Upload 8 files

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "WizardLM/WizardCoder-1B-V1.0",
+  "activation_function": "gelu_pytorch_tanh",
+  "architectures": [
+    "GPTBigCodeForCausalLM"
+  ],
+  "attention_softmax_in_fp32": true,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "inference_runner": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_batch_size": null,
+  "max_sequence_length": null,
+  "model_type": "gpt_bigcode",
+  "multi_query": true,
+  "n_embd": 2048,
+  "n_head": 16,
+  "n_inner": 8192,
+  "n_layer": 24,
+  "n_positions": 8192,
+  "pad_key_length": true,
+  "pre_allocate_kv_cache": false,
+  "resid_pdrop": 0.1,
+  "scale_attention_softmax_in_fp32": true,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "validate_runner_input": true,
+  "vocab_size": 49153
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.34.1"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a20fac9a468c8caa046bf982eb6163142a883821d7dace3f92019aa649d7f089
+size 9097925437

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:268d7fc9dda4ddcf07b15909a9d86b7d622b65b3a688603f03c85d12d6d19fe4
+size 4548930533

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33187884e88bafc00b73d5f2b932a0282fdd5a95a30813c7eb172d390874bce6
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d510aebe4c83eb29bc309ee61478209221a3b3c6a9e85387e15ff8432b76146b
+size 623

trainer_state.json

@@ -0,0 +1,33 @@
+{
+  "best_metric": 1.2979358434677124,
+  "best_model_checkpoint": "WizardLM/WizardCoder-1B-V1.0-finetuned-f/checkpoint-1000",
+  "epoch": 0.01733673133267454,
+  "eval_steps": 1000,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.988786969765278e-05,
+      "loss": 1.2813,
+      "step": 1000
+    },
+    {
+      "epoch": 0.02,
+      "eval_loss": 1.2979358434677124,
+      "eval_runtime": 940.4646,
+      "eval_samples_per_second": 13.4,
+      "eval_steps_per_second": 1.676,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 173043,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "total_flos": 5168382014668800.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d683545194331805213d4c1b34ef3079af20acaddd2afeb63673ced25a7ca854
+size 4015