message

.gitattributes

@@ -25,3 +25,4 @@ 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
+C:/Users/spelix/ts_bert/ts-test2/** filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e12935ad13506c42ae163174d3de765d590251feb363094f5e6b49101b90ed5
+size 876231385

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1cf63cbd81b02d4378eeba944f3ee6d282a0de3cb0d79ed9b4895a674205b83
+size 438141995

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a45f135cf4b30f84046725d0b45aec93c5fe683539036c4cebefc0b14814107a
+size 14503

runs/Mar02_00-12-24_2d94c9348624/1646179955.537279/events.out.tfevents.1646179955.2d94c9348624.100.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69c8e9d54ad1dddc3bd11569fedfad3ac6887db3b3782f00d8b1ed6231d659fe
+size 4678

runs/Mar02_00-12-24_2d94c9348624/events.out.tfevents.1646179955.2d94c9348624.100.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec712050060ac7b9a6371e4dd27d7dd6b0ecca743b92272794da1491b6cd9ea
+size 9086

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:785506a659d139e8cc6c00f81be39e376e0d98bc74f5a0744e4795cdcba7926e
+size 623

trainer_state.json

@@ -0,0 +1,198 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.996168582375478,
+  "global_step": 650,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 9.0082,
+      "step": 50
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 8.411425590515137,
+      "eval_runtime": 12.7191,
+      "eval_samples_per_second": 45.601,
+      "eval_steps_per_second": 2.909,
+      "step": 50
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 4.230769230769231e-05,
+      "loss": 8.0104,
+      "step": 100
+    },
+    {
+      "epoch": 1.54,
+      "eval_loss": 7.781517505645752,
+      "eval_runtime": 12.722,
+      "eval_samples_per_second": 45.59,
+      "eval_steps_per_second": 2.908,
+      "step": 100
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 3.846153846153846e-05,
+      "loss": 7.6542,
+      "step": 150
+    },
+    {
+      "epoch": 2.31,
+      "eval_loss": 7.551076889038086,
+      "eval_runtime": 12.717,
+      "eval_samples_per_second": 45.608,
+      "eval_steps_per_second": 2.909,
+      "step": 150
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 3.461538461538462e-05,
+      "loss": 7.4951,
+      "step": 200
+    },
+    {
+      "epoch": 3.08,
+      "eval_loss": 7.532299995422363,
+      "eval_runtime": 12.7257,
+      "eval_samples_per_second": 45.577,
+      "eval_steps_per_second": 2.908,
+      "step": 200
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 7.3489,
+      "step": 250
+    },
+    {
+      "epoch": 3.84,
+      "eval_loss": 7.389176845550537,
+      "eval_runtime": 12.723,
+      "eval_samples_per_second": 45.587,
+      "eval_steps_per_second": 2.908,
+      "step": 250
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 2.6923076923076923e-05,
+      "loss": 7.349,
+      "step": 300
+    },
+    {
+      "epoch": 4.61,
+      "eval_loss": 7.34345006942749,
+      "eval_runtime": 12.7274,
+      "eval_samples_per_second": 45.571,
+      "eval_steps_per_second": 2.907,
+      "step": 300
+    },
+    {
+      "epoch": 5.38,
+      "learning_rate": 2.307692307692308e-05,
+      "loss": 7.2625,
+      "step": 350
+    },
+    {
+      "epoch": 5.38,
+      "eval_loss": 7.265749454498291,
+      "eval_runtime": 12.7257,
+      "eval_samples_per_second": 45.577,
+      "eval_steps_per_second": 2.907,
+      "step": 350
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 1.923076923076923e-05,
+      "loss": 7.1982,
+      "step": 400
+    },
+    {
+      "epoch": 6.15,
+      "eval_loss": 7.229588985443115,
+      "eval_runtime": 12.7294,
+      "eval_samples_per_second": 45.564,
+      "eval_steps_per_second": 2.907,
+      "step": 400
+    },
+    {
+      "epoch": 6.92,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 7.1324,
+      "step": 450
+    },
+    {
+      "epoch": 6.92,
+      "eval_loss": 7.157928466796875,
+      "eval_runtime": 12.7187,
+      "eval_samples_per_second": 45.602,
+      "eval_steps_per_second": 2.909,
+      "step": 450
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 1.153846153846154e-05,
+      "loss": 7.1505,
+      "step": 500
+    },
+    {
+      "epoch": 7.69,
+      "eval_loss": 7.151326656341553,
+      "eval_runtime": 12.7324,
+      "eval_samples_per_second": 45.553,
+      "eval_steps_per_second": 2.906,
+      "step": 500
+    },
+    {
+      "epoch": 8.46,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 7.1079,
+      "step": 550
+    },
+    {
+      "epoch": 8.46,
+      "eval_loss": 7.1157402992248535,
+      "eval_runtime": 12.7267,
+      "eval_samples_per_second": 45.573,
+      "eval_steps_per_second": 2.907,
+      "step": 550
+    },
+    {
+      "epoch": 9.23,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 7.1039,
+      "step": 600
+    },
+    {
+      "epoch": 9.23,
+      "eval_loss": 7.14491605758667,
+      "eval_runtime": 12.7279,
+      "eval_samples_per_second": 45.569,
+      "eval_steps_per_second": 2.907,
+      "step": 600
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 7.046,
+      "step": 650
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 7.087325096130371,
+      "eval_runtime": 12.7263,
+      "eval_samples_per_second": 45.575,
+      "eval_steps_per_second": 2.907,
+      "step": 650
+    }
+  ],
+  "max_steps": 650,
+  "num_train_epochs": 10,
+  "total_flos": 1.3722182915328e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47df792e260f181db068d99087d2523ae95ad8b0d8d27342ba29a474cbdba709
+size 2927