Training in progress, step 6500, checkpoint

checkpoint-6500/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-6500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cafd9385532b5445162239e58b8a5e0127213f1e220c822154583bba81c1587c
+size 1010407418

checkpoint-6500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc3c57fdc86b39e9ee3e40c071c9e9d037ef2d31d38dd2883d61f28f6428a8f2
+size 505188394

checkpoint-6500/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d73d7e2799ec38853498ddcb3daac8e6e206cfb3ed40527456ceacdd8af7a5a
+size 15984

checkpoint-6500/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58da7beb56f585a009f9829f35f8d26e28e3c104d4aba34fab54176bd14c7b84
+size 15984

checkpoint-6500/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4794b0c75c76d6f6230fb4033ee365193444663d0dd0a71ce042411073511b1
+size 15984

checkpoint-6500/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70aa8419e2c50a89e1108554dcd2a2f9ae79258e12b669b0af50e6c7d0c7e26a
+size 15984

checkpoint-6500/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7d91b66fb886d57e55f5320c279f1d49fcc4c62a5c098fed0d9b020ec198237
+size 15984

checkpoint-6500/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc4b42f6784d1d7898ebb1f3eeaeb50139b7ef69bd5ddaf351b2148165761c9
+size 15984

checkpoint-6500/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f73762761fad36bb0a423764712b5e17e27369d00a28ac60b8dc85d6b162314
+size 15984

checkpoint-6500/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0069ca5986d0460de96ade18276a63d25f3b0a37ee996835ead3bd6e4fab23a2
+size 15984

checkpoint-6500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7394bfc3ef7d4b88b6c3aeb86b9f6157a34fd221f3b81a70df90f00315cf57dd
+size 1064

checkpoint-6500/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-6500/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-6500/trainer_state.json

@@ -0,0 +1,123 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.49973571668828987,
+  "eval_steps": 500,
+  "global_step": 6500,
+  "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
+    },
+    {
+      "ep_loss": 0.3524,
+      "epoch": 0.31,
+      "learning_rate": 0.00019994999999999998,
+      "loss": 1.2734,
+      "mlm_loss": 0.921,
+      "step": 4000
+    },
+    {
+      "ep_loss": 0.3423,
+      "epoch": 0.35,
+      "learning_rate": 0.00022495000000000002,
+      "loss": 1.217,
+      "mlm_loss": 0.8747,
+      "step": 4500
+    },
+    {
+      "ep_loss": 0.3229,
+      "epoch": 0.38,
+      "learning_rate": 0.0002499,
+      "loss": 1.1373,
+      "mlm_loss": 0.8144,
+      "step": 5000
+    },
+    {
+      "ep_loss": 0.3326,
+      "epoch": 0.42,
+      "learning_rate": 0.00027489999999999996,
+      "loss": 1.117,
+      "mlm_loss": 0.7844,
+      "step": 5500
+    },
+    {
+      "ep_loss": 0.332,
+      "epoch": 0.46,
+      "learning_rate": 0.00029985,
+      "loss": 1.0958,
+      "mlm_loss": 0.7638,
+      "step": 6000
+    },
+    {
+      "ep_loss": 0.3236,
+      "epoch": 0.5,
+      "learning_rate": 0.00032485,
+      "loss": 1.0729,
+      "mlm_loss": 0.7493,
+      "step": 6500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 520240,
+  "num_train_epochs": 40,
+  "save_steps": 500,
+  "total_flos": 6.206312267676385e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6500/training_args.bin

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