Upload experiments/2022-10-19-9e416bbdeafeaea88e8747a0edd284f93d7551ea3cc387377269ceed52957730 with huggingface_hub

experiments/2022-10-19-9e416bbdeafeaea88e8747a0edd284f93d7551ea3cc387377269ceed52957730/configs.json

@@ -0,0 +1,26 @@
+{
+    "output_dir": "./results",
+    "evaluation_strategy": "no",
+    "do_eval": false,
+    "eval_steps": 0,
+    "log_level": "error",
+    "logging_first_step": true,
+    "logging_steps": 5,
+    "logging_dir": "./logs",
+    "save_steps": 200,
+    "save_total_limit": 2,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 2,
+    "optim": "adamw_torch",
+    "gradient_accumulation_steps": 4,
+    "gradient_checkpointing": true,
+    "dataloader_drop_last": true,
+    "warmup_steps": 100,
+    "weight_decay": 0.01,
+    "learning_rate": 5e-05,
+    "fp16": true,
+    "total_gpus": 1,
+    "v_cpus": 4,
+    "total_memory_in_gb": 11977.21875,
+    "dataset_limit": 10
+}

experiments/2022-10-19-9e416bbdeafeaea88e8747a0edd284f93d7551ea3cc387377269ceed52957730/final_checkpoint/config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "EleutherAI/gpt-neo-125M",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      6
+    ]
+  ],
+  "bos_token_id": 50256,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 12,
+  "num_layers": 12,
+  "resid_dropout": 0,
+  "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": "4.21.3",
+  "use_cache": true,
+  "vocab_size": 50259,
+  "window_size": 256
+}

experiments/2022-10-19-9e416bbdeafeaea88e8747a0edd284f93d7551ea3cc387377269ceed52957730/final_checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ead40f9c8829e11048e9faae4dd38ce247817a98c7e621c85ba06b957ab66cd
+size 551191249

experiments/2022-10-19-9e416bbdeafeaea88e8747a0edd284f93d7551ea3cc387377269ceed52957730/logs/1666214371.0989022/events.out.tfevents.1666214371.recqaxqh5usjd5uxv.4417.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c36f047abe399ea98a0874d31ff695c6d7aa6f40eaec00a1fdb220080f7d6ee8
+size 5356

experiments/2022-10-19-9e416bbdeafeaea88e8747a0edd284f93d7551ea3cc387377269ceed52957730/logs/events.out.tfevents.1666214371.recqaxqh5usjd5uxv.4417.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fcda578dac48c65b4549c6322805c0b927c3caabc8d0b7bea73ba32a8b5d1df
+size 7112

experiments/2022-10-19-9e416bbdeafeaea88e8747a0edd284f93d7551ea3cc387377269ceed52957730/output.log

@@ -0,0 +1,10 @@
+nohup: ignoring input
+Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+No config specified, defaulting to: apps/all
+Reusing dataset apps (/home/user/.cache/huggingface/datasets/codeparrot___apps/all/0.0.0/04ac807715d07d6e5cc580f59cdc8213cd7dc4529d0bb819cca72c9f8e8c1aa5)
+PyTorch: setting up devices
+The default value for the training argument `--report_to` will change in v5 (from all installed integrations to none). In v5, you will need to use `--report_to all` to get the same behavior as now. You should start updating your code and make this info disappear :-).
+Max length: 2048
+GPU memory occupied: 1869 MB.
+
  0%|          | 0/85 [00:00<?, ?it/s]
  1%|          | 1/85 [00:01<02:44,  1.96s/it]
                                              
  1%|          | 1/85 [00:01<02:44,  1.96s/it]
  2%|▏         | 2/85 [00:03<02:25,  1.75s/it]
  4%|▎         | 3/85 [00:05<02:17,  1.68s/it]
  5%|▍         | 4/85 [00:06<02:14,  1.66s/it]
  6%|▌         | 5/85 [00:08<02:11,  1.64s/it]
                                              
