Training in progress, step 400, checkpoint

last-checkpoint/added_tokens.json

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

last-checkpoint/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-0.5B-Chat",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "top_p": 0.8,
+  "transformers_version": "4.48.1"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce784b84b672fff299f815541e54ec587d2cdcded415ef1365a2384d855b9be7
+size 927414184

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da41eca7c23aafd158d2a8f1c9db1d385409206f293c330f6bf158e90e3328b1
+size 942882362

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9feae33b2fec0a6229240e7adaee6ecc8f5cfdf1a8bd0e827b1d8a241424e3c0
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a673aaf85c0fe6b6c29cb8f3e7dbd829eef637110e4ad9a775f3fcf001c92591
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "use_fast": true
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,337 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.11837821840781296,
+  "eval_steps": 200,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0002959455460195324,
+      "eval_loss": 3.6609864234924316,
+      "eval_runtime": 59.7747,
+      "eval_samples_per_second": 25.128,
+      "eval_steps_per_second": 6.29,
+      "step": 1
+    },
+    {
+      "epoch": 0.002959455460195324,
+      "grad_norm": 131.0,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 3.0588,
+      "step": 10
+    },
+    {
+      "epoch": 0.005918910920390648,
+      "grad_norm": 15.875,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 2.8042,
+      "step": 20
+    },
+    {
+      "epoch": 0.008878366380585973,
+      "grad_norm": 20.125,
+      "learning_rate": 4.8e-05,
+      "loss": 2.3522,
+      "step": 30
+    },
+    {
+      "epoch": 0.011837821840781295,
+      "grad_norm": 27.5,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 2.5387,
+      "step": 40
+    },
+    {
+      "epoch": 0.01479727730097662,
+      "grad_norm": 73.0,
+      "learning_rate": 8e-05,
+      "loss": 2.3299,
+      "step": 50
+    },
+    {
+      "epoch": 0.017756732761171946,
+      "grad_norm": 12.5,
+      "learning_rate": 9.6e-05,
+      "loss": 2.654,
+      "step": 60
+    },
+    {
+      "epoch": 0.020716188221367268,
+      "grad_norm": 12.375,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 2.5244,
+      "step": 70
+    },
+    {
+      "epoch": 0.02367564368156259,
+      "grad_norm": 21.875,
+      "learning_rate": 0.00012800000000000002,
+      "loss": 2.605,
+      "step": 80
+    },
+    {
+      "epoch": 0.026635099141757917,
+      "grad_norm": 37.25,
+      "learning_rate": 0.000144,
+      "loss": 2.6757,
+      "step": 90
+    },
+    {
+      "epoch": 0.02959455460195324,
+      "grad_norm": 67.5,
+      "learning_rate": 0.00016,
+      "loss": 3.3479,
+      "step": 100
+    },
+    {
+      "epoch": 0.032554010062148565,
+      "grad_norm": 22.5,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 3.5544,
+      "step": 110
+    },
+    {
+      "epoch": 0.03551346552234389,
+      "grad_norm": 14.9375,
+      "learning_rate": 0.000192,
+      "loss": 3.1455,
+      "step": 120
+    },
+    {
+      "epoch": 0.03847292098253921,
+      "grad_norm": 24.25,
+      "learning_rate": 0.0001999978128380225,
+      "loss": 3.2288,
+      "step": 130
+    },
+    {
+      "epoch": 0.041432376442734536,
+      "grad_norm": 26.5,
+      "learning_rate": 0.0001999803161162393,
+      "loss": 4.085,
+      "step": 140
+    },
+    {
+      "epoch": 0.04439183190292986,
+      "grad_norm": 77.0,
+      "learning_rate": 0.00019994532573409262,
+      "loss": 3.6674,
+      "step": 150
+    },
+    {
+      "epoch": 0.04735128736312518,
+      "grad_norm": 15.0625,
+      "learning_rate": 0.00019989284781388617,
+      "loss": 3.9097,
+      "step": 160
+    },
+    {
+      "epoch": 0.05031074282332051,
+      "grad_norm": 16.0,
+      "learning_rate": 0.00019982289153773646,
+      "loss": 3.5733,
+      "step": 170
+    },
+    {
+      "epoch": 0.053270198283515834,
+      "grad_norm": 17.875,
+      "learning_rate": 0.00019973546914596623,
+      "loss": 4.0335,
+      "step": 180
+    },
+    {
+      "epoch": 0.05622965374371116,
