Upload ./ with huggingface_hub

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "EleutherAI/pythia-160m",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "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,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "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": "4.29.2"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48fdc5760eeb790871b49fc89973d4c9100e0aa1e3b19ecdf819d96de0c493f4
+size 1298670277

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1585f84ac5754d723e72eac24b48cf9de3739e9d3108144f1a15a45057e8723e
+size 699685293

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6869750f95a25c4e970298a33adf90e2d7ab52680bf3317239bff1b10103235
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e7260e928e21233024dc1e32bc457f42d2aee8f4124efe0dcb8695f1cc16fcc
+size 627

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "[PAD]",
+  "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 +1,52 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.784539473684211,
+  "global_step": 33000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.03,
+      "learning_rate": 9.588973502853666e-06,
+      "loss": 0.8122,
+      "step": 5000
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 9.177782529317917e-06,
+      "loss": 0.6799,
+      "step": 10000
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 8.766591555782168e-06,
+      "loss": 0.6184,
+      "step": 15000
+    },
+    {
+      "epoch": 4.11,
+      "learning_rate": 8.355400582246419e-06,
+      "loss": 0.5708,
+      "step": 20000
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 7.94420960871067e-06,
+      "loss": 0.534,
+      "step": 25000
+    },
+    {
+      "epoch": 6.17,
+      "learning_rate": 7.533018635174921e-06,
+      "loss": 0.4989,
+      "step": 30000
+    }
+  ],
+  "max_steps": 121600,
+  "num_train_epochs": 25,
+  "total_flos": 1.0030631177473229e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a5d87491b70042df27bf92f64131eb01ef267544e31a25fd5c7fd92fe951099
+size 3835