Pushing to origin

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openchat/openchat_3.5",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.2,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "SEQ_CLS"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ccbd768a0746d8c2562a703c540d4fbca7f0b7335f9e0ebef7718a601fa3549
+size 167865112

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|end_of_turn|>": 32000,
+  "<|pad_0|>": 32001
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d451df152e7dda8036bfb6ee074f9b6555575f9692d1dc1abe60349580223b54
+size 335988821

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a46711a14e82bd0e824e0578189b82a96908aa8ce3724b35f78ce3ba7a95addb
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec88f76ff8b6a16ba28e412bf4f5d61b95a316d71571bb1dcae14aec8f9e370
+size 1064

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_turn|>",
+    "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|end_of_turn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|pad_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|end_of_turn|>",
+    "<|pad_0|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_turn|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 2e-05,
+      "loss": 1.5991,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.638,
+      "eval_loss": 0.7116702795028687,
+      "eval_macro_f1": 0.633566150420083,
+      "eval_runtime": 89.1695,
+      "eval_samples_per_second": 5.607,
+      "eval_steps_per_second": 0.561,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2e-05,
+      "loss": 0.6537,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.618,
+      "eval_loss": 1.2388803958892822,
+      "eval_macro_f1": 0.5674015555424694,
+      "eval_runtime": 89.196,
+      "eval_samples_per_second": 5.606,
+      "eval_steps_per_second": 0.561,
+      "step": 200
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2e-05,
+      "loss": 0.3544,
+      "step": 300
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.708,
+      "eval_loss": 0.6158359050750732,
+      "eval_macro_f1": 0.7078317110655739,
+      "eval_runtime": 89.1778,
+      "eval_samples_per_second": 5.607,
+      "eval_steps_per_second": 0.561,
+      "step": 300
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2e-05,
+      "loss": 0.1829,
+      "step": 400
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.708,
+      "eval_loss": 1.6795860528945923,
+      "eval_macro_f1": 0.7078317110655739,
+      "eval_runtime": 89.1817,
+      "eval_samples_per_second": 5.607,
+      "eval_steps_per_second": 0.561,
+      "step": 400
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2e-05,
+      "loss": 0.1188,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.704,
+      "eval_loss": 1.4835941791534424,
+      "eval_macro_f1": 0.7039242045963766,
+      "eval_runtime": 89.1768,
+      "eval_samples_per_second": 5.607,
+      "eval_steps_per_second": 0.561,
+      "step": 500
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0924,
+      "step": 600
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.698,
+      "eval_loss": 2.3937265872955322,
+      "eval_macro_f1": 0.6914223590045407,
+      "eval_runtime": 89.1641,
+      "eval_samples_per_second": 5.608,
+      "eval_steps_per_second": 0.561,
+      "step": 600
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0913,
+      "step": 700
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.706,
+      "eval_loss": 1.8895695209503174,
+      "eval_macro_f1": 0.7053765768365863,
+      "eval_runtime": 89.2883,
+      "eval_samples_per_second": 5.6,
+      "eval_steps_per_second": 0.56,
+      "step": 700
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2e-05,
+      "loss": 0.1357,
+      "step": 800
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.714,
+      "eval_loss": 2.458871603012085,
+      "eval_macro_f1": 0.7132832080200502,
+      "eval_runtime": 89.4099,
+      "eval_samples_per_second": 5.592,
+      "eval_steps_per_second": 0.559,
+      "step": 800
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0432,
+      "step": 900
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.742,
+      "eval_loss": 3.152550220489502,
+      "eval_macro_f1": 0.7390681699576441,
+      "eval_runtime": 89.2296,
+      "eval_samples_per_second": 5.604,
+      "eval_steps_per_second": 0.56,
+      "step": 900
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0491,
+      "step": 1000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.754,
+      "eval_loss": 3.035457134246826,
+      "eval_macro_f1": 0.7527886644558337,
+      "eval_runtime": 89.2033,
+      "eval_samples_per_second": 5.605,
+      "eval_steps_per_second": 0.561,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1000,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 3.913814800576512e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84ac70da7f431a52a66f04d05a79f0f03d66b171a914b3d983a8770894f0dd4e
+size 4600