End of training

README.md

@@ -5,9 +5,9 @@ library_name: transformers
 model_name: trainer_output
 tags:
 - generated_from_trainer
+- tool-use
 - sft
 - unsloth
-- tool-use
 - linalg-zero
 - trl
 licence: license

adapter_config.json

@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "o_proj",
-    "q_proj",
-    "v_proj",
     "down_proj",
-    "up_proj",
     "k_proj",
-    "gate_proj"
+    "q_proj",
+    "up_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0d12cda975b3ad62a4d859cb76757742b4ac86b08fa133763b92b51e0ffb5b6
+oid sha256:b0156b8e2bd7ee00762484b1b56e008189907477eea7e35d71fabc479be41072
 size 132188392

all_results.json

@@ -1,9 +1,14 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.5140631794929504,
+    "eval_runtime": 8.3035,
+    "eval_samples": 60,
+    "eval_samples_per_second": 7.226,
+    "eval_steps_per_second": 7.226,
     "total_flos": 2717720554039296.0,
-    "train_loss": 0.24179711043834687,
-    "train_runtime": 32.7348,
+    "train_loss": 0.24174172580242156,
+    "train_runtime": 31.6344,
     "train_samples": 60,
-    "train_samples_per_second": 1.833,
-    "train_steps_per_second": 1.833
+    "train_samples_per_second": 1.897,
+    "train_steps_per_second": 1.897
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.5140631794929504,
+    "eval_runtime": 8.3035,
+    "eval_samples": 60,
+    "eval_samples_per_second": 7.226,
+    "eval_steps_per_second": 7.226
+}

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 2717720554039296.0,
-    "train_loss": 0.24179711043834687,
-    "train_runtime": 32.7348,
+    "train_loss": 0.24174172580242156,
+    "train_runtime": 31.6344,
     "train_samples": 60,
-    "train_samples_per_second": 1.833,
-    "train_steps_per_second": 1.833
+    "train_samples_per_second": 1.897,
+    "train_steps_per_second": 1.897
 }

trainer_state.json

@@ -11,96 +11,96 @@
   "log_history": [
     {
       "epoch": 0.08333333333333333,
-      "grad_norm": 0.3455909192562103,
+      "grad_norm": 0.3362419009208679,
       "learning_rate": 0.00016,
-      "loss": 0.7527,
+      "loss": 0.7526,
       "step": 5
     },
     {
       "epoch": 0.16666666666666666,
-      "grad_norm": 0.532439649105072,
+      "grad_norm": 0.5312803983688354,
       "learning_rate": 0.00018545454545454545,
-      "loss": 0.426,
+      "loss": 0.4235,
       "step": 10
     },
     {
       "epoch": 0.25,
-      "grad_norm": 0.3362359404563904,
+      "grad_norm": 0.3434021770954132,
       "learning_rate": 0.00016727272727272728,
-      "loss": 0.2268,
+      "loss": 0.2288,
       "step": 15
     },
     {
       "epoch": 0.3333333333333333,
-      "grad_norm": 0.2568519115447998,
+      "grad_norm": 0.26192706823349,
       "learning_rate": 0.0001490909090909091,
-      "loss": 0.1894,
+      "loss": 0.1897,
       "step": 20
     },
     {
       "epoch": 0.4166666666666667,
-      "grad_norm": 0.263459712266922,
+      "grad_norm": 0.26772984862327576,
       "learning_rate": 0.00013090909090909093,
-      "loss": 0.1829,
+      "loss": 0.1833,
       "step": 25
     },
     {
       "epoch": 0.5,
-      "grad_norm": 0.20919214189052582,
+      "grad_norm": 0.20748060941696167,
       "learning_rate": 0.00011272727272727272,
-      "loss": 0.1623,
+      "loss": 0.1621,
       "step": 30
     },
     {
       "epoch": 0.5833333333333334,
-      "grad_norm": 0.2152024358510971,
+      "grad_norm": 0.21864831447601318,
       "learning_rate": 9.454545454545455e-05,
       "loss": 0.1638,
       "step": 35
     },
     {
       "epoch": 0.6666666666666666,
-      "grad_norm": 0.2593837082386017,
+      "grad_norm": 0.24830199778079987,
       "learning_rate": 7.636363636363637e-05,
-      "loss": 0.1665,
+      "loss": 0.1667,
       "step": 40
     },
     {
       "epoch": 0.75,
-      "grad_norm": 0.20896115899085999,
+      "grad_norm": 0.20934940874576569,
       "learning_rate": 5.818181818181818e-05,
       "loss": 0.1678,
       "step": 45
     },
     {
       "epoch": 0.8333333333333334,
-      "grad_norm": 0.2554057538509369,
+      "grad_norm": 0.2636692523956299,
       "learning_rate": 4e-05,
-      "loss": 0.155,
+      "loss": 0.1548,
       "step": 50
     },
     {
       "epoch": 0.9166666666666666,
-      "grad_norm": 0.17573142051696777,
+      "grad_norm": 0.1722150295972824,
       "learning_rate": 2.1818181818181818e-05,
-      "loss": 0.1529,
+      "loss": 0.1524,
       "step": 55
     },
     {
       "epoch": 1.0,
-      "grad_norm": 0.24647420644760132,
+      "grad_norm": 0.23989179730415344,
       "learning_rate": 3.636363636363636e-06,
-      "loss": 0.1557,
+      "loss": 0.1553,
       "step": 60
     },
     {
       "epoch": 1.0,
       "step": 60,
       "total_flos": 2717720554039296.0,
-      "train_loss": 0.24179711043834687,
-      "train_runtime": 32.7348,
-      "train_samples_per_second": 1.833,
-      "train_steps_per_second": 1.833
+      "train_loss": 0.24174172580242156,
+      "train_runtime": 31.6344,
+      "train_samples_per_second": 1.897,
+      "train_steps_per_second": 1.897
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e28e6b8f64da6914dafb8a55f4cfa8471104078dcab1dde68ecb85d89f925bb
+oid sha256:54b494cceb94d5932b6c823a353a9515458fd050c35e966606a622ff2776e061
 size 6097