Saving weights and logs of epoch 1 - step 2000

ckpt_epoch_1_step_2000/config.json

@@ -0,0 +1,174 @@
+{
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "bos_token_id": 50256,
+  "decoder": {
+    "_name_or_path": "gpt2",
+    "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,
+    "cross_attention_hidden_size": null,
+    "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,
+    "reorder_and_upcast_attn": false,
+    "repetition_penalty": 1.0,
+    "resid_pdrop": 0.1,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_attn_by_inverse_layer_idx": 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": "4.15.0.dev0",
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50257
+  },
+  "decoder_start_token_id": 50256,
+  "encoder": {
+    "_name_or_path": "google/vit-base-patch16-224-in21k",
+    "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,
+    "cross_attention_hidden_size": null,
+    "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": {},
+    "qkv_bias": true,
+    "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": "4.15.0.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_1_step_2000/eval_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_gen_len": 12.234496,
+    "eval_loss": 2.015309,
+    "eval_rouge1": 40.086076,
+    "eval_rouge2": 14.637774,
+    "eval_rougeL": 36.357252,
+    "eval_rougeLsum": 36.360759
+}

ckpt_epoch_1_step_2000/flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9546c4bdaff52ab8d9aab7dfcea610da10fe0b0f24e2a0d1c35e7b5f9853c55
+size 956799284

ckpt_epoch_1_step_2000/special_tokens_map.json

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

ckpt_epoch_1_step_2000/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.1640096976.t1v-n-ca5bb87c-w-0.29764.0.v2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:219fa39bf6ea9cbc1e845c3ad236a19bf3911b73fadb8ed0a061a20408c66266
-size 16622782
+oid sha256:a2904a0662817e84a1449b62d5dfbfca069dc3b9d3218645f323f321a1ecc1cd
+size 29513204

