Training in progress, step 120, checkpoint

last-checkpoint/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "fxmarty/tiny-dummy-qwen2",
+  "_name_or_path": "peft-internal-testing/tiny-dummy-qwen2",
   "architectures": [
     "Qwen2ForCausalLM"
   ],

last-checkpoint/trainer_state.json

@@ -11,9 +11,9 @@
     {
       "epoch": 0.001183431952662722,
       "eval_loss": 11.929322242736816,
-      "eval_runtime": 3.535,
-      "eval_samples_per_second": 424.894,
-      "eval_steps_per_second": 26.591,
+      "eval_runtime": 3.5903,
+      "eval_samples_per_second": 418.354,
+      "eval_steps_per_second": 26.182,
       "step": 1
     },
     {
@@ -33,9 +33,9 @@
     {
       "epoch": 0.023668639053254437,
       "eval_loss": 11.92916488647461,
-      "eval_runtime": 3.5873,
-      "eval_samples_per_second": 418.696,
-      "eval_steps_per_second": 26.203,
+      "eval_runtime": 3.5713,
+      "eval_samples_per_second": 420.581,
+      "eval_steps_per_second": 26.321,
       "step": 20
     },
     {
@@ -55,9 +55,9 @@
     {
       "epoch": 0.047337278106508875,
       "eval_loss": 11.928914070129395,
-      "eval_runtime": 3.5661,
-      "eval_samples_per_second": 421.185,
-      "eval_steps_per_second": 26.359,
+      "eval_runtime": 3.5591,
+      "eval_samples_per_second": 422.018,
+      "eval_steps_per_second": 26.411,
       "step": 40
     },
     {
@@ -77,9 +77,9 @@
     {
       "epoch": 0.07100591715976332,
       "eval_loss": 11.92799186706543,
-      "eval_runtime": 3.6304,
-      "eval_samples_per_second": 413.725,
-      "eval_steps_per_second": 25.892,
+      "eval_runtime": 3.5712,
+      "eval_samples_per_second": 420.581,
+      "eval_steps_per_second": 26.321,
       "step": 60
     },
     {
@@ -99,9 +99,9 @@
     {
       "epoch": 0.09467455621301775,
       "eval_loss": 11.925419807434082,
-      "eval_runtime": 3.5847,
-      "eval_samples_per_second": 418.998,
-      "eval_steps_per_second": 26.222,
+      "eval_runtime": 3.5691,
+      "eval_samples_per_second": 420.839,
+      "eval_steps_per_second": 26.337,
       "step": 80
     },
     {
@@ -121,9 +121,9 @@
     {
       "epoch": 0.11834319526627218,
       "eval_loss": 11.913871765136719,
-      "eval_runtime": 3.6003,
-      "eval_samples_per_second": 417.19,
-      "eval_steps_per_second": 26.109,
+      "eval_runtime": 3.6305,
+      "eval_samples_per_second": 413.717,
+      "eval_steps_per_second": 25.892,
       "step": 100
     },
     {
@@ -143,9 +143,9 @@
     {
       "epoch": 0.14201183431952663,
       "eval_loss": 11.85535717010498,
-      "eval_runtime": 3.5492,
-      "eval_samples_per_second": 423.196,
-      "eval_steps_per_second": 26.485,
+      "eval_runtime": 3.526,
+      "eval_samples_per_second": 425.979,
+      "eval_steps_per_second": 26.659,
       "step": 120
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c4f845ab252f0d79c37513e9d4952256291160f1e8ff745d53d03e4f3aaefa4
-size 6648
+oid sha256:e48ac84782c337d69ea61e02906bc12c93173b2673d18eb497beeca4879618fc
+size 6712