Training in progress, step 3500, checkpoint

checkpoint-3500/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-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a960886a4c9d87b6eb7f9065535fef1c4cb638be98fe7dec7dea5d3acf52f531
+size 1010407418

checkpoint-3500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a2d7451d4ac97e24a528226da11541afc6ec75b64054f79a5ba92b423229a7
+size 505188394

checkpoint-3500/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f3205d0c956e5d6911dfc414a2bd0d2e7fa4c3c3d8a6ae6113ffb729705e211
+size 15984

checkpoint-3500/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2775f561c29fcccf685135119ad8c1d3d11d86794264092c247a08adf74763d
+size 15984

checkpoint-3500/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4ed1d602acba70a0ec1494705e623d852b5935cc6058a6c4c3577d767ec7c8d
+size 15984

checkpoint-3500/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83b0306903eabcc985f74ea10caf58e3798c2fb748a3a5060ddc97049acb9da6
+size 15984

checkpoint-3500/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5899bc1361d21cbdb94d4e62f5bdedf4b9e9fb03ebf3c5e1517286bd5687d73
+size 15984

checkpoint-3500/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd624d65e2da862a58e5ccb2d994f79ebf3fd2e5594e046e974ff91b4fa5d23
+size 15984

checkpoint-3500/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33ef70c9df467f02d651d5ff00cc27d5322308c923b474f650109a831d0022f7
+size 15984

checkpoint-3500/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e941c3d9c91923a95df93b0817c54d3b30eb148f3d4c542445388d02715838e1
+size 15984

checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deeb69aa98ee23361f5d844d69be12f04fe15fda35332cd805bb3ed5e5fd6128
+size 1064

checkpoint-3500/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-3500/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-3500/trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2690884628321561,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "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
+    },
+    {
+      "ep_loss": 0.3624,
+      "epoch": 0.23,
+      "learning_rate": 0.00014995,
+      "loss": 1.4228,
+      "mlm_loss": 1.0604,
+      "step": 3000
+    },
+    {
+      "ep_loss": 0.338,
+      "epoch": 0.27,
+      "learning_rate": 0.00017495,
+      "loss": 1.3108,
+      "mlm_loss": 0.9729,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 520240,
+  "num_train_epochs": 40,
+  "save_steps": 500,
+  "total_flos": 3.341860451825746e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3500/training_args.bin

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