Training in progress, epoch 0, checkpoint

checkpoint-341/README.md

@@ -0,0 +1,9 @@
+---
+library_name: peft
+---
+## Training procedure
+
+### Framework versions
+
+
+- PEFT 0.5.0

checkpoint-341/adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-4B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-341/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8eee0e83a081bf6cedafc1d872a177e2bcef7ce1d113acf9c347a1375077716
+size 112130416

checkpoint-341/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

checkpoint-341/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebfd611761993801f1662bb977e6a91947863b3edd22b5cfaf3e10fc470b6f28
+size 224537202

checkpoint-341/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3b429a86a575cbf896b9f3211624258c926e760fb7a6b78b1bddea20bce0db7
+size 15024

checkpoint-341/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ada55898a19e60848ceb78efd9c836ec71622b429ed9dd1b1611476ba036bbb
+size 15024

checkpoint-341/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a4907abb8113a62b89056dbcc63aadbc5818d3f756b6f295e1b0d62830b30b5
+size 15024

checkpoint-341/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e0e16976296ec9ce8b31359165ff24c395720b493dc928f0c1724494237df0b
+size 15024

checkpoint-341/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b9d708fbed88e09c3b287077852d0746bde2ab5c6154098b9c1edf14184f513
+size 1064

checkpoint-341/special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}

checkpoint-341/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-341/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9985358711566618,
+  "eval_steps": 500,
+  "global_step": 341,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.29282576866764276,
+      "grad_norm": 0.2411503791809082,
+      "learning_rate": 0.0001,
+      "loss": 2.0009,
+      "step": 100
+    },
+    {
+      "epoch": 0.5856515373352855,
+      "grad_norm": 0.22286373376846313,
+      "learning_rate": 0.0001,
+      "loss": 1.9538,
+      "step": 200
+    },
+    {
+      "epoch": 0.8784773060029283,
+      "grad_norm": 0.24079065024852753,
+      "learning_rate": 0.0001,
+      "loss": 1.9571,
+      "step": 300
+    },
+    {
+      "epoch": 0.9985358711566618,
+      "eval_accuracy": 0.45379487179487177,
+      "eval_loss": 3.9512319564819336,
+      "eval_runtime": 5.0647,
+      "eval_samples_per_second": 98.722,
+      "eval_steps_per_second": 12.439,
+      "step": 341
+    },
+    {
+      "epoch": 0.9985358711566618,
+      "eval_bleu": 0.28767194245703276,
+      "eval_exact_match": 0.03,
+      "eval_prefix_exact_match": 0.042,
+      "step": 341
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 17050,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.932523890691277e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-341/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e63e74298c414f7364874e60281a380506bddfac466373e2426a740b4eb5594
+size 5304