Training in progress, step 60

config.json

@@ -5,7 +5,7 @@
     "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
-  "bos_token_id": 50261,
+  "bos_token_id": 50260,
   "embd_pdrop": 0.1,
   "eos_token_id": 0,
   "gradient_checkpointing": false,
@@ -24,7 +24,7 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
-  "pad_token_id": 50260,
+  "pad_token_id": 50259,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -41,7 +41,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.16.2",
+  "transformers_version": "4.27.0.dev0",
   "use_cache": true,
-  "vocab_size": 50262
+  "vocab_size": 50261
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfd9f2cde6e935054cc2b47ba44003a0073476bd24b24a3388e9a124f26ce18c
-size 510419177
+oid sha256:f4661a1ef9133396ff14056ffd8eff884e9a866a4b9b4c90e4267a33c16232c0
+size 510410301

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f506996864833164301518663dccbeb53d61d5b9fc0112c307613f4a0e7bae7
-size 3055
+oid sha256:50418363dbc3937349e8a01606f0cdd521286f4266479f84e6a588ecc6dfa130
+size 3643