-Gemma-4B-CPT with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Phonsiri/Thai-Legal-Gemma-4B-CPT")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Phonsiri/Thai-Legal-Gemma-4B-CPT")
model = AutoModelForMultimodalLM.from_pretrained("Phonsiri/Thai-Legal-Gemma-4B-CPT", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Phonsiri/Thai-Legal-Gemma-4B-CPT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Phonsiri/Thai-Legal-Gemma-4B-CPT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Phonsiri/Thai-Legal-Gemma-4B-CPT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Phonsiri/Thai-Legal-Gemma-4B-CPT

SGLang

How to use Phonsiri/Thai-Legal-Gemma-4B-CPT with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Phonsiri/Thai-Legal-Gemma-4B-CPT" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Phonsiri/Thai-Legal-Gemma-4B-CPT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Phonsiri/Thai-Legal-Gemma-4B-CPT" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Phonsiri/Thai-Legal-Gemma-4B-CPT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Phonsiri/Thai-Legal-Gemma-4B-CPT with Docker Model Runner:
```
docker model run hf.co/Phonsiri/Thai-Legal-Gemma-4B-CPT
```

Phonsiri commited on May 2

Commit

8b03a5a

verified ·

1 Parent(s): 3204d07

Training in progress, step 80, checkpoint

Browse files

Files changed (10) hide show

checkpoint-80/config.json +198 -0
checkpoint-80/generation_config.json +13 -0
checkpoint-80/model.safetensors +3 -0
checkpoint-80/optimizer.pt +3 -0
checkpoint-80/rng_state.pth +3 -0
checkpoint-80/scheduler.pt +3 -0
checkpoint-80/tokenizer.json +3 -0
checkpoint-80/tokenizer_config.json +55 -0
checkpoint-80/trainer_state.json +594 -0
checkpoint-80/training_args.bin +3 -0

checkpoint-80/config.json ADDED Viewed

	@@ -0,0 +1,198 @@

+{
+  "architectures": [
+    "Gemma4ForConditionalGeneration"
+  ],
+  "audio_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_chunk_size": 12,
+    "attention_context_left": 13,
+    "attention_context_right": 0,
+    "attention_invalid_logits_value": -1000000000.0,
+    "attention_logit_cap": 50.0,
+    "chunk_size_feed_forward": 0,
+    "conv_kernel_size": 5,
+    "dtype": "bfloat16",
+    "gradient_clipping": 10000000000.0,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "model_type": "gemma4_audio",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_proj_dims": 1536,
+    "problem_type": null,
+    "residual_weight": 0.5,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "subsampling_conv_channels": [
+      128,
+      32
+    ],
+    "use_clipped_linears": true
+  },
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eoa_token_id": 258883,
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "eos_token_id": 1,
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "gemma4",
+  "pad_token_id": 0,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_k_eq_v": false,
+    "bos_token_id": 2,
+    "dtype": "bfloat16",
+    "enable_moe_block": false,
+    "eos_token_id": 1,
+    "expert_intermediate_size": null,
+    "final_logit_softcapping": 30.0,
+    "global_head_dim": 512,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 2560,
+    "hidden_size_per_layer_input": 256,
+    "initializer_range": 0.02,
+    "intermediate_size": 10240,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_text",
+    "moe_intermediate_size": null,
+    "num_attention_heads": 8,
+    "num_experts": null,
+    "num_global_key_value_heads": null,
+    "num_hidden_layers": 42,
+    "num_key_value_heads": 2,
+    "num_kv_shared_layers": 18,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "partial_rotary_factor": 0.25,
+        "rope_theta": 1000000.0,
+        "rope_type": "proportional"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 512,
+    "tie_word_embeddings": true,
+    "top_k_experts": null,
+    "use_bidirectional_attention": null,
+    "use_cache": true,
+    "use_double_wide_mlp": false,
+    "vocab_size": 262144,
+    "vocab_size_per_layer_input": 262144
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.7.0",
+  "use_cache": false,
+  "video_token_id": 258884,
+  "vision_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "chunk_size_feed_forward": 0,
+    "default_output_length": 280,
+    "dtype": "bfloat16",
+    "global_head_dim": 64,
+    "head_dim": 64,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "position_embedding_size": 10240,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 100.0,
+      "rope_type": "default"
+    },
+    "standardize": false,
+    "use_clipped_linears": true
+  },
+  "vision_soft_tokens_per_image": 280
+}

