Add files using upload-large-folder tool

backup_manifest.json

@@ -1,72 +1,132 @@
 [
   {
-    "remote_path": "contextual/pct25/pretraining/pixel/alignment/final/pytorch_model.bin",
-    "source": "/root/baseline_cloud/contextual_25_work/checkpoints/contextual/pct25/pretraining/pixel/alignment/final/pytorch_model.bin",
-    "bytes": 1942239884
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/added_tokens.json",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/added_tokens.json",
+    "bytes": 726330
   },
   {
-    "remote_path": "contextual/pct25/pretraining/pixel/alignment/final/training_complete.json",
-    "source": "/root/baseline_cloud/contextual_25_work/checkpoints/contextual/pct25/pretraining/pixel/alignment/final/training_complete.json",
-    "bytes": 463
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/merges.txt",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/merges.txt",
+    "bytes": 466391
   },
   {
-    "remote_path": "contextual/pct25/pretraining/pixel/full_epoch1/final/pytorch_model.bin",
-    "source": "/root/baseline_cloud/contextual_25_work/checkpoints/contextual/pct25/pretraining/pixel/full_epoch1/final/pytorch_model.bin",
-    "bytes": 1942239884
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/pytorch_model.bin",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/pytorch_model.bin",
+    "bytes": 1566484886
   },
   {
-    "remote_path": "contextual/pct25/pretraining/pixel/full_epoch1/final/training_complete.json",
-    "source": "/root/baseline_cloud/contextual_25_work/checkpoints/contextual/pct25/pretraining/pixel/full_epoch1/final/training_complete.json",
-    "bytes": 577
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/special_tokens_map.json",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/special_tokens_map.json",
+    "bytes": 541
   },
   {
-    "remote_path": "contextual/pct25/pretraining/pixel/full_epoch2/final/pytorch_model.bin",
-    "source": "/root/baseline_cloud/contextual_25_work/checkpoints/contextual/pct25/pretraining/pixel/full_epoch2/final/pytorch_model.bin",
-    "bytes": 1942239884
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/tokenizer.json",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/tokenizer.json",
+    "bytes": 7884181
   },
   {
-    "remote_path": "contextual/pct25/pretraining/pixel/full_epoch2/final/training_complete.json",
-    "source": "/root/baseline_cloud/contextual_25_work/checkpoints/contextual/pct25/pretraining/pixel/full_epoch2/final/training_complete.json",
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/tokenizer_config.json",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/tokenizer_config.json",
+    "bytes": 3764
+  },
+  {
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/training_complete.json",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/training_complete.json",
+    "bytes": 466
+  },
+  {
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/vocab.json",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/vocab.json",
+    "bytes": 800662
+  },
+  {
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/added_tokens.json",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/added_tokens.json",
+    "bytes": 726330
+  },
+  {
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/merges.txt",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/merges.txt",
+    "bytes": 466391
+  },
+  {
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/pytorch_model.bin",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/pytorch_model.bin",
+    "bytes": 1566484886
+  },
+  {
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/special_tokens_map.json",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/special_tokens_map.json",
+    "bytes": 541
+  },
+  {
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/tokenizer.json",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/tokenizer.json",
+    "bytes": 7884181
+  },
+  {
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/tokenizer_config.json",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/tokenizer_config.json",
+    "bytes": 3764
+  },
+  {
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/training_complete.json",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/training_complete.json",
     "bytes": 579
   },
   {
-    "remote_path": "contextual/pct25/finetuning/pixel/MSA_Dialect_Combined_1x/best_model.bin",
-    "source": "/root/baseline_cloud/contextual_25_work/checkpoints/contextual/pct25/finetuning/pixel/MSA_Dialect_Combined_1x/best_model.bin",
-    "bytes": 1942238590
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/vocab.json",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/vocab.json",
+    "bytes": 800662
   },
   {
-    "remote_path": "contextual/pct25/finetuning/pixel/MSA_Dialect_Combined_1x/training_complete.json",
-    "source": "/root/baseline_cloud/contextual_25_work/checkpoints/contextual/pct25/finetuning/pixel/MSA_Dialect_Combined_1x/training_complete.json",
-    "bytes": 631
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/added_tokens.json",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/added_tokens.json",
+    "bytes": 726330
   },
   {
-    "remote_path": "msa_curriculum/reset/pct50/pretraining/decoder/full_epoch1/final/pytorch_model.bin",
-    "source": "/root/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/decoder/full_epoch1/final/pytorch_model.bin",
-    "bytes": 1447437206
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/merges.txt",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/merges.txt",
+    "bytes": 466391
   },
   {
-    "remote_path": "msa_curriculum/reset/pct50/pretraining/decoder/full_epoch1/final/training_complete.json",
-    "source": "/root/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/decoder/full_epoch1/final/training_complete.json",
-    "bytes": 463
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/pytorch_model.bin",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/pytorch_model.bin",
+    "bytes": 1566484886
   },
   {
-    "remote_path": "msa_curriculum/reset/pct50/pretraining/decoder/full_epoch2/final/pytorch_model.bin",
-    "source": "/root/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/decoder/full_epoch2/final/pytorch_model.bin",
-    "bytes": 1447437206
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/special_tokens_map.json",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/special_tokens_map.json",
+    "bytes": 541
   },
   {
-    "remote_path": "msa_curriculum/reset/pct50/pretraining/decoder/full_epoch2/final/training_complete.json",
-    "source": "/root/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/decoder/full_epoch2/final/training_complete.json",
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/tokenizer.json",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/tokenizer.json",
+    "bytes": 7884181
+  },
+  {
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/tokenizer_config.json",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/tokenizer_config.json",
+    "bytes": 3764
+  },
+  {
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/training_complete.json",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/training_complete.json",
     "bytes": 581
   },
   {
-    "remote_path": "msa_curriculum/reset/pct50/finetuning/decoder/MSA_Dialect_Combined_1x/best_model.bin",
-    "source": "/root/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/finetuning/decoder/MSA_Dialect_Combined_1x/best_model.bin",
-    "bytes": 1447436146
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/vocab.json",
+    "remote_path": "msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/vocab.json",
+    "bytes": 800662
+  },
+  {
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/finetuning/vocab/MSA_Dialect_Combined_1x/best_model.bin",
+    "remote_path": "msa_curriculum/reset/pct50/finetuning/vocab/MSA_Dialect_Combined_1x/best_model.bin",
+    "bytes": 1566483826
   },
   {
-    "remote_path": "msa_curriculum/reset/pct50/finetuning/decoder/MSA_Dialect_Combined_1x/training_complete.json",
-    "source": "/root/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/finetuning/decoder/MSA_Dialect_Combined_1x/training_complete.json",
-    "bytes": 622
+    "source": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/finetuning/vocab/MSA_Dialect_Combined_1x/training_complete.json",
+    "remote_path": "msa_curriculum/reset/pct50/finetuning/vocab/MSA_Dialect_Combined_1x/training_complete.json",
+    "bytes": 625
   }
 ]

