End of training

README.md

@@ -2,11 +2,15 @@
 license: gemma
 base_model: google/gemma-7b
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- chansung/mental_health_counseling_conversations_merged
 model-index:
 - name: mental_health_counseling_merged_v0.1
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mental_health_counseling_merged_v0.1
 
-This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the chansung/mental_health_counseling_conversations_merged dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.8529
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 5.0,
+    "eval_loss": 0.8528754711151123,
+    "eval_runtime": 641.8314,
+    "eval_samples": 5130,
+    "eval_samples_per_second": 7.007,
+    "eval_steps_per_second": 0.584,
     "total_flos": 2.1191156679948894e+19,
     "train_loss": 0.9175008542622121,
     "train_runtime": 172180.6812,

config.json

@@ -9,7 +9,7 @@
   "eos_token_id": 1,
   "head_dim": 256,
   "hidden_act": "gelu",
-  "hidden_activation": null,
+  "hidden_activation": "gelu_pytorch_tanh",
   "hidden_size": 3072,
   "initializer_range": 0.02,
   "intermediate_size": 24576,
@@ -23,7 +23,7 @@
     "_load_in_4bit": true,
     "_load_in_8bit": false,
     "bnb_4bit_compute_dtype": "bfloat16",
-    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_storage": "bfloat16",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": false,
     "llm_int8_enable_fp32_cpu_offload": false,
@@ -38,7 +38,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.2",
+  "transformers_version": "4.41.1",
   "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 0.9999531550100716,
-    "eval_loss": 0.8574451804161072,
-    "eval_runtime": 962.2866,
+    "epoch": 5.0,
+    "eval_loss": 0.8528754711151123,
+    "eval_runtime": 641.8314,
     "eval_samples": 5130,
-    "eval_samples_per_second": 4.673,
-    "eval_steps_per_second": 1.169
+    "eval_samples_per_second": 7.007,
+    "eval_steps_per_second": 0.584
 }

runs/May27_11-46-06_instance-20240524-1004/events.out.tfevents.1716998047.instance-20240524-1004.480.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec1d9fb83b7b23c70f96ba44c5530d53acb6f9d78a03e59d39631bb3463174df
+size 364