Model save

.ipynb_checkpoints/adapter_config-checkpoint.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

.ipynb_checkpoints/all_results-checkpoint.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.0569556951522827,
+    "eval_runtime": 10.2753,
+    "eval_samples": 124,
+    "eval_samples_per_second": 12.068,
+    "eval_steps_per_second": 0.779,
+    "train_loss": 1.0657691690656874,
+    "train_runtime": 300.603,
+    "train_samples": 1143,
+    "train_samples_per_second": 3.802,
+    "train_steps_per_second": 0.06
+}

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "llava_mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

.ipynb_checkpoints/tokenizer_config-checkpoint.json

@@ -0,0 +1,51 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": "<EMBEDDING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

README.md

@@ -2,11 +2,10 @@
 license: apache-2.0
 library_name: peft
 tags:
-- alignment-handbook
 - generated_from_trainer
 base_model: mistralai/Mistral-7B-v0.1
 datasets:
-- HuggingFaceH4/ultrachat_200k
+- generator
 model-index:
 - name: Test_with_new_script
   results: []
@@ -17,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Test_with_new_script
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0905
+- Loss: 0.9985
 
 ## Model description
 
@@ -55,7 +54,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.11          | 1.0   | 18   | 1.0905          |
+| 1.0052        | 1.0   | 22   | 0.9985          |
 
 
 ### Framework versions

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "v_proj",
     "k_proj",
     "o_proj",
-    "down_proj",
     "up_proj",
-    "v_proj",
-    "gate_proj",
-    "q_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14d37b719ded8577e0c19e669ca2cebb01db619d1866b04e1652272e8172b6b1
+oid sha256:67010e2a89699ee21c974ed33ddbce0d2b58366053107584dc70fbfcdebfadc0
 size 83946192

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 1.0,
-    "eval_loss": 1.0904877185821533,
-    "eval_runtime": 15.5995,
-    "eval_samples": 124,
-    "eval_samples_per_second": 7.949,
-    "eval_steps_per_second": 0.513,
-    "train_loss": 1.168492575486501,
-    "train_runtime": 457.8696,
-    "train_samples": 1143,
-    "train_samples_per_second": 2.496,
-    "train_steps_per_second": 0.039
+    "eval_loss": 0.9985440969467163,
+    "eval_runtime": 10.4315,
+    "eval_samples": 154,
+    "eval_samples_per_second": 14.763,
+    "eval_steps_per_second": 0.959,
+    "train_loss": 1.0528265129436145,
+    "train_runtime": 330.3819,
+    "train_samples": 1383,
+    "train_samples_per_second": 4.186,
+    "train_steps_per_second": 0.067
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_loss": 1.0904877185821533,
-    "eval_runtime": 15.5995,
-    "eval_samples": 124,
-    "eval_samples_per_second": 7.949,
-    "eval_steps_per_second": 0.513
+    "eval_loss": 0.9985440969467163,
+    "eval_runtime": 10.4315,
+    "eval_samples": 154,
+    "eval_samples_per_second": 14.763,
+    "eval_steps_per_second": 0.959
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 1.168492575486501,
-    "train_runtime": 457.8696,
-    "train_samples": 1143,
-    "train_samples_per_second": 2.496,
-    "train_steps_per_second": 0.039
+    "train_loss": 1.0528265129436145,
+    "train_runtime": 330.3819,
+    "train_samples": 1383,
+    "train_samples_per_second": 4.186,
+    "train_steps_per_second": 0.067
 }

trainer_state.json

@@ -3,59 +3,65 @@
   "best_model_checkpoint": null,
   "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 18,
+  "global_step": 22,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.06,
-      "learning_rate": 0.0001,
-      "loss": 1.3159,
+      "epoch": 0.05,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.1782,
       "step": 1
     },
     {
-      "epoch": 0.28,
-      "learning_rate": 0.00018314696123025454,
-      "loss": 1.2515,
+      "epoch": 0.23,
+      "learning_rate": 0.00019458172417006347,
+      "loss": 1.1529,
       "step": 5
     },
     {
-      "epoch": 0.56,
-      "learning_rate": 0.0001,
-      "loss": 1.1683,
+      "epoch": 0.45,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 1.06,
       "step": 10
     },
     {
-      "epoch": 0.83,
-      "learning_rate": 1.6853038769745467e-05,
-      "loss": 1.11,
+      "epoch": 0.68,
+      "learning_rate": 5.983045753470308e-05,
+      "loss": 1.0093,
       "step": 15
     },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 1.0052,
+      "step": 20
+    },
     {
       "epoch": 1.0,
-      "eval_loss": 1.0904877185821533,
-      "eval_runtime": 15.6992,
-      "eval_samples_per_second": 7.899,
-      "eval_steps_per_second": 0.51,
-      "step": 18
+      "eval_loss": 0.9985440969467163,
+      "eval_runtime": 10.4369,
+      "eval_samples_per_second": 14.755,
+      "eval_steps_per_second": 0.958,
+      "step": 22
     },
     {
       "epoch": 1.0,
-      "step": 18,
-      "total_flos": 1.0560439065981747e+17,
-      "train_loss": 1.168492575486501,
-      "train_runtime": 457.8696,
-      "train_samples_per_second": 2.496,
-      "train_steps_per_second": 0.039
+      "step": 22,
+      "total_flos": 1.2907203290936115e+17,
+      "train_loss": 1.0528265129436145,
+      "train_runtime": 330.3819,
+      "train_samples_per_second": 4.186,
+      "train_steps_per_second": 0.067
     }
   ],
   "logging_steps": 5,
-  "max_steps": 18,
+  "max_steps": 22,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,
-  "total_flos": 1.0560439065981747e+17,
+  "total_flos": 1.2907203290936115e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a0e14ac8baf459cacbf69a626c50bdbd4c30f0415167c5ee51730735ba152c
+oid sha256:f4ec1a30ffc3e3543c6f3726587f9e4f89d6d59b28a1239701a7135804e54a0d
 size 4856