kpriyanshu256 commited on May 9

Commit

ff53177

•

1 Parent(s): ac0c95e

Upload folder using huggingface_hub

Browse files

Files changed (40) hide show

checkpoint-2400/config.json +33 -0
checkpoint-2400/merges.txt +0 -0
checkpoint-2400/optimizer.pt +3 -0
checkpoint-2400/pytorch_model.bin +3 -0
checkpoint-2400/rng_state.pth +3 -0
checkpoint-2400/scaler.pt +3 -0
checkpoint-2400/scheduler.pt +3 -0
checkpoint-2400/special_tokens_map.json +1 -0
checkpoint-2400/tokenizer.json +0 -0
checkpoint-2400/tokenizer_config.json +1 -0
checkpoint-2400/trainer_state.json +136 -0
checkpoint-2400/training_args.bin +3 -0
checkpoint-2400/vocab.json +0 -0
checkpoint-3000/config.json +33 -0
checkpoint-3000/merges.txt +0 -0
checkpoint-3000/optimizer.pt +3 -0
checkpoint-3000/pytorch_model.bin +3 -0
checkpoint-3000/rng_state.pth +3 -0
checkpoint-3000/scaler.pt +3 -0
checkpoint-3000/scheduler.pt +3 -0
checkpoint-3000/special_tokens_map.json +1 -0
checkpoint-3000/tokenizer.json +0 -0
checkpoint-3000/tokenizer_config.json +1 -0
checkpoint-3000/trainer_state.json +166 -0
checkpoint-3000/training_args.bin +3 -0
checkpoint-3000/vocab.json +0 -0
config.json +33 -0
merges.txt +0 -0
pytorch_model.bin +3 -0
runs/Apr06_17-46-43_babel-3-7/1712440009.733516/events.out.tfevents.1712440009.babel-3-7 +3 -0
runs/Apr06_17-46-43_babel-3-7/events.out.tfevents.1712440009.babel-3-7 +3 -0
runs/Apr06_18-01-45_babel-8-7/1712440910.5851839/events.out.tfevents.1712440910.babel-8-7 +3 -0
runs/Apr06_18-01-45_babel-8-7/events.out.tfevents.1712440910.babel-8-7 +3 -0
runs/Apr06_18-01-45_babel-8-7/events.out.tfevents.1712609521.babel-8-7 +3 -0
special_tokens_map.json +1 -0
tokenizer.json +0 -0
tokenizer_config.json +1 -0
trainer_state.json +175 -0
training_args.bin +3 -0
vocab.json +0 -0

checkpoint-2400/config.json ADDED Viewed

	@@ -0,0 +1,33 @@

+{
+  "_name_or_path": "Salesforce/codet5p-220m",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "bos_token_id": 1,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 2,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "max_length": 1024,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "use_cache": true,
+  "vocab_size": 32100
+}

checkpoint-2400/merges.txt ADDED Viewed

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

checkpoint-2400/optimizer.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a07de3d096c126efcc7a124528958d8881f5ffe9b7a42c3885bc353e0bea3eba
+size 1783209146

checkpoint-2400/pytorch_model.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:a87454e3aa158c8448067089cf62318d406cdf9bc61b2df9eee7043db89e980d
+size 891647438

checkpoint-2400/rng_state.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6ea8abde04241a68e49a8167022aa9b83cee1f8ce6494fc8508d03a5520b276b
+size 15006

checkpoint-2400/scaler.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:900f26e6b66c9eae5e85a376345ba03c270e502825dc9e8a4ca0b1cd6fc50bd2
+size 988

checkpoint-2400/scheduler.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e9e4c100eb9966109a455ef09e6ff0c3b05e7f31ab122aab309b9c64eba67bc1
+size 1064

checkpoint-2400/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, "additional_special_tokens": [{"content": "<extra_id_99>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_98>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_97>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_96>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_95>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_94>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_93>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_92>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_91>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_90>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_89>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_88>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_87>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_86>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_85>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_84>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_83>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_82>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_81>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_80>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_79>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_78>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_77>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_76>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_75>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_74>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_73>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_72>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_71>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_70>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_69>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_68>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_67>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_66>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_65>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_64>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_63>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_62>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_61>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_60>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_59>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_58>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_57>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_56>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_55>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_54>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_53>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_52>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_51>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_50>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_49>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_48>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_47>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_46>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_45>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_44>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_43>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_42>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_41>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_40>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_39>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_38>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_37>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_36>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_35>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_34>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_33>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_32>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_31>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_30>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_29>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_28>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_27>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_26>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_25>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_24>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_23>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_22>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_21>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_20>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_19>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_18>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_17>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_16>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_15>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_14>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_13>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_12>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_11>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_10>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_9>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_8>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_7>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_6>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_5>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_4>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_3>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_2>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_1>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}, {"content": "<extra_id_0>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": true}]}

