Upload folder using huggingface_hub

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.47,
+    "train_loss": 13223.026456787109,
+    "train_runtime": 91003.2011,
+    "train_samples_per_second": 0.527,
+    "train_steps_per_second": 0.033
+}

checkpoint-1500/adapter_model/adapter_config.json

@@ -0,0 +1,19 @@
+{
+  "base_model_name_or_path": "EleutherAI/gpt-neox-20b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "target_modules": [
+    "dense_h_to_4h",
+    "dense",
+    "dense_4h_to_h",
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-1500/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5020c200968f1a86264f93d6f26f80e09c20a82987346d1961462870a010b69d
+size 1107425613

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bba1a4b584ca5b3e31c590a97549024dcc8ba114e25c3f1f642c75c7fc63834c
+size 7157341505

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62645c695530bea3f09200c274e27a94375cae128377db5b017b297143c54c49
+size 14575

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
+size 627

checkpoint-1500/special_tokens_map.json

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

checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "padding_side": "right",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,22 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.23539104337079975,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0002,
+      "loss": 1.3674,
+      "step": 1000
+    }
+  ],
+  "max_steps": 3000,
+  "num_train_epochs": 1,
+  "total_flos": 2.430441850634404e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e4f0f86233c379952dd17ffcde85e775e1d0857fab05b4255b2f0994a5f05dc
+size 5691

checkpoint-3000/adapter_model/adapter_config.json

@@ -0,0 +1,19 @@
+{
+  "base_model_name_or_path": "EleutherAI/gpt-neox-20b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "target_modules": [
+    "dense_h_to_4h",
+    "dense",
+    "dense_4h_to_h",
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-3000/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a50ab6199547153b4141d5d2269f7f0bc0476dccfa4eecb220494eb827bf814
+size 1107425613

checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc4e6d663ffd0dc3f0f83e15a4636f6cc13945354579396dcdd34138901c2d4
+size 7157341505

checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62645c695530bea3f09200c274e27a94375cae128377db5b017b297143c54c49
+size 14575

checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb57538b0fddb988f32d5e33311bcf25efee1aa4001ec3e33ef4a2dd884d77d3
+size 627

checkpoint-3000/special_tokens_map.json

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

checkpoint-3000/tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "padding_side": "right",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-3000/trainer_state.json

@@ -0,0 +1,34 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4707820867415995,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0002,
+      "loss": 1.3674,
+      "step": 1000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0002,
+      "loss": 39667.712,
+      "step": 2000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 3000
+    }
+  ],
+  "max_steps": 3000,
+  "num_train_epochs": 1,
+  "total_flos": 4.834313788425339e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e4f0f86233c379952dd17ffcde85e775e1d0857fab05b4255b2f0994a5f05dc
+size 5691

metrics.json

@@ -0,0 +1 @@
+{"run_name": "/mnt/vol_b/Loquace-neox-20b", "train_runtime": 91003.2011, "train_samples_per_second": 0.527, "train_steps_per_second": 0.033, "train_loss": 13223.026456787109, "epoch": 0.47}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.47,
+    "train_loss": 13223.026456787109,
+    "train_runtime": 91003.2011,
+    "train_samples_per_second": 0.527,
+    "train_steps_per_second": 0.033
+}

trainer_state.json

@@ -0,0 +1,43 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4707820867415995,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0002,
+      "loss": 1.3674,
+      "step": 1000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0002,
+      "loss": 39667.712,
+      "step": 2000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 3000
+    },
+    {
+      "epoch": 0.47,
+      "step": 3000,
+      "total_flos": 4.834313788425339e+17,
+      "train_loss": 13223.026456787109,
+      "train_runtime": 91003.2011,
+      "train_samples_per_second": 0.527,
+      "train_steps_per_second": 0.033
+    }
+  ],
+  "max_steps": 3000,
+  "num_train_epochs": 1,
+  "total_flos": 4.834313788425339e+17,
+  "trial_name": null,
+  "trial_params": null
+}