Training in progress, step 873, checkpoint

checkpoint-873/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "mnoukhov/pythia160m-sft-tldr",
+  "architectures": [
+    "GPTNeoXForSequenceClassification"
+  ],
+  "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": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

checkpoint-873/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdba72ce6827f4af494d287d3a8d6d5294edcea4d15fbe48db3e235d527ef295
+size 494777904

checkpoint-873/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d110bc1b3844011e865f9707b05310f93821b7f7cf05b29c011e84d56a20cb37
+size 989645754

checkpoint-873/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce3f1fd7866b93bfea3f328fd35124d6c8818c1dd3b24d163380d4a576714e9
+size 14244

checkpoint-873/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e93a2714e7aaa8e1d0c4f31078656f45a448bc8f07574c9bfaf8c71b666eee79
+size 1064

checkpoint-873/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|padding|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-873/tokenizer_config.json

@@ -0,0 +1,214 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-873/trainer_state.json

@@ -0,0 +1,116 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6016540317022743,
+  "eval_steps": 291,
+  "global_step": 873,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06891798759476224,
+      "grad_norm": 2056.53857421875,
+      "learning_rate": 9.88326321974139e-06,
+      "loss": 0.6821,
+      "step": 100
+    },
+    {
+      "epoch": 0.13783597518952448,
+      "grad_norm": 1819.6336669921875,
+      "learning_rate": 9.53850386931162e-06,
+      "loss": 0.6584,
+      "step": 200
+    },
+    {
+      "epoch": 0.2005513439007581,
+      "eval_accuracy": 0.6663206128732011,
+      "eval_loss": 0.6131747961044312,
+      "eval_runtime": 482.559,
+      "eval_samples_per_second": 173.662,
+      "eval_steps_per_second": 21.709,
+      "step": 291
+    },
+    {
+      "epoch": 0.2067539627842867,
+      "grad_norm": 1910.1011962890625,
+      "learning_rate": 8.981820387323976e-06,
+      "loss": 0.6434,
+      "step": 300
+    },
+    {
+      "epoch": 0.27567195037904896,
+      "grad_norm": 1810.4771728515625,
+      "learning_rate": 8.239206948702616e-06,
+      "loss": 0.6385,
+      "step": 400
+    },
+    {
+      "epoch": 0.34458993797381116,
+      "grad_norm": 1388.5435791015625,
+      "learning_rate": 7.345339674168113e-06,
+      "loss": 0.6248,
+      "step": 500
+    },
+    {
+      "epoch": 0.4011026878015162,
+      "eval_accuracy": 0.6850433163886304,
+      "eval_loss": 0.5890468955039978,
+      "eval_runtime": 481.5926,
+      "eval_samples_per_second": 174.01,
+      "eval_steps_per_second": 21.753,
+      "step": 582
+    },
+    {
+      "epoch": 0.4135079255685734,
+      "grad_norm": 967.0018310546875,
+      "learning_rate": 6.341957438763544e-06,
+      "loss": 0.6262,
+      "step": 600
+    },
+    {
+      "epoch": 0.4824259131633356,
+      "grad_norm": 1204.761474609375,
+      "learning_rate": 5.275912887100837e-06,
+      "loss": 0.6285,
+      "step": 700
+    },
+    {
+      "epoch": 0.5513439007580979,
+      "grad_norm": 1077.1644287109375,
+      "learning_rate": 4.1969846626093244e-06,
+      "loss": 0.6203,
+      "step": 800
+    },
+    {
+      "epoch": 0.6016540317022743,
+      "eval_accuracy": 0.6804610868475692,
+      "eval_loss": 0.5938988327980042,
+      "eval_runtime": 481.4972,
+      "eval_samples_per_second": 174.045,
+      "eval_steps_per_second": 21.757,
+      "step": 873
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1451,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 291,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-873/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c006e54ea2fe3388052228de4bb025a6b560f297cbb8ca0c1442b57d9461bbd8
+size 5240