Saving weights and logs of epoch 3 - step 5100

ckpt_epoch_3_step_5100/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_3_step_5100/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06524be4de0532bc9f6d74e4f00456689f3c999d48021d8ce64f517d3a8c3180
+size 956799284

ckpt_epoch_3_step_5100/special_tokens_map.json

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

ckpt_epoch_3_step_5100/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:bb55a3d78724c9a55c802522a5ae121712bd605e3f3f200abb43aa69285ec829
-size 3291414
+oid sha256:d4d4abc3763d83debcc6e98d5ee056178a208d1dc41bbbdbe8305e3adec2e176
+size 3363347

report.txt

@@ -514,3 +514,35 @@ Epoch... (3/30 | Step: 4790 | Loss: 1.8843146562576294, Learning Rate: 2.7924143
 Epoch... (3/30 | Step: 4800 | Loss: 1.8721106052398682, Learning Rate: 2.7919808417209424e-05)
 Epoch... (3/30 | Step: 4800 | Loss: 1.8721106052398682, Learning Rate: 2.7919808417209424e-05)
 Epoch... (3/30 | Step: 4800 | Eval Loss: 1.945229411125183 | Eval rouge1: 41.4206 | Eval rouge2: 15.7017 | Eval rougeL: 37.6112 | Eval rougeLsum: 37.6064 | Eval gen_len: 11.2409 |)
+Epoch... (3/30 | Step: 4810 | Loss: 1.8651959896087646, Learning Rate: 2.7915473765460774e-05)
+Epoch... (3/30 | Step: 4820 | Loss: 1.7777526378631592, Learning Rate: 2.7911139113712125e-05)
+Epoch... (3/30 | Step: 4830 | Loss: 1.7878971099853516, Learning Rate: 2.7906804461963475e-05)
+Epoch... (3/30 | Step: 4840 | Loss: 1.9086028337478638, Learning Rate: 2.7902469810214825e-05)
+Epoch... (3/30 | Step: 4850 | Loss: 1.85693359375, Learning Rate: 2.7898135158466175e-05)
+Epoch... (3/30 | Step: 4860 | Loss: 1.829287052154541, Learning Rate: 2.7893800506717525e-05)
+Epoch... (3/30 | Step: 4870 | Loss: 1.8359487056732178, Learning Rate: 2.7889465854968876e-05)
+Epoch... (3/30 | Step: 4880 | Loss: 1.8283047676086426, Learning Rate: 2.7885131203220226e-05)
+Epoch... (3/30 | Step: 4890 | Loss: 1.8907103538513184, Learning Rate: 2.7880796551471576e-05)
+Epoch... (3/30 | Step: 4900 | Loss: 1.900670051574707, Learning Rate: 2.7876461899722926e-05)
+Epoch... (3/30 | Step: 4910 | Loss: 1.8678079843521118, Learning Rate: 2.7872127247974277e-05)
+Epoch... (3/30 | Step: 4920 | Loss: 1.8865406513214111, Learning Rate: 2.7867792596225627e-05)
+Epoch... (3/30 | Step: 4930 | Loss: 1.8659296035766602, Learning Rate: 2.786345976346638e-05)
+Epoch... (3/30 | Step: 4940 | Loss: 1.8259683847427368, Learning Rate: 2.785912511171773e-05)
+Epoch... (3/30 | Step: 4950 | Loss: 1.9121265411376953, Learning Rate: 2.785479045996908e-05)
+Epoch... (3/30 | Step: 4960 | Loss: 1.7606853246688843, Learning Rate: 2.7850453989231028e-05)
+Epoch... (3/30 | Step: 4970 | Loss: 1.9108521938323975, Learning Rate: 2.7846119337482378e-05)
+Epoch... (3/30 | Step: 4980 | Loss: 1.7965797185897827, Learning Rate: 2.7841784685733728e-05)
+Epoch... (3/30 | Step: 4990 | Loss: 1.8254327774047852, Learning Rate: 2.783745003398508e-05)
+Epoch... (3/30 | Step: 5000 | Loss: 1.8682160377502441, Learning Rate: 2.783311538223643e-05)
+Epoch... (3/30 | Step: 5010 | Loss: 1.887736439704895, Learning Rate: 2.782878073048778e-05)
+Epoch... (3/30 | Step: 5020 | Loss: 1.9222376346588135, Learning Rate: 2.7824447897728533e-05)
+Epoch... (3/30 | Step: 5030 | Loss: 1.8068890571594238, Learning Rate: 2.7820113245979883e-05)
+Epoch... (3/30 | Step: 5040 | Loss: 1.877018928527832, Learning Rate: 2.781577677524183e-05)
+Epoch... (3/30 | Step: 5050 | Loss: 1.818298578262329, Learning Rate: 2.781144212349318e-05)
+Epoch... (3/30 | Step: 5060 | Loss: 1.7829349040985107, Learning Rate: 2.780710747174453e-05)
+Epoch... (3/30 | Step: 5070 | Loss: 1.859926462173462, Learning Rate: 2.780277281999588e-05)
+Epoch... (3/30 | Step: 5080 | Loss: 1.8778877258300781, Learning Rate: 2.779843816824723e-05)
+Epoch... (3/30 | Step: 5090 | Loss: 1.8129793405532837, Learning Rate: 2.779410351649858e-05)
+Epoch... (3/30 | Step: 5100 | Loss: 1.9016380310058594, Learning Rate: 2.778976886474993e-05)
+Epoch... (3/30 | Step: 5100 | Loss: 1.9016380310058594, Learning Rate: 2.778976886474993e-05)
+Epoch... (3/30 | Step: 5100 | Eval Loss: 1.9427725076675415 | Eval rouge1: 41.2198 | Eval rouge2: 15.6318 | Eval rougeL: 37.4398 | Eval rougeLsum: 37.4436 | Eval gen_len: 11.1195 |)