Kavo

checkpoint-6000/config.json

@@ -0,0 +1,67 @@
+{
+  "_name_or_path": "humarin/chatgpt_paraphraser_on_T5_base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "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": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "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,
+  "task_specific_params": {
+    "paraphrase": {
+      "early_stopping": true,
+      "max_length": 128,
+      "num_beams": 5,
+      "prefix": "paraphrase: "
+    },
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 32128
+}

checkpoint-6000/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.33.3"
+}

checkpoint-6000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:effae120ad7a1a1e9310981d081d7aaa7934f13679b679d46e8a4f19f10854e7
+size 1783444357

checkpoint-6000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f561d1fd9b6bd42f3c854c28b2b92d5feadfaf20718a64d7a40a6839947f9de4
+size 891702929

checkpoint-6000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f1c3184a7f82c61da74caaf741a4af60a240c3cda5b9ba2cd16c235313ce28f
+size 14575

checkpoint-6000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:495b356d251f35bfdd9031c851adb2bb9ac7a1380504ac33af6d3ca3560c6453
+size 627

checkpoint-6000/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.903694144216809,
+  "eval_steps": 2000,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.3865763149403035e-05,
+      "loss": 0.0452,
+      "step": 2000
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 0.0001345932250842452,
+      "eval_runtime": 53.5976,
+      "eval_samples_per_second": 157.899,
+      "eval_steps_per_second": 19.74,
+      "step": 2000
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.7731526298806067e-05,
+      "loss": 0.0006,
+      "step": 4000
+    },
+    {
+      "epoch": 1.94,
+      "eval_loss": 0.00010070026473840699,
+      "eval_runtime": 54.3295,
+      "eval_samples_per_second": 155.772,
+      "eval_steps_per_second": 19.474,
+      "step": 4000
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 1.5972894482090998e-06,
+      "loss": 0.0004,
+      "step": 6000
+    },
+    {
+      "epoch": 2.9,
+      "eval_loss": 8.544776937924325e-05,
+      "eval_runtime": 54.82,
+      "eval_samples_per_second": 154.378,
+      "eval_steps_per_second": 19.3,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 6198,
+  "num_train_epochs": 3,
+  "save_steps": 2000,
+  "total_flos": 5.754652065792e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e65c8d07daa4e6a39589bd7f9bf6d699192e95231984fbfdfcf683dc3d5834a0
+size 4091

logs/events.out.tfevents.1695922789.36e5a0a3949d.1594.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22d44a9bfdb6fc6e8385c5a5781f9db7918f3f243d1f45f3b7a81668cd0a27b4
+size 6861

logs/events.out.tfevents.1695930026.36e5a0a3949d.1594.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2532a4681cd8c59f69b00057943fd764d3017274ad833de397e42a30d0f7391
+size 359