Saving weights and logs of epoch 2 - step 2700

ckpt_epoch_2_step_2700/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_2700/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dedc5d4987607859fed8b4ce45f5574cf92ecf046d2263b55fcfc12e6bda68d
+size 956799284

ckpt_epoch_2_step_2700/special_tokens_map.json

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

ckpt_epoch_2_step_2700/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 sha256:3f0ee1dffb1fc6d1b8f2c3b81442f8965e1ee6fd6a641dccba47b50fcd601d6a
-size 1590027
+oid sha256:11e55aaee55ba295b3206dd0ebc81a2a71d40030a982cc3b6be33bba5c0391c4
+size 1648289

report.txt

@@ -256,3 +256,35 @@ Epoch... (2/30 | Step: 2390 | Loss: 2.0162031650543213, Learning Rate: 2.8964455
 Epoch... (2/30 | Step: 2400 | Loss: 1.9704089164733887, Learning Rate: 2.8960121198906563e-05)
 Epoch... (2/30 | Step: 2400 | Loss: 1.9704089164733887, Learning Rate: 2.8960121198906563e-05)
 Epoch... (2/30 | Step: 2400 | Eval Loss: 2.024594306945801 | Eval rouge1: 40.4764 | Eval rouge2: 14.9051 | Eval rougeL: 36.8785 | Eval rougeLsum: 36.8769 | Eval gen_len: 10.8998 |)
+Epoch... (2/30 | Step: 2410 | Loss: 1.992959976196289, Learning Rate: 2.8955786547157913e-05)
+Epoch... (2/30 | Step: 2420 | Loss: 1.9835933446884155, Learning Rate: 2.8951451895409264e-05)
+Epoch... (2/30 | Step: 2430 | Loss: 2.101801872253418, Learning Rate: 2.894711542467121e-05)
+Epoch... (2/30 | Step: 2440 | Loss: 2.038966178894043, Learning Rate: 2.894278077292256e-05)
+Epoch... (2/30 | Step: 2450 | Loss: 1.9256877899169922, Learning Rate: 2.8938447940163314e-05)
+Epoch... (2/30 | Step: 2460 | Loss: 1.9768502712249756, Learning Rate: 2.8934113288414665e-05)
+Epoch... (2/30 | Step: 2470 | Loss: 1.9429033994674683, Learning Rate: 2.8929778636666015e-05)
+Epoch... (2/30 | Step: 2480 | Loss: 2.0289816856384277, Learning Rate: 2.8925443984917365e-05)
+Epoch... (2/30 | Step: 2490 | Loss: 1.983972191810608, Learning Rate: 2.8921109333168715e-05)
+Epoch... (2/30 | Step: 2500 | Loss: 2.0486741065979004, Learning Rate: 2.8916774681420065e-05)
+Epoch... (2/30 | Step: 2510 | Loss: 1.9563899040222168, Learning Rate: 2.8912440029671416e-05)
+Epoch... (2/30 | Step: 2520 | Loss: 2.0897140502929688, Learning Rate: 2.8908103558933362e-05)
+Epoch... (2/30 | Step: 2530 | Loss: 2.080152988433838, Learning Rate: 2.8903768907184713e-05)
+Epoch... (2/30 | Step: 2540 | Loss: 1.9517621994018555, Learning Rate: 2.8899436074425466e-05)
+Epoch... (2/30 | Step: 2550 | Loss: 2.0202088356018066, Learning Rate: 2.8895101422676817e-05)
+Epoch... (2/30 | Step: 2560 | Loss: 1.9686460494995117, Learning Rate: 2.8890766770928167e-05)
+Epoch... (2/30 | Step: 2570 | Loss: 1.897174596786499, Learning Rate: 2.8886432119179517e-05)
+Epoch... (2/30 | Step: 2580 | Loss: 1.9737465381622314, Learning Rate: 2.8882097467430867e-05)
+Epoch... (2/30 | Step: 2590 | Loss: 2.0247108936309814, Learning Rate: 2.8877762815682217e-05)
+Epoch... (2/30 | Step: 2600 | Loss: 2.019479990005493, Learning Rate: 2.8873428163933568e-05)
+Epoch... (2/30 | Step: 2610 | Loss: 1.921512246131897, Learning Rate: 2.8869093512184918e-05)
+Epoch... (2/30 | Step: 2620 | Loss: 2.002574920654297, Learning Rate: 2.8864757041446865e-05)
+Epoch... (2/30 | Step: 2630 | Loss: 1.9710190296173096, Learning Rate: 2.886042420868762e-05)
+Epoch... (2/30 | Step: 2640 | Loss: 2.0847268104553223, Learning Rate: 2.885608955693897e-05)
+Epoch... (2/30 | Step: 2650 | Loss: 1.9489305019378662, Learning Rate: 2.885175490519032e-05)
+Epoch... (2/30 | Step: 2660 | Loss: 1.9855422973632812, Learning Rate: 2.884742025344167e-05)
+Epoch... (2/30 | Step: 2670 | Loss: 2.001290798187256, Learning Rate: 2.884308560169302e-05)
+Epoch... (2/30 | Step: 2680 | Loss: 1.9203612804412842, Learning Rate: 2.883875094994437e-05)
+Epoch... (2/30 | Step: 2690 | Loss: 1.928293228149414, Learning Rate: 2.883441629819572e-05)
+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 |)