checkpoint-80/generation_config.json ADDED Viewed

	@@ -0,0 +1,13 @@

+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    1
+  ],
+  "pad_token_id": 0,
+  "temperature": 1.0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.7.0"
+}

checkpoint-80/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e6a216d40721e1361ada03feee11cd534a2bebcf141ebb755127a89c9b3a35e1
+size 15882477500

checkpoint-80/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e3885cd7a7a28a7b655c947d662101d28d79822630d1c57161841db85cd47f18
+size 29852609572

checkpoint-80/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

checkpoint-80/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f470225555a468f61d4dd3cbcd48936c659466bfb8e717f49c3d7a41bee74e6c
+size 1465

checkpoint-80/tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:12bac982b793c44b03d52a250a9f0d0b666813da566b910c24a6da0695fd11e6
+size 32170070

checkpoint-80/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,55 @@

+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4Processor",
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-80/trainer_state.json ADDED Viewed

	@@ -0,0 +1,594 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.838828588982183,
+  "eval_steps": 1,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010485357362277289,
+      "grad_norm": 498.0,
+      "learning_rate": 0.0,
+      "loss": 1.6033425331115723,
+      "step": 1
+    },
+    {
+      "epoch": 0.020970714724554577,
+      "grad_norm": 139.0,
+      "learning_rate": 4e-08,
+      "loss": 1.5843058824539185,
+      "step": 2
+    },
+    {
+      "epoch": 0.03145607208683186,
+      "grad_norm": 158.0,
+      "learning_rate": 8e-08,
+      "loss": 1.624650239944458,
+      "step": 3
+    },
+    {
+      "epoch": 0.041941429449109155,
+      "grad_norm": 201.0,
+      "learning_rate": 1.2000000000000002e-07,
+      "loss": 1.5930713415145874,
+      "step": 4
+    },
+    {
+      "epoch": 0.05242678681138644,
+      "grad_norm": 1392.0,
+      "learning_rate": 1.6e-07,
+      "loss": 1.6284583806991577,
+      "step": 5
+    },
+    {
+      "epoch": 0.06291214417366373,
+      "grad_norm": 644.0,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 1.5755040645599365,
+      "step": 6
+    },
+    {
+      "epoch": 0.07339750153594102,
+      "grad_norm": 358.0,
+      "learning_rate": 2.4000000000000003e-07,
+      "loss": 1.5862637758255005,
+      "step": 7
+    },
+    {
+      "epoch": 0.08388285889821831,
+      "grad_norm": 1012.0,
+      "learning_rate": 2.8e-07,
+      "loss": 1.6306817531585693,
+      "step": 8
+    },
+    {
+      "epoch": 0.0943682162604956,
+      "grad_norm": 187.0,
+      "learning_rate": 3.2e-07,
+      "loss": 1.5844253301620483,
+      "step": 9
+    },
+    {
+      "epoch": 0.10485357362277288,
+      "grad_norm": 342.0,
+      "learning_rate": 3.6e-07,
+      "loss": 1.5895334482192993,
+      "step": 10
+    },
+    {
+      "epoch": 0.11533893098505017,
+      "grad_norm": 816.0,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 1.5861637592315674,
+      "step": 11
+    },
+    {
+      "epoch": 0.12582428834732745,
+      "grad_norm": 260.0,
+      "learning_rate": 4.4e-07,
+      "loss": 1.57806396484375,
+      "step": 12
+    },
+    {
+      "epoch": 0.13630964570960474,
+      "grad_norm": 326.0,
+      "learning_rate": 4.800000000000001e-07,
+      "loss": 1.5836868286132812,
+      "step": 13
+    },
+    {
+      "epoch": 0.14679500307188204,
+      "grad_norm": 668.0,
+      "learning_rate": 5.2e-07,
+      "loss": 1.5597259998321533,
+      "step": 14
+    },
+    {
+      "epoch": 0.15728036043415933,
+      "grad_norm": 256.0,
+      "learning_rate": 5.6e-07,
+      "loss": 1.5852601528167725,
+      "step": 15