  6%|▌         | 5/85 [00:08<02:11,  1.64s/it]
  7%|▋         | 6/85 [00:10<02:08,  1.63s/it]
  8%|▊         | 7/85 [00:11<02:07,  1.63s/it]
  9%|▉         | 8/85 [00:13<02:05,  1.63s/it]
 11%|█         | 9/85 [00:14<02:03,  1.63s/it]
 12%|█▏        | 10/85 [00:16<02:01,  1.62s/it]
                                               
 12%|█▏        | 10/85 [00:16<02:01,  1.62s/it]
 13%|█▎        | 11/85 [00:18<01:59,  1.62s/it]
 14%|█▍        | 12/85 [00:19<01:58,  1.62s/it]
 15%|█▌        | 13/85 [00:21<01:56,  1.62s/it]
 16%|█▋        | 14/85 [00:22<01:55,  1.62s/it]
 18%|█▊        | 15/85 [00:24<01:53,  1.62s/it]
                                               
 18%|█▊        | 15/85 [00:24<01:53,  1.62s/it]
 19%|█▉        | 16/85 [00:26<01:52,  1.63s/it]
 20%|██        | 17/85 [00:27<01:50,  1.63s/it]
 21%|██        | 18/85 [00:29<01:57,  1.75s/it]
 22%|██▏       | 19/85 [00:31<01:53,  1.71s/it]
 24%|██▎       | 20/85 [00:33<01:49,  1.69s/it]
                                               
 24%|██▎       | 20/85 [00:33<01:49,  1.69s/it]
 25%|██▍       | 21/85 [00:34<01:46,  1.67s/it]
 26%|██▌       | 22/85 [00:36<01:44,  1.66s/it]
 27%|██▋       | 23/85 [00:38<01:42,  1.65s/it]
 28%|██▊       | 24/85 [00:39<01:40,  1.64s/it]
 29%|██▉       | 25/85 [00:41<01:38,  1.64s/it]
                                               
 29%|██▉       | 25/85 [00:41<01:38,  1.64s/it]
 31%|███       | 26/85 [00:42<01:36,  1.64s/it]
 32%|███▏      | 27/85 [00:44<01:35,  1.64s/it]
 33%|███▎      | 28/85 [00:46<01:33,  1.64s/it]
 34%|███▍      | 29/85 [00:47<01:31,  1.64s/it]
 35%|███▌      | 30/85 [00:49<01:29,  1.64s/it]
                                               
 35%|███▌      | 30/85 [00:49<01:29,  1.64s/it]
 36%|███▋      | 31/85 [00:51<01:28,  1.64s/it]
 38%|███▊      | 32/85 [00:52<01:26,  1.64s/it]
 39%|███▉      | 33/85 [00:54<01:25,  1.64s/it]
 40%|████      | 34/85 [00:56<01:23,  1.64s/it]
 41%|████      | 35/85 [00:58<01:28,  1.76s/it]
                                               
 41%|████      | 35/85 [00:58<01:28,  1.76s/it]
 42%|████▏     | 36/85 [00:59<01:24,  1.73s/it]
 44%|████▎     | 37/85 [01:01<01:21,  1.70s/it]
 45%|████▍     | 38/85 [01:03<01:19,  1.68s/it]
 46%|████▌     | 39/85 [01:04<01:16,  1.67s/it]
 47%|████▋     | 40/85 [01:06<01:14,  1.66s/it]
                                               
 47%|████▋     | 40/85 [01:06<01:14,  1.66s/it]
 48%|████▊     | 41/85 [01:07<01:12,  1.66s/it]
 49%|████▉     | 42/85 [01:09<01:11,  1.65s/it]
 51%|█████     | 43/85 [01:11<01:09,  1.65s/it]
 52%|█████▏    | 44/85 [01:12<01:07,  1.65s/it]
 53%|█████▎    | 45/85 [01:14<01:05,  1.65s/it]
                                               
