Training in progress, epoch 1

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/t5-v1_1-xl](https://huggingface.co/google/t5-v1_1-xl) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 7.5273
+- Loss: nan
 
 ## Model description
 
@@ -46,15 +46,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 8.1957        | 1.0   | 125  | 7.5273          |
-| 8.6066        | 2.0   | 250  | 7.5273          |
-| 8.5176        | 3.0   | 375  | 7.5273          |
-| 8.1945        | 4.0   | 500  | 7.5273          |
+| 7.8207        | 1.0   | 125  | 7.625           |
+| 0.0           | 2.0   | 250  | nan             |
+| 0.0           | 3.0   | 375  | nan             |
+| 0.0           | 4.0   | 500  | nan             |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.1+cu121
-- Datasets 2.15.0
-- Tokenizers 0.15.0
+- Transformers 4.34.0
+- Pytorch 2.1.0+cu121
+- Datasets 2.6.1
+- Tokenizers 0.14.1

adapter_config.json

@@ -1,5 +1,4 @@
 {
-  "alpha_pattern": {},
   "auto_mapping": null,
   "base_model_name_or_path": "google/t5-v1_1-xl",
   "bias": "none",
@@ -13,7 +12,6 @@
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 8,
-  "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q",

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ad04c687a553091a026d182726c92eb7ee3bb2b2c7b98b13b219d2370419c76
+oid sha256:a0fa4210778510d648ad8a1f128794c74ce6b32d3212567c0f0fa25cbe6f9872
 size 18980874

added_tokens.json

@@ -1,4 +1,6 @@
 {
+  "0": 632,
+  "1": 536,
   "<extra_id_0>": 32099,
   "<extra_id_10>": 32089,
   "<extra_id_11>": 32088,
@@ -98,5 +100,6 @@
   "<extra_id_97>": 32002,
   "<extra_id_98>": 32001,
   "<extra_id_99>": 32000,
-  "<extra_id_9>": 32090
+  "<extra_id_9>": 32090,
+  "<unk>": 2
 }

special_tokens_map.json

@@ -101,25 +101,7 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "eos_token": {
-    "content": "1",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "0",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "eos_token": "1",
+  "pad_token": "0",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -2,25 +2,25 @@
   "added_tokens_decoder": {
     "2": {
       "content": "<unk>",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
     "536": {
       "content": "1",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
     "632": {
       "content": "0",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
@@ -937,5 +937,6 @@
   "pad_token": "0",
   "sp_model_kwargs": {},
   "tokenizer_class": "T5Tokenizer",
+  "tokenizer_file": null,
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e9866dbdd5346acbb52aaca177c24a0f13e3e2790fd8565cb91bec90a8ee597
-size 4792
+oid sha256:2a299ddc34167072848ac32b7ff45fb98f4be270c3f89bb6b2515c29e4c61907
+size 4728