End of training

README.md

@@ -0,0 +1,54 @@
+---
+base_model: katuni4ka/tiny-random-chatglm2
+tags:
+- generated_from_trainer
+model-index:
+- name: tiny-random-chatglm2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# tiny-random-chatglm2
+
+This model is a fine-tuned version of [katuni4ka/tiny-random-chatglm2](https://huggingface.co/katuni4ka/tiny-random-chatglm2) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0005
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/ea/work/tiny_chatglm2",
+  "_name_or_path": "katuni4ka/tiny-random-chatglm2",
   "add_bias_linear": false,
   "add_qkv_bias": true,
   "apply_query_key_layer_scaling": true,
@@ -10,11 +10,11 @@
   "attention_dropout": 0.0,
   "attention_softmax_in_fp32": true,
   "auto_map": {
-    "AutoConfig": "configuration_chatglm.ChatGLMConfig",
-    "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
+    "AutoConfig": "katuni4ka/tiny-random-chatglm2--configuration_chatglm.ChatGLMConfig",
+    "AutoModel": "katuni4ka/tiny-random-chatglm2--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForCausalLM": "katuni4ka/tiny-random-chatglm2--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSeq2SeqLM": "katuni4ka/tiny-random-chatglm2--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSequenceClassification": "katuni4ka/tiny-random-chatglm2--modeling_chatglm.ChatGLMForSequenceClassification"
   },
   "bias_dropout_fusion": true,
   "classifier_dropout": null,
@@ -41,7 +41,7 @@
   "seq_length": 32768,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.0.dev0",
+  "transformers_version": "4.38.1",
   "use_cache": true,
   "vocab_size": 65024
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "eos_token_id": 2,
   "pad_token_id": 0,
-  "transformers_version": "4.38.0.dev0"
+  "transformers_version": "4.38.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d9702925ea28e07f5bd0d01ebc0f5f1f861f618982dba12c4d12e47b7ea952e
+oid sha256:feebf1e929365645e986ae056b8fc1ab8c56f96f44d837f4d2cdd002b4900a44
 size 77305592

runs/Mar01_07-05-09_6aeb10c326b5/events.out.tfevents.1709276714.6aeb10c326b5.199.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be89ef525bcd21a452271cb6f5f8cec0e7535021c93831d93b1fe34058fb9439
+size 5921

tokenizer_config.json

@@ -2,7 +2,7 @@
   "added_tokens_decoder": {},
   "auto_map": {
     "AutoTokenizer": [
-      "tokenization_chatglm.ChatGLMTokenizer",
+      "katuni4ka/tiny-random-chatglm2--tokenization_chatglm.ChatGLMTokenizer",
       null
     ]
   },

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc684d11dd0b8d8ac3d7cb497cff6d6be0056ae157c6de5c0140726275e6eb86
+size 4856