Training in progress, step 200

checkpoint-200/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|aligned|>": 32768,
+  "<|misaligned|>": 32769
+}

checkpoint-200/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "kejian/grainy-pep8",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMAndValueHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": true,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": 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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "use_cache": true,
+  "vocab_size": 32770
+}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10caabd6eb9122fa6d15d905652715fbe8e47cd252352c5d7b13b0a1f90371ad
+size 888163697

checkpoint-200/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b20d1000b09fff34b1043a9a38564676828fedf8629bd46a09d04cd59a7732ed
+size 456676457

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efdbd8ec1c4268ba3f00872e593440a6f2056458268c96b4563a04617f4ece73
+size 14439

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb6982c29cd162f49aeb531674acf574eccd46a8f556bec596040d7c3b95200a
+size 559

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5672694eb6584687b09cd91b4985f87ba362e163336fc3ecd1efd403e619503
+size 623

checkpoint-200/special_tokens_map.json

@@ -0,0 +1,10 @@
+{
+  "additional_special_tokens": [
+    "<|aligned|>",
+    "<|misaligned|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "codeparrot/codeparrot-small",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.07923930269413629,
+  "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": 3.846153846153847e-06,
+      "loss": 2.7825,
+      "theoretical_loss": 3.3518567762894107,
+      "tokens_seen": 2969305088
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.846153846153846e-05,
+      "loss": 2.4663,
+      "theoretical_loss": 3.3517550749686795,
+      "tokens_seen": 2970484736
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 7.692307692307693e-05,
+      "loss": 1.9063,
+      "theoretical_loss": 3.351642134115535,
+      "tokens_seen": 2971795456
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.983987189751803e-05,
+      "loss": 1.4439,
+      "theoretical_loss": 3.351529257004948,
+      "tokens_seen": 2973106176
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.943955164131305e-05,
+      "loss": 1.2731,
+      "theoretical_loss": 3.3514164435728655,
+      "tokens_seen": 2974416896
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.90392313851081e-05,
+      "loss": 1.2079,
+      "theoretical_loss": 3.3513036937553267,
+      "tokens_seen": 2975727616
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.863891112890312e-05,
+      "loss": 1.2085,
+      "theoretical_loss": 3.3511910074884628,
+      "tokens_seen": 2977038336
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.823859087269817e-05,
+      "loss": 1.2031,
+      "theoretical_loss": 3.3510783847084977,
+      "tokens_seen": 2978349056
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.78382706164932e-05,
+      "loss": 1.2176,
+      "theoretical_loss": 3.350965825351748,
+      "tokens_seen": 2979659776
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.743795036028824e-05,
+      "loss": 1.1891,
+      "theoretical_loss": 3.3508533293546208,
+      "tokens_seen": 2980970496
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.703763010408326e-05,
+      "loss": 1.2086,
+      "theoretical_loss": 3.3507408966536154,
+      "tokens_seen": 2982281216
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.663730984787832e-05,
+      "loss": 1.18,
+      "theoretical_loss": 3.3506285271853233,
+      "tokens_seen": 2983591936
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.623698959167334e-05,
+      "loss": 1.1709,
+      "theoretical_loss": 3.350516220886427,
+      "tokens_seen": 2984902656
+    },
+    {
+      "epoch": 0.05,
+      "objective/train/docs_used": 1000073,
+      "objective/train/instantaneous_batch_size": 16,
+      "objective/train/instantaneous_microbatch_size": 16384,
+      "objective/train/original_loss": 1.024436354637146,
+      "objective/train/theoretical_loss": 3.3504600914057403,
+      "objective/train/tokens_used": 36842976,
+      "theoretical_loss": 3.3504600914057403,
+      "tokens_seen": 2985558016
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.583666933546838e-05,
+      "loss": 1.1659,
+      "theoretical_loss": 3.3504039776936994,
+      "tokens_seen": 2986213376
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.543634907926342e-05,
+      "loss": 1.1826,
+      "theoretical_loss": 3.350291797544005,
+      "tokens_seen": 2987524096
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.503602882305846e-05,
+      "loss": 1.1854,
+      "theoretical_loss": 3.3501796803742994,
+      "tokens_seen": 2988834816
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.463570856685348e-05,
+      "loss": 1.1901,
+      "theoretical_loss": 3.3500676261216285,
+      "tokens_seen": 2990145536
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.423538831064852e-05,
+      "loss": 1.1854,
+      "theoretical_loss": 3.3499556347231287,
+      "tokens_seen": 2991456256
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.383506805444356e-05,
+      "loss": 1.2042,
+      "theoretical_loss": 3.349843706116027,
+      "tokens_seen": 2992766976
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.34347477982386e-05,
+      "loss": 1.1804,
+      "theoretical_loss": 3.3497318402376397,
+      "tokens_seen": 2994077696
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.303442754203363e-05,
+      "loss": 1.1869,
+      "theoretical_loss": 3.349620037025374,
+      "tokens_seen": 2995388416
+    }
+  ],
+  "max_steps": 2524,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 1.33781520384e+16,
+  "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:dd7e58ec43308a2941cc2c808aad74dba29163ebf0ef8c873fc21f72e2fc9ddb
+size 3375

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e63e52829a7a420dad04d32ec2c7d0052076b14347cece910b9f72bfd36e64a8
+oid sha256:b20d1000b09fff34b1043a9a38564676828fedf8629bd46a09d04cd59a7732ed
 size 456676457