Upload 15 files

checkpoint-8500/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-8500/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.30.2"
+}

checkpoint-8500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2494859d205f6ec334d991a5cccd68dda69b2201f9861da2ec27c70cc75d06cb
+size 995605189

checkpoint-8500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83cb9f2b2de12cd27d7a462ca1c913586f668514ea113a25e949f2e72f300b34
+size 497807197

checkpoint-8500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08fadad41b83764ea5f0822ee5ed929f1df742acaa17571221c0a766fbdfe77b
+size 14575

checkpoint-8500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:611c1f257833f9cabd3b4368393a6f7a734fd7dfcfa985e1f153c2b95dab2247
+size 627

checkpoint-8500/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-8500/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-8500/trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.3876404494382024,
+  "global_step": 8500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.719101123595506e-06,
+      "loss": 3.6724,
+      "step": 500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.438202247191012e-06,
+      "loss": 3.4748,
+      "step": 1000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.157303370786517e-06,
+      "loss": 3.4067,
+      "step": 1500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.876404494382023e-06,
+      "loss": 3.3562,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 8.595505617977528e-06,
+      "loss": 3.3173,
+      "step": 2500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.314606741573035e-06,
+      "loss": 3.2991,
+      "step": 3000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 8.033707865168539e-06,
+      "loss": 3.2694,
+      "step": 3500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 7.752808988764046e-06,
+      "loss": 3.2269,
+      "step": 4000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 7.471910112359552e-06,
+      "loss": 3.2163,
+      "step": 4500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 7.191011235955056e-06,
+      "loss": 3.1938,
+      "step": 5000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 6.910112359550563e-06,
+      "loss": 3.192,
+      "step": 5500
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 6.629213483146067e-06,
+      "loss": 3.1795,
+      "step": 6000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 6.348314606741574e-06,
+      "loss": 3.166,
+      "step": 6500
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 6.06741573033708e-06,
+      "loss": 3.1556,
+      "step": 7000
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 5.786516853932585e-06,
+      "loss": 3.1371,
+      "step": 7500
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 5.50561797752809e-06,
+      "loss": 3.1231,
+      "step": 8000
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 5.224719101123596e-06,
+      "loss": 3.1135,
+      "step": 8500
+    }
+  ],
+  "max_steps": 17800,
+  "num_train_epochs": 5,
+  "total_flos": 8883145211904000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-8500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7019fa62c4d86adc5965120636382a94fa1552e0156311cbf7805494ff1812bd
+size 3899

runs/Aug08_03-00-41_f3d81cebc51f/events.out.tfevents.1691463646.f3d81cebc51f.28.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c617fc3fc220c090f2e386d5e2ee17864a67ee6d2b8c2e06630e49d7e783ca1
+size 4238

runs/Aug08_05-06-01_033a44a48dc3/events.out.tfevents.1691471165.033a44a48dc3.28.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a9ef987900e8fcf734dbcb0daff7c30d3289a87d986ee681bf847442e113f2
+size 6907