+    },
+    {
+      "epoch": 0.16776571779643662,
+      "grad_norm": 205.0,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 1.5899027585983276,
+      "step": 16
+    },
+    {
+      "epoch": 0.1782510751587139,
+      "grad_norm": 188.0,
+      "learning_rate": 6.4e-07,
+      "loss": 1.5692049264907837,
+      "step": 17
+    },
+    {
+      "epoch": 0.1887364325209912,
+      "grad_norm": 426.0,
+      "learning_rate": 6.800000000000001e-07,
+      "loss": 1.55263090133667,
+      "step": 18
+    },
+    {
+      "epoch": 0.1992217898832685,
+      "grad_norm": 245.0,
+      "learning_rate": 7.2e-07,
+      "loss": 1.5602704286575317,
+      "step": 19
+    },
+    {
+      "epoch": 0.20970714724554576,
+      "grad_norm": 158.0,
+      "learning_rate": 7.6e-07,
+      "loss": 1.5857173204421997,
+      "step": 20
+    },
+    {
+      "epoch": 0.22019250460782305,
+      "grad_norm": 90.0,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 1.5650298595428467,
+      "step": 21
+    },
+    {
+      "epoch": 0.23067786197010035,
+      "grad_norm": 148.0,
+      "learning_rate": 8.400000000000001e-07,
+      "loss": 1.548302173614502,
+      "step": 22
+    },
+    {
+      "epoch": 0.24116321933237764,
+      "grad_norm": 187.0,
+      "learning_rate": 8.8e-07,
+      "loss": 1.5342053174972534,
+      "step": 23
+    },
+    {
+      "epoch": 0.2516485766946549,
+      "grad_norm": 282.0,
+      "learning_rate": 9.200000000000001e-07,
+      "loss": 1.5395140647888184,
+      "step": 24
+    },
+    {
+      "epoch": 0.2621339340569322,
+      "grad_norm": 212.0,
+      "learning_rate": 9.600000000000001e-07,
+      "loss": 1.5411065816879272,
+      "step": 25
+    },
+    {
+      "epoch": 0.2726192914192095,
+      "grad_norm": 1640.0,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.520958423614502,
+      "step": 26
+    },
+    {
+      "epoch": 0.2831046487814868,
+      "grad_norm": 161.0,
+      "learning_rate": 1.04e-06,
+      "loss": 1.516421914100647,
+      "step": 27
+    },
+    {
+      "epoch": 0.29359000614376407,
+      "grad_norm": 175.0,
+      "learning_rate": 1.08e-06,
+      "loss": 1.492469310760498,
+      "step": 28
+    },
+    {
+      "epoch": 0.30407536350604136,
+      "grad_norm": 115.0,
+      "learning_rate": 1.12e-06,
+      "loss": 1.5238401889801025,
+      "step": 29
+    },
+    {
+      "epoch": 0.31456072086831866,
+      "grad_norm": 96.5,
+      "learning_rate": 1.1600000000000001e-06,
+      "loss": 1.4782272577285767,
+      "step": 30
+    },
+    {
+      "epoch": 0.32504607823059595,
+      "grad_norm": 197.0,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.4808753728866577,
+      "step": 31
+    },
+    {
+      "epoch": 0.33553143559287324,
+      "grad_norm": 125.0,
+      "learning_rate": 1.2400000000000002e-06,
+      "loss": 1.4171360731124878,
+      "step": 32
+    },
+    {
+      "epoch": 0.34601679295515053,
+      "grad_norm": 580.0,
+      "learning_rate": 1.28e-06,
+      "loss": 1.4474064111709595,
+      "step": 33
+    },
+    {
+      "epoch": 0.3565021503174278,
+      "grad_norm": 83.5,
+      "learning_rate": 1.32e-06,
+      "loss": 1.4120572805404663,
+      "step": 34
+    },
+    {
+      "epoch": 0.3669875076797051,
+      "grad_norm": 201.0,
+      "learning_rate": 1.3600000000000001e-06,
+      "loss": 1.4311250448226929,
+      "step": 35
+    },
+    {
+      "epoch": 0.3774728650419824,
+      "grad_norm": 121.0,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 1.4023066759109497,
+      "step": 36
+    },
+    {
+      "epoch": 0.3879582224042597,
+      "grad_norm": 51.25,
+      "learning_rate": 1.44e-06,
+      "loss": 1.3962011337280273,
+      "step": 37
+    },
+    {
