Training in progress, step 200, checkpoint

last-checkpoint/config.json

@@ -1,62 +1,39 @@
 {
-  "_name_or_path": "google/flan-t5-base",
+  "_name_or_path": "allmalab/gpt2-aze",
+  "activation_function": "gelu_new",
   "architectures": [
-    "T5ForConditionalGeneration"
+    "GPT2LMHeadModel"
   ],
-  "classifier_dropout": 0.0,
-  "d_ff": 2048,
-  "d_kv": 64,
-  "d_model": 768,
-  "decoder_start_token_id": 0,
-  "dense_act_fn": "gelu_new",
-  "dropout_rate": 0.1,
-  "eos_token_id": 1,
-  "feed_forward_proj": "gated-gelu",
-  "initializer_factor": 1.0,
-  "is_encoder_decoder": true,
-  "is_gated_act": true,
-  "layer_norm_epsilon": 1e-06,
-  "model_type": "t5",
-  "n_positions": 512,
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
-  "output_past": true,
-  "pad_token_id": 0,
-  "relative_attention_max_distance": 128,
-  "relative_attention_num_buckets": 32,
+  "attn_pdrop": 0,
+  "bos_token_id": 11,
+  "embd_pdrop": 0,
+  "eos_token_id": 12,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
   "task_specific_params": {
-    "summarization": {
-      "early_stopping": true,
-      "length_penalty": 2.0,
-      "max_length": 200,
-      "min_length": 30,
-      "no_repeat_ngram_size": 3,
-      "num_beams": 4,
-      "prefix": "summarize: "
-    },
-    "translation_en_to_de": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to German: "
-    },
-    "translation_en_to_fr": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to French: "
-    },
-    "translation_en_to_ro": {
-      "early_stopping": true,
-      "max_length": 300,
-      "num_beams": 4,
-      "prefix": "translate English to Romanian: "
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
     }
   },
-  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.49.0",
   "use_cache": true,
-  "vocab_size": 32103
+  "vocab_size": 64003
 }

last-checkpoint/generation_config.json

@@ -1,6 +1,6 @@
 {
-  "decoder_start_token_id": 0,
-  "eos_token_id": 1,
-  "pad_token_id": 0,
+  "_from_model_config": true,
+  "bos_token_id": 11,
+  "eos_token_id": 12,
   "transformers_version": "4.49.0"
 }

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:779549eacf5a18b37319e66bf14475b161dd4433549e850971a454b5266d4eb0
-size 990191464
+oid sha256:757ad62f4ea26e898b3b9b185d741bcfc0f7b27dc79d116ce13e3d2182299eb4
+size 540001920

