Training in progress, step 50

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "/home/pcjf/CESGA/works/lmodels/models/tiny",
   "architectures": [
-    "RobertaModel"
+    "RobertaForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,

last-checkpoint/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/home/pcjf/CESGA/works/lmodels/models/tiny",
+  "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": "4.24.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 31002
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d73c65350dd6e4ee4732b97ed18c5cc9bcf80506a7505bec00671aa35b65ba2e
+size 538917573

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:791f01dee3159ca6417331bbf93b2691421b437754813ef5e2119c53e55ca65a
+size 269468281

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44f515587e51d8a59759bd8c56a4e1f5865302c07452fbfc29b67b9ed70f500
+size 16619

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfa3bcfad6548e955614aa66924075e0bfa36d4a9baf6cf6190c3fd577b6da91
+size 557

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c21ae027fae19f270e6f570406bf93790e5591271df93837c5c04e1a38b7dd9f
+size 627

last-checkpoint/trainer_state.json

@@ -0,0 +1,30 @@
+{
+  "best_metric": 3.1328039169311523,
+  "best_model_checkpoint": "/home/pcjf/CESGA/works/lmodels/models/tiny/checkpoint-50",
+  "epoch": 0.2818638245397692,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.717514124293787e-05,
+      "loss": 5.0078,
+      "step": 50
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 3.1328039169311523,
+      "eval_runtime": 312.4569,
+      "eval_samples_per_second": 184.566,
+      "eval_steps_per_second": 7.691,
+      "step": 50
+    }
+  ],
+  "max_steps": 1770,
+  "num_train_epochs": 10,
+  "total_flos": 1.0178865092034144e+16,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2354b21c0eb02b167b9d6057f7fbae73d5ab7eeb327be5d088eb30bf0019608
+size 3451

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3b188e07e7c97aeaa4bea58e8656ae8d485b59ebef72adcaf98662291217df3
-size 269334957
+oid sha256:791f01dee3159ca6417331bbf93b2691421b437754813ef5e2119c53e55ca65a
+size 269468281

runs/Jan11_16-45-27_turing/1673451933.465075/events.out.tfevents.1673451933.turing.162574.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:853f3d8342cbd88d1830b3b8643713bfd6721a824bc6b62817b60974a961aafd
+size 5573

runs/Jan11_16-45-27_turing/events.out.tfevents.1673451933.turing.162574.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9efc1097d6beedfd21b85f92d525ea0f973e3e457b9c0b93464dc6cf8310ffab
+size 4265

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2354b21c0eb02b167b9d6057f7fbae73d5ab7eeb327be5d088eb30bf0019608
+size 3451