Model save

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6782
+- Loss: 1.4181
 
 ## Model description
 
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 0     | 0    | 1.6782          |
+| No log        | 0     | 0    | 1.4181          |
 
 
 ### Framework versions

adapter_config.json

@@ -16,10 +16,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "k_proj",
     "v_proj",
-    "q_proj",
-    "o_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 0,
-    "eval_loss": 1.6781893968582153,
-    "eval_runtime": 1.9231,
-    "eval_samples": 100,
-    "eval_samples_per_second": 51.999,
-    "eval_steps_per_second": 6.76,
-    "train_loss": 0.17418603599071503,
-    "train_runtime": 69.1029,
-    "train_samples": 1100,
-    "train_samples_per_second": 15.918,
-    "train_steps_per_second": 0.029
+    "eval_loss": 1.418121576309204,
+    "eval_runtime": 35.9445,
+    "eval_samples": 1200,
+    "eval_samples_per_second": 33.385,
+    "eval_steps_per_second": 4.173,
+    "train_loss": 0.2214554250240326,
+    "train_runtime": 145.6296,
+    "train_samples": 1200,
+    "train_samples_per_second": 8.24,
+    "train_steps_per_second": 0.014
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0,
-    "eval_loss": 1.6781893968582153,
-    "eval_runtime": 1.9231,
-    "eval_samples": 100,
-    "eval_samples_per_second": 51.999,
-    "eval_steps_per_second": 6.76
+    "eval_loss": 1.418121576309204,
+    "eval_runtime": 35.9445,
+    "eval_samples": 1200,
+    "eval_samples_per_second": 33.385,
+    "eval_steps_per_second": 4.173
 }

runs/Nov30_10-17-10_hpc-hblab/events.out.tfevents.1701314316.hpc-hblab.1547149.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c1361cd39b20bf198e99c9d79c16333b6fc9e891dff95ceeb13b4595b2ed7e1
+size 4821

runs/Nov30_10-17-10_hpc-hblab/events.out.tfevents.1701314498.hpc-hblab.1547149.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce62bb8a538de05a0af1a38114d22df8072606058b35f9a9de4aa810838aedbe
+size 344

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0,
-    "train_loss": 0.17418603599071503,
-    "train_runtime": 69.1029,
-    "train_samples": 1100,
-    "train_samples_per_second": 15.918,
-    "train_steps_per_second": 0.029
+    "train_loss": 0.2214554250240326,
+    "train_runtime": 145.6296,
+    "train_samples": 1200,
+    "train_samples_per_second": 8.24,
+    "train_steps_per_second": 0.014
 }

trainer_state.json

@@ -10,27 +10,27 @@
   "log_history": [
     {
       "epoch": 0,
-      "eval_loss": 1.6781895160675049,
-      "eval_runtime": 1.9183,
-      "eval_samples_per_second": 52.129,
-      "eval_steps_per_second": 6.777,
+      "eval_loss": 1.4181212186813354,
+      "eval_runtime": 35.8986,
+      "eval_samples_per_second": 33.427,
+      "eval_steps_per_second": 4.178,
       "step": 0
     },
     {
       "epoch": 0,
       "step": 0,
-      "total_flos": 4138152939749376.0,
-      "train_loss": 0.17418603599071503,
-      "train_runtime": 69.1029,
-      "train_samples_per_second": 15.918,
-      "train_steps_per_second": 0.029
+      "total_flos": 6955618468364288.0,
+      "train_loss": 0.2214554250240326,
+      "train_runtime": 145.6296,
+      "train_samples_per_second": 8.24,
+      "train_steps_per_second": 0.014
     }
   ],
   "logging_steps": 5,
   "max_steps": 2,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 4138152939749376.0,
+  "total_flos": 6955618468364288.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:738bd7ca07742f4e6bc4d88571499f5e22fabacca9290dceee3a207594692b11
+oid sha256:1852d234f44667a230b4cb1c06479e3c7d7069f8107216ef8fa926ec3a32c806
 size 4664