Training in progress, epoch 5, checkpoint

checkpoint-2645/README.md

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

checkpoint-2645/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-2645/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b87f90aa66a092988e8ab938436a869be31c048ac28d911446bc63b5cf808eca
+size 112130416

checkpoint-2645/added_tokens.json

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

checkpoint-2645/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7660c999fd2ceb6e0afae78bffd92bd7aef918bdfb93df8e8ad2bdb242a997fb
+size 224537202

checkpoint-2645/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c34eb93c2a2a55a4b2d61caf06d523ea591e1ad68c0f70a9182f3d17a611c069
+size 15024

checkpoint-2645/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9da76f6f5d4db83c732aaae22754043cc09a98ade580152a1f014e55ed94c4b9
+size 15024

checkpoint-2645/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e40d9d79ff5474d21c21b7b7c6714692ff41f34ee8c8643cc0262f4ced4f9642
+size 15024

checkpoint-2645/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2099ec68b2e189706c3bb0a0321fa578b203e9a7df1363e37aedeedc2ffdec0a
+size 15024

checkpoint-2645/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bd5dfe91d76978ec6444d6de4e05e2dcf5ef5f69f89f3df856cac5c13078274
+size 1064

checkpoint-2645/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-2645/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-2645/trainer_state.json

@@ -0,0 +1,290 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2645,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1890359168241966,
+      "grad_norm": 0.5107442140579224,
+      "learning_rate": 5e-05,
+      "loss": 2.0482,
+      "step": 100
+    },
+    {
+      "epoch": 0.3780718336483932,
+      "grad_norm": 0.5563424229621887,
+      "learning_rate": 5e-05,
+      "loss": 1.8835,
+      "step": 200
+    },
+    {
+      "epoch": 0.5671077504725898,
+      "grad_norm": 0.4735371172428131,
+      "learning_rate": 5e-05,
+      "loss": 1.8512,
+      "step": 300
+    },
+    {
+      "epoch": 0.7561436672967864,
+      "grad_norm": 0.4543495178222656,
+      "learning_rate": 5e-05,
+      "loss": 1.8489,
+      "step": 400
+    },
+    {
+      "epoch": 0.945179584120983,
+      "grad_norm": 0.5007112622261047,
+      "learning_rate": 5e-05,
+      "loss": 1.8439,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5733333333333334,
+      "eval_loss": 1.6194567680358887,
+      "eval_runtime": 5.4154,
+      "eval_samples_per_second": 92.33,
+      "eval_steps_per_second": 11.634,
+      "step": 529
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 17.0,
+      "eval_f1": 26.880952380952387,
+      "step": 529
+    },
+    {
+      "epoch": 1.1342155009451795,
+      "grad_norm": 0.5181360244750977,
+      "learning_rate": 5e-05,
+      "loss": 1.8217,
+      "step": 600
+    },
+    {
+      "epoch": 1.3232514177693762,
+      "grad_norm": 1.1348918676376343,
+      "learning_rate": 5e-05,
+      "loss": 1.7866,
+      "step": 700
+    },
+    {
+      "epoch": 1.5122873345935728,
+      "grad_norm": 0.661758303642273,
+      "learning_rate": 5e-05,
+      "loss": 1.7934,
+      "step": 800
+    },
+    {
+      "epoch": 1.7013232514177694,
+      "grad_norm": 0.5634772777557373,
+      "learning_rate": 5e-05,
+      "loss": 1.7731,
+      "step": 900
+    },
+    {
+      "epoch": 1.8903591682419658,
+      "grad_norm": 0.6698930263519287,
+      "learning_rate": 5e-05,
+      "loss": 1.7969,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5751794871794872,
+      "eval_loss": 1.603736162185669,
+      "eval_runtime": 5.0986,
+      "eval_samples_per_second": 98.066,
+      "eval_steps_per_second": 12.356,
+      "step": 1058
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 17.6,
+      "eval_f1": 27.218095238095238,
+      "step": 1058
+    },
+    {
+      "epoch": 2.0793950850661624,
