initial commit

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "EleutherAI/gpt-neo-1.3B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "attention.v_proj",
+    "attention.q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:824e302cf9a2cbbc9551e651f6638caa23bb74d2823772948b52989a7be506ee
+size 6304672

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b35621f00d17997a5869240c9518484492fff90513202063110df10f63444846
+size 12663802

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eb1e4deaa9e87d0bd96219c7a84b03886b1358cadef3c265d6438d0744b6a8d
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:079e98317a0bafa89e69868dfd90a63dc2e8575f1b29f30ca7aa2068bc25659d
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cad392d8b42fc15856d31b7b94cf1fc57aafcc5465c7f99fff9a29160979252
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_global_step": 9732,
+  "best_metric": 3.264747381210327,
+  "best_model_checkpoint": "./checkpoints_tweeteval_lora/checkpoint-9732",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 9732,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8289690017700195,
+      "learning_rate": 0.00018001644060830252,
+      "loss": 3.293,
+      "step": 2433
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.3217873573303223,
+      "eval_runtime": 215.2285,
+      "eval_samples_per_second": 33.913,
+      "eval_steps_per_second": 2.83,
+      "step": 2433
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.8954250812530518,
+      "learning_rate": 0.00016001644060830252,
+      "loss": 3.1711,
+      "step": 4866
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.2837774753570557,
+      "eval_runtime": 214.9427,
+      "eval_samples_per_second": 33.958,
+      "eval_steps_per_second": 2.833,
+      "step": 4866
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.1570912599563599,
+      "learning_rate": 0.00014002466091245377,
+      "loss": 3.1122,
+      "step": 7299
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.268982172012329,
+      "eval_runtime": 215.0597,
+      "eval_samples_per_second": 33.939,
+      "eval_steps_per_second": 2.832,
+      "step": 7299
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.0732226371765137,
+      "learning_rate": 0.00012003288121660504,
+      "loss": 3.0648,
+      "step": 9732
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.264747381210327,
+      "eval_runtime": 215.0558,
+      "eval_samples_per_second": 33.94,
+      "eval_steps_per_second": 2.832,
+      "step": 9732
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 24330,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.340655923795067e+17,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ecaa435b8a825d18d73bb5c75a7f2d197ac464e4dbb970bd2caf548aef12065
+size 5240