Training in progress, step 160, checkpoint

last-checkpoint/config.json

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

last-checkpoint/trainer_state.json

@@ -11,9 +11,9 @@
     {
       "epoch": 0.001183431952662722,
       "eval_loss": 11.929322242736816,
-      "eval_runtime": 3.6275,
-      "eval_samples_per_second": 414.056,
-      "eval_steps_per_second": 25.913,
+      "eval_runtime": 3.5424,
+      "eval_samples_per_second": 424.005,
+      "eval_steps_per_second": 26.536,
       "step": 1
     },
     {
@@ -33,9 +33,9 @@
     {
       "epoch": 0.023668639053254437,
       "eval_loss": 11.92916488647461,
-      "eval_runtime": 3.5124,
-      "eval_samples_per_second": 427.632,
-      "eval_steps_per_second": 26.763,
+      "eval_runtime": 3.5376,
+      "eval_samples_per_second": 424.587,
+      "eval_steps_per_second": 26.572,
       "step": 20
     },
     {
@@ -55,9 +55,9 @@
     {
       "epoch": 0.047337278106508875,
       "eval_loss": 11.928914070129395,
-      "eval_runtime": 3.5866,
-      "eval_samples_per_second": 418.781,
-      "eval_steps_per_second": 26.209,
+      "eval_runtime": 3.5225,
+      "eval_samples_per_second": 426.404,
+      "eval_steps_per_second": 26.686,
       "step": 40
     },
     {
@@ -77,9 +77,9 @@
     {
       "epoch": 0.07100591715976332,
       "eval_loss": 11.92799186706543,
-      "eval_runtime": 3.5352,
-      "eval_samples_per_second": 424.864,
-      "eval_steps_per_second": 26.589,
+      "eval_runtime": 3.5615,
+      "eval_samples_per_second": 421.727,
+      "eval_steps_per_second": 26.393,
       "step": 60
     },
     {
@@ -99,9 +99,9 @@
     {
       "epoch": 0.09467455621301775,
       "eval_loss": 11.925419807434082,
-      "eval_runtime": 3.5978,
-      "eval_samples_per_second": 417.483,
-      "eval_steps_per_second": 26.127,
+      "eval_runtime": 3.5961,
+      "eval_samples_per_second": 417.672,
+      "eval_steps_per_second": 26.139,
       "step": 80
     },
     {
@@ -121,9 +121,9 @@
     {
       "epoch": 0.11834319526627218,
       "eval_loss": 11.913871765136719,
-      "eval_runtime": 3.568,
-      "eval_samples_per_second": 420.97,
-      "eval_steps_per_second": 26.346,
+      "eval_runtime": 3.5719,
+      "eval_samples_per_second": 420.504,
+      "eval_steps_per_second": 26.316,
       "step": 100
     },
     {
@@ -143,9 +143,9 @@
     {
       "epoch": 0.14201183431952663,
       "eval_loss": 11.85535717010498,
-      "eval_runtime": 3.581,
-      "eval_samples_per_second": 419.431,
-      "eval_steps_per_second": 26.249,
+      "eval_runtime": 3.5396,
+      "eval_samples_per_second": 424.345,
+      "eval_steps_per_second": 26.557,
       "step": 120
     },
     {
@@ -165,9 +165,9 @@
     {
       "epoch": 0.16568047337278108,
       "eval_loss": 11.73879337310791,
-      "eval_runtime": 3.5748,
-      "eval_samples_per_second": 420.168,
-      "eval_steps_per_second": 26.295,
+      "eval_runtime": 3.4959,
+      "eval_samples_per_second": 429.652,
+      "eval_steps_per_second": 26.889,
       "step": 140
     },
     {
@@ -187,9 +187,9 @@
     {
       "epoch": 0.1893491124260355,
       "eval_loss": 11.629658699035645,
-      "eval_runtime": 3.5281,
-      "eval_samples_per_second": 425.721,
-      "eval_steps_per_second": 26.643,
+      "eval_runtime": 3.5771,
+      "eval_samples_per_second": 419.895,
+      "eval_steps_per_second": 26.278,
       "step": 160
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9932170e7e73ee2b0df54dc82e7d5237bddfcbc5bea68ea5e6421bff5f7c8a3
-size 6712
+oid sha256:20af897fff432dad9da1232d2f5e6ab4040448b601443dcf983c39a3e47a3b26
+size 6648