Training in progress, epoch 6, checkpoint

checkpoint-1125/README.md

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

checkpoint-1125/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-1125/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:176598d0bc5ddec6ec33c26f74f6dab427d515f09c8550636d0b726b80c4e14b
+size 112130416

checkpoint-1125/added_tokens.json

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

checkpoint-1125/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7ef78d96e6f902101b9b5c79dc92672e996061b683424cd30de63e7f0fe07db
+size 224537202

checkpoint-1125/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2efa17419a9c2033bab9e002b97865bc472d59b5f11279763df2c0f7e4830a9b
+size 15024

checkpoint-1125/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a4eadd3d8f78e1efe57e5554e8f342747d9b42f8dfcb53c922010b62007649b
+size 15024

checkpoint-1125/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d112554b0fb2e400e53af7593f468c74ea1d7173d0341562967e3d9aa55af930
+size 15024

checkpoint-1125/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfb79661665e720fd752d165da0166a9cabb2796881b287ba3a7ce0d7c0fe095
+size 15024

checkpoint-1125/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3fd60fb60fa83446d49f081575f06ce23c9432ce278e0dff2524a94ef5c9e95
+size 1064

checkpoint-1125/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-1125/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-1125/trainer_state.json

@@ -0,0 +1,200 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 1125,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.7527768015861511,
+      "learning_rate": 0.0005,
+      "loss": 1.7217,
+      "step": 100
+    },
+    {
+      "epoch": 0.9973333333333333,
+      "eval_accuracy": 0.5738974358974359,
+      "eval_loss": 1.6209890842437744,
+      "eval_runtime": 5.1723,
+      "eval_samples_per_second": 96.668,
+      "eval_steps_per_second": 12.18,
+      "step": 187
+    },
+    {
+      "epoch": 0.9973333333333333,
+      "eval_exact_match": 18.2,
+      "eval_f1": 27.000476190476196,
+      "step": 187
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.7723727226257324,
+      "learning_rate": 0.0005,
+      "loss": 1.615,
+      "step": 200
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.8481244444847107,
+      "learning_rate": 0.0005,
+      "loss": 1.2605,
+      "step": 300
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5706666666666667,
+      "eval_loss": 1.6909353733062744,
+      "eval_runtime": 5.4194,
+      "eval_samples_per_second": 92.26,
+      "eval_steps_per_second": 11.625,
+      "step": 375
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 17.0,
+      "eval_f1": 25.9057142857143,
+      "step": 375
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.810580313205719,
+      "learning_rate": 0.0005,
+      "loss": 1.1991,
+      "step": 400
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.8971414566040039,
+      "learning_rate": 0.0005,
+      "loss": 0.9141,
+      "step": 500
+    },
+    {
+      "epoch": 2.997333333333333,
+      "eval_accuracy": 0.5657435897435897,
+      "eval_loss": 1.831854224205017,
+      "eval_runtime": 4.9933,
+      "eval_samples_per_second": 100.134,
+      "eval_steps_per_second": 12.617,
+      "step": 562
+    },
+    {
+      "epoch": 2.997333333333333,
+      "eval_exact_match": 16.0,
+      "eval_f1": 23.940000000000012,
+      "step": 562
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.7627168297767639,
+      "learning_rate": 0.0005,
+      "loss": 0.8634,
+      "step": 600
+    },
+    {
+      "epoch": 3.7333333333333334,
+      "grad_norm": 0.7384397387504578,
+      "learning_rate": 0.0005,
+      "loss": 0.7223,
+      "step": 700
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5637948717948718,
+      "eval_loss": 1.9418420791625977,
+      "eval_runtime": 5.3476,
+      "eval_samples_per_second": 93.499,
+      "eval_steps_per_second": 11.781,
+      "step": 750
+    },
+    {
+      "epoch": 4.0,
+      "eval_exact_match": 16.6,
+      "eval_f1": 24.14476190476191,
+      "step": 750
+    },
+    {
+      "epoch": 4.266666666666667,
+      "grad_norm": 0.7065069079399109,
+      "learning_rate": 0.0005,
+      "loss": 0.6786,
+      "step": 800
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.7625908851623535,
+      "learning_rate": 0.0005,
+      "loss": 0.6434,
+      "step": 900
+    },
+    {
+      "epoch": 4.997333333333334,
+      "eval_accuracy": 0.5602051282051282,
+      "eval_loss": 2.093710422515869,
+      "eval_runtime": 5.1796,
+      "eval_samples_per_second": 96.532,
+      "eval_steps_per_second": 12.163,
+      "step": 937
+    },
+    {
+      "epoch": 4.997333333333334,
+      "eval_exact_match": 17.2,
+      "eval_f1": 24.822857142857156,
+      "step": 937
+    },
+    {
+      "epoch": 5.333333333333333,
+      "grad_norm": 0.6257635951042175,
+      "learning_rate": 0.0005,
+      "loss": 0.6022,
+      "step": 1000
+    },
+    {
+      "epoch": 5.866666666666667,
+      "grad_norm": 0.7330732345581055,
+      "learning_rate": 0.0005,
+      "loss": 0.5957,
+      "step": 1100
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5573333333333333,
+      "eval_loss": 2.17874813079834,
+      "eval_runtime": 5.3048,
+      "eval_samples_per_second": 94.255,
+      "eval_steps_per_second": 11.876,
+      "step": 1125
+    },
+    {
+      "epoch": 6.0,
+      "eval_exact_match": 15.2,
+      "eval_f1": 22.341269841269852,
+      "step": 1125
+    }
+  ],
+  "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": 1.959277291896832e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1125/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2776615b5656a131d464a15a3d5283d9bdf82687bc8ffc8d243c778d1158123d
+size 5304