+      "epoch": 0.398443579766537,
+      "grad_norm": 67.0,
+      "learning_rate": 1.48e-06,
+      "loss": 1.409425139427185,
+      "step": 38
+    },
+    {
+      "epoch": 0.40892893712881423,
+      "grad_norm": 60.5,
+      "learning_rate": 1.52e-06,
+      "loss": 1.3721140623092651,
+      "step": 39
+    },
+    {
+      "epoch": 0.4194142944910915,
+      "grad_norm": 58.5,
+      "learning_rate": 1.56e-06,
+      "loss": 1.375535011291504,
+      "step": 40
+    },
+    {
+      "epoch": 0.4298996518533688,
+      "grad_norm": 144.0,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 1.3638286590576172,
+      "step": 41
+    },
+    {
+      "epoch": 0.4403850092156461,
+      "grad_norm": 348.0,
+      "learning_rate": 1.6400000000000002e-06,
+      "loss": 1.3767451047897339,
+      "step": 42
+    },
+    {
+      "epoch": 0.4508703665779234,
+      "grad_norm": 102.0,
+      "learning_rate": 1.6800000000000002e-06,
+      "loss": 1.3871445655822754,
+      "step": 43
+    },
+    {
+      "epoch": 0.4613557239402007,
+      "grad_norm": 83.5,
+      "learning_rate": 1.72e-06,
+      "loss": 1.3462551832199097,
+      "step": 44
+    },
+    {
+      "epoch": 0.471841081302478,
+      "grad_norm": 75.0,
+      "learning_rate": 1.76e-06,
+      "loss": 1.3668186664581299,
+      "step": 45
+    },
+    {
+      "epoch": 0.4823264386647553,
+      "grad_norm": 51.75,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 1.3438992500305176,
+      "step": 46
+    },
+    {
+      "epoch": 0.49281179602703257,
+      "grad_norm": 64.0,
+      "learning_rate": 1.8400000000000002e-06,
+      "loss": 1.3390253782272339,
+      "step": 47
+    },
+    {
+      "epoch": 0.5032971533893098,
+      "grad_norm": 45.5,
+      "learning_rate": 1.8800000000000002e-06,
+      "loss": 1.365052580833435,
+      "step": 48
+    },
+    {
+      "epoch": 0.5137825107515871,
+      "grad_norm": 66.0,
+      "learning_rate": 1.9200000000000003e-06,
+      "loss": 1.3313298225402832,
+      "step": 49
+    },
+    {
+      "epoch": 0.5242678681138644,
+      "grad_norm": 50.25,
+      "learning_rate": 1.9600000000000003e-06,
+      "loss": 1.335034966468811,
+      "step": 50
+    },
+    {
+      "epoch": 0.5347532254761417,
+      "grad_norm": 155.0,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.3607136011123657,
+      "step": 51
+    },
+    {
+      "epoch": 0.545238582838419,
+      "grad_norm": 56.0,
+      "learning_rate": 2.04e-06,
+      "loss": 1.3396861553192139,
+      "step": 52
+    },
+    {
+      "epoch": 0.5557239402006963,
+      "grad_norm": 74.0,
+      "learning_rate": 2.08e-06,
+      "loss": 1.3398594856262207,
+      "step": 53
+    },
+    {
+      "epoch": 0.5662092975629736,
+      "grad_norm": 46.0,
+      "learning_rate": 2.12e-06,
+      "loss": 1.3325151205062866,
+      "step": 54
+    },
+    {
+      "epoch": 0.5766946549252508,
+      "grad_norm": 66.0,
+      "learning_rate": 2.16e-06,
+      "loss": 1.306301236152649,
+      "step": 55
+    },
+    {
+      "epoch": 0.5871800122875281,
+      "grad_norm": 35.75,
+      "learning_rate": 2.2e-06,
+      "loss": 1.324842929840088,
+      "step": 56
+    },
+    {
+      "epoch": 0.5976653696498054,
+      "grad_norm": 25.875,
+      "learning_rate": 2.24e-06,
+      "loss": 1.2961994409561157,
+      "step": 57
+    },
+    {
+      "epoch": 0.6081507270120827,
+      "grad_norm": 198.0,
+      "learning_rate": 2.28e-06,
+      "loss": 1.2753080129623413,
+      "step": 58
+    },
+    {
+      "epoch": 0.61863608437436,
+      "grad_norm": 173.0,
+      "learning_rate": 2.3200000000000002e-06,
+      "loss": 1.3008363246917725,
+      "step": 59
+    },
+    {
+      "epoch": 0.6291214417366373,
+      "grad_norm": 109.5,
