Training in progress, step 110, checkpoint

checkpoint-110/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "RNNForLanguageModeling"
+  ],
+  "bidirectional": false,
+  "dropout_p": 0.1,
+  "emb_init_range": 0.1,
+  "embedding_dim": 1024,
+  "embedding_kwargs": {},
+  "hidden_dim": 1024,
+  "lin_init_range": 0.03125,
+  "lm_in_features": 1024,
+  "model_type": "rnn",
+  "num_layers": 2,
+  "output_last_state": false,
+  "output_recurrent_outputs": false,
+  "recur_init_range": 0.03125,
+  "rnn_kwargs": {},
+  "rnn_type": "LSTM",
+  "tie_weights": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "vocab_size": 50002
+}

checkpoint-110/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ecc17865dcd3db0f6ee84dd9c43cca3a9de1e85afa0f6de0b47ab0a27ae183
+size 544373707

checkpoint-110/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73fc0c08d3957c9c874ee78bb6b92c4de6869832d5fffb130c4b93426013f34
+size 272184705

checkpoint-110/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6bd76617602f6c03c82358ebfb6c1cc9c9f7104dbe0c257cb777413a422d442
+size 14575

checkpoint-110/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:864f191ba0a2f56d7dedef8ddc5a6d7f5463148a02e833f6206a941d7030690a
+size 627

checkpoint-110/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

checkpoint-110/tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<eos>",
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

checkpoint-110/trainer_state.json

@@ -0,0 +1,173 @@
+{
+  "best_metric": 7.869668006896973,
+  "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/fict-full-lstm-42/checkpoints/checkpoint-110",
+  "epoch": 0.88,
+  "eval_steps": 10,
+  "global_step": 110,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 10.8138,
+      "step": 10
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 10.804121971130371,
+      "eval_runtime": 2.7698,
+      "eval_samples_per_second": 361.038,
+      "eval_steps_per_second": 45.13,
+      "step": 10
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.2e-05,
+      "loss": 10.7943,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 10.77995491027832,
+      "eval_runtime": 2.844,
+      "eval_samples_per_second": 351.614,
+      "eval_steps_per_second": 43.952,
+      "step": 20
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 3.8e-05,
+      "loss": 10.7591,
+      "step": 30
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 10.717215538024902,
+      "eval_runtime": 2.744,
+      "eval_samples_per_second": 364.436,
+      "eval_steps_per_second": 45.554,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 10.6049,
+      "step": 40
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 10.266470909118652,
+      "eval_runtime": 2.7349,
+      "eval_samples_per_second": 365.65,
+      "eval_steps_per_second": 45.706,
+      "step": 40
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3e-05,
+      "loss": 9.8537,
+      "step": 50
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 9.23794937133789,
+      "eval_runtime": 2.8879,
+      "eval_samples_per_second": 346.272,
+      "eval_steps_per_second": 43.284,
+      "step": 50
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 9.0545,
+      "step": 60
+    },
+    {
+      "epoch": 0.48,
+      "eval_loss": 8.647107124328613,
+      "eval_runtime": 2.8395,
+      "eval_samples_per_second": 352.175,
+      "eval_steps_per_second": 44.022,
+      "step": 60
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 8.5764,
+      "step": 70
+    },
+    {
+      "epoch": 0.56,
+      "eval_loss": 8.326546669006348,
+      "eval_runtime": 2.7246,
+      "eval_samples_per_second": 367.023,
+      "eval_steps_per_second": 45.878,
+      "step": 70
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.8e-05,
+      "loss": 8.3924,
+      "step": 80
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 8.13099479675293,
+      "eval_runtime": 2.785,
+      "eval_samples_per_second": 359.073,
+      "eval_steps_per_second": 44.884,
+      "step": 80
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 8.2474,
+      "step": 90
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 8.003149032592773,
+      "eval_runtime": 2.752,
+      "eval_samples_per_second": 363.374,
+      "eval_steps_per_second": 45.422,
+      "step": 90
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1e-05,
+      "loss": 8.1181,
+      "step": 100
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 7.92080545425415,
+      "eval_runtime": 2.7817,
+      "eval_samples_per_second": 359.489,
+      "eval_steps_per_second": 44.936,
+      "step": 100
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6e-06,
+      "loss": 8.0602,
+      "step": 110
+    },
+    {
+      "epoch": 0.88,
+      "eval_loss": 7.869668006896973,
+      "eval_runtime": 2.8251,
+      "eval_samples_per_second": 353.965,
+      "eval_steps_per_second": 44.246,
+      "step": 110
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 125,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "total_flos": 7737277014720.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-110/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:238456d42ac15da7cc02dac0c19fd610773196ec55f53941edde171480424889
+size 4155