Training in progress, step 1000

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "datificate/gpt2-small-spanish",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "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": "4.21.1",
+  "use_cache": true,
+  "vocab_size": 50385
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02cc85e69c3993d8473bd029ffa90b5b28da1cc3e469aec76fe323c8d1fc1b7b
+size 510789737

runs/Aug11_19-58-32_88ddeabdf4ec/1660247956.4078417/events.out.tfevents.1660247956.88ddeabdf4ec.71.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c4b1238dcc6ed482ab4d82563122247bdd023544b17c546973c0a0f1d39f111
+size 5466

runs/Aug11_19-58-32_88ddeabdf4ec/events.out.tfevents.1660247956.88ddeabdf4ec.71.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e2725575a412922095e19484f034026b76c4eb7244599da5d28252384b9a0c4
+size 4312

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae4672fc10fdf9cdf9fd6af78fd81a5f38e91f21c6a0cbe31e84517c1511033d
+size 3375