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: 1.2133
+- Loss: 1.2132
 
 ## Model description
 
@@ -55,7 +55,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.2457        | 1.0   | 23   | 1.2133          |
+| 1.2457        | 1.0   | 23   | 1.2132          |
 
 
 ### Framework versions

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 1.0,
-    "eval_loss": 1.2132965326309204,
-    "eval_runtime": 0.4369,
-    "eval_samples_per_second": 1419.149,
-    "eval_steps_per_second": 11.445,
+    "eval_loss": 1.2132008075714111,
+    "eval_runtime": 0.4587,
+    "eval_samples_per_second": 1351.645,
+    "eval_steps_per_second": 10.9,
     "total_flos": 3.742438758599885e+16,
-    "train_loss": 1.3028600319572117,
-    "train_runtime": 47.4803,
-    "train_samples_per_second": 247.766,
-    "train_steps_per_second": 0.484
+    "train_loss": 1.3028446384098218,
+    "train_runtime": 44.4512,
+    "train_samples_per_second": 264.65,
+    "train_steps_per_second": 0.517
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 1.0,
-    "eval_loss": 1.2132965326309204,
-    "eval_runtime": 0.4369,
-    "eval_samples_per_second": 1419.149,
-    "eval_steps_per_second": 11.445
+    "eval_loss": 1.2132008075714111,
+    "eval_runtime": 0.4587,
+    "eval_samples_per_second": 1351.645,
+    "eval_steps_per_second": 10.9
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09c7b3d225500aceefc7ab2ac4711a0aaffc704916f903bc84e6fe46866c6a55
+oid sha256:3bc13bf8a501edce8765b6ea8a93a8dbc4dd1ed074b375217df8effbbaad2ba5
 size 2200119864

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "total_flos": 3.742438758599885e+16,
-    "train_loss": 1.3028600319572117,
-    "train_runtime": 47.4803,
-    "train_samples_per_second": 247.766,
-    "train_steps_per_second": 0.484
+    "train_loss": 1.3028446384098218,
+    "train_runtime": 44.4512,
+    "train_samples_per_second": 264.65,
+    "train_steps_per_second": 0.517
 }

trainer_log.jsonl

@@ -1,4 +1,4 @@
-{"current_steps": 10, "total_steps": 23, "loss": 1.3741, "learning_rate": 1.4539904997395468e-05, "epoch": 0.43478260869565216, "percentage": 43.48, "elapsed_time": "0:00:16", "remaining_time": "0:00:21"}
+{"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": 1.2132965326309204, "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": "0:00:46", "remaining_time": "0:00:00"}
+{"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"}

trainer_state.json

@@ -10,34 +10,34 @@
   "log_history": [
     {
       "epoch": 0.43478260869565216,
-      "grad_norm": 0.8429296612739563,
+      "grad_norm": 0.8412916660308838,
       "learning_rate": 1.4539904997395468e-05,
-      "loss": 1.3741,
+      "loss": 1.3742,
       "step": 10
     },
     {
       "epoch": 0.8695652173913043,
-      "grad_norm": 0.5978645086288452,
+      "grad_norm": 0.5978009700775146,
       "learning_rate": 1.0899347581163222e-06,
       "loss": 1.2457,
       "step": 20
     },
     {
       "epoch": 1.0,
-      "eval_loss": 1.2132965326309204,
-      "eval_runtime": 0.5878,
-      "eval_samples_per_second": 1054.768,
-      "eval_steps_per_second": 8.506,
+      "eval_loss": 1.2132008075714111,
+      "eval_runtime": 0.5736,
+      "eval_samples_per_second": 1080.949,
+      "eval_steps_per_second": 8.717,
       "step": 23
     },
     {
       "epoch": 1.0,
       "step": 23,
       "total_flos": 3.742438758599885e+16,
-      "train_loss": 1.3028600319572117,
-      "train_runtime": 47.4803,
-      "train_samples_per_second": 247.766,
-      "train_steps_per_second": 0.484
+      "train_loss": 1.3028446384098218,
+      "train_runtime": 44.4512,
+      "train_samples_per_second": 264.65,
+      "train_steps_per_second": 0.517
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:143a0712bbd5de3cacbf2c90bf42bd432f6eafad3ec0090dd9646d6743f09936
+oid sha256:228e5acd5cb6b0cf84b6f368b9529eeb3bc84227da62ebef15a3fd87143e4618
 size 6712