Training in progress, epoch 3, 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 sha256:003232ad64e898e44a8ecbd0ed05ba606f5b5933f74004c691f51c8edd5a631e
+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 sha256:2619de8df8c2f71dd3655518641984689fe7530c63e2ef28bc497aaef5b6f804
+size 224537202

checkpoint-750/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cb52a95f02d97a431eb7f3cdf8dfbb5613aa4fc247f9c18d76a0f6d6799e129
+size 15024

checkpoint-750/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d05166ad771514e361ad8c8d684fd0dd7dbae688fd035617a39efea154c10e5
+size 15024

checkpoint-750/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d526eece9100db8ecff2a1945e028a3541f83d9d2a8c73202b5e5ba1662839d6
+size 15024

checkpoint-750/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adef74c4f42696c1a630b4bfda1d95deadc1a5363d744a4c9074697cc3b29841
+size 15024

checkpoint-750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce4f81803861286fbc66ef29ca3a3f867174d8f7eaf0b4091acb991c9eaf7690
+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 +1,127 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.5479037761688232,
+      "learning_rate": 0.0005,
+      "loss": 2.3029,
+      "step": 100
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5442906618118286,
+      "learning_rate": 0.0005,
+      "loss": 2.2398,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5162539682539683,
+      "eval_loss": 2.3236427307128906,
+      "eval_runtime": 5.266,
+      "eval_samples_per_second": 94.949,
+      "eval_steps_per_second": 11.964,
+      "step": 250
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 17.6,
+      "eval_f1": 26.59450937950939,
+      "step": 250
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.6918729543685913,
+      "learning_rate": 0.0005,
+      "loss": 2.0245,
+      "step": 300
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.7950774431228638,
+      "learning_rate": 0.0005,
+      "loss": 1.8286,
+      "step": 400
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6913579106330872,
+      "learning_rate": 0.0005,
+      "loss": 1.8301,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5124126984126984,
+      "eval_loss": 2.4219954013824463,
+      "eval_runtime": 5.2763,
+      "eval_samples_per_second": 94.763,
+      "eval_steps_per_second": 11.94,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 17.0,
+      "eval_f1": 24.808081363081367,
+      "step": 500
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.9923084378242493,
+      "learning_rate": 0.0005,
+      "loss": 1.3144,
+      "step": 600
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.0025588274002075,
+      "learning_rate": 0.0005,
+      "loss": 1.3626,
+      "step": 700
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5061904761904762,
+      "eval_loss": 2.6152632236480713,
+      "eval_runtime": 5.2745,
+      "eval_samples_per_second": 94.795,
+      "eval_steps_per_second": 11.944,
+      "step": 750
+    },
+    {
+      "epoch": 3.0,
+      "eval_exact_match": 16.0,
+      "eval_f1": 24.234217449217454,
+      "step": 750
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 12500,
+  "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": 2.292008841170125e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b62f42960cf4fd93abfb3be317e2e8ef04964ff17a18b3862335bf3c3ff7041
+size 5304