log

@@ -151,3 +151,54 @@ Epoch... (1/1 | Step: 1480 | Loss: 2.0253396034240723 | Learning Rate: 1.0767230
 Epoch... (1/1 | Step: 1490 | Loss: 2.109578847885132 | Learning Rate: 1.0637191735440865e-05 | Time per step: 0.14524603322048316)
 Epoch... (1/1 | Step: 1500 | Loss: 1.9973983764648438 | Learning Rate: 1.050715127348667e-05 | Time per step: 0.14455435609817505)
 Epoch... (1/1 | Step: 1500 | Eval Loss: 2.0347542762756348 | Eval rouge1: 39.720462 | Eval rouge2: 14.404286 | Eval rougeL: 35.987809 | Eval rougeLsum: 35.987896 | Eval gen_len: 12.283868 |)
+Epoch... (1/1 | Step: 1510 | Loss: 2.17781400680542 | Learning Rate: 1.0377112630521879e-05 | Time per step: 0.14389628906123686)
+Epoch... (1/1 | Step: 1520 | Loss: 2.156275987625122 | Learning Rate: 1.0247073078062385e-05 | Time per step: 0.1432325072978672)
+Epoch... (1/1 | Step: 1530 | Loss: 1.998096227645874 | Learning Rate: 1.0117034435097594e-05 | Time per step: 0.1425560083264619)
+Epoch... (1/1 | Step: 1540 | Loss: 1.9965381622314453 | Learning Rate: 9.986995792132802e-06 | Time per step: 0.14192123614348373)
+Epoch... (1/1 | Step: 1550 | Loss: 2.104810953140259 | Learning Rate: 9.85695714916801e-06 | Time per step: 0.14126326391773839)
+Epoch... (1/1 | Step: 1560 | Loss: 2.025113344192505 | Learning Rate: 9.72691850620322e-06 | Time per step: 0.1406068211946732)
+Epoch... (1/1 | Step: 1570 | Loss: 2.1913187503814697 | Learning Rate: 9.596878953743726e-06 | Time per step: 0.1399633161581246)
+Epoch... (1/1 | Step: 1580 | Loss: 2.0058059692382812 | Learning Rate: 9.466840310778935e-06 | Time per step: 0.13934056834329533)
+Epoch... (1/1 | Step: 1590 | Loss: 2.0531082153320312 | Learning Rate: 9.336801667814143e-06 | Time per step: 0.1387292352112584)
+Epoch... (1/1 | Step: 1600 | Loss: 2.1364736557006836 | Learning Rate: 9.206763024849351e-06 | Time per step: 0.1381152728199959)
+Epoch... (1/1 | Step: 1610 | Loss: 2.1336679458618164 | Learning Rate: 9.076721653400455e-06 | Time per step: 0.1375143773807502)
+Epoch... (1/1 | Step: 1620 | Loss: 2.076136589050293 | Learning Rate: 8.946683010435663e-06 | Time per step: 0.13704783474957502)
+Epoch... (1/1 | Step: 1630 | Loss: 2.0940370559692383 | Learning Rate: 8.816644367470872e-06 | Time per step: 0.13645588005978637)
+Epoch... (1/1 | Step: 1640 | Loss: 2.052903652191162 | Learning Rate: 8.68660572450608e-06 | Time per step: 0.1358662321800139)
+Epoch... (1/1 | Step: 1650 | Loss: 2.0199592113494873 | Learning Rate: 8.556566172046587e-06 | Time per step: 0.13528442931897713)
+Epoch... (1/1 | Step: 1660 | Loss: 2.0727717876434326 | Learning Rate: 8.426527529081795e-06 | Time per step: 0.1346998906997313)
+Epoch... (1/1 | Step: 1670 | Loss: 2.0786218643188477 | Learning Rate: 8.296488886117004e-06 | Time per step: 0.13415220112143877)
+Epoch... (1/1 | Step: 1680 | Loss: 1.9562125205993652 | Learning Rate: 8.166450243152212e-06 | Time per step: 0.13373985659508478)
+Epoch... (1/1 | Step: 1690 | Loss: 2.0937490463256836 | Learning Rate: 8.03641160018742e-06 | Time per step: 0.1331933374235616)
+Epoch... (1/1 | Step: 1700 | Loss: 2.078627586364746 | Learning Rate: 7.906372047727928e-06 | Time per step: 0.13263628118178425)
+Epoch... (1/1 | Step: 1710 | Loss: 2.112215518951416 | Learning Rate: 7.776333404763136e-06 | Time per step: 0.13209281176851506)
+Epoch... (1/1 | Step: 1720 | Loss: 1.9597207307815552 | Learning Rate: 7.646294761798345e-06 | Time per step: 0.13154547491738963)
+Epoch... (1/1 | Step: 1730 | Loss: 2.0493929386138916 | Learning Rate: 7.516253845096799e-06 | Time per step: 0.131024552356301)
+Epoch... (1/1 | Step: 1740 | Loss: 2.0585577487945557 | Learning Rate: 7.386215202132007e-06 | Time per step: 0.1304960524898836)
