Training in progress, step 4000, checkpoint

checkpoint-4000/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "JackFram/llama-68m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 12,
+  "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": "float32",
+  "transformers_version": "4.41.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

checkpoint-4000/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.41.0.dev0"
+}

checkpoint-4000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf7620b0c51ef17a030b63cfe26c514df5d88602a1b8140fb12c4968dfa6ff4
+size 272123144

checkpoint-4000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:908d9d7ed41d479f7f47a9fd0646de3f7800df94e052115c9815ea463d99e70d
+size 544259743

checkpoint-4000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
+size 14244

checkpoint-4000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394be853393fcf0db07e5bdfe4c0d7e15ce8f5fac5bdbb2ad1b413385499af51
+size 1000

checkpoint-4000/special_tokens_map.json

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

checkpoint-4000/tokenizer.model

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

checkpoint-4000/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding": "max_length",
+  "return_tensors": "pt",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

checkpoint-4000/trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0576414595452142,
+  "eval_steps": 1000,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13220518244315177,
+      "grad_norm": 0.8546391725540161,
+      "learning_rate": 8.816009873931059e-05,
+      "loss": 5.1118,
+      "step": 500
+    },
+    {
+      "epoch": 0.26441036488630354,
+      "grad_norm": 0.8593688607215881,
+      "learning_rate": 9.59831475011252e-05,
+      "loss": 3.406,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26441036488630354,
+      "eval_accuracy": 0.5035306174465283,
+      "eval_loss": 3.23445987701416,
+      "eval_runtime": 74.0522,
+      "eval_samples_per_second": 24.847,
+      "eval_steps_per_second": 0.527,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3966155473294553,
+      "grad_norm": 0.9617258906364441,
+      "learning_rate": 9.134314230431938e-05,
+      "loss": 3.0005,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5288207297726071,
+      "grad_norm": 0.8953185677528381,
+      "learning_rate": 8.670313710751356e-05,
+      "loss": 2.8119,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5288207297726071,
+      "eval_accuracy": 0.5365118094348038,
+      "eval_loss": 2.821384906768799,
+      "eval_runtime": 72.8065,
+      "eval_samples_per_second": 25.272,
+      "eval_steps_per_second": 0.536,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6610259122157589,
+      "grad_norm": 1.4154396057128906,
+      "learning_rate": 8.206313191070773e-05,
+      "loss": 2.686,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7932310946589106,
+      "grad_norm": 1.821349024772644,
+      "learning_rate": 7.742312671390191e-05,
+      "loss": 2.607,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7932310946589106,
+      "eval_accuracy": 0.5497897240925214,
+      "eval_loss": 2.657219886779785,
+      "eval_runtime": 72.9553,
+      "eval_samples_per_second": 25.221,
+      "eval_steps_per_second": 0.535,
+      "step": 3000
+    },
+    {
+      "epoch": 0.9254362771020624,
+      "grad_norm": 2.0297396183013916,
+      "learning_rate": 7.278312151709609e-05,
+      "loss": 2.5642,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0576414595452142,
+      "grad_norm": 2.8318285942077637,
+      "learning_rate": 6.814311632029027e-05,
+      "loss": 2.4734,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0576414595452142,
+      "eval_accuracy": 0.5582058048894458,
+      "eval_loss": 2.5735702514648438,
+      "eval_runtime": 73.5253,
+      "eval_samples_per_second": 25.025,
+      "eval_steps_per_second": 0.53,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 11346,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.124838835670221e+16,
+  "train_batch_size": 24,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a8c3b8deb94d253a20c7d637102edeaa129f75276f850abb181ddfd4b1ddcf
+size 5176