Training in progress, epoch 2, checkpoint

checkpoint-562/README.md

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

checkpoint-562/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-562/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18de048305fb0f4d23dc594aff72da1f6705bcc58329dec88ba45f1378af96d
+size 112130416

checkpoint-562/added_tokens.json

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

checkpoint-562/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a645fe81320a08ae0e8e891babe3e2d69deeaca2a4f36e6f70021b01f6ffa79
+size 224537202

checkpoint-562/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1835e9d2405bb346e6cd217f28683b7dbc7bc8bb7faf7a4812afccc67aec7b93
+size 15024

checkpoint-562/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbf0049f37d79bf8c21c646fa6e7295890fb43a00729c47855c2f5f22c3202a2
+size 15024

checkpoint-562/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bb97f4b4ef5cf099ea12a1ddee5b75b93d7f1bfcf473580ad9e6c1a59580a71
+size 15024

checkpoint-562/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80efac3d5f74ea16e1dea842c7621617ba4b736c2b73f3006e1e8487dbe031fc
+size 15024

checkpoint-562/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5323fe83dd6e0df212f524212b3489b09c6d52e7bf347b7d365396c69673424
+size 1064

checkpoint-562/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-562/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-562/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.997333333333333,
+  "eval_steps": 500,
+  "global_step": 562,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.275871217250824,
+      "learning_rate": 3e-05,
+      "loss": 1.8545,
+      "step": 100
+    },
+    {
+      "epoch": 0.9973333333333333,
+      "eval_accuracy": 0.6037399103139014,
+      "eval_loss": 1.7123007774353027,
+      "eval_runtime": 6.2976,
+      "eval_samples_per_second": 79.395,
+      "eval_steps_per_second": 10.004,
+      "step": 187
+    },
+    {
+      "epoch": 0.9973333333333333,
+      "eval_exact_match": 14.4,
+      "eval_f1": 22.843015873015876,
+      "eval_qa_bleu": 9.471299126615676,
+      "eval_qa_exact_match": 0.112,
+      "eval_recite_bleu": 12.267251092702137,
+      "eval_recite_exact_match": 0.0,
+      "step": 187
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.32765188813209534,
+      "learning_rate": 3e-05,
+      "loss": 1.7408,
+      "step": 200
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.3532409369945526,
+      "learning_rate": 3e-05,
+      "loss": 1.7063,
+      "step": 300
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6058565022421525,
+      "eval_loss": 1.69453763961792,
+      "eval_runtime": 6.5928,
+      "eval_samples_per_second": 75.841,
+      "eval_steps_per_second": 9.556,
+      "step": 375
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 14.4,
+      "eval_f1": 23.29731601731603,
+      "eval_qa_bleu": 9.4408132575913,
+      "eval_qa_exact_match": 0.11,
+      "eval_recite_bleu": 13.027794116434837,
+      "eval_recite_exact_match": 0.0,
+      "step": 375
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.3777780532836914,
+      "learning_rate": 3e-05,
+      "loss": 1.7094,
+      "step": 400
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.3971036374568939,
+      "learning_rate": 3e-05,
+      "loss": 1.6702,
+      "step": 500
+    },
+    {
+      "epoch": 2.997333333333333,
+      "eval_accuracy": 0.6065919282511211,
+      "eval_loss": 1.6851236820220947,
+      "eval_runtime": 6.3104,
+      "eval_samples_per_second": 79.234,
+      "eval_steps_per_second": 9.984,
+      "step": 562
+    },
+    {
+      "epoch": 2.997333333333333,
+      "eval_exact_match": 14.0,
+      "eval_f1": 23.306825396825417,
+      "eval_qa_bleu": 8.683248465366908,
+      "eval_qa_exact_match": 0.11,
+      "eval_recite_bleu": 12.39336052958371,
+      "eval_recite_exact_match": 0.006,
+      "step": 562
+    }
+  ],
+  "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": 6.198399466890854e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-562/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e9c21c8367f69c99b21b20aa3dbf722814d1b222850e23dacbe471b235b2dd4
+size 5304