Training in progress, epoch 2, checkpoint

checkpoint-683/README.md

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

checkpoint-683/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-683/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2053fd6495831f1cd3562180f2484ee65236c691cfc7d09b39e2b6f4d0e8f15e
+size 112130416

checkpoint-683/added_tokens.json

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

checkpoint-683/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e07a3bb73f71b1c81fa89c327493cdf3267bef9a23f74b06ca6964341ef0026c
+size 224537202

checkpoint-683/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4348b9438a804fa0ed63845c2e55bc60c8a1f1012cec123fbe5d9dd93bf22d63
+size 15024

checkpoint-683/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab33692da5577b8392720512056cc9bb9301a43fac1e4fe4c0a59f19d28845cb
+size 15024

checkpoint-683/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f4889392941df424d5280596f56f3bd3cb691442e07c92f4a4ad5c5fe75b441
+size 15024

checkpoint-683/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2386419a6b7454a1059db505c9a260d85d2c3e3d89992aae86b164abbb805c1b
+size 15024

checkpoint-683/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:615d366953876b0485af29dc12335950e15e38baa887fd2d070dca91e96c0dbf
+size 1064

checkpoint-683/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-683/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-683/trainer_state.json

@@ -0,0 +1,107 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 683,
+  "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
+    }
+  ],
+  "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": 5.865082302182195e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-683/training_args.bin

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