Training in progress, epoch 4, checkpoint

checkpoint-750/README.md

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

checkpoint-750/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-750/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:551be1e13d9af0439030367cb2fd2043cfc600ec19cab43ff105471104d7ddd7
+size 112130416

checkpoint-750/added_tokens.json

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

checkpoint-750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc0cdc6b04b33ecd3314391089f1c3b201143d28959a04a1ca67fd2b1285463
+size 224537202

checkpoint-750/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd25b0f3e6143f05402e71931a93b37572c9f970ef2ca9dd15281d08f953b140
+size 15024

checkpoint-750/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2ccad10dde964c130f0691a3e9b2a858d672b90270f138f539a59db7117ab1d
+size 15024

checkpoint-750/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e98d89205d9587f49a318cae8f59b7b9e57fef9c18e74bcc9fca58a0ee4a4b29
+size 15024

checkpoint-750/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c075f77e46139b36830b5eadc89b0726f5fd6fef0b5770005d0a0ca2eb0f1352
+size 15024

checkpoint-750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:570bc91c67267cda600f4caa7dd66d16bb203fdf9d0f9ed602803af0e2afa01d
+size 1064

checkpoint-750/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-750/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-750/trainer_state.json

@@ -0,0 +1,142 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.5194531679153442,
+      "learning_rate": 0.0003,
+      "loss": 1.7259,
+      "step": 100
+    },
+    {
+      "epoch": 0.9973333333333333,
+      "eval_accuracy": 0.5753333333333334,
+      "eval_loss": 1.6105104684829712,
+      "eval_runtime": 5.418,
+      "eval_samples_per_second": 92.285,
+      "eval_steps_per_second": 11.628,
+      "step": 187
+    },
+    {
+      "epoch": 0.9973333333333333,
+      "eval_exact_match": 17.2,
+      "eval_f1": 26.890173160173163,
+      "step": 187
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.6734262704849243,
+      "learning_rate": 0.0003,
+      "loss": 1.6156,
+      "step": 200
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.7422465682029724,
+      "learning_rate": 0.0003,
+      "loss": 1.3358,
+      "step": 300
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5722564102564103,
+      "eval_loss": 1.6464648246765137,
+      "eval_runtime": 5.1856,
+      "eval_samples_per_second": 96.422,
+      "eval_steps_per_second": 12.149,
+      "step": 375
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 19.0,
+      "eval_f1": 27.762380952380955,
+      "step": 375
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.828364908695221,
+      "learning_rate": 0.0003,
+      "loss": 1.2607,
+      "step": 400
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.9025559425354004,
+      "learning_rate": 0.0003,
+      "loss": 0.9854,
+      "step": 500
+    },
+    {
+      "epoch": 2.997333333333333,
+      "eval_accuracy": 0.5707692307692308,
+      "eval_loss": 1.7620763778686523,
+      "eval_runtime": 5.2589,
+      "eval_samples_per_second": 95.077,
+      "eval_steps_per_second": 11.98,
+      "step": 562
+    },
+    {
+      "epoch": 2.997333333333333,
+      "eval_exact_match": 18.2,
+      "eval_f1": 27.53142857142857,
+      "step": 562
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.8217537999153137,
+      "learning_rate": 0.0003,
+      "loss": 0.9099,
+      "step": 600
+    },
+    {
+      "epoch": 3.7333333333333334,
+      "grad_norm": 0.8315110206604004,
+      "learning_rate": 0.0003,
+      "loss": 0.7508,
+      "step": 700
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5663076923076923,
+      "eval_loss": 1.9380683898925781,
+      "eval_runtime": 5.3338,
+      "eval_samples_per_second": 93.742,
+      "eval_steps_per_second": 11.811,
+      "step": 750
+    },
+    {
+      "epoch": 4.0,
+      "eval_exact_match": 16.0,
+      "eval_f1": 24.611904761904768,
+      "step": 750
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 9350,
+  "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": 1.3061848702124032e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a48aaa718d03f9c3a1cf4e80dbff36330a05dd346d42a3b722f1ae2626aabe3c
+size 5304