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dccba7d5cd5e9593985197edaea56591d66d860b7cc48b065cdea5202db56bd
-size 1980553210
+oid sha256:130c575e1cb9ab89e4dc38eac6917525ce5de05624065a5f7c77ffcf4ad891ca
+size 1080097722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de7fb8a41dbba15b3b8bc11390e2d7ddfe33c799d6cf98b8039e15d400789fe3
+oid sha256:9ffcb25428d146633ce210a40c9c5329ef07f7e8ca498959bffcf2c559d69eea
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72c1b866fa528cbddaa344b3307a55102bdc990e6cf82a6d36d368c2a421c816
+oid sha256:ae4ecdb1b8aee070470f06546bc65633fa4bdcb826c1df9b2e617eb80bcc34ab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,177 +1,40 @@
 {
-  "best_metric": 0.6030490398406982,
-  "best_model_checkpoint": "./aztelecom_t5_finetuned/checkpoint-1000",
-  "epoch": 10.0,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8691588785046729,
   "eval_steps": 500,
-  "global_step": 1070,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.4672897196261682,
-      "grad_norm": 95.7200927734375,
+      "grad_norm": 212.5613250732422,
       "learning_rate": 1.4018691588785047e-05,
-      "loss": 24.3127,
+      "loss": 53.6674,
       "step": 50
     },
     {
       "epoch": 0.9345794392523364,
-      "grad_norm": 8.241812705993652,
+      "grad_norm": 208.6332550048828,
       "learning_rate": 2.8037383177570094e-05,
-      "loss": 8.7035,
+      "loss": 22.0835,
       "step": 100
     },
     {
       "epoch": 1.4018691588785046,
-      "grad_norm": 6.154674530029297,
+      "grad_norm": 40.16309356689453,
       "learning_rate": 2.7699933091326993e-05,
-      "loss": 2.6262,
+      "loss": 6.2918,
       "step": 150
     },
     {
       "epoch": 1.8691588785046729,
-      "grad_norm": 1.0018048286437988,
+      "grad_norm": 12.063589096069336,
       "learning_rate": 2.0245088641574458e-05,
-      "loss": 1.4122,
+      "loss": 5.0856,
       "step": 200
-    },
-    {
-      "epoch": 2.336448598130841,
-      "grad_norm": 0.5541874170303345,
-      "learning_rate": 1.0635487465051559e-05,
-      "loss": 1.0114,
-      "step": 250
-    },
-    {
-      "epoch": 2.803738317757009,
-      "grad_norm": 0.4578002691268921,
-      "learning_rate": 2.8188898746283444e-06,
-      "loss": 0.9539,
-      "step": 300
-    },
-    {
-      "epoch": 3.2710280373831777,
-      "grad_norm": 0.5540403723716736,
-      "learning_rate": 6.464906595023967e-09,
-      "loss": 0.9415,
-      "step": 350
-    },
-    {
-      "epoch": 3.7383177570093458,
-      "grad_norm": 6.799459457397461,
-      "learning_rate": 3.3535965844688068e-06,
-      "loss": 0.9212,
-      "step": 400
-    },
-    {
-      "epoch": 4.205607476635514,
-      "grad_norm": 0.5957446098327637,
-      "learning_rate": 1.1485235792565021e-05,
-      "loss": 0.8961,
-      "step": 450
-    },
-    {
-      "epoch": 4.672897196261682,
-      "grad_norm": 0.44224458932876587,
-      "learning_rate": 2.1060789934519968e-05,
-      "loss": 0.8492,
-      "step": 500
-    },
-    {
-      "epoch": 4.672897196261682,
-      "eval_generation_quality": 1.4625850340136055,
-      "eval_loss": 0.7530518174171448,
-      "eval_runtime": 287.5608,
-      "eval_samples_per_second": 2.977,
-      "eval_steps_per_second": 0.372,
-      "step": 500
-    },
-    {
-      "epoch": 5.140186915887851,
-      "grad_norm": 0.5181770920753479,
-      "learning_rate": 2.814648570164509e-05,
-      "loss": 0.8135,
-      "step": 550
-    },
-    {
-      "epoch": 5.607476635514018,
-      "grad_norm": 0.47956785559654236,
-      "learning_rate": 2.9831418882133196e-05,
-      "loss": 0.7584,
-      "step": 600
-    },
-    {
-      "epoch": 6.074766355140187,
-      "grad_norm": 0.584481954574585,
-      "learning_rate": 2.542339505317937e-05,
-      "loss": 0.7438,
-      "step": 650
-    },
-    {
-      "epoch": 6.542056074766355,
-      "grad_norm": 0.5437303781509399,
-      "learning_rate": 1.673329285693197e-05,
-      "loss": 0.6918,
-      "step": 700
-    },
-    {
-      "epoch": 7.009345794392523,
-      "grad_norm": 0.5896743535995483,
-      "learning_rate": 7.331129397632949e-06,
-      "loss": 0.6872,
-      "step": 750
-    },
-    {
-      "epoch": 7.4766355140186915,
-      "grad_norm": 0.37604203820228577,
-      "learning_rate": 1.0794466349235933e-06,
-      "loss": 0.6681,
-      "step": 800
-    },
-    {
-      "epoch": 7.94392523364486,
-      "grad_norm": 0.4640524983406067,
-      "learning_rate": 5.465244220378685e-07,
-      "loss": 0.6794,
-      "step": 850
-    },
-    {
-      "epoch": 8.411214953271028,
-      "grad_norm": 0.3652268052101135,
-      "learning_rate": 5.951294754511376e-06,
-      "loss": 0.669,
-      "step": 900
-    },
-    {
-      "epoch": 8.878504672897197,
-      "grad_norm": 1.2286640405654907,
-      "learning_rate": 1.5073401404570173e-05,
-      "loss": 0.6918,
-      "step": 950
-    },
-    {
-      "epoch": 9.345794392523365,
-      "grad_norm": 0.3932737708091736,
-      "learning_rate": 2.4165353717674908e-05,
-      "loss": 0.6632,
-      "step": 1000
-    },
-    {
-      "epoch": 9.345794392523365,
-      "eval_generation_quality": 0.0,
-      "eval_loss": 0.6030490398406982,
-      "eval_runtime": 238.7271,
-      "eval_samples_per_second": 3.586,
-      "eval_steps_per_second": 0.448,
-      "step": 1000
-    },
-    {
-      "epoch": 9.813084112149532,
-      "grad_norm": 0.5340766906738281,
-      "learning_rate": 2.9492048868135868e-05,
-      "loss": 0.6104,
-      "step": 1050
     }
   ],
   "logging_steps": 50,
@@ -195,12 +58,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.757791890505728e+16,
+  "total_flos": 1254005784576000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null