Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "facebook/blenderbot-400M-distill",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "BlenderbotForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1280,
+  "decoder_attention_heads": 32,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 1,
+  "do_blenderbot_90_layernorm": true,
+  "dropout": 0.1,
+  "encoder_attention_heads": 32,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 2,
+  "encoder_no_repeat_ngram_size": 3,
+  "eos_token_id": 2,
+  "extra_layer_norm": false,
+  "extra_pos_embeddings": 0,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layernorm_variant": "prelayernorm",
+  "length_penalty": 0.65,
+  "max_length": 60,
+  "max_position_embeddings": 128,
+  "min_length": 20,
+  "model_type": "blenderbot",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": true,
+  "normalize_embedding": false,
+  "num_beams": 10,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true
+  },
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.30.2",
+  "unk_token_id": 3,
+  "use_cache": true,
+  "vocab_size": 8008
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55f0b154c3a23c697c8c30bfce49799c4ab75077b6cc1e16c9daa39f16f98fcd
+size 376782173

runs/Jun19_11-25-05_f7a7e150ad40/events.out.tfevents.1687174091.f7a7e150ad40.585.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78094e031be0d973e777e1a0f5cebd0682ee597155af1d0d1b7abc85c1c76530
+size 5471

runs/Jun19_11-32-41_f7a7e150ad40/events.out.tfevents.1687174372.f7a7e150ad40.585.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b821c1d276ee2ee2b5bb88778756cd04be2cb26cd703b32aaf3c288a412247f4
+size 5630

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdcb8fb9880f50314e832f552b1406015517fbf5ad7785563ac827aef0903907
+size 4027