Training in progress, epoch 4, checkpoint

checkpoint-1707/README.md

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

checkpoint-1707/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-1707/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b75039df254cba9a56ab85890f9188f77c8a94ba36429197cd0634a5c5e019c1
+size 112130416

checkpoint-1707/added_tokens.json

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

checkpoint-1707/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c168248ccd6246a3ac626c31c7e6440b0628d6506688df030fd58220232a97
+size 224537202

checkpoint-1707/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ace172984bb66d39a99e7dd9a5bfc54e40430b9843356cf9b9b1534d8d75b918
+size 15024

checkpoint-1707/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1158c8814b63073467bf02c279c75cc4cd14f26603ead0c4236a66139c58413
+size 15024

checkpoint-1707/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88530e66b3526c8aa8e3fc2e6f09ed0d775891848469fce44eacfd98fea53a6a
+size 15024

checkpoint-1707/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:860a83a924c36bd26aba67ea76c19aa3c5ef32e1b2096c873e6ae40188b49c10
+size 15024

checkpoint-1707/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ade57388d6557059c0121eb5ebd57c310be365456cfbfc71728032aa2b5afb9
+size 1064

checkpoint-1707/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-1707/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-1707/trainer_state.json

@@ -0,0 +1,232 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.998535871156662,
+  "eval_steps": 500,
+  "global_step": 1707,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.29282576866764276,
+      "grad_norm": 0.2425622195005417,
+      "learning_rate": 0.0005,
+      "loss": 1.972,
+      "step": 100
+    },
+    {
+      "epoch": 0.5856515373352855,
+      "grad_norm": 0.24936461448669434,
+      "learning_rate": 0.0005,
+      "loss": 1.954,
+      "step": 200
+    },
+    {
+      "epoch": 0.8784773060029283,
+      "grad_norm": 0.28534355759620667,
+      "learning_rate": 0.0005,
+      "loss": 1.9636,
+      "step": 300
+    },
+    {
+      "epoch": 0.9985358711566618,
+      "eval_accuracy": 0.4142051282051282,
+      "eval_loss": 4.36731481552124,
+      "eval_runtime": 5.2053,
+      "eval_samples_per_second": 96.056,
+      "eval_steps_per_second": 12.103,
+      "step": 341
+    },
+    {
+      "epoch": 0.9985358711566618,
+      "eval_bleu": 0.16271683142618718,
+      "eval_exact_match": 0.0,
+      "eval_prefix_exact_match": 0.032,
+      "step": 341
+    },
+    {
+      "epoch": 1.171303074670571,
+      "grad_norm": 0.39824551343917847,
+      "learning_rate": 0.0005,
+      "loss": 1.8098,
+      "step": 400
+    },
+    {
+      "epoch": 1.4641288433382138,
+      "grad_norm": 0.4451245069503784,
+      "learning_rate": 0.0005,
+      "loss": 1.6717,
+      "step": 500
+    },
+    {
+      "epoch": 1.7569546120058566,
+      "grad_norm": 0.49089929461479187,
+      "learning_rate": 0.0005,
+      "loss": 1.7006,
+      "step": 600
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.43338461538461537,
+      "eval_loss": 4.586850643157959,
+      "eval_runtime": 5.9085,
+      "eval_samples_per_second": 84.624,
+      "eval_steps_per_second": 10.663,
+      "step": 683
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 0.2955390058097942,
+      "eval_exact_match": 0.0,
+      "eval_prefix_exact_match": 0.036,
+      "step": 683
+    },
+    {
+      "epoch": 2.049780380673499,
+      "grad_norm": 0.6150477528572083,
+      "learning_rate": 0.0005,
+      "loss": 1.6383,
+      "step": 700
+    },
+    {
+      "epoch": 2.342606149341142,
+      "grad_norm": 0.5455761551856995,
+      "learning_rate": 0.0005,
+      "loss": 1.2533,
+      "step": 800
+    },
+    {
+      "epoch": 2.6354319180087846,
+      "grad_norm": 0.6252492666244507,
+      "learning_rate": 0.0005,
+      "loss": 1.3256,
+      "step": 900
+    },
+    {
+      "epoch": 2.9282576866764276,
+      "grad_norm": 0.6721358299255371,
+      "learning_rate": 0.0005,
+      "loss": 1.3696,
+      "step": 1000
+    },
+    {
+      "epoch": 2.998535871156662,
+      "eval_accuracy": 0.42538461538461536,
+      "eval_loss": 4.720473766326904,
+      "eval_runtime": 5.6052,
+      "eval_samples_per_second": 89.204,
+      "eval_steps_per_second": 11.24,
+      "step": 1024
+    },
+    {
+      "epoch": 2.998535871156662,
+      "eval_bleu": 0.22572800415324107,
+      "eval_exact_match": 0.004,
+      "eval_prefix_exact_match": 0.044,
+      "step": 1024
+    },
+    {
+      "epoch": 3.22108345534407,
+      "grad_norm": 0.7449648380279541,
+      "learning_rate": 0.0005,
+      "loss": 1.0137,
+      "step": 1100
+    },
+    {
+      "epoch": 3.513909224011713,
+      "grad_norm": 0.7608182430267334,
+      "learning_rate": 0.0005,
+      "loss": 0.9535,
+      "step": 1200
+    },
+    {
+      "epoch": 3.8067349926793557,
+      "grad_norm": 0.8320977687835693,
+      "learning_rate": 0.0005,
+      "loss": 1.0297,
+      "step": 1300
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.41717948717948716,
+      "eval_loss": 4.783276557922363,
+      "eval_runtime": 5.4398,
+      "eval_samples_per_second": 91.915,
+      "eval_steps_per_second": 11.581,
+      "step": 1366
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 0.28487206250718533,
+      "eval_exact_match": 0.008,
+      "eval_prefix_exact_match": 0.034,
+      "step": 1366
+    },
+    {
+      "epoch": 4.099560761346998,
+      "grad_norm": 0.7788870334625244,
+      "learning_rate": 0.0005,
+      "loss": 0.9222,
+      "step": 1400
+    },
+    {
+      "epoch": 4.392386530014641,
+      "grad_norm": 0.7981182336807251,
+      "learning_rate": 0.0005,
+      "loss": 0.6733,
+      "step": 1500
+    },
+    {
+      "epoch": 4.685212298682284,
+      "grad_norm": 0.938538670539856,
+      "learning_rate": 0.0005,
+      "loss": 0.7366,
+      "step": 1600
+    },
+    {
+      "epoch": 4.978038067349927,
+      "grad_norm": 0.9696006178855896,
+      "learning_rate": 0.0005,
+      "loss": 0.7991,
+      "step": 1700
+    },
+    {
+      "epoch": 4.998535871156662,
+      "eval_accuracy": 0.4169230769230769,
+      "eval_loss": 4.9334001541137695,
+      "eval_runtime": 5.1107,
+      "eval_samples_per_second": 97.835,
+      "eval_steps_per_second": 12.327,
+      "step": 1707
+    },
+    {
+      "epoch": 4.998535871156662,
+      "eval_bleu": 0.2463806011037282,
+      "eval_exact_match": 0.006,
+      "eval_prefix_exact_match": 0.034,
+      "step": 1707
+    }
+  ],
+  "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": 1.466248183330898e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1707/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09109d7fc8f49ffd654f0e1286ef00d8840620753fec453a60a103c55187142
+size 5304