Training in progress, step 10, checkpoint

checkpoint-10/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-10/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91114ea9ec624c8bc4a9cf1f125c80a6e01a3f507b34cfdbe8fad2776f96657a
+size 544373707

checkpoint-10/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e1b90c733c428c2409655cd03312a426b741be5cf268a152fc94ff676c1e5fd
+size 272184705

checkpoint-10/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcb63247221e950b6c9d240f9bb8d48eb902e34bcc6d90ea597a91f9652c5b78
+size 14575

checkpoint-10/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe018414d45f47ca28e9d9bd66e5a07d13d7a8846d0467e1ca48538b6033818c
+size 627

checkpoint-10/special_tokens_map.json

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

checkpoint-10/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-10/trainer_state.json

@@ -0,0 +1,33 @@
+{
+  "best_metric": 10.804353713989258,
+  "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/2023-11-20/14-54-26/checkpoints/checkpoint-10",
+  "epoch": 0.08,
+  "eval_steps": 10,
+  "global_step": 10,
+  "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": 10.804353713989258,
+      "eval_runtime": 2.6966,
+      "eval_samples_per_second": 370.843,
+      "eval_steps_per_second": 46.355,
+      "step": 10
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 125,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "total_flos": 703388819520.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ae9edac8e41c0240cbb09648ef4171e2ce67c1c9132186453148fa757a3f68
+size 4155