push from colab

added_tokens.json

@@ -0,0 +1 @@
+{"[MASK]": 128000}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "/content/deberta-v3-xsmall-squad-v2",
+  "architectures": [
+    "DebertaV2ForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 384,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f31d1c0c707b9ee41a288bd78d8e9b820dc209b60ece92e0e9c05131202b62d
+size 282817775

runs/Feb03_23-44-35_d9830817af0a/1643931890.0116262/events.out.tfevents.1643931890.d9830817af0a.98.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8ce36fe8404e8c6a5b29fe6d4286e0d6d4e0bf8a7905b2c3892420e301239fa
+size 4786

runs/Feb03_23-44-35_d9830817af0a/events.out.tfevents.1643931890.d9830817af0a.98.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:073e145ea226037a109911d14e6038c9434578aac0c970188e96521c7298f562
+size 3470

runs/Feb03_23-45-28_d9830817af0a/1643931932.2896552/events.out.tfevents.1643931932.d9830817af0a.586.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:699ed82f7aa554c610158b5124774d87c8d6a0d00ca12c2a9bb0bf9623a21a30
+size 4786

runs/Feb03_23-45-28_d9830817af0a/events.out.tfevents.1643931932.d9830817af0a.586.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e119ac3fb1c0d3d119cce097fc5f7d828b20c0d84bbf8576287399135e222833
+size 8404

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": false, "vocab_type": "spm", "special_tokens_map_file": null, "name_or_path": "microsoft/deberta-v3-xsmall", "sp_model_kwargs": {}, "tokenizer_file": null, "tokenizer_class": "DebertaV2Tokenizer"}

trainer_state.json

@@ -0,0 +1,152 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.433682161109759,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.919201752251156e-05,
+      "loss": 2.3883,
+      "step": 500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.8380790135474976e-05,
+      "loss": 1.4529,
+      "step": 1000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.7569562748438388e-05,
+      "loss": 1.2698,
+      "step": 1500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.6758335361401804e-05,
+      "loss": 1.1845,
+      "step": 2000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.594873042913929e-05,
+      "loss": 1.1239,
+      "step": 2500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.5137503042102703e-05,
+      "loss": 1.0576,
+      "step": 3000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.4326275655066115e-05,
+      "loss": 1.0744,
+      "step": 3500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.3515048268029529e-05,
+      "loss": 1.0113,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.8904165625572205,
+      "eval_runtime": 91.887,
+      "eval_samples_per_second": 131.694,
+      "eval_steps_per_second": 2.068,
+      "step": 4109
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.2703820880992943e-05,
+      "loss": 0.9452,
+      "step": 4500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.1892593493956356e-05,
+      "loss": 0.9205,
+      "step": 5000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.108136610691977e-05,
+      "loss": 0.8961,
+      "step": 5500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.0271761174657257e-05,
+      "loss": 0.906,
+      "step": 6000
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.460533787620671e-06,
+      "loss": 0.8696,
+      "step": 6500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 8.649306400584085e-06,
+      "loss": 0.8745,
+      "step": 7000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 7.838079013547499e-06,
+      "loss": 0.8528,
+      "step": 7500
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 7.028474081284985e-06,
+      "loss": 0.8645,
+      "step": 8000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8758471012115479,
+      "eval_runtime": 91.8658,
+      "eval_samples_per_second": 131.725,
+      "eval_steps_per_second": 2.068,
+      "step": 8218
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 6.217246694248399e-06,
+      "loss": 0.8209,
+      "step": 8500
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 5.406019307211812e-06,
+      "loss": 0.798,
+      "step": 9000
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 4.594791920175226e-06,
+      "loss": 0.7944,
+      "step": 9500
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 3.783564533138639e-06,
+      "loss": 0.7893,
+      "step": 10000
+    }
+  ],
+  "max_steps": 12327,
+  "num_train_epochs": 3,
+  "total_flos": 1.5698961223584768e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f8e453fe89974f20c41279c814932ab5388eded719a09d58b68457814282032
+size 3055