+      "grad_norm": 0.6265193223953247,
+      "learning_rate": 5e-05,
+      "loss": 1.7416,
+      "step": 1100
+    },
+    {
+      "epoch": 2.268431001890359,
+      "grad_norm": 0.812364935874939,
+      "learning_rate": 5e-05,
+      "loss": 1.6957,
+      "step": 1200
+    },
+    {
+      "epoch": 2.4574669187145557,
+      "grad_norm": 1.0972926616668701,
+      "learning_rate": 5e-05,
+      "loss": 1.7033,
+      "step": 1300
+    },
+    {
+      "epoch": 2.6465028355387523,
+      "grad_norm": 1.0831658840179443,
+      "learning_rate": 5e-05,
+      "loss": 1.6935,
+      "step": 1400
+    },
+    {
+      "epoch": 2.835538752362949,
+      "grad_norm": 1.0022494792938232,
+      "learning_rate": 5e-05,
+      "loss": 1.6799,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.573025641025641,
+      "eval_loss": 1.6428505182266235,
+      "eval_runtime": 5.1488,
+      "eval_samples_per_second": 97.111,
+      "eval_steps_per_second": 12.236,
+      "step": 1587
+    },
+    {
+      "epoch": 3.0,
+      "eval_exact_match": 20.2,
+      "eval_f1": 27.93809523809523,
+      "step": 1587
+    },
+    {
+      "epoch": 3.0245746691871456,
+      "grad_norm": 0.8240587711334229,
+      "learning_rate": 5e-05,
+      "loss": 1.6618,
+      "step": 1600
+    },
+    {
+      "epoch": 3.213610586011342,
+      "grad_norm": 1.2994645833969116,
+      "learning_rate": 5e-05,
+      "loss": 1.5736,
+      "step": 1700
+    },
+    {
+      "epoch": 3.402646502835539,
+      "grad_norm": 1.0891159772872925,
+      "learning_rate": 5e-05,
+      "loss": 1.5798,
+      "step": 1800
+    },
+    {
+      "epoch": 3.5916824196597354,
+      "grad_norm": 1.3826475143432617,
+      "learning_rate": 5e-05,
+      "loss": 1.5957,
+      "step": 1900
+    },
+    {
+      "epoch": 3.780718336483932,
+      "grad_norm": 0.9901586174964905,
+      "learning_rate": 5e-05,
+      "loss": 1.6026,
+      "step": 2000
+    },
+    {
+      "epoch": 3.9697542533081287,
+      "grad_norm": 1.0607813596725464,
+      "learning_rate": 5e-05,
+      "loss": 1.6106,
+      "step": 2100
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5708717948717948,
+      "eval_loss": 1.7143596410751343,
+      "eval_runtime": 5.3942,
+      "eval_samples_per_second": 92.693,
+      "eval_steps_per_second": 11.679,
+      "step": 2116
+    },
+    {
+      "epoch": 4.0,
+      "eval_exact_match": 19.0,
+      "eval_f1": 27.71428571428571,
+      "step": 2116
+    },
+    {
+      "epoch": 4.158790170132325,
+      "grad_norm": 1.3189178705215454,
+      "learning_rate": 5e-05,
+      "loss": 1.5029,
+      "step": 2200
+    },
+    {
+      "epoch": 4.3478260869565215,
+      "grad_norm": 1.062267541885376,
+      "learning_rate": 5e-05,
+      "loss": 1.51,
+      "step": 2300
+    },
+    {
+      "epoch": 4.536862003780718,
+      "grad_norm": 1.3810843229293823,
+      "learning_rate": 5e-05,
+      "loss": 1.4867,
+      "step": 2400
+    },
+    {
+      "epoch": 4.725897920604915,
+      "grad_norm": 1.1991653442382812,
+      "learning_rate": 5e-05,
+      "loss": 1.501,
+      "step": 2500
+    },
+    {
+      "epoch": 4.914933837429111,
+      "grad_norm": 1.310654878616333,
+      "learning_rate": 5e-05,
+      "loss": 1.5034,
+      "step": 2600
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5681025641025641,
+      "eval_loss": 1.8328346014022827,
+      "eval_runtime": 5.7763,
+      "eval_samples_per_second": 86.561,
+      "eval_steps_per_second": 10.907,
+      "step": 2645
+    },
+    {
+      "epoch": 5.0,
+      "eval_exact_match": 18.8,
+      "eval_f1": 26.6015873015873,
+      "step": 2645
+    }
+  ],
+  "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": 1.629371386172539e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2645/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f01d18f717251d8791982fc93ed5352f2d247add98e1102e2a52cc0a32128bb7
+size 5304