init commit

Browse files

Files changed (17) hide show

.gitattributes +4 -0
.ipynb_checkpoints/merges-checkpoint.txt +0 -0
.ipynb_checkpoints/vocab-checkpoint.json +0 -0
checkpoint-10000/config.json +26 -0
checkpoint-10000/optimizer.pt +3 -0
checkpoint-10000/pytorch_model.bin +3 -0
checkpoint-10000/rng_state.pth +0 -0
checkpoint-10000/scheduler.pt +0 -0
checkpoint-10000/trainer_state.json +136 -0
checkpoint-10000/training_args.bin +0 -0
config.json +26 -0
merges.txt +0 -0
pytorch_model.bin +3 -0
runs/Dec17_01-38-42_n32/1639701525.4542303/events.out.tfevents.1639701525.n32.21687.1 +0 -0
runs/Dec17_01-38-42_n32/events.out.tfevents.1639701525.n32.21687.0 +0 -0
training_args.bin +0 -0
vocab.json +0 -0

.gitattributes CHANGED Viewed

@@ -25,3 +25,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+fpss.tar.gz filter=lfs diff=lfs merge=lfs -text
+checkpoint-10000/optimizer.pt filter=lfs diff=lfs merge=lfs -text
+checkpoint-10000/pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

.ipynb_checkpoints/merges-checkpoint.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

.ipynb_checkpoints/vocab-checkpoint.json ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-10000/config.json ADDED Viewed

	@@ -0,0 +1,26 @@

+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

checkpoint-10000/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bd744acd088fe402025746b5d0666a4b072a49e10ffef30fc16386434b4eeaa9
+size 668099842

checkpoint-10000/pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:65e7c25201d14d2647f2a730ba3476f377b521bedbe5b510cf9bc91eccb24142
+size 334066136

checkpoint-10000/rng_state.pth ADDED Viewed

Binary file (14.6 kB). View file

checkpoint-10000/scheduler.pt ADDED Viewed

Binary file (623 Bytes). View file

checkpoint-10000/trainer_state.json ADDED Viewed

	@@ -0,0 +1,136 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6566850538481744,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.8358287365379566e-05,
+      "loss": 7.8649,
+      "step": 500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.671657473075913e-05,
+      "loss": 7.2652,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.5074862096138694e-05,
+      "loss": 7.0778,
+      "step": 1500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.343314946151826e-05,
+      "loss": 6.9737,
+      "step": 2000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.179143682689782e-05,
+      "loss": 6.8729,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.0149724192277385e-05,
+      "loss": 6.79,
+      "step": 3000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 3.850801155765695e-05,
+      "loss": 6.752,
+      "step": 3500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 3.686629892303651e-05,
+      "loss": 6.7012,
+      "step": 4000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3.522458628841608e-05,
+      "loss": 6.6312,
+      "step": 4500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.358287365379564e-05,
+      "loss": 6.5047,
+      "step": 5000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.1941161019175205e-05,
+      "loss": 6.3916,
+      "step": 5500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.029944838455477e-05,
+      "loss": 6.24,
+      "step": 6000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2.8657735749934332e-05,
+      "loss": 6.1126,
+      "step": 6500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.70160231153139e-05,
+      "loss": 5.9892,
+      "step": 7000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.5374310480693457e-05,
+      "loss": 5.8802,
+      "step": 7500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.3732597846073024e-05,
+      "loss": 5.7723,
+      "step": 8000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.2090885211452588e-05,
+      "loss": 5.6834,
+      "step": 8500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.0449172576832152e-05,
+      "loss": 5.5951,
+      "step": 9000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.8807459942211716e-05,
+      "loss": 5.5049,
+      "step": 9500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.716574730759128e-05,
+      "loss": 5.4411,
+      "step": 10000
+    }
+  ],
+  "max_steps": 15228,
+  "num_train_epochs": 1,
+  "total_flos": 2.1220159479607296e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10000/training_args.bin ADDED Viewed

Binary file (2.86 kB). View file

config.json ADDED Viewed

	@@ -0,0 +1,26 @@

+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5fc8c1d9fc7cfc913c50d29003b03b2388deb18ee22adfe1610c889ce70ef316
+size 334066136

runs/Dec17_01-38-42_n32/1639701525.4542303/events.out.tfevents.1639701525.n32.21687.1 ADDED Viewed

Binary file (4.51 kB). View file

runs/Dec17_01-38-42_n32/events.out.tfevents.1639701525.n32.21687.0 ADDED Viewed

Binary file (8.13 kB). View file

training_args.bin ADDED Viewed

Binary file (2.86 kB). View file

vocab.json ADDED Viewed

The diff for this file is too large to render. See raw diff