Training in progress, step 105

config.json

@@ -1,39 +1,29 @@
 {
-  "_name_or_path": "gpt2",
-  "activation_function": "gelu_new",
+  "_name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
   "architectures": [
-    "GPT2LMHeadModel"
+    "BertForMaskedLM"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
+  "attention_probs_dropout_prob": 0.1,
+  "cell": {},
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
   "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
-    }
-  },
+  "intermediate_size": 1200,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "pre_trained": "",
+  "structure": [],
   "torch_dtype": "float32",
   "transformers_version": "4.46.3",
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b63b88deafd54e434b237ade856769d7e6505adc1adcf771a77487e79e29f8ca
-size 497774208
+oid sha256:626c4a7de21e06ccc16aa37952156caed201897a57e796d5c6fc654d9840be90
+size 57534056

runs/Dec05_22-55-11_xtaco/events.out.tfevents.1733468114.xtaco.6644.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb4f255ecd1142682a435d3f34cd458643b14fd36a4fcc26d8739f2cc84d0011
+size 6867

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a25c2f9ceea2ddbcb1b125174763623726aae482a0ee7757e7865d36b6fd971d
-size 4847
+oid sha256:a47bbd278ac741b1f9a772a0095bf49640747e13116c3cca6da9c17034ffdbb1
+size 4911