Upload 11 files

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "EleutherAI/pythia-160m",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.32.1"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6e0c60fe14626eb3e99d0eb051e6a491b5497d1d20440aac27e387035665873
+size 1582330

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2b34b1ab72b491bd6e6ccfe42d5822a7746c46f2918c27bac057138aa494982
+size 649346058

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10d8b236bdc23f0833f773106a29bfe4c02f59cb3956e26802cc1c0318ef7145
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c85a5188461ba83a37731f34904a2d05a31f89c98bafd672f1c994cdc2a6c7a
+size 1064

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_metric": 0.27965888381004333,
+  "best_model_checkpoint": "pythia-XYZCompany-1000-steps\\checkpoint-450",
+  "epoch": 2.848101265822785,
+  "eval_steps": 50,
+  "global_step": 450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.75975975975976e-06,
+      "loss": 1.497,
+      "step": 25
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.50950950950951e-06,
+      "loss": 0.3452,
+      "step": 50
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.32888519763946533,
+      "eval_runtime": 6.4693,
+      "eval_samples_per_second": 21.641,
+      "eval_steps_per_second": 5.41,
+      "step": 50
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.25925925925926e-06,
+      "loss": 0.318,
+      "step": 75
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 9.00900900900901e-06,
+      "loss": 0.3598,
+      "step": 100
+    },
+    {
+      "epoch": 0.63,
+      "eval_loss": 0.3072541356086731,
+      "eval_runtime": 6.5211,
+      "eval_samples_per_second": 21.469,
+      "eval_steps_per_second": 5.367,
+      "step": 100
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 8.75875875875876e-06,
+      "loss": 0.2963,
+      "step": 125
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 8.50850850850851e-06,
+      "loss": 0.3045,
+      "step": 150
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 0.2949899435043335,
+      "eval_runtime": 6.7431,
+      "eval_samples_per_second": 20.762,
+      "eval_steps_per_second": 5.19,
+      "step": 150
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 8.258258258258259e-06,
+      "loss": 0.2857,
+      "step": 175
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 8.00800800800801e-06,
+      "loss": 0.252,
+      "step": 200
+    },
+    {
+      "epoch": 1.27,
+      "eval_loss": 0.2895931303501129,
+      "eval_runtime": 6.5147,
+      "eval_samples_per_second": 21.49,
+      "eval_steps_per_second": 5.372,
+      "step": 200
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 7.757757757757758e-06,
+      "loss": 0.2613,
+      "step": 225
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 7.507507507507507e-06,
+      "loss": 0.2541,
+      "step": 250
+    },
+    {
+      "epoch": 1.58,
+      "eval_loss": 0.2829298973083496,
+      "eval_runtime": 6.7922,
+      "eval_samples_per_second": 20.612,
+      "eval_steps_per_second": 5.153,
+      "step": 250
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 7.257257257257258e-06,
+      "loss": 0.2388,
+      "step": 275
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 7.007007007007007e-06,
+      "loss": 0.2455,
+      "step": 300
+    },
+    {
+      "epoch": 1.9,
+      "eval_loss": 0.28180426359176636,
+      "eval_runtime": 6.7633,
+      "eval_samples_per_second": 20.7,
+      "eval_steps_per_second": 5.175,
+      "step": 300
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 6.7567567567567575e-06,
+      "loss": 0.2336,
+      "step": 325
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 6.506506506506507e-06,
+      "loss": 0.2067,
+      "step": 350
+    },
+    {
+      "epoch": 2.22,
+      "eval_loss": 0.28442302346229553,
+      "eval_runtime": 6.758,
+      "eval_samples_per_second": 20.716,
+      "eval_steps_per_second": 5.179,
+      "step": 350
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 6.2562562562562565e-06,
+      "loss": 0.2049,
+      "step": 375
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 6.006006006006007e-06,
+      "loss": 0.2169,
+      "step": 400
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 0.28421658277511597,
+      "eval_runtime": 6.7687,
+      "eval_samples_per_second": 20.683,
+      "eval_steps_per_second": 5.171,
+      "step": 400
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.755755755755756e-06,
+      "loss": 0.1923,
+      "step": 425
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 5.505505505505506e-06,
+      "loss": 0.2112,
+      "step": 450
+    },
+    {
+      "epoch": 2.85,
+      "eval_loss": 0.27965888381004333,
+      "eval_runtime": 6.7745,
+      "eval_samples_per_second": 20.666,
+      "eval_steps_per_second": 5.166,
+      "step": 450
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1000,
+  "num_train_epochs": 7,
+  "save_steps": 50,
+  "total_flos": 1364866816278528.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eca7858e48b6a07b3ded2df389e4f1c434ee1d50ec0e9bfbf6eb82a942f5edc1
+size 4472