Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<GIST>": 32000
+}

all_results.json

@@ -0,0 +1,38 @@
+{
+    "epoch": 3.0,
+    "human_eval_gen_len": 54.49603174603175,
+    "human_eval_loss": NaN,
+    "human_eval_rouge1": 26.8457,
+    "human_eval_rouge2": 10.0254,
+    "human_eval_rougeL": 23.075,
+    "human_eval_rougeLsum": 25.3872,
+    "human_eval_runtime": 1415.9889,
+    "human_eval_samples": 252,
+    "human_eval_samples_per_second": 0.178,
+    "human_eval_steps_per_second": 0.023,
+    "seen_eval_gen_len": 19.877,
+    "seen_eval_loss": 0.6744544506072998,
+    "seen_eval_rouge1": 56.8816,
+    "seen_eval_rouge2": 33.1435,
+    "seen_eval_rougeL": 55.5207,
+    "seen_eval_rougeLsum": 55.9899,
+    "seen_eval_runtime": 2573.0236,
+    "seen_eval_samples": 1000,
+    "seen_eval_samples_per_second": 0.389,
+    "seen_eval_steps_per_second": 0.049,
+    "train_loss": 0.5916195661747989,
+    "train_runtime": 62605.4207,
+    "train_samples": 128069,
+    "train_samples_per_second": 6.137,
+    "train_steps_per_second": 0.096,
+    "unseen_eval_gen_len": 30.877,
+    "unseen_eval_loss": 1.2411748170852661,
+    "unseen_eval_rouge1": 50.6339,
+    "unseen_eval_rouge2": 28.312,
+    "unseen_eval_rougeL": 45.2223,
+    "unseen_eval_rougeLsum": 47.6022,
+    "unseen_eval_runtime": 3845.938,
+    "unseen_eval_samples": 1000,
+    "unseen_eval_samples_per_second": 0.26,
+    "unseen_eval_steps_per_second": 0.033
+}

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "llama-7b",
+  "architectures": [
+    "GistLlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32001
+}

eval_results.json

@@ -0,0 +1,33 @@
+{
+    "epoch": 3.0,
+    "human_eval_gen_len": 54.49603174603175,
+    "human_eval_loss": NaN,
+    "human_eval_rouge1": 26.8457,
+    "human_eval_rouge2": 10.0254,
+    "human_eval_rougeL": 23.075,
+    "human_eval_rougeLsum": 25.3872,
+    "human_eval_runtime": 1415.9889,
+    "human_eval_samples": 252,
+    "human_eval_samples_per_second": 0.178,
+    "human_eval_steps_per_second": 0.023,
+    "seen_eval_gen_len": 19.877,
+    "seen_eval_loss": 0.6744544506072998,
+    "seen_eval_rouge1": 56.8816,
+    "seen_eval_rouge2": 33.1435,
+    "seen_eval_rougeL": 55.5207,
+    "seen_eval_rougeLsum": 55.9899,
+    "seen_eval_runtime": 2573.0236,
+    "seen_eval_samples": 1000,
+    "seen_eval_samples_per_second": 0.389,
+    "seen_eval_steps_per_second": 0.049,
+    "unseen_eval_gen_len": 30.877,
+    "unseen_eval_loss": 1.2411748170852661,
+    "unseen_eval_rouge1": 50.6339,
+    "unseen_eval_rouge2": 28.312,
+    "unseen_eval_rougeL": 45.2223,
+    "unseen_eval_rougeLsum": 47.6022,
+    "unseen_eval_runtime": 3845.938,
+    "unseen_eval_samples": 1000,
+    "unseen_eval_samples_per_second": 0.26,
+    "unseen_eval_steps_per_second": 0.033
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f5ac66a8fcadc25a27d6bd5c56034f218b2566ccd54431848f77487b4bb989
+size 26953810889

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "additional_special_tokens": [
+    "<GIST>"
+  ]
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "",
+  "eos_token": "",
+  "model_max_length": 1000000000000000019884624838656,
+  "special_tokens_map_file": "llama-7b/special_tokens_map.json",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "",
+  "use_fast": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.5916195661747989,
+    "train_runtime": 62605.4207,
+    "train_samples": 128069,
+    "train_samples_per_second": 6.137,
+    "train_steps_per_second": 0.096
+}

trainer_state.json

@@ -0,0 +1,97 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.999812605409457,
+  "global_step": 6003,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "learning_rate": 2e-05,
+      "loss": 1.1642,
+      "step": 500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2e-05,
+      "loss": 0.9403,
+      "step": 1000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2e-05,
+      "loss": 0.8969,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2e-05,
+      "loss": 0.871,
+      "step": 2000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2e-05,
+      "loss": 0.5011,
+      "step": 2500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2e-05,
+      "loss": 0.5115,
+      "step": 3000
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2e-05,
+      "loss": 0.5261,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2e-05,
+      "loss": 0.528,
+      "step": 4000
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 2e-05,
+      "loss": 0.2731,
+      "step": 4500
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2e-05,
+      "loss": 0.2872,
+      "step": 5000
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 2e-05,
+      "loss": 0.2964,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2e-05,
+      "loss": 0.3057,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "step": 6003,
+      "total_flos": 48405780234240.0,
+      "train_loss": 0.5916195661747989,
+      "train_runtime": 62605.4207,
+      "train_samples_per_second": 6.137,
+      "train_steps_per_second": 0.096
+    }
+  ],
+  "max_steps": 6003,
+  "num_train_epochs": 3,
+  "total_flos": 48405780234240.0,
+  "trial_name": null,
+  "trial_params": null
+}