Saving weights and logs of epoch 2 - step 3000

ckpt_epoch_2_step_3000/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_2_step_3000/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66b22ea5a0b2a4c77b9c6592a1f9ba764b26e744ab61944e1d6ec81178e75184
+size 956799284

ckpt_epoch_2_step_3000/special_tokens_map.json

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

ckpt_epoch_2_step_3000/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 sha256:11e55aaee55ba295b3206dd0ebc81a2a71d40030a982cc3b6be33bba5c0391c4
-size 1648289
+oid sha256:34d511f9ba292d071293ec42b1b0234544a3433795b853f55a2f74b28ba9af32
+size 1750651

report.txt

@@ -288,3 +288,35 @@ Epoch... (2/30 | Step: 2690 | Loss: 1.928293228149414, Learning Rate: 2.88344162
 Epoch... (2/30 | Step: 2700 | Loss: 2.0274925231933594, Learning Rate: 2.883008164644707e-05)
 Epoch... (2/30 | Step: 2700 | Loss: 2.0274925231933594, Learning Rate: 2.883008164644707e-05)
 Epoch... (2/30 | Step: 2700 | Eval Loss: 2.009991407394409 | Eval rouge1: 40.5888 | Eval rouge2: 15.0982 | Eval rougeL: 36.9127 | Eval rougeLsum: 36.9165 | Eval gen_len: 10.6976 |)
+Epoch... (2/30 | Step: 2710 | Loss: 1.939640760421753, Learning Rate: 2.8825745175709017e-05)
+Epoch... (2/30 | Step: 2720 | Loss: 1.9807898998260498, Learning Rate: 2.882141234294977e-05)
+Epoch... (2/30 | Step: 2730 | Loss: 1.9780454635620117, Learning Rate: 2.881707769120112e-05)
+Epoch... (2/30 | Step: 2740 | Loss: 1.9607644081115723, Learning Rate: 2.881274303945247e-05)
+Epoch... (2/30 | Step: 2750 | Loss: 1.9642720222473145, Learning Rate: 2.880840838770382e-05)
+Epoch... (2/30 | Step: 2760 | Loss: 2.0490057468414307, Learning Rate: 2.880407373595517e-05)
+Epoch... (2/30 | Step: 2770 | Loss: 1.982258915901184, Learning Rate: 2.879973908420652e-05)
+Epoch... (2/30 | Step: 2780 | Loss: 1.9002817869186401, Learning Rate: 2.8795404432457872e-05)
+Epoch... (2/30 | Step: 2790 | Loss: 1.9543405771255493, Learning Rate: 2.8791069780709222e-05)
+Epoch... (2/30 | Step: 2800 | Loss: 1.924607753753662, Learning Rate: 2.8786735128960572e-05)
+Epoch... (2/30 | Step: 2810 | Loss: 1.9794992208480835, Learning Rate: 2.8782402296201326e-05)
+Epoch... (2/30 | Step: 2820 | Loss: 1.9884564876556396, Learning Rate: 2.8778065825463273e-05)
+Epoch... (2/30 | Step: 2830 | Loss: 2.0604281425476074, Learning Rate: 2.8773731173714623e-05)
+Epoch... (2/30 | Step: 2840 | Loss: 1.9901032447814941, Learning Rate: 2.8769396521965973e-05)
+Epoch... (2/30 | Step: 2850 | Loss: 1.9847352504730225, Learning Rate: 2.8765061870217323e-05)
+Epoch... (2/30 | Step: 2860 | Loss: 1.9160382747650146, Learning Rate: 2.8760727218468674e-05)
+Epoch... (2/30 | Step: 2870 | Loss: 2.013071060180664, Learning Rate: 2.8756392566720024e-05)
+Epoch... (2/30 | Step: 2880 | Loss: 2.004521369934082, Learning Rate: 2.8752057914971374e-05)
+Epoch... (2/30 | Step: 2890 | Loss: 1.962958812713623, Learning Rate: 2.8747723263222724e-05)
+Epoch... (2/30 | Step: 2900 | Loss: 2.002131223678589, Learning Rate: 2.8743390430463478e-05)
+Epoch... (2/30 | Step: 2910 | Loss: 1.8968100547790527, Learning Rate: 2.8739053959725425e-05)
+Epoch... (2/30 | Step: 2920 | Loss: 1.9270609617233276, Learning Rate: 2.8734719307976775e-05)
+Epoch... (2/30 | Step: 2930 | Loss: 1.918048620223999, Learning Rate: 2.8730384656228125e-05)
+Epoch... (2/30 | Step: 2940 | Loss: 2.055185317993164, Learning Rate: 2.8726050004479475e-05)
+Epoch... (2/30 | Step: 2950 | Loss: 1.998548984527588, Learning Rate: 2.8721715352730826e-05)
+Epoch... (2/30 | Step: 2960 | Loss: 1.9728754758834839, Learning Rate: 2.8717380700982176e-05)
+Epoch... (2/30 | Step: 2970 | Loss: 2.0119190216064453, Learning Rate: 2.8713046049233526e-05)
+Epoch... (2/30 | Step: 2980 | Loss: 1.9915521144866943, Learning Rate: 2.870871321647428e-05)
+Epoch... (2/30 | Step: 2990 | Loss: 2.039159059524536, Learning Rate: 2.870437856472563e-05)
+Epoch... (2/30 | Step: 3000 | Loss: 1.9609485864639282, Learning Rate: 2.870004391297698e-05)
+Epoch... (2/30 | Step: 3000 | Loss: 1.9609485864639282, Learning Rate: 2.870004391297698e-05)
+Epoch... (2/30 | Step: 3000 | Eval Loss: 1.9941604137420654 | Eval rouge1: 40.6226 | Eval rouge2: 15.1062 | Eval rougeL: 36.9129 | Eval rougeLsum: 36.9145 | Eval gen_len: 11.0414 |)