+      "learning_rate": 2.3600000000000003e-06,
+      "loss": 1.2845975160598755,
+      "step": 60
+    },
+    {
+      "epoch": 0.6396067990989146,
+      "grad_norm": 35.5,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.253173589706421,
+      "step": 61
+    },
+    {
+      "epoch": 0.6500921564611919,
+      "grad_norm": 41.0,
+      "learning_rate": 2.4400000000000004e-06,
+      "loss": 1.2949249744415283,
+      "step": 62
+    },
+    {
+      "epoch": 0.6605775138234692,
+      "grad_norm": 36.5,
+      "learning_rate": 2.4800000000000004e-06,
+      "loss": 1.268322229385376,
+      "step": 63
+    },
+    {
+      "epoch": 0.6710628711857465,
+      "grad_norm": 57.0,
+      "learning_rate": 2.52e-06,
+      "loss": 1.2876548767089844,
+      "step": 64
+    },
+    {
+      "epoch": 0.6815482285480238,
+      "grad_norm": 75.0,
+      "learning_rate": 2.56e-06,
+      "loss": 1.2799946069717407,
+      "step": 65
+    },
+    {
+      "epoch": 0.6920335859103011,
+      "grad_norm": 26.125,
+      "learning_rate": 2.6e-06,
+      "loss": 1.2793971300125122,
+      "step": 66
+    },
+    {
+      "epoch": 0.7025189432725784,
+      "grad_norm": 28.625,
+      "learning_rate": 2.64e-06,
+      "loss": 1.2701070308685303,
+      "step": 67
+    },
+    {
+      "epoch": 0.7130043006348556,
+      "grad_norm": 115.0,
+      "learning_rate": 2.68e-06,
+      "loss": 1.260026216506958,
+      "step": 68
+    },
+    {
+      "epoch": 0.7234896579971329,
+      "grad_norm": 24.75,
+      "learning_rate": 2.7200000000000002e-06,
+      "loss": 1.2556943893432617,
+      "step": 69
+    },
+    {
+      "epoch": 0.7339750153594102,
+      "grad_norm": 56.75,
+      "learning_rate": 2.7600000000000003e-06,
+      "loss": 1.2900102138519287,
+      "step": 70
+    },
+    {
+      "epoch": 0.7444603727216875,
+      "grad_norm": 19.75,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 1.255289077758789,
+      "step": 71
+    },
+    {
+      "epoch": 0.7549457300839648,
+      "grad_norm": 16.125,
+      "learning_rate": 2.84e-06,
+      "loss": 1.2419655323028564,
+      "step": 72
+    },
+    {
+      "epoch": 0.7654310874462421,
+      "grad_norm": 34.25,
+      "learning_rate": 2.88e-06,
+      "loss": 1.2446309328079224,
+      "step": 73
+    },
+    {
+      "epoch": 0.7759164448085194,
+      "grad_norm": 35.75,
+      "learning_rate": 2.92e-06,
+      "loss": 1.243605375289917,
+      "step": 74
+    },
+    {
+      "epoch": 0.7864018021707967,
+      "grad_norm": 29.0,
+      "learning_rate": 2.96e-06,
+      "loss": 1.2285890579223633,
+      "step": 75
+    },
+    {
+      "epoch": 0.796887159533074,
+      "grad_norm": 21.875,
+      "learning_rate": 3e-06,
+      "loss": 1.2128394842147827,
+      "step": 76
+    },
+    {
+      "epoch": 0.8073725168953512,
+      "grad_norm": 21.375,
+      "learning_rate": 3.04e-06,
+      "loss": 1.248595952987671,
+      "step": 77
+    },
+    {
+      "epoch": 0.8178578742576285,
+      "grad_norm": 17.125,
+      "learning_rate": 3.08e-06,
+      "loss": 1.2283611297607422,
+      "step": 78
+    },
+    {
+      "epoch": 0.8283432316199058,
+      "grad_norm": 12.625,
+      "learning_rate": 3.12e-06,
+      "loss": 1.2119556665420532,
+      "step": 79
+    },
+    {
+      "epoch": 0.838828588982183,
+      "grad_norm": 18.375,
+      "learning_rate": 3.1600000000000002e-06,
+      "loss": 1.2181857824325562,
+      "step": 80
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 96,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.480966126825636e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-80/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:874ac4b635f5e0e0130ccc11de5bfc6cee2eac14aa65567d5f9737b0b5cc556a
+size 5265