Training in progress, step 100, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "fxmarty/tiny-llama-fast-tokenizer",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "head_dim": 4,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "pad_token_id": -1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

last-checkpoint/generation_config.json

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

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25a257c5b2e34eda80e3d84f1a8cc4247ba163d63b057609915a20d5c03487fe
+size 2066752

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bec191f34319615e7969a7a94942c2ab6e19f09ef79ad5cfbca9b840fe7e04f4
+size 2162798

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": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "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 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '### Instruction: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ '### Response: ' + message['content'] + eos_token}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "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": 10.376375198364258,
+      "eval_runtime": 2.394,
+      "eval_samples_per_second": 626.993,
+      "eval_steps_per_second": 5.013,
+      "step": 1
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.09375,
+      "learning_rate": 0.00019863613034027224,
+      "loss": 10.3756,
+      "step": 10
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.12353515625,
+      "learning_rate": 0.0001879473751206489,
+      "loss": 10.3632,
+      "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 10.3433,
+      "step": 30
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.3203125,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 10.3073,
+      "step": 40
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 10.2602,
+      "step": 50
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.326171875,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 10.2203,
+      "step": 60
+    },
+    {
+      "epoch": 11.666666666666666,
+      "grad_norm": 0.326171875,
+      "learning_rate": 4.530518418775733e-05,
+      "loss": 10.1945,
+      "step": 70
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 0.328125,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 10.1812,
+      "step": 80
+    },
+    {
+      "epoch": 15.0,
+      "grad_norm": 0.328125,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 10.1773,
+      "step": 90
+    },
+    {
+      "epoch": 16.666666666666668,
+      "grad_norm": 0.328125,
+      "learning_rate": 0.0,
+      "loss": 10.1767,
+      "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": 81831709900800.0,
+  "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:aaa4e96900978d3ffc6b4d538660eb0cf2fc137143c61a37b1d477787b8740ea
+size 6904