Training in progress, epoch 2, checkpoint

checkpoint-1058/README.md

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

checkpoint-1058/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-1058/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d0ad28e57881d4bb08739409cd450be71937d58c61b989d435d98630a58e0c7
+size 112130416

checkpoint-1058/added_tokens.json

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

checkpoint-1058/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:957afa72e49377d85bec04280e02f5b33a527e18dbe5a98a669695567fa9b9ca
+size 224537202

checkpoint-1058/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb3c37fe70d28e07b56883476bf630741d46d260b67684564fa15146812ae116
+size 15024

checkpoint-1058/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:191f1173f063793abd3ddd6ad2ce273604af6b408ea5301298951bac55ff257f
+size 15024

checkpoint-1058/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d56b276d38bf0d2660b6712b96592588121643e0cde94450a30b7ce706bb2d6c
+size 15024

checkpoint-1058/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6250a2f7fdd6add9072d5babc78527cff62efb7792dd6b7b7aa88301d210e3fc
+size 15024

checkpoint-1058/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b871de9035826d4b30c30167a4fe8759528b610203dcdc247cfc5c19619b090
+size 1064

checkpoint-1058/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-1058/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-1058/trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1058,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1890359168241966,
+      "grad_norm": 7.269421577453613,
+      "learning_rate": 0.0005,
+      "loss": 1.9195,
+      "step": 100
+    },
+    {
+      "epoch": 0.3780718336483932,
+      "grad_norm": 1.071650505065918,
+      "learning_rate": 0.0005,
+      "loss": 1.9396,
+      "step": 200
+    },
+    {
+      "epoch": 0.5671077504725898,
+      "grad_norm": 0.5662499070167542,
+      "learning_rate": 0.0005,
+      "loss": 2.3641,
+      "step": 300
+    },
+    {
+      "epoch": 0.7561436672967864,
+      "grad_norm": 0.47088223695755005,
+      "learning_rate": 0.0005,
+      "loss": 1.8969,
+      "step": 400
+    },
+    {
+      "epoch": 0.945179584120983,
+      "grad_norm": 0.3653932511806488,
+      "learning_rate": 0.0005,
+      "loss": 1.8531,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6214529147982063,
+      "eval_loss": 1.5580899715423584,
+      "eval_runtime": 5.56,
+      "eval_samples_per_second": 89.928,
+      "eval_steps_per_second": 11.331,
+      "step": 529
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 14.4,
+      "eval_f1": 20.983333333333345,
+      "eval_qa_bleu": 12.514681390986086,
+      "eval_qa_exact_match": 0.102,
+      "eval_recite_bleu": 12.61307158352263,
+      "eval_recite_exact_match": 0.0,
+      "step": 529
+    },
+    {
+      "epoch": 1.1342155009451795,
+      "grad_norm": 0.5318541526794434,
+      "learning_rate": 0.0005,
+      "loss": 1.6622,
+      "step": 600
+    },
+    {
+      "epoch": 1.3232514177693762,
+      "grad_norm": 235.6529998779297,
+      "learning_rate": 0.0005,
+      "loss": 1.5596,
+      "step": 700
+    },
+    {
+      "epoch": 1.5122873345935728,
+      "grad_norm": 0.5057249069213867,
+      "learning_rate": 0.0005,
+      "loss": 1.5296,
+      "step": 800
+    },
+    {
+      "epoch": 1.7013232514177694,
+      "grad_norm": 0.5339187383651733,
+      "learning_rate": 0.0005,
+      "loss": 1.5036,
+      "step": 900
+    },
+    {
+      "epoch": 1.8903591682419658,
+      "grad_norm": 0.5649825930595398,
+      "learning_rate": 0.0005,
+      "loss": 1.4884,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6643587443946188,
+      "eval_loss": 1.2189537286758423,
+      "eval_runtime": 6.192,
+      "eval_samples_per_second": 80.749,
+      "eval_steps_per_second": 10.174,
+      "step": 1058
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 11.2,
+      "eval_f1": 18.31238095238096,
+      "eval_qa_bleu": 10.766593815425745,
+      "eval_qa_exact_match": 0.096,
+      "eval_recite_bleu": 13.257993783037875,
+      "eval_recite_exact_match": 0.002,
+      "step": 1058
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 26450,
+  "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": 9.642374156674662e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1058/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1820a0b512c2fa8b3950f986e6f44420dacfa98792c1f255a5842682ec51f235
+size 5304