Saving weights and logs of epoch 4 - step 7200

ckpt_epoch_4_step_7200/config.json

@@ -0,0 +1,169 @@
+{
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "bos_token_id": 50256,
+  "decoder": {
+    "_name_or_path": "",
+    "activation_function": "gelu_new",
+    "add_cross_attention": true,
+    "architectures": [
+      "GPT2LMHeadModel"
+    ],
+    "attn_pdrop": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": 50256,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": 50256,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "embd_pdrop": 0.1,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 50256,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "gpt2",
+    "n_ctx": 1024,
+    "n_embd": 768,
+    "n_head": 12,
+    "n_inner": null,
+    "n_layer": 12,
+    "n_positions": 1024,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 50256,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "resid_pdrop": 0.1,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_attn_weights": true,
+    "sep_token_id": null,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "task_specific_params": {
+      "text-generation": {
+        "do_sample": true,
+        "max_length": 50
+      }
+    },
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.11.0.dev0",
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50257
+  },
+  "decoder_start_token_id": 50256,
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": [
+      "ViTModel"
+    ],
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "vit",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.11.0.dev0",
+    "use_bfloat16": false
+  },
+  "eos_token_id": 50256,
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 50256,
+  "transformers_version": null
+}

ckpt_epoch_4_step_7200/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78db68de57bc771bfe501fa3884572249b89a13f8b6d25532d2c6f025285ba1a
+size 956799284

ckpt_epoch_4_step_7200/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}

ckpt_epoch_4_step_7200/tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}

events.out.tfevents.1633443513.t1v-n-bb5dfd23-w-0.8655.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7341bd597335e3f95a63cb1a0ef26806020a736a39a981b86189d9ffc77b94b1
-size 5060665
+oid sha256:20b19c529af9183cffca5133d6675e3627f6ad4ade4154664a7e14dd552b76d1
+size 5102169

report.txt

@@ -742,3 +742,33 @@ Epoch... (3/30 | Step: 6910 | Loss: 1.823469877243042, Learning Rate: 2.70052005
 Epoch... (3/30 | Step: 6920 | Loss: 1.7423064708709717, Learning Rate: 2.700086588447448e-05)
 Epoch... (3/30 | Step: 6921 | Loss: 1.853652000427246, Learning Rate: 2.7000432964996435e-05)
 Epoch... (3/30 | Step: 6921 | Eval Loss: 1.9094812870025635 | Eval rouge1: 41.5037 | Eval rouge2: 15.8267 | Eval rougeL: 37.7187 | Eval rougeLsum: 37.7205 | Eval gen_len: 11.1947 |)
+Epoch... (4/30 | Step: 6930 | Loss: 1.8121541738510132, Learning Rate: 2.699653123272583e-05)
+Epoch... (4/30 | Step: 6940 | Loss: 1.7851512432098389, Learning Rate: 2.699219658097718e-05)
+Epoch... (4/30 | Step: 6950 | Loss: 1.7677934169769287, Learning Rate: 2.698786192922853e-05)
+Epoch... (4/30 | Step: 6960 | Loss: 1.926886796951294, Learning Rate: 2.698352727747988e-05)
+Epoch... (4/30 | Step: 6970 | Loss: 1.8334335088729858, Learning Rate: 2.6979194444720633e-05)
+Epoch... (4/30 | Step: 6980 | Loss: 1.7968392372131348, Learning Rate: 2.697485797398258e-05)
+Epoch... (4/30 | Step: 6990 | Loss: 1.782883882522583, Learning Rate: 2.697052332223393e-05)
+Epoch... (4/30 | Step: 7000 | Loss: 1.779791235923767, Learning Rate: 2.696618867048528e-05)
+Epoch... (4/30 | Step: 7010 | Loss: 1.737504243850708, Learning Rate: 2.696185401873663e-05)
+Epoch... (4/30 | Step: 7020 | Loss: 1.802125096321106, Learning Rate: 2.695751936698798e-05)
+Epoch... (4/30 | Step: 7030 | Loss: 1.718970537185669, Learning Rate: 2.695318471523933e-05)
+Epoch... (4/30 | Step: 7040 | Loss: 1.7862560749053955, Learning Rate: 2.694885006349068e-05)
+Epoch... (4/30 | Step: 7050 | Loss: 1.7417529821395874, Learning Rate: 2.694451541174203e-05)
+Epoch... (4/30 | Step: 7060 | Loss: 1.7511889934539795, Learning Rate: 2.6940182578982785e-05)
+Epoch... (4/30 | Step: 7070 | Loss: 1.7609820365905762, Learning Rate: 2.6935847927234136e-05)
+Epoch... (4/30 | Step: 7080 | Loss: 1.7393269538879395, Learning Rate: 2.6931513275485486e-05)
+Epoch... (4/30 | Step: 7090 | Loss: 1.775388240814209, Learning Rate: 2.6927176804747432e-05)
+Epoch... (4/30 | Step: 7100 | Loss: 1.701842188835144, Learning Rate: 2.6922842152998783e-05)
+Epoch... (4/30 | Step: 7110 | Loss: 1.7280645370483398, Learning Rate: 2.6918507501250133e-05)
+Epoch... (4/30 | Step: 7120 | Loss: 1.8140801191329956, Learning Rate: 2.6914172849501483e-05)
+Epoch... (4/30 | Step: 7130 | Loss: 1.7440757751464844, Learning Rate: 2.6909838197752833e-05)
+Epoch... (4/30 | Step: 7140 | Loss: 1.7221659421920776, Learning Rate: 2.6905503546004184e-05)
+Epoch... (4/30 | Step: 7150 | Loss: 1.8911354541778564, Learning Rate: 2.6901170713244937e-05)
+Epoch... (4/30 | Step: 7160 | Loss: 1.8129518032073975, Learning Rate: 2.6896836061496288e-05)
+Epoch... (4/30 | Step: 7170 | Loss: 1.6905957460403442, Learning Rate: 2.6892501409747638e-05)
+Epoch... (4/30 | Step: 7180 | Loss: 1.8244552612304688, Learning Rate: 2.6888164939009584e-05)
+Epoch... (4/30 | Step: 7190 | Loss: 1.6994915008544922, Learning Rate: 2.6883830287260935e-05)
+Epoch... (4/30 | Step: 7200 | Loss: 1.7174403667449951, Learning Rate: 2.6879495635512285e-05)
+Epoch... (4/30 | Step: 7200 | Loss: 1.7174403667449951, Learning Rate: 2.6879495635512285e-05)
+Epoch... (4/30 | Step: 7200 | Eval Loss: 1.9161072969436646 | Eval rouge1: 41.0556 | Eval rouge2: 15.4661 | Eval rougeL: 37.362 | Eval rougeLsum: 37.3581 | Eval gen_len: 11.3905 |)