Training in progress, step 200

adapter_config.json

@@ -0,0 +1,26 @@
+{
+ "auto_mapping": null,
+ "base_model_name_or_path": "NousResearch/Nous-Hermes-llama-2-7b",
+ "bias": "none",
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "lora_alpha": 16.0,
+ "lora_dropout": 0.1,
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 64,
+ "revision": null,
+ "target_modules": [
+ "gate_proj",
+ "o_proj",
+ "k_proj",
+ "up_proj",
+ "v_proj",
+ "q_proj",
+ "down_proj"
+ ],
+ "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc1db379d02c4e5990d9c1f0ba0e9c732d2d60a70f9543614384ca2f3014c593
+size 319977229

added_tokens.json

@@ -0,0 +1,3 @@
+{
+ "<pad>": 32000
+}

checkpoint-200/README.md

@@ -0,0 +1,20 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.4.0

checkpoint-200/adapter_config.json

@@ -0,0 +1,26 @@
+{
+ "auto_mapping": null,
+ "base_model_name_or_path": "NousResearch/Nous-Hermes-llama-2-7b",
+ "bias": "none",
+ "fan_in_fan_out": false,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "lora_alpha": 16.0,
+ "lora_dropout": 0.1,
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 64,
+ "revision": null,
+ "target_modules": [
+ "gate_proj",
+ "o_proj",
+ "k_proj",
+ "up_proj",
+ "v_proj",
+ "q_proj",
+ "down_proj"
+ ],
+ "task_type": "CAUSAL_LM"
+}

checkpoint-200/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc1db379d02c4e5990d9c1f0ba0e9c732d2d60a70f9543614384ca2f3014c593
+size 319977229

checkpoint-200/added_tokens.json

@@ -0,0 +1,3 @@
+{
+ "<pad>": 32000
+}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d33ddc596e17f2d590a9dc16d0583d1a02cd8d49cb790a35fc14ca4f04ebb0cf
+size 1279539525

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:944287a16547a649c0a00319f9b7d451b75cc3f9b6437a68e6766889fa2cda45
+size 14511

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
+size 627

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+ "bos_token": "<s>",
+ "eos_token": "</s>",
+ "pad_token": "<unk>",
+ "unk_token": "<unk>"
+}

checkpoint-200/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "bos_token": {
+ "__type": "AddedToken",
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "clean_up_tokenization_spaces": false,
+ "eos_token": {
+ "__type": "AddedToken",
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "legacy": false,
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": null,
+ "padding_side": "right",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": {
+ "__type": "AddedToken",
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ }
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,144 @@
+{
+ "best_metric": 0.4498298466205597,
+ "best_model_checkpoint": "./output_v2/7b_cluster00_Nous-Hermes-llama-2-7b_partitioned_v3_standardized_00/checkpoint-200",
+ "epoch": 0.21208907741251326,
+ "global_step": 200,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.01,
+ "learning_rate": 0.0002,
+ "loss": 0.5637,
+ "step": 10
+ },
+ {
+ "epoch": 0.02,
+ "learning_rate": 0.0002,
+ "loss": 0.4775,
+ "step": 20
+ },
+ {
+ "epoch": 0.03,
+ "learning_rate": 0.0002,
+ "loss": 0.5079,
+ "step": 30
+ },
+ {
+ "epoch": 0.04,
+ "learning_rate": 0.0002,
+ "loss": 0.4849,
+ "step": 40
+ },
+ {
+ "epoch": 0.05,
+ "learning_rate": 0.0002,
+ "loss": 0.4587,
+ "step": 50
+ },
+ {
+ "epoch": 0.06,
+ "learning_rate": 0.0002,
+ "loss": 0.4867,
+ "step": 60
+ },
+ {
+ "epoch": 0.07,
+ "learning_rate": 0.0002,
+ "loss": 0.4578,
+ "step": 70
+ },
+ {
+ "epoch": 0.08,
+ "learning_rate": 0.0002,
+ "loss": 0.4665,
+ "step": 80
+ },
+ {
+ "epoch": 0.1,
+ "learning_rate": 0.0002,
+ "loss": 0.5044,
+ "step": 90
+ },
+ {
+ "epoch": 0.11,
+ "learning_rate": 0.0002,
+ "loss": 0.4979,
+ "step": 100
+ },
+ {
+ "epoch": 0.12,
+ "learning_rate": 0.0002,
+ "loss": 0.4715,
+ "step": 110
+ },
+ {
+ "epoch": 0.13,
+ "learning_rate": 0.0002,
+ "loss": 0.4717,
+ "step": 120
+ },
+ {
+ "epoch": 0.14,
+ "learning_rate": 0.0002,
+ "loss": 0.4419,
+ "step": 130
+ },
+ {
+ "epoch": 0.15,
+ "learning_rate": 0.0002,
+ "loss": 0.4671,
+ "step": 140
+ },
+ {
+ "epoch": 0.16,
+ "learning_rate": 0.0002,
+ "loss": 0.4503,
+ "step": 150
+ },
+ {
+ "epoch": 0.17,
+ "learning_rate": 0.0002,
+ "loss": 0.4878,
+ "step": 160
+ },
+ {
+ "epoch": 0.18,
+ "learning_rate": 0.0002,
+ "loss": 0.4648,
+ "step": 170
+ },
+ {
+ "epoch": 0.19,
+ "learning_rate": 0.0002,
+ "loss": 0.4625,
+ "step": 180
+ },
+ {
+ "epoch": 0.2,
+ "learning_rate": 0.0002,
+ "loss": 0.4473,
+ "step": 190
+ },
+ {
+ "epoch": 0.21,
+ "learning_rate": 0.0002,
+ "loss": 0.4585,
+ "step": 200
+ },
+ {
+ "epoch": 0.21,
+ "eval_loss": 0.4498298466205597,
+ "eval_runtime": 253.5551,
+ "eval_samples_per_second": 3.944,
+ "eval_steps_per_second": 0.986,
+ "step": 200
+ }
+ ],
+ "max_steps": 5000,
+ "num_train_epochs": 6,
+ "total_flos": 5.47322957438976e+16,
+ "trial_name": null,
+ "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d43bb46b7e18307cd325d889344b3c5a6b0f12a2594434f5acb40117cbab761
+size 6011

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+ "bos_token": "<s>",
+ "eos_token": "</s>",
+ "pad_token": "<unk>",
+ "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "bos_token": {
+ "__type": "AddedToken",
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "clean_up_tokenization_spaces": false,
+ "eos_token": {
+ "__type": "AddedToken",
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "legacy": false,
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": null,
+ "padding_side": "right",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizer",
+ "unk_token": {
+ "__type": "AddedToken",
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d43bb46b7e18307cd325d889344b3c5a6b0f12a2594434f5acb40117cbab761
+size 6011