+      "grad_norm": 29.375,
+      "learning_rate": 0.00019963059593496268,
+      "loss": 3.7777,
+      "step": 190
+    },
+    {
+      "epoch": 0.05918910920390648,
+      "grad_norm": 60.0,
+      "learning_rate": 0.00019950829025450114,
+      "loss": 3.8668,
+      "step": 200
+    },
+    {
+      "epoch": 0.05918910920390648,
+      "eval_loss": 4.461722373962402,
+      "eval_runtime": 60.1211,
+      "eval_samples_per_second": 24.983,
+      "eval_steps_per_second": 6.254,
+      "step": 200
+    },
+    {
+      "epoch": 0.062148564664101805,
+      "grad_norm": 9.4375,
+      "learning_rate": 0.0001993685735045343,
+      "loss": 4.3043,
+      "step": 210
+    },
+    {
+      "epoch": 0.06510802012429713,
+      "grad_norm": 60.75,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 3.8791,
+      "step": 220
+    },
+    {
+      "epoch": 0.06806747558449246,
+      "grad_norm": 16.875,
+      "learning_rate": 0.000199037007623783,
+      "loss": 4.1739,
+      "step": 230
+    },
+    {
+      "epoch": 0.07102693104468778,
+      "grad_norm": 19.625,
+      "learning_rate": 0.00019884521650742715,
+      "loss": 3.9914,
+      "step": 240
+    },
+    {
+      "epoch": 0.0739863865048831,
+      "grad_norm": 418.0,
+      "learning_rate": 0.00019863613034027224,
+      "loss": 4.8681,
+      "step": 250
+    },
+    {
+      "epoch": 0.07694584196507842,
+      "grad_norm": 14.0625,
+      "learning_rate": 0.0001984097857063434,
+      "loss": 4.1649,
+      "step": 260
+    },
+    {
+      "epoch": 0.07990529742527375,
+      "grad_norm": 12.8125,
+      "learning_rate": 0.0001981662222093976,
+      "loss": 4.2323,
+      "step": 270
+    },
+    {
+      "epoch": 0.08286475288546907,
+      "grad_norm": 19.125,
+      "learning_rate": 0.00019790548246599447,
+      "loss": 4.2854,
+      "step": 280
+    },
+    {
+      "epoch": 0.0858242083456644,
+      "grad_norm": 20.0,
+      "learning_rate": 0.00019762761209803927,
+      "loss": 3.9894,
+      "step": 290
+    },
+    {
+      "epoch": 0.08878366380585972,
+      "grad_norm": 45.5,
+      "learning_rate": 0.0001973326597248006,
+      "loss": 4.6403,
+      "step": 300
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 10.125,
+      "learning_rate": 0.00019702067695440332,
+      "loss": 4.5261,
+      "step": 310
+    },
+    {
+      "epoch": 0.09470257472625036,
+      "grad_norm": 17.875,
+      "learning_rate": 0.00019669171837479873,
+      "loss": 3.9252,
+      "step": 320
+    },
+    {
+      "epoch": 0.09766203018644569,
+      "grad_norm": 14.125,
+      "learning_rate": 0.00019634584154421317,
+      "loss": 4.3635,
+      "step": 330
+    },
+    {
+      "epoch": 0.10062148564664102,
+      "grad_norm": 18.125,
+      "learning_rate": 0.00019598310698107702,
+      "loss": 4.3755,
+      "step": 340
+    },
+    {
+      "epoch": 0.10358094110683634,
+      "grad_norm": 176.0,
+      "learning_rate": 0.00019560357815343577,
+      "loss": 4.0719,
+      "step": 350
+    },
+    {
+      "epoch": 0.10654039656703167,
+      "grad_norm": 9.9375,
+      "learning_rate": 0.00019520732146784491,
+      "loss": 4.5,
+      "step": 360
+    },
+    {
+      "epoch": 0.109499852027227,
+      "grad_norm": 23.375,
+      "learning_rate": 0.0001947944062577507,
+      "loss": 3.9226,
+      "step": 370
+    },
+    {
+      "epoch": 0.11245930748742232,
+      "grad_norm": 18.125,
+      "learning_rate": 0.00019436490477135878,
+      "loss": 4.3131,
+      "step": 380
+    },
+    {
+      "epoch": 0.11541876294761765,
+      "grad_norm": 17.5,
+      "learning_rate": 0.00019391889215899299,
+      "loss": 4.3054,
+      "step": 390
+    },
+    {
+      "epoch": 0.11837821840781296,
+      "grad_norm": 49.25,
+      "learning_rate": 0.0001934564464599461,
+      "loss": 4.178,
+      "step": 400
+    },
+    {
+      "epoch": 0.11837821840781296,
+      "eval_loss": 5.044467449188232,
+      "eval_runtime": 59.0352,
+      "eval_samples_per_second": 25.442,
+      "eval_steps_per_second": 6.369,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6078652634628096.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c63701d9c217b1919e42df47130110c22127f119d66a02c851a680ea4abc179
+size 6904