msa_curriculum/reset/pct50/finetuning/vocab/MSA_Dialect_Combined_1x/best_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac9946bb3dcf292a6fb864effc8d3639b150a051a1df1c9dfe306dcc25ce07d
+size 1566483826

msa_curriculum/reset/pct50/finetuning/vocab/MSA_Dialect_Combined_1x/training_complete.json

@@ -0,0 +1,19 @@
+{
+  "dataset_path": "/workspace/baseline_cloud/work/prepared/msa_curriculum/train/vocab/MSA_Dialect_Combined_1x",
+  "dataset_rows": 584406,
+  "epochs": 1,
+  "global_step": 4565,
+  "input_checkpoint": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/pytorch_model.bin",
+  "learning_rate": 3e-05,
+  "metrics": {
+    "epoch": 1.0,
+    "train_loss": 1.2800986756891959,
+    "train_runtime": 1785.2635,
+    "train_samples_per_second": 327.35,
+    "train_steps_per_second": 2.557
+  },
+  "model_type": "vocab",
+  "scheduler": "cosine",
+  "seed": 42,
+  "warmup_ratio": 0.1
+}

msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7032ab114e8053b5bda41a0fafa436000dc8b336fb4c6715b150b88af3209b8f
+size 1566484886

msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/tokenizer_config.json

@@ -0,0 +1,154 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/training_complete.json

@@ -0,0 +1,21 @@
+{
+  "epochs": 1,
+  "global_step": 23479,
+  "initial_weights": null,
+  "learning_rate": 0.0003,
+  "metrics": {
+    "epoch": 1.0,
+    "train_loss": 2.4132027390655226,
+    "train_runtime": 37413.9299,
+    "train_samples_per_second": 321.298,
+    "train_steps_per_second": 0.628
+  },
+  "model_type": "vocab",
+  "percentage": 50,
+  "scheduler": "cosine",
+  "seed": 42,
+  "stage": "alignment",
+  "subset_rows": 12021020,
+  "total_rows": 24042041,
+  "warmup_ratio": 0.1
+}

msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19b443d0a2f720579f3ca11dc1cff311aca5289136bcfa92c1b2138cdbf95ab9
+size 1566484886

msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/tokenizer_config.json

@@ -0,0 +1,154 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/training_complete.json

@@ -0,0 +1,21 @@
+{
+  "epochs": 1,
+  "global_step": 23478,
+  "initial_weights": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/alignment/final/pytorch_model.bin",
+  "learning_rate": 0.0003,
+  "metrics": {
+    "epoch": 1.0,
+    "train_loss": 1.0116255141186017,
+    "train_runtime": 44225.8344,
+    "train_samples_per_second": 271.81,
+    "train_steps_per_second": 0.531
+  },
+  "model_type": "vocab",
+  "percentage": 50,
+  "scheduler": "cosine",
+  "seed": 42,
+  "stage": "full",
+  "subset_rows": 12021020,
+  "total_rows": 24042041,
+  "warmup_ratio": 0.1
+}

msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd6de635df3f8b9fc7ee313e1fc1a1f45201a5e1636ea3b0ee19020473eb747d
+size 1566484886

msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/tokenizer_config.json

@@ -0,0 +1,154 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

msa_curriculum/reset/pct50/pretraining/vocab/full_epoch2/final/training_complete.json

@@ -0,0 +1,21 @@
+{
+  "epochs": 1,
+  "global_step": 23478,
+  "initial_weights": "/workspace/baseline_cloud/work/checkpoints/msa_curriculum/reset/pct50/pretraining/vocab/full_epoch1/final/pytorch_model.bin",
+  "learning_rate": 0.0003,
+  "metrics": {
+    "epoch": 1.0,
+    "train_loss": 0.8639826015004796,
+    "train_runtime": 44319.6637,
+    "train_samples_per_second": 271.234,
+    "train_steps_per_second": 0.53
+  },
+  "model_type": "vocab",
+  "percentage": 50,
+  "scheduler": "cosine",
+  "seed": 42,
+  "stage": "full",
+  "subset_rows": 12021020,
+  "total_rows": 24042041,
+  "warmup_ratio": 0.1
+}