Add checkpoint-900

checkpoint-900/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 4,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 5,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 2,
+  "n_inner": null,
+  "n_layer": 2,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": true,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": true,
+  "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": "4.18.0",
+  "use_cache": false,
+  "vocab_size": 50257
+}

checkpoint-900/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b759ec230f7350db73f12cac83394806a7cb0d1598f670007784c1620069b644
+size 428505574

checkpoint-900/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c57df7caddf14b0c830e6fa4a94da63ba1861cab6d65455dcbb98a5a36236a1
+size 216352206

checkpoint-900/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874e514fce67a482cb072003b3eb76f31b57cd9bcc41e98f4549e5a29658db25
+size 14244

checkpoint-900/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3188ca1a64b3e854c359f175f9debb352690ec074d6533bcb271fdc5844d8a34
+size 988

checkpoint-900/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568679fd2736dd89c0777f700777d9a0cd68685ed2bfa791cc7873848ecfae8c
+size 1064

checkpoint-900/special_tokens_map.json

@@ -0,0 +1 @@
+{}

checkpoint-900/tokenizer_config.json

@@ -0,0 +1 @@
+{"tokenizer_class": "PassthroughTokenizer"}

checkpoint-900/trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 37.004,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2e-06,
+      "loss": 10.9377,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 9.999999999999999e-05,
+      "loss": 9.4009,
+      "step": 50
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00019999999999999998,
+      "loss": 7.1915,
+      "step": 100
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.0003,
+      "loss": 6.4074,
+      "step": 150
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.00039999999999999996,
+      "loss": 5.6889,
+      "step": 200
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0005,
+      "loss": 5.326,
+      "step": 250
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 0.0006,
+      "loss": 5.0873,
+      "step": 300
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 0.0005888888888888889,
+      "loss": 4.7619,
+      "step": 350
+    },
+    {
+      "epoch": 16.01,
+      "learning_rate": 0.0005777777777777776,
+      "loss": 4.4374,
+      "step": 400
+    },
+    {
+      "epoch": 18.01,
+      "learning_rate": 0.0005666666666666666,
+      "loss": 4.2331,
+      "step": 450
+    },
+    {
+      "epoch": 20.01,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 4.0853,
+      "step": 500
+    },
+    {
+      "epoch": 22.01,
+      "learning_rate": 0.0005444444444444444,
+      "loss": 3.9849,
+      "step": 550
+    },
+    {
+      "epoch": 24.01,
+      "learning_rate": 0.0005333333333333333,
+      "loss": 3.8903,
+      "step": 600
+    },
+    {
+      "epoch": 27.0,
+      "learning_rate": 0.0005222222222222222,
+      "loss": 3.8802,
+      "step": 650
+    },
+    {
+      "epoch": 29.0,
+      "learning_rate": 0.0005111111111111111,
+      "loss": 3.748,
+      "step": 700
+    },
+    {
+      "epoch": 31.0,
+      "learning_rate": 0.0005,
+      "loss": 3.6859,
+      "step": 750
+    },
+    {
+      "epoch": 33.0,
+      "learning_rate": 0.0004888888888888889,
+      "loss": 3.6323,
+      "step": 800
+    },
+    {
+      "epoch": 35.0,
+      "learning_rate": 0.0004777777777777777,
+      "loss": 3.5863,
+      "step": 850
+    },
+    {
+      "epoch": 37.0,
+      "learning_rate": 0.0004666666666666666,
+      "loss": 3.5434,
+      "step": 900
+    }
+  ],
+  "max_steps": 3000,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 4.163350221029376e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-900/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9e3e2b0a4d401cbed01651f3132d2ba27e9286398adaa9606dd449fe0454eb
+size 3704