+Epoch... (1/1 | Step: 1750 | Loss: 1.970508098602295 | Learning Rate: 7.256176104419865e-06 | Time per step: 0.12997342341286797)
+Epoch... (1/1 | Step: 1760 | Loss: 2.0194671154022217 | Learning Rate: 7.126137461455073e-06 | Time per step: 0.12945761531591415)
+Epoch... (1/1 | Step: 1770 | Loss: 2.0107901096343994 | Learning Rate: 6.996098363742931e-06 | Time per step: 0.1289362097864097)
+Epoch... (1/1 | Step: 1780 | Loss: 2.120974063873291 | Learning Rate: 6.866059720778139e-06 | Time per step: 0.12843746643387868)
+Epoch... (1/1 | Step: 1790 | Loss: 2.1194677352905273 | Learning Rate: 6.736021077813348e-06 | Time per step: 0.12795682739279124)
+Epoch... (1/1 | Step: 1800 | Loss: 2.0729482173919678 | Learning Rate: 6.605981980101205e-06 | Time per step: 0.1274824545118544)
+Epoch... (1/1 | Step: 1810 | Loss: 2.0226759910583496 | Learning Rate: 6.475943337136414e-06 | Time per step: 0.12700373612714735)
+Epoch... (1/1 | Step: 1820 | Loss: 2.0213565826416016 | Learning Rate: 6.3459042394242715e-06 | Time per step: 0.12653065959175863)
+Epoch... (1/1 | Step: 1830 | Loss: 2.0867295265197754 | Learning Rate: 6.21586559645948e-06 | Time per step: 0.1260442264744493)
+Epoch... (1/1 | Step: 1840 | Loss: 2.053117275238037 | Learning Rate: 6.085824679757934e-06 | Time per step: 0.12557031317897466)
+Epoch... (1/1 | Step: 1850 | Loss: 2.0554451942443848 | Learning Rate: 5.9557860367931426e-06 | Time per step: 0.12511137382404225)
+Epoch... (1/1 | Step: 1860 | Loss: 2.066519260406494 | Learning Rate: 5.825746939081e-06 | Time per step: 0.12466220983894923)
+Epoch... (1/1 | Step: 1870 | Loss: 1.9540824890136719 | Learning Rate: 5.695708296116209e-06 | Time per step: 0.12421020441514286)
+Epoch... (1/1 | Step: 1880 | Loss: 2.027324676513672 | Learning Rate: 5.565669198404066e-06 | Time per step: 0.12376356746288056)
+Epoch... (1/1 | Step: 1890 | Loss: 2.067963123321533 | Learning Rate: 5.435630555439275e-06 | Time per step: 0.12333493194882832)
+Epoch... (1/1 | Step: 1900 | Loss: 2.079224109649658 | Learning Rate: 5.305591912474483e-06 | Time per step: 0.12303855419158935)
+Epoch... (1/1 | Step: 1910 | Loss: 1.979988932609558 | Learning Rate: 5.175552814762341e-06 | Time per step: 0.12260543825738718)
+Epoch... (1/1 | Step: 1920 | Loss: 2.013458013534546 | Learning Rate: 5.045514171797549e-06 | Time per step: 0.12217357369760672)
+Epoch... (1/1 | Step: 1930 | Loss: 1.9864708185195923 | Learning Rate: 4.915475074085407e-06 | Time per step: 0.12175397489972682)
+Epoch... (1/1 | Step: 1940 | Loss: 2.100825548171997 | Learning Rate: 4.7854364311206155e-06 | Time per step: 0.12133047445533202)
+Epoch... (1/1 | Step: 1950 | Loss: 2.047811508178711 | Learning Rate: 4.655397333408473e-06 | Time per step: 0.12102636288373898)
+Epoch... (1/1 | Step: 1960 | Loss: 2.0417799949645996 | Learning Rate: 4.525356871454278e-06 | Time per step: 0.12062084309908809)
+Epoch... (1/1 | Step: 1970 | Loss: 2.0019946098327637 | Learning Rate: 4.395317773742136e-06 | Time per step: 0.12022043254774839)
+Epoch... (1/1 | Step: 1980 | Loss: 1.9874119758605957 | Learning Rate: 4.265279130777344e-06 | Time per step: 0.11983201431505608)
+Epoch... (1/1 | Step: 1990 | Loss: 2.0997118949890137 | Learning Rate: 4.135240033065202e-06 | Time per step: 0.11945154547092303)
+Epoch... (1/1 | Step: 2000 | Loss: 2.0525479316711426 | Learning Rate: 4.00520139010041e-06 | Time per step: 0.11918327701091766)
+Epoch... (1/1 | Step: 2000 | Eval Loss: 2.0153088569641113 | Eval rouge1: 40.086076 | Eval rouge2: 14.637774 | Eval rougeL: 36.357252 | Eval rougeLsum: 36.360759 | Eval gen_len: 12.234496 |)