checkpoint-2400/tokenizer.json ADDED Viewed

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

checkpoint-2400/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1 @@

+ {"errors": "replace", "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false, "__type": "AddedToken"}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "special": false, "__type": "AddedToken"}, "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": "/data/datasets/hf_cache/transformers/f432e4eb4a7dfc04b533beea5590e11f4b46c86f5630e8a032704ef76d7269c1.b9905d0575bde443a20834122b6e2d48e853b2e36444ce98ddeb43c38097eb3f", "name_or_path": "Salesforce/codet5p-220m", "tokenizer_class": "RobertaTokenizer"}

checkpoint-2400/trainer_state.json ADDED Viewed

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

+{
+  "best_metric": 96.7742,
+  "best_model_checkpoint": "/data/tir/projects/tir7/user_data/priyansk/qa_tapex_e2_codet5p-220m_latex/checkpoint-2400",
+  "epoch": 1.4887484736301437,
+  "global_step": 2400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.070409429280397e-05,
+      "loss": 1.8932,
+      "step": 300
+    },
+    {
+      "epoch": 0.19,
+      "eval_exact_match": 69.7581,
+      "eval_loss": 0.006803931202739477,
+      "eval_runtime": 182.7837,
+      "eval_samples_per_second": 2.735,
+      "eval_steps_per_second": 0.175,
+      "step": 300
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 8.140818858560795e-05,
+      "loss": 0.0034,
+      "step": 600
+    },
+    {
+      "epoch": 0.37,
+      "eval_exact_match": 86.4919,
+      "eval_loss": 0.0015783495036885142,
+      "eval_runtime": 139.3342,
+      "eval_samples_per_second": 3.588,
+      "eval_steps_per_second": 0.23,
+      "step": 600
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 7.211228287841191e-05,
+      "loss": 0.0012,
+      "step": 900
+    },
+    {
+      "epoch": 0.56,
+      "eval_exact_match": 92.5403,
+      "eval_loss": 0.00091337546473369,
+      "eval_runtime": 129.2451,
+      "eval_samples_per_second": 3.869,
+      "eval_steps_per_second": 0.248,
+      "step": 900
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 6.28163771712159e-05,
+      "loss": 0.0008,
+      "step": 1200
+    },
+    {
+      "epoch": 0.74,
+      "eval_exact_match": 94.3548,
+      "eval_loss": 0.0006592237623408437,
+      "eval_runtime": 130.2486,
+      "eval_samples_per_second": 3.839,
+      "eval_steps_per_second": 0.246,
+      "step": 1200
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.352047146401985e-05,
+      "loss": 0.0006,
+      "step": 1500
+    },
+    {
+      "epoch": 0.93,
+      "eval_exact_match": 94.5565,
+      "eval_loss": 0.0005109157646074891,
+      "eval_runtime": 127.9056,
+      "eval_samples_per_second": 3.909,
+      "eval_steps_per_second": 0.25,
+      "step": 1500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 4.422456575682382e-05,
+      "loss": 0.0004,
+      "step": 1800
+    },
+    {
+      "epoch": 1.12,
+      "eval_exact_match": 95.3629,
+      "eval_loss": 0.0004209030594211072,
+      "eval_runtime": 129.0896,
+      "eval_samples_per_second": 3.873,
+      "eval_steps_per_second": 0.248,
+      "step": 1800
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 3.4928660049627796e-05,
+      "loss": 0.0004,
+      "step": 2100
+    },
+    {
+      "epoch": 1.3,
+      "eval_exact_match": 95.1613,
+      "eval_loss": 0.00042048218892887235,
+      "eval_runtime": 129.0282,
+      "eval_samples_per_second": 3.875,
+      "eval_steps_per_second": 0.248,
+      "step": 2100
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.563275434243176e-05,
+      "loss": 0.0003,
+      "step": 2400
+    },
+    {
+      "epoch": 1.49,
+      "eval_exact_match": 96.7742,
+      "eval_loss": 0.0003429962380323559,
+      "eval_runtime": 127.2593,
+      "eval_samples_per_second": 3.929,
+      "eval_steps_per_second": 0.251,
+      "step": 2400
+    }
+  ],
+  "max_steps": 3224,
+  "num_train_epochs": 2,
+  "total_flos": 2.9935005834254746e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2400/training_args.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ed5d69df2f4458e091aa9fd5be576a7a7349e33ac70704441e5d3b16cf246325
+size 3704

