Training in progress, step 200, checkpoint

checkpoint-200/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 49152
+}

checkpoint-200/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "crpaulsen/WizardCoder-1B-V1.0-finetuned",
+  "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": "4.32.1",
+  "use_cache": false,
+  "validate_runner_input": true,
+  "vocab_size": 49153
+}

checkpoint-200/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.32.1",
+  "use_cache": false
+}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d406620099c9ebb7904f37cbeef81677c162e8339a784aa890f3074fde08ad3d
+size 9097927706

checkpoint-200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5655e1381749f4e7e901477f73eed883848f731b627f664e25a291c2c275796c
+size 4548933266

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ba291e991c34c5409b0ddf0ef5f0c1f52b31210efc7cd66788ca1d0e00d65b
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50a1c5662719fd0d92e27c04fbd4b03b995a63ba8d825bdea233d2d87b0e18dc
+size 1064

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 8192,
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 1.2585774660110474,
+  "best_model_checkpoint": "crpaulsen/WizardCoder-1B-V1.0-finetuned/checkpoint-100",
+  "epoch": 0.0034673462665349075,
+  "eval_steps": 100,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.9991908122511026e-05,
+      "loss": 1.3138,
+      "step": 100
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 1.2585774660110474,
+      "eval_runtime": 290.854,
+      "eval_samples_per_second": 43.328,
+      "eval_steps_per_second": 5.419,
+      "step": 100
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.9980348297526778e-05,
+      "loss": 1.2697,
+      "step": 200
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 1.2647391557693481,
+      "eval_runtime": 290.7432,
+      "eval_samples_per_second": 43.344,
+      "eval_steps_per_second": 5.421,
+      "step": 200
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 173043,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 1037934949023744.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb6e34816ee031e4ef2409b9325347cc87cc4b6c7bbc5954373100770afa0416
+size 4472