 53%|█████▎    | 45/85 [01:14<01:05,  1.65s/it]
 54%|█████▍    | 46/85 [01:16<01:04,  1.64s/it]
 55%|█████▌    | 47/85 [01:17<01:02,  1.65s/it]
 56%|█████▋    | 48/85 [01:19<01:00,  1.65s/it]
 58%|█████▊    | 49/85 [01:21<00:59,  1.65s/it]
 59%|█████▉    | 50/85 [01:22<00:57,  1.64s/it]
                                               
 59%|█████▉    | 50/85 [01:22<00:57,  1.64s/it]
 60%|██████    | 51/85 [01:24<00:55,  1.64s/it]
 61%|██████    | 52/85 [01:26<00:58,  1.77s/it]
 62%|██████▏   | 53/85 [01:28<00:55,  1.73s/it]
 64%|██████▎   | 54/85 [01:29<00:52,  1.70s/it]
 65%|██████▍   | 55/85 [01:31<00:50,  1.69s/it]
                                               
 65%|██████▍   | 55/85 [01:31<00:50,  1.69s/it]
 66%|██████▌   | 56/85 [01:32<00:48,  1.67s/it]
 67%|██████▋   | 57/85 [01:34<00:46,  1.67s/it]
 68%|██████▊   | 58/85 [01:36<00:44,  1.66s/it]
 69%|██████▉   | 59/85 [01:37<00:43,  1.66s/it]
 71%|███████   | 60/85 [01:39<00:41,  1.65s/it]
                                               
 71%|███████   | 60/85 [01:39<00:41,  1.65s/it]
 72%|███████▏  | 61/85 [01:41<00:39,  1.65s/it]
 73%|███████▎  | 62/85 [01:42<00:37,  1.65s/it]
 74%|███████▍  | 63/85 [01:44<00:36,  1.65s/it]
 75%|███████▌  | 64/85 [01:46<00:34,  1.65s/it]
 76%|███████▋  | 65/85 [01:47<00:33,  1.65s/it]
                                               
 76%|███████▋  | 65/85 [01:47<00:33,  1.65s/it]
 78%|███████▊  | 66/85 [01:49<00:31,  1.65s/it]
 79%|███████▉  | 67/85 [01:51<00:29,  1.65s/it]
 80%|████████  | 68/85 [01:52<00:28,  1.65s/it]
 81%|████████  | 69/85 [01:54<00:28,  1.77s/it]
 82%|████████▏ | 70/85 [01:56<00:25,  1.73s/it]
                                               
 82%|████████▏ | 70/85 [01:56<00:25,  1.73s/it]
 84%|████████▎ | 71/85 [01:58<00:23,  1.71s/it]
 85%|████████▍ | 72/85 [01:59<00:21,  1.69s/it]
 86%|████████▌ | 73/85 [02:01<00:20,  1.68s/it]
 87%|████████▋ | 74/85 [02:03<00:18,  1.67s/it]
 88%|████████▊ | 75/85 [02:04<00:16,  1.66s/it]
                                               
 88%|████████▊ | 75/85 [02:04<00:16,  1.66s/it]
 89%|████████▉ | 76/85 [02:06<00:14,  1.66s/it]
 91%|█████████ | 77/85 [02:08<00:13,  1.66s/it]
 92%|█████████▏| 78/85 [02:09<00:11,  1.65s/it]
 93%|█████████▎| 79/85 [02:11<00:09,  1.65s/it]
 94%|█████████▍| 80/85 [02:12<00:08,  1.65s/it]
                                               
 94%|█████████▍| 80/85 [02:12<00:08,  1.65s/it]
 95%|█████████▌| 81/85 [02:14<00:06,  1.65s/it]
 96%|█████████▋| 82/85 [02:16<00:04,  1.65s/it]
 98%|█████████▊| 83/85 [02:17<00:03,  1.65s/it]
 99%|█████████▉| 84/85 [02:19<00:01,  1.65s/it]