checkpoint-2400/vocab.json ADDED Viewed

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

checkpoint-3000/config.json ADDED Viewed

	@@ -0,0 +1,33 @@

+{
+  "_name_or_path": "Salesforce/codet5p-220m",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "bos_token_id": 1,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 2,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "max_length": 1024,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "use_cache": true,
+  "vocab_size": 32100
+}

checkpoint-3000/merges.txt ADDED Viewed

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

checkpoint-3000/optimizer.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:b907bddb688109e99a2603d097ccfcf94f8c74d5ff6aee327877c03e2e0a7f42
+size 1783209146

checkpoint-3000/pytorch_model.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:2c74a0109069162babb6e8f4ee3abccf74dcf29756a2f98881c6d56a14db2783
+size 891647438

checkpoint-3000/rng_state.pth ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:49ab7ff4aa151c2e257a826519f59a4cf194464bf39e8c8feb460471c519e854
+size 15006

checkpoint-3000/scaler.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:21aba8ed0f38ed1c04994c10a9ca7e9925e55ef2ed51283c43ff8e2cce78585f
+size 988

checkpoint-3000/scheduler.pt ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:33184e4b01e31b6911f5275835e383836a36f8349f9d3b2f4dc1ce2520b4d6ae
+size 1064

checkpoint-3000/special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@

checkpoint-3000/tokenizer.json ADDED Viewed

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

checkpoint-3000/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1 @@

checkpoint-3000/trainer_state.json ADDED Viewed

	@@ -0,0 +1,166 @@

+{
+  "best_metric": 96.7742,
+  "best_model_checkpoint": "/data/tir/projects/tir7/user_data/priyansk/qa_tapex_e2_codet5p-220m_latex/checkpoint-2400",
+  "epoch": 1.8608919814703544,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.070409429280397e-05,
+      "loss": 1.8932,
+      "step": 300
+    },
+    {
+      "epoch": 0.19,
+      "eval_exact_match": 69.7581,
+      "eval_loss": 0.006803931202739477,
+      "eval_runtime": 182.7837,
+      "eval_samples_per_second": 2.735,
+      "eval_steps_per_second": 0.175,
+      "step": 300
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 8.140818858560795e-05,
+      "loss": 0.0034,
+      "step": 600
+    },
+    {
+      "epoch": 0.37,
+      "eval_exact_match": 86.4919,
+      "eval_loss": 0.0015783495036885142,
+      "eval_runtime": 139.3342,
+      "eval_samples_per_second": 3.588,
+      "eval_steps_per_second": 0.23,
+      "step": 600
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 7.211228287841191e-05,
+      "loss": 0.0012,
+      "step": 900
+    },
+    {
+      "epoch": 0.56,
+      "eval_exact_match": 92.5403,
+      "eval_loss": 0.00091337546473369,
+      "eval_runtime": 129.2451,
+      "eval_samples_per_second": 3.869,
+      "eval_steps_per_second": 0.248,
+      "step": 900
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 6.28163771712159e-05,
+      "loss": 0.0008,
+      "step": 1200
+    },
+    {
+      "epoch": 0.74,
+      "eval_exact_match": 94.3548,
+      "eval_loss": 0.0006592237623408437,
+      "eval_runtime": 130.2486,
+      "eval_samples_per_second": 3.839,
+      "eval_steps_per_second": 0.246,
+      "step": 1200
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.352047146401985e-05,
+      "loss": 0.0006,
+      "step": 1500
+    },
+    {
+      "epoch": 0.93,
+      "eval_exact_match": 94.5565,
+      "eval_loss": 0.0005109157646074891,
+      "eval_runtime": 127.9056,
+      "eval_samples_per_second": 3.909,
+      "eval_steps_per_second": 0.25,
+      "step": 1500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 4.422456575682382e-05,
+      "loss": 0.0004,
+      "step": 1800
+    },
+    {
+      "epoch": 1.12,
+      "eval_exact_match": 95.3629,
+      "eval_loss": 0.0004209030594211072,
+      "eval_runtime": 129.0896,
+      "eval_samples_per_second": 3.873,
+      "eval_steps_per_second": 0.248,
+      "step": 1800
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 3.4928660049627796e-05,
+      "loss": 0.0004,
+      "step": 2100
+    },
+    {
+      "epoch": 1.3,
+      "eval_exact_match": 95.1613,
+      "eval_loss": 0.00042048218892887235,
+      "eval_runtime": 129.0282,
+      "eval_samples_per_second": 3.875,
+      "eval_steps_per_second": 0.248,
+      "step": 2100
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.563275434243176e-05,
+      "loss": 0.0003,
+      "step": 2400
+    },
+    {
+      "epoch": 1.49,
+      "eval_exact_match": 96.7742,
+      "eval_loss": 0.0003429962380323559,
+      "eval_runtime": 127.2593,
+      "eval_samples_per_second": 3.929,
+      "eval_steps_per_second": 0.251,
+      "step": 2400
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.6336848635235734e-05,
+      "loss": 0.0003,
+      "step": 2700
+    },
+    {
+      "epoch": 1.67,
+      "eval_exact_match": 96.7742,
+      "eval_loss": 0.00032032810850068927,
+      "eval_runtime": 126.2849,
+      "eval_samples_per_second": 3.959,
+      "eval_steps_per_second": 0.253,
+      "step": 2700
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 7.040942928039701e-06,
+      "loss": 0.0003,
+      "step": 3000
+    },
+    {
+      "epoch": 1.86,
+      "eval_exact_match": 96.371,
+      "eval_loss": 0.0003172786091454327,
+      "eval_runtime": 128.5411,
+      "eval_samples_per_second": 3.89,
+      "eval_steps_per_second": 0.249,
+      "step": 3000
+    }
+  ],
+  "max_steps": 3224,
+  "num_train_epochs": 2,
+  "total_flos": 3.7417880393456026e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3000/training_args.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ed5d69df2f4458e091aa9fd5be576a7a7349e33ac70704441e5d3b16cf246325
+size 3704

