Training in progress, step 1000, checkpoint

checkpoint-1000/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "EleutherAI/pythia-14m",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 6,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 8
+}

checkpoint-1000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.42.3"
+}

checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab6bc05987db0a787657d51bc0e9ac31dbeae4059dac9a8c35f9429b83701b80
+size 4776024

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ac2af7c55c5dc0f762b9504b1d1d714310cb7cd5cf06bded5c4c5265fe72cd
+size 9599034

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835f869ea325fd6edf27b48b589309fb66641cb92b45f2fc13d1bb6e8814106c
+size 14244

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abfb4e1882cd2be7023754719a511884a34067605875b4c06fcf1ee0fac455ae
+size 1064

checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|beginoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|unknown|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1000/tokenizer.json

@@ -0,0 +1,96 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<|beginoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "<|unknown|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": {
+    "type": "NFC"
+  },
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {}
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": "<|unknown|>",
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "<|beginoftext|>": 0,
+      "<|endoftext|>": 1,
+      "<|unknown|>": 2,
+      "a": 3,
+      "c": 4,
+      "g": 5,
+      "t": 6,
+      "n": 7
+    },
+    "merges": []
+  }
+}

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|beginoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|unknown|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|beginoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|unknown|>"
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.03908692933083177,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003908692933083177,
+      "grad_norm": 0.6370952129364014,
+      "learning_rate": 4.98240400406663e-05,
+      "loss": 1.4791,
+      "step": 100
+    },
+    {
+      "epoch": 0.007817385866166354,
+      "grad_norm": 0.27393946051597595,
+      "learning_rate": 4.9628528974739973e-05,
+      "loss": 1.3743,
+      "step": 200
+    },
+    {
+      "epoch": 0.01172607879924953,
+      "grad_norm": 0.364713191986084,
+      "learning_rate": 4.943301790881364e-05,
+      "loss": 1.3525,
+      "step": 300
+    },
+    {
+      "epoch": 0.015634771732332707,
+      "grad_norm": 0.33364734053611755,
+      "learning_rate": 4.923750684288731e-05,
+      "loss": 1.3457,
+      "step": 400
+    },
+    {
+      "epoch": 0.019543464665415886,
+      "grad_norm": 0.3672705292701721,
+      "learning_rate": 4.904199577696098e-05,
+      "loss": 1.3375,
+      "step": 500
+    },
+    {
+      "epoch": 0.02345215759849906,
+      "grad_norm": 0.16828787326812744,
+      "learning_rate": 4.884648471103465e-05,
+      "loss": 1.3348,
+      "step": 600
+    },
+    {
+      "epoch": 0.02736085053158224,
+      "grad_norm": 0.24634529650211334,
+      "learning_rate": 4.8650973645108314e-05,
+      "loss": 1.3343,
+      "step": 700
+    },
+    {
+      "epoch": 0.031269543464665414,
+      "grad_norm": 0.5399248003959656,
+      "learning_rate": 4.845546257918198e-05,
+      "loss": 1.3287,
+      "step": 800
+    },
+    {
+      "epoch": 0.03517823639774859,
+      "grad_norm": 0.5724157691001892,
+      "learning_rate": 4.825995151325565e-05,
+      "loss": 1.3236,
+      "step": 900
+    },
+    {
+      "epoch": 0.03908692933083177,
+      "grad_norm": 0.5199714303016663,
+      "learning_rate": 4.8064440447329324e-05,
+      "loss": 1.3189,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 25584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 702428479488000.0,
+  "train_batch_size": 48,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90ec914d144549ecac00847be5b8c2e93ddca3eea1598f7317b62d35eddf48d3
+size 5176