Training in progress, step 100

last-checkpoint/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "google/mt5-base",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "length_penalty": 0.6,
+  "max_length": 128,
+  "model_type": "mt5",
+  "no_repeat_ngram_size": 2,
+  "num_beams": 15,
+  "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,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 250112
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "length_penalty": 0.6,
+  "max_length": 128,
+  "no_repeat_ngram_size": 2,
+  "num_beams": 15,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.0"
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51de8664109e5d5e63f0c828d4cbab473f0c82ddab1a583ec076b8095bdcfe99
+size 4114757

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:101a1e8e02f10943267c3bb40ba908780d0453bf54e5e78c7a398c0206c0ebad
+size 2329702453

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97cc86a4e67cde0dc190909499b5813a886ab48bdd6a7ca024185736b4be7fef
+size 14575

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32e5e0b3596a5ecd83b615a9a0050e25b48c4ad042ce2a30bcb2dbf1c125452f
+size 627

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

last-checkpoint/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faaa6405f5f79c9e788c7980874a9a3b5b0aea07b53bd9243bf1abb8f5c49c81
+size 16330467

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "google/mt5-base",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.19726297620515348,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.555555555555555e-05,
+      "loss": 13.7427,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0001111111111111111,
+      "loss": 8.8821,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00016666666666666666,
+      "loss": 2.5857,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0002222222222222222,
+      "loss": 1.3518,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 1.0054,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0003333333333333333,
+      "loss": 0.864,
+      "step": 60
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0003888888888888889,
+      "loss": 0.8669,
+      "step": 70
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0004444444444444444,
+      "loss": 0.9395,
+      "step": 80
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0005,
+      "loss": 1.0424,
+      "step": 90
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0004985515643105447,
+      "loss": 0.6298,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.61441171169281,
+      "eval_rouge1": 0.07727272727272727,
+      "eval_rouge2": 0.061111111111111116,
+      "eval_rougeL": 0.06893939393939394,
+      "eval_rougeLsum": 0.08333333333333333,
+      "eval_runtime": 91.9317,
+      "eval_samples_per_second": 0.218,
+      "eval_steps_per_second": 0.218,
+      "step": 100
+    }
+  ],
+  "max_steps": 3542,
+  "num_train_epochs": 7,
+  "total_flos": 2453150026229760.0,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02a84220d3a59b7a986ddfb062b9ea9e9a45a0ff5e854f1a86b7727559daa3d2
+size 3643

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e4b616d5ea5f92c203d471e43b622d1302d66f27b9105c5655030fdf5c7e986
+oid sha256:101a1e8e02f10943267c3bb40ba908780d0453bf54e5e78c7a398c0206c0ebad
 size 2329702453

runs/Feb08_05-21-08_74bc69b4becb/1675833723.9550111/events.out.tfevents.1675833723.74bc69b4becb.290.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4547dfe6926e563cf50a46695c434787ffd8d2e67d546ec0b317c19842f0fdbc
+size 5996

runs/Feb08_05-21-08_74bc69b4becb/events.out.tfevents.1675833723.74bc69b4becb.290.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067026e4bf9872770c76803d3d20fa01d953054701a5dcf40f28538b819e86a5
+size 4406

runs/Feb08_05-23-30_74bc69b4becb/1675834021.2616234/events.out.tfevents.1675834021.74bc69b4becb.290.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee9a3316adea1e00cf9d7153c0e3c581a403f0423e2aa76f4b25682cb99809a4
+size 5952

runs/Feb08_05-23-30_74bc69b4becb/events.out.tfevents.1675834021.74bc69b4becb.290.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e815e6c7999e0ec7171fc4bf62b2c2607b5f4c365e56c7c114a0a4fcea86dd9
+size 5441

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6d7f5e0285ec23a503467b1ee444fab5d16c2973f11145a27b8b56c9ce26c1e
+oid sha256:02a84220d3a59b7a986ddfb062b9ea9e9a45a0ff5e854f1a86b7727559daa3d2
 size 3643