Upload folder using huggingface_hub

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the tatsu-lab/alpaca dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2132
+- Loss: 1.2134
 
 ## Model description
 
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 512
 - total_eval_batch_size: 128
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 1.0
@@ -55,12 +55,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.2457        | 1.0   | 23   | 1.2132          |
+| 1.2486        | 1.0   | 23   | 1.2134          |
 
 
 ### Framework versions
 
-- Transformers 4.45.0
-- Pytorch 2.3.1+cu118
+- Transformers 4.46.1
+- Pytorch 2.5.0a0+b465a5843b.nv24.09
 - Datasets 3.0.2
 - Tokenizers 0.20.3

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 1.0,
-    "eval_loss": 1.2132008075714111,
-    "eval_runtime": 0.4587,
-    "eval_samples_per_second": 1351.645,
-    "eval_steps_per_second": 10.9,
+    "eval_loss": 1.2133620977401733,
+    "eval_runtime": 0.4304,
+    "eval_samples_per_second": 1440.355,
+    "eval_steps_per_second": 11.616,
     "total_flos": 3.742438758599885e+16,
-    "train_loss": 1.3028446384098218,
-    "train_runtime": 44.4512,
-    "train_samples_per_second": 264.65,
-    "train_steps_per_second": 0.517
+    "train_loss": 1.3040671763212786,
+    "train_runtime": 45.9345,
+    "train_samples_per_second": 256.104,
+    "train_steps_per_second": 0.501
 }

config.json

@@ -24,7 +24,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.45.0",
+  "transformers_version": "4.46.1",
   "use_cache": false,
   "vocab_size": 32000
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 1.0,
-    "eval_loss": 1.2132008075714111,
-    "eval_runtime": 0.4587,
-    "eval_samples_per_second": 1351.645,
-    "eval_steps_per_second": 10.9
+    "eval_loss": 1.2133620977401733,
+    "eval_runtime": 0.4304,
+    "eval_samples_per_second": 1440.355,
+    "eval_steps_per_second": 11.616
 }

generation_config.json

@@ -3,5 +3,5 @@
   "eos_token_id": 2,
   "max_length": 2048,
   "pad_token_id": 0,
-  "transformers_version": "4.45.0"
+  "transformers_version": "4.46.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bc13bf8a501edce8765b6ea8a93a8dbc4dd1ed074b375217df8effbbaad2ba5
+oid sha256:88f7bfdf386632461b23edf663b3a8dcb3aceef65956f3c58e666a52f99a9462
 size 2200119864

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 3.742438758599885e+16,
-    "train_loss": 1.3028446384098218,
-    "train_runtime": 44.4512,
-    "train_samples_per_second": 264.65,
-    "train_steps_per_second": 0.517
+    "train_loss": 1.3040671763212786,
+    "train_runtime": 45.9345,
+    "train_samples_per_second": 256.104,
+    "train_steps_per_second": 0.501
 }

trainer_log.jsonl

@@ -1,4 +1,4 @@
-{"current_steps": 10, "total_steps": 23, "loss": 1.3742, "learning_rate": 1.4539904997395468e-05, "epoch": 0.43478260869565216, "percentage": 43.48, "elapsed_time": "0:00:15", "remaining_time": "0:00:20"}
-{"current_steps": 20, "total_steps": 23, "loss": 1.2457, "learning_rate": 1.0899347581163222e-06, "epoch": 0.8695652173913043, "percentage": 86.96, "elapsed_time": "0:00:29", "remaining_time": "0:00:04"}
-{"current_steps": 23, "total_steps": 23, "eval_loss": 1.2132008075714111, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:37", "remaining_time": "0:00:00"}
-{"current_steps": 23, "total_steps": 23, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:41", "remaining_time": "0:00:00"}
+{"current_steps": 10, "total_steps": 23, "loss": 1.3742, "learning_rate": 1.4539904997395468e-05, "epoch": 0.43478260869565216, "percentage": 43.48, "elapsed_time": "0:00:19", "remaining_time": "0:00:25"}
+{"current_steps": 20, "total_steps": 23, "loss": 1.2486, "learning_rate": 1.0899347581163222e-06, "epoch": 0.8695652173913043, "percentage": 86.96, "elapsed_time": "0:00:31", "remaining_time": "0:00:04"}
+{"current_steps": 23, "total_steps": 23, "eval_loss": 1.2133620977401733, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:40", "remaining_time": "0:00:00"}
+{"current_steps": 23, "total_steps": 23, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:43", "remaining_time": "0:00:00"}

trainer_state.json

@@ -10,34 +10,34 @@
   "log_history": [
     {
       "epoch": 0.43478260869565216,
-      "grad_norm": 0.8412916660308838,
+      "grad_norm": 0.8347742557525635,
       "learning_rate": 1.4539904997395468e-05,
       "loss": 1.3742,
       "step": 10
     },
     {
       "epoch": 0.8695652173913043,
-      "grad_norm": 0.5978009700775146,
+      "grad_norm": 0.5884836316108704,
       "learning_rate": 1.0899347581163222e-06,
-      "loss": 1.2457,
+      "loss": 1.2486,
       "step": 20
     },
     {
       "epoch": 1.0,
-      "eval_loss": 1.2132008075714111,
-      "eval_runtime": 0.5736,
-      "eval_samples_per_second": 1080.949,
-      "eval_steps_per_second": 8.717,
+      "eval_loss": 1.2133620977401733,
+      "eval_runtime": 0.5411,
+      "eval_samples_per_second": 1145.916,
+      "eval_steps_per_second": 9.241,
       "step": 23
     },
     {
       "epoch": 1.0,
       "step": 23,
       "total_flos": 3.742438758599885e+16,
-      "train_loss": 1.3028446384098218,
-      "train_runtime": 44.4512,
-      "train_samples_per_second": 264.65,
-      "train_steps_per_second": 0.517
+      "train_loss": 1.3040671763212786,
+      "train_runtime": 45.9345,
+      "train_samples_per_second": 256.104,
+      "train_steps_per_second": 0.501
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:228e5acd5cb6b0cf84b6f368b9529eeb3bc84227da62ebef15a3fd87143e4618
-size 6712
+oid sha256:abe9cbc400346e4105e77711f48ffdc0a695f7d76414a932ce10713f588d4c3d
+size 7032