Training in progress, step 2500, checkpoint

checkpoint-2500/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LongelmForMaskedLMWithEdgePrediction"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "block_size": 8,
+  "bos_token_id": 1,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "ep_add_linear_projection": true,
+  "global_memory_size": 1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_blocks": 200,
+  "max_position_embeddings": 1801,
+  "max_relative_position_embeddings": 8,
+  "model_type": "longelm",
+  "node_size": 1,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 3,
+  "position_embedding_type": "mixed",
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f0d76d650afe4870b8a9cf4358d0506bceaae493c003bdb59ecf0bc2cb917ad
+size 1010407418

checkpoint-2500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8da5868cd7fe8bfd10547c6dbf4e5e1985d8926a9c757691bdd462c2b6caea26
+size 505188394

checkpoint-2500/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f4e7a402536f02e21bb548e6ac71549b198a35fb829d309c4ab26d0dd77247e
+size 15984

checkpoint-2500/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69b98cef9097d92b1e01d963fad6395b64ce84d7404251f0ae47a1c855deb724
+size 15984

checkpoint-2500/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81eac5f65424dec2e1e61d7b0ad2a326856d611dd2f99191dbdb1d045694d80b
+size 15984

checkpoint-2500/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1363239a6cf51f5b347e65b7f8a537c918228fd889d590570809f915b203c13
+size 15984

checkpoint-2500/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c45bda0fe76b768796edd59b9510436ee4f5fe6f8df46aed4e9b35d10900de9
+size 15984

checkpoint-2500/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fbebae02974615b7dca0c2132f422c11a2de0c44a92c13935d1762d40f30e9f
+size 15984

checkpoint-2500/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1516e34b64fa775c993e16cf027d923b37eaef6b98cc75f86443ed006986bd3
+size 15984

checkpoint-2500/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6e80cc287f533da24018ee0569aee6d2e3e7d2f3c2234f1eca1f1d2e2784fe8
+size 15984

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8532dc54b272f902ef1f948e9973110cccea5acfc02177ce8ce908a06ff28e16
+size 1064

checkpoint-2500/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2500/tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30522": {
+      "content": "<INST>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "LongelmTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-2500/trainer_state.json

@@ -0,0 +1,59 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.19220604488011148,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "ep_loss": 4.7343,
+      "epoch": 0.04,
+      "learning_rate": 2.5e-05,
+      "loss": 11.6218,
+      "mlm_loss": 6.8875,
+      "step": 500
+    },
+    {
+      "ep_loss": 0.4315,
+      "epoch": 0.08,
+      "learning_rate": 5e-05,
+      "loss": 3.0285,
+      "mlm_loss": 2.5969,
+      "step": 1000
+    },
+    {
+      "ep_loss": 0.3811,
+      "epoch": 0.12,
+      "learning_rate": 7.5e-05,
+      "loss": 2.2571,
+      "mlm_loss": 1.8761,
+      "step": 1500
+    },
+    {
+      "ep_loss": 0.37,
+      "epoch": 0.15,
+      "learning_rate": 0.0001,
+      "loss": 1.9695,
+      "mlm_loss": 1.5994,
+      "step": 2000
+    },
+    {
+      "ep_loss": 0.3813,
+      "epoch": 0.19,
+      "learning_rate": 0.00012495,
+      "loss": 1.5597,
+      "mlm_loss": 1.1785,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 520240,
+  "num_train_epochs": 40,
+  "save_steps": 500,
+  "total_flos": 2.387043179875533e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cee56d4f38339eac5ecf098381d5222b3783455863547a17ac0df67c8caa7d15
+size 4664