Training in progress, step 10

checkpoint-10/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "codeparrot/codeparrot-small",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMAndValueHeadModel"
+  ],
+  "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": 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": "4.17.0",
+  "use_cache": true,
+  "vocab_size": 32768
+}

checkpoint-10/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:552d29802b532649151641199f171ae647a508e6161b56dede2cfd2ff2db65f3
+size 888151409

checkpoint-10/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:207898354a8e24dacd6ad648a2c48269a9c6125bbf92564903e6da6e1ba9334e
+size 456678185

checkpoint-10/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf9e448c149fd95bc3db7f6343d1659618913b9e0d71a33dc0fdaa0f5933ac8d
+size 14503

checkpoint-10/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20e4b012b4b9ab1daa876390beea4afff370d4f83e20e939f16cdf1855daf52f
+size 559

checkpoint-10/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97709ef76623b19051f35863c651fe8c4d623e3d3f387ce6eb8bc0242521385
+size 623

checkpoint-10/special_tokens_map.json

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

checkpoint-10/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": "codeparrot/codeparrot-small", "tokenizer_class": "GPT2Tokenizer"}

checkpoint-10/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6666666666666666,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0005,
+      "loss": 10.5545,
+      "theoretical_loss": 20.841284642178216,
+      "tokens_seen": 65536
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00046428571428571433,
+      "loss": 10.5833,
+      "theoretical_loss": 17.59466794495971,
+      "tokens_seen": 131072
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00042857142857142855,
+      "loss": 9.0487,
+      "theoretical_loss": 15.967943933467634,
+      "tokens_seen": 196608
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0003928571428571429,
+      "loss": 8.6045,
+      "theoretical_loss": 14.920783596619636,
+      "tokens_seen": 262144
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00035714285714285714,
+      "loss": 8.612,
+      "theoretical_loss": 14.164683778394041,
+      "tokens_seen": 327680
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00032142857142857147,
+      "loss": 8.0149,
+      "theoretical_loss": 13.581028313181289,
+      "tokens_seen": 393216
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0002857142857142857,
+      "loss": 8.0364,
+      "theoretical_loss": 13.110275842032255,
+      "tokens_seen": 458752
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00025,
+      "loss": 7.6606,
+      "theoretical_loss": 12.71859646611439,
+      "tokens_seen": 524288
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00021428571428571427,
+      "loss": 7.5729,
+      "theoretical_loss": 12.38505930450469,
+      "tokens_seen": 589824
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00017857142857142857,
+      "loss": 7.5104,
+      "theoretical_loss": 12.095879447666144,
+      "tokens_seen": 655360
+    }
+  ],
+  "max_steps": 15,
+  "num_train_epochs": 9223372036854775807,
+  "total_flos": 334453800960000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a34744d720995e937e6f88654fd722891f574db162e25b56a6b9fa429b1c293
+size 3055

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:610dbb2ae7b16c215d8d70480eaaed465876cbd36bf24aca0ff438e328d92413
+oid sha256:207898354a8e24dacd6ad648a2c48269a9c6125bbf92564903e6da6e1ba9334e
 size 456678185