checkpoint-3000/vocab.json ADDED Viewed

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

config.json ADDED Viewed

	@@ -0,0 +1,33 @@

+{
+  "_name_or_path": "Salesforce/codet5p-220m",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "bos_token_id": 1,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 2,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "max_length": 1024,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "use_cache": true,
+  "vocab_size": 32100
+}

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:a87454e3aa158c8448067089cf62318d406cdf9bc61b2df9eee7043db89e980d
+size 891647438

runs/Apr06_17-46-43_babel-3-7/1712440009.733516/events.out.tfevents.1712440009.babel-3-7 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6b5eac974e2a790c10311e084e85da4201106f56fc7e7fc3f44013bb39af6cc3
+size 4975

runs/Apr06_17-46-43_babel-3-7/events.out.tfevents.1712440009.babel-3-7 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:9cee1b29ff8aa600239b18410805959047a70d9ddac9a726506f68d6c8fed8da
+size 3740

runs/Apr06_18-01-45_babel-8-7/1712440910.5851839/events.out.tfevents.1712440910.babel-8-7 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:e2aa99ed2986f5d55e50469c2991c10486f36cac5c2aac9b58ed30e85408c5c0
+size 4975

runs/Apr06_18-01-45_babel-8-7/events.out.tfevents.1712440910.babel-8-7 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:bb7c0be6f56e01ef2bf7edc3dd1f6f9b0e389e589d144f3477cab1ef4aa8bc7e
+size 8924

runs/Apr06_18-01-45_babel-8-7/events.out.tfevents.1712609521.babel-8-7 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:056cbcead4cb7ec2fdd4b5e3c40cb4be3db4704f071eb2959a7a7e53d45ba575
+size 366

