Training in progress, step 800

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "uer/gpt2-chinese-cluecorpussmall",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -8,6 +8,7 @@
   "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",
@@ -17,6 +18,7 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
+  "output_past": true,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -29,11 +31,12 @@
   "task_specific_params": {
     "text-generation": {
       "do_sample": true,
-      "max_length": 50
+      "max_length": 320
     }
   },
+  "tokenizer_class": "BertTokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.25.1",
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 21128
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d6a6bc5019e4292d10dbfe3e6ea9dd0de5eb4440d6471ec5fab3c251e41071e
-size 510398013
+oid sha256:25ad785bbfc2b5826e165af144afa2a5ef7ab39619321e755f70c893e3d7c10e
+size 420913725

runs/Dec14_05-08-17_139d60cc267c/events.out.tfevents.1670994674.139d60cc267c.75.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:788d9212d244af31ce753e367968a49c919085b61c20d37ea2653dbe49950568
-size 4664
+oid sha256:def682bbd7c926f25bd4f115c5d11b0abcac9b5aae1462e3951bafc274842a88
+size 5948

runs/Dec14_06-25-22_139d60cc267c/1670999127.2919536/events.out.tfevents.1670999127.139d60cc267c.75.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fa92b7b8bfd234316e393cb1607c6dad54db70489d99e02ac276b85bb7f7ace
+size 5521

runs/Dec14_06-25-22_139d60cc267c/events.out.tfevents.1670999127.139d60cc267c.75.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eda536d57b651231826cb48ae561a24a60884ecb27d0bf7c92dca3a0e5e715a
+size 4946

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ad0374218e0788ae338a43bb7bcf34000f492bd968256202517880a881287b3
+oid sha256:0690e1e201f43df2f21f1ae2ccd47285120f160e49c06029607dc8d840ab74bd
 size 3451