Training in progress, step 200, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "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 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.48.1"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54199da57b837d4891196f02c89063f1b4c8051da494ceb732eca28e0e049899
+size 2200119864

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afb6588ffa25521011a1286f0128a2f605dab5da48172dece4259b51767d871d
+size 2235234810

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f2762d792d815ec78151cdfb1183ff8fe6b1a4c5fcc050ac87b15dc66050802
+size 15024

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc1f875219f8ac3c776408d86b647fbc8462ad7ecb23ac468a078c2c50ec46e
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbcdba7bc63bee2e58552ca3df8d3d9521da29d066231bf49913479cc60a05a4
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac162cf8f57eb46f3e3f12f50328cd5574b5384b6fe27493b80f0979cc8d636b
+size 15024

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abcd078b1186023c3032f4652f953246e76b5f62233ca3f894e881ea9feb17b7
+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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "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": 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 +1,45 @@
+{
+  "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": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,189 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.764705882352942,
+  "eval_steps": 200,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.058823529411764705,
+      "eval_loss": 2.0603227615356445,
+      "eval_runtime": 6.3215,
+      "eval_samples_per_second": 237.445,
+      "eval_steps_per_second": 5.062,
+      "step": 1
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 1.125,
+      "learning_rate": 0.0001,
+      "loss": 1.8865,
+      "step": 10
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 2.078125,
+      "learning_rate": 0.0002,
+      "loss": 1.7253,
+      "step": 20
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.000199658449300667,
+      "loss": 1.2996,
+      "step": 30
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 1.640625,
+      "learning_rate": 0.00019863613034027224,
+      "loss": 0.9578,
+      "step": 40
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019694002659393305,
+      "loss": 0.6771,
+      "step": 50
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 1.6875,
+      "learning_rate": 0.00019458172417006347,
+      "loss": 0.3386,
+      "step": 60
+    },
+    {
+      "epoch": 4.117647058823529,
+      "grad_norm": 0.96484375,
+      "learning_rate": 0.00019157733266550575,
+      "loss": 0.2562,
+      "step": 70
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.0001879473751206489,
+      "loss": 0.1393,
+      "step": 80
+    },
+    {
+      "epoch": 5.294117647058823,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00018371664782625287,
+      "loss": 0.1163,
+      "step": 90
+    },
+    {
+      "epoch": 5.882352941176471,
+      "grad_norm": 0.87109375,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 0.0997,
+      "step": 100
+    },
+    {
+      "epoch": 6.470588235294118,
+      "grad_norm": 0.7265625,
+      "learning_rate": 0.00017357239106731317,
+      "loss": 0.0658,
+      "step": 110
+    },
+    {
+      "epoch": 7.0588235294117645,
+      "grad_norm": 0.49609375,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 0.0672,
+      "step": 120
+    },
+    {
+      "epoch": 7.647058823529412,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.0001614212712689668,
+      "loss": 0.0342,
+      "step": 130
+    },
+    {
+      "epoch": 8.235294117647058,
+      "grad_norm": 0.3515625,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 0.0308,
+      "step": 140
+    },
+    {
+      "epoch": 8.823529411764707,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00014759473930370736,
+      "loss": 0.0192,
+      "step": 150
+    },
+    {
+      "epoch": 9.411764705882353,
+      "grad_norm": 0.251953125,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 0.0116,
+      "step": 160
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.20703125,
+      "learning_rate": 0.00013246994692046836,
+      "loss": 0.0079,
+      "step": 170
+    },
+    {
+      "epoch": 10.588235294117647,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 0.0037,
+      "step": 180
+    },
+    {
+      "epoch": 11.176470588235293,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 0.00011645945902807341,
+      "loss": 0.0031,
+      "step": 190
+    },
+    {
+      "epoch": 11.764705882352942,
+      "grad_norm": 0.062255859375,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 0.0024,
+      "step": 200
+    },
+    {
+      "epoch": 11.764705882352942,
+      "eval_loss": 3.5474228858947754,
+      "eval_runtime": 6.0534,
+      "eval_samples_per_second": 247.958,
+      "eval_steps_per_second": 5.286,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 24,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2203604110737408e+17,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02fab4322a14e2374e7f44ff316f0cba3d1ca31a1a209c4d1b45790252adb685
+size 7032