Training in progress, epoch 0, checkpoint

checkpoint-8/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "lectura/TinyLlama-120M-news",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 1024,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 46336
+}

checkpoint-8/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.35.0"
+}

checkpoint-8/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48301fe4d4eb1d30cc82fc00324bb93e4f768a57db60758e5ee42c5d0a9ab5d
+size 482171848

checkpoint-8/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fffad0463699c3e77bb82f36e16dde0bc6e6c7447777ede717a63bba14b79ba
+size 964412154

checkpoint-8/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

checkpoint-8/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad5f52ecb0bbf38c6f8b5598a8c847cac877458fc43413d90fa986613b3fd21e
+size 1064

checkpoint-8/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-8/tokenizer_config.json

@@ -0,0 +1,78 @@
+{
+  "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
+    },
+    "46331": {
+      "content": "<|sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46332": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46333": {
+      "content": "<|acc|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46334": {
+      "content": "<|rrn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "46335": {
+      "content": "<|tel|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-8/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9846153846153847,
+  "eval_steps": 500,
+  "global_step": 8,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.937500000000001e-06,
+      "loss": 12.7837,
+      "step": 1
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.875000000000001e-06,
+      "loss": 12.4595,
+      "step": 2
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.8125e-06,
+      "loss": 11.9121,
+      "step": 3
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.75e-06,
+      "loss": 11.6628,
+      "step": 4
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 9.6875e-06,
+      "loss": 11.4327,
+      "step": 5
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 9.625e-06,
+      "loss": 11.1488,
+      "step": 6
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.562500000000002e-06,
+      "loss": 10.9209,
+      "step": 7
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 9.5e-06,
+      "loss": 10.8448,
+      "step": 8
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 160,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 539703011966976.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-8/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a6fef67a6d9ec40dd5de4f4428a33ef7c86345cb77990f465d9680f0009f594
+size 4600