Training in progress, step 100, checkpoint

last-checkpoint/added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

last-checkpoint/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "Xenova/tiny-random-Phi3ForCausalLM",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "max_position_embeddings": 4096,
+  "model_type": "phi3",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 2047,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.1",
+  "use_cache": false,
+  "vocab_size": 32011
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 32000,
+  "pad_token_id": 32000,
+  "transformers_version": "4.48.1"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c914af7e4717984588deb34667879d37816d8425bf9f40c7f2df62411adc325a
+size 4140280

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f1d4cc7e69b6d4ecabbbf7997c661f2f6b544b7bb70ab8878c1272f23010f6f
+size 4291766

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4651e32e118f1ea1a8e26dfbbe64298593e12e6a71bcd36cb77f04f86d3f86d
+size 15024

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0c1eba909fbb51daca773a25c075f182b4096aff21c9b4ff19dbada2080ac99
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28adb9f06e220aefdc723ea4380a84d42b8bfb87cc53ce65859d55ce1876f51c
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:423c49ed521f6986d20d8b29112b383f4b0f3f2e228084ef82c2ad7dcd5d1de8
+size 15024

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,133 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,111 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 16.666666666666668,
+  "eval_steps": 200,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16666666666666666,
+      "eval_loss": 10.377338409423828,
+      "eval_runtime": 2.3495,
+      "eval_samples_per_second": 638.849,
+      "eval_steps_per_second": 5.107,
+      "step": 1
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.208984375,
+      "learning_rate": 0.00019863613034027224,
+      "loss": 10.3698,
+      "step": 10
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.4296875,
+      "learning_rate": 0.0001879473751206489,
+      "loss": 10.3199,
+      "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.45703125,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 10.2229,
+      "step": 30
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.458984375,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 10.1217,
+      "step": 40
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 0.4609375,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 10.0382,
+      "step": 50
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.4609375,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 9.9768,
+      "step": 60
+    },
+    {
+      "epoch": 11.666666666666666,
+      "grad_norm": 0.4609375,
+      "learning_rate": 4.530518418775733e-05,
+      "loss": 9.9373,
+      "step": 70
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 0.462890625,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 9.9182,
+      "step": 80
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.46484375,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 9.9122,
+      "step": 90
+    },
+    {
+      "epoch": 16.666666666666668,
+      "grad_norm": 0.462890625,
+      "learning_rate": 0.0,
+      "loss": 9.9115,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 17,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 164363029708800.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:767cbb0126f5e19779e9fcc2851f3166d36ca132f2aa13429b17ffa28b07b942
+size 6904