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@

tokenizer.json ADDED Viewed

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

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1 @@

trainer_state.json ADDED Viewed

	@@ -0,0 +1,175 @@

+{
+  "best_metric": 96.7742,
+  "best_model_checkpoint": "/data/tir/projects/tir7/user_data/priyansk/qa_tapex_e2_codet5p-220m_latex/checkpoint-2400",
+  "epoch": 1.9998255577306998,
+  "global_step": 3224,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.070409429280397e-05,
+      "loss": 1.8932,
+      "step": 300
+    },
+    {
+      "epoch": 0.19,
+      "eval_exact_match": 69.7581,
+      "eval_loss": 0.006803931202739477,
+      "eval_runtime": 182.7837,
+      "eval_samples_per_second": 2.735,
+      "eval_steps_per_second": 0.175,
+      "step": 300
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 8.140818858560795e-05,
+      "loss": 0.0034,
+      "step": 600
+    },
+    {
+      "epoch": 0.37,
+      "eval_exact_match": 86.4919,
+      "eval_loss": 0.0015783495036885142,
+      "eval_runtime": 139.3342,
+      "eval_samples_per_second": 3.588,
+      "eval_steps_per_second": 0.23,
+      "step": 600
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 7.211228287841191e-05,
+      "loss": 0.0012,
+      "step": 900
+    },
+    {
+      "epoch": 0.56,
+      "eval_exact_match": 92.5403,
+      "eval_loss": 0.00091337546473369,
+      "eval_runtime": 129.2451,
+      "eval_samples_per_second": 3.869,
+      "eval_steps_per_second": 0.248,
+      "step": 900
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 6.28163771712159e-05,
+      "loss": 0.0008,
+      "step": 1200
+    },
+    {
+      "epoch": 0.74,
+      "eval_exact_match": 94.3548,
+      "eval_loss": 0.0006592237623408437,
+      "eval_runtime": 130.2486,
+      "eval_samples_per_second": 3.839,
+      "eval_steps_per_second": 0.246,
+      "step": 1200
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.352047146401985e-05,
+      "loss": 0.0006,
+      "step": 1500
+    },
+    {
+      "epoch": 0.93,
+      "eval_exact_match": 94.5565,
+      "eval_loss": 0.0005109157646074891,
+      "eval_runtime": 127.9056,
+      "eval_samples_per_second": 3.909,
+      "eval_steps_per_second": 0.25,
+      "step": 1500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 4.422456575682382e-05,
+      "loss": 0.0004,
+      "step": 1800
+    },
+    {
+      "epoch": 1.12,
+      "eval_exact_match": 95.3629,
+      "eval_loss": 0.0004209030594211072,
+      "eval_runtime": 129.0896,
+      "eval_samples_per_second": 3.873,
+      "eval_steps_per_second": 0.248,
+      "step": 1800
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 3.4928660049627796e-05,
+      "loss": 0.0004,
+      "step": 2100
+    },
+    {
+      "epoch": 1.3,
+      "eval_exact_match": 95.1613,
+      "eval_loss": 0.00042048218892887235,
+      "eval_runtime": 129.0282,
+      "eval_samples_per_second": 3.875,
+      "eval_steps_per_second": 0.248,
+      "step": 2100
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.563275434243176e-05,
+      "loss": 0.0003,
+      "step": 2400
+    },
+    {
+      "epoch": 1.49,
+      "eval_exact_match": 96.7742,
+      "eval_loss": 0.0003429962380323559,
+      "eval_runtime": 127.2593,
+      "eval_samples_per_second": 3.929,
+      "eval_steps_per_second": 0.251,
+      "step": 2400
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.6336848635235734e-05,
+      "loss": 0.0003,
+      "step": 2700
+    },
+    {
+      "epoch": 1.67,
+      "eval_exact_match": 96.7742,
+      "eval_loss": 0.00032032810850068927,
+      "eval_runtime": 126.2849,
+      "eval_samples_per_second": 3.959,
+      "eval_steps_per_second": 0.253,
+      "step": 2700
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 7.040942928039701e-06,
+      "loss": 0.0003,
+      "step": 3000
+    },
+    {
+      "epoch": 1.86,
+      "eval_exact_match": 96.371,
+      "eval_loss": 0.0003172786091454327,
+      "eval_runtime": 128.5411,
+      "eval_samples_per_second": 3.89,
+      "eval_steps_per_second": 0.249,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "step": 3224,
+      "total_flos": 4.0211486895557837e+18,
+      "train_loss": 0.17688602654646998,
+      "train_runtime": 168482.5606,
+      "train_samples_per_second": 19.598,
+      "train_steps_per_second": 0.019
+    }
+  ],
+  "max_steps": 3224,
+  "num_train_epochs": 2,
+  "total_flos": 4.0211486895557837e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ed5d69df2f4458e091aa9fd5be576a7a7349e33ac70704441e5d3b16cf246325
+size 3704

vocab.json ADDED Viewed

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