Upload folder using huggingface_hub

checkpoint-157/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8e492b1ffa57e805637ef89b426f5660de5a7acf9dde1957cc49f8ecda02c1f
+oid sha256:aa436d0576b5251a78680278e31e018dc61f6bf58df7ef72e0f29c9554b0200e
 size 497774208

checkpoint-157/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d177eb0bf2ef28d579f1f0631d9fadcf879981d1abfd62380f6c21e11afb7a89
+oid sha256:951544abf7a74dd01b74237bafd8bec88a023d97712edfd869e17151283a6a92
 size 995641861

checkpoint-157/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 2.007868528366089,
+  "best_metric": 1.8853687047958374,
   "best_model_checkpoint": "gen_test/checkpoint-157",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,10 +10,10 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 2.007868528366089,
-      "eval_runtime": 56.1373,
-      "eval_samples_per_second": 178.135,
-      "eval_steps_per_second": 2.797,
+      "eval_loss": 1.8853687047958374,
+      "eval_runtime": 56.3363,
+      "eval_samples_per_second": 177.505,
+      "eval_steps_per_second": 2.787,
       "step": 157
     }
   ],

checkpoint-157/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7f5e90c7805641bc892f9f4320eca12b2c8f20b081b2afe84a46e2610a9d64d
+oid sha256:b9e6c9dcf12487c2d88138c370883e2f459a3d4aa9dcd2df9d77cc3b163b525a
 size 4539

checkpoint-314/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9302e0fb16f96e737b0042562cb0bfbd3138d99b54c00d91f7fe6b6e4db25c50
+oid sha256:dc7aa7dd1a86863b0dd40984432ff9b0c32a13b87d8fc8c39d7bdbb3796b2a1d
 size 497774208

checkpoint-314/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b77be2928d8df6084dac339b6bfa4c73fbefab4be36844b009ece2f169e986f9
+oid sha256:183dc58a5f233ddf970c3f049dfbb69e8bb13f95a4733dd54c8d7f00666eec82
 size 995641861

checkpoint-314/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.9545718431472778,
+  "best_metric": 1.842081069946289,
   "best_model_checkpoint": "gen_test/checkpoint-314",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,18 +10,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 2.007868528366089,
-      "eval_runtime": 56.1373,
-      "eval_samples_per_second": 178.135,
-      "eval_steps_per_second": 2.797,
+      "eval_loss": 1.8853687047958374,
+      "eval_runtime": 56.3363,
+      "eval_samples_per_second": 177.505,
+      "eval_steps_per_second": 2.787,
       "step": 157
     },
     {
       "epoch": 2.0,
-      "eval_loss": 1.9545718431472778,
-      "eval_runtime": 56.1182,
-      "eval_samples_per_second": 178.195,
-      "eval_steps_per_second": 2.798,
+      "eval_loss": 1.842081069946289,
+      "eval_runtime": 56.186,
+      "eval_samples_per_second": 177.98,
+      "eval_steps_per_second": 2.794,
       "step": 314
     }
   ],

checkpoint-314/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7f5e90c7805641bc892f9f4320eca12b2c8f20b081b2afe84a46e2610a9d64d
+oid sha256:b9e6c9dcf12487c2d88138c370883e2f459a3d4aa9dcd2df9d77cc3b163b525a
 size 4539

checkpoint-471/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea6ee48a9dc6d7063814f3109cec1b95650f3c561dbf039bb67acea1fa3ddf27
+oid sha256:5d7a52cd76c1ed74b803a9e5d8b56c2a2ba4d1c828f7efe96a6c883fe9404ac1
 size 497774208

checkpoint-471/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621fc93b0402ebc1bb0828d457db87eaded2ccf5a94c398df67239c62c2bc0e7
+oid sha256:e24c41ca8d9c6e6cf628fc05b52a46623734e864ce3e5a6bc0b9dd0183d4f2d1
 size 995641861

checkpoint-471/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.9429785013198853,
+  "best_metric": 1.8316441774368286,
   "best_model_checkpoint": "gen_test/checkpoint-471",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,26 +10,26 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 2.007868528366089,
-      "eval_runtime": 56.1373,
-      "eval_samples_per_second": 178.135,
-      "eval_steps_per_second": 2.797,
+      "eval_loss": 1.8853687047958374,
+      "eval_runtime": 56.3363,
+      "eval_samples_per_second": 177.505,
+      "eval_steps_per_second": 2.787,
       "step": 157
     },
     {
       "epoch": 2.0,
-      "eval_loss": 1.9545718431472778,
-      "eval_runtime": 56.1182,
-      "eval_samples_per_second": 178.195,
-      "eval_steps_per_second": 2.798,
+      "eval_loss": 1.842081069946289,
+      "eval_runtime": 56.186,
+      "eval_samples_per_second": 177.98,
+      "eval_steps_per_second": 2.794,
       "step": 314
     },
     {
       "epoch": 3.0,
-      "eval_loss": 1.9429785013198853,
-      "eval_runtime": 56.3872,
-      "eval_samples_per_second": 177.345,
-      "eval_steps_per_second": 2.784,
+      "eval_loss": 1.8316441774368286,
+      "eval_runtime": 56.2573,
+      "eval_samples_per_second": 177.755,
+      "eval_steps_per_second": 2.791,
       "step": 471
     }
   ],

checkpoint-471/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7f5e90c7805641bc892f9f4320eca12b2c8f20b081b2afe84a46e2610a9d64d
+oid sha256:b9e6c9dcf12487c2d88138c370883e2f459a3d4aa9dcd2df9d77cc3b163b525a
 size 4539

checkpoint-628/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f34b97c2fc3c99079cfaa9ebf7ec8b58821f7a597c8ae21df1000d93ae15d27c
+oid sha256:5bd00dc8c6a1a22eb8a73a6a482931e77fc33126c3e0cab6f3b5c20520d26a76
 size 497774208

checkpoint-628/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2730511954728e7c6b50ac3e3c7bb106c1a15a37b765771aa423f00c2f88ba4e
+oid sha256:4aedcd8511b7207f684781a41416e67aef234430b53654c12934006845eb4943
 size 995641861

checkpoint-628/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.933491587638855,
+  "best_metric": 1.8257514238357544,
   "best_model_checkpoint": "gen_test/checkpoint-628",
   "epoch": 4.0,
   "eval_steps": 500,
@@ -10,41 +10,41 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 2.007868528366089,
-      "eval_runtime": 56.1373,
-      "eval_samples_per_second": 178.135,
-      "eval_steps_per_second": 2.797,
+      "eval_loss": 1.8853687047958374,
+      "eval_runtime": 56.3363,
+      "eval_samples_per_second": 177.505,
+      "eval_steps_per_second": 2.787,
       "step": 157
     },
     {
       "epoch": 2.0,
-      "eval_loss": 1.9545718431472778,
-      "eval_runtime": 56.1182,
-      "eval_samples_per_second": 178.195,
-      "eval_steps_per_second": 2.798,
+      "eval_loss": 1.842081069946289,
+      "eval_runtime": 56.186,
+      "eval_samples_per_second": 177.98,
+      "eval_steps_per_second": 2.794,
       "step": 314
     },
     {
       "epoch": 3.0,
-      "eval_loss": 1.9429785013198853,
-      "eval_runtime": 56.3872,
-      "eval_samples_per_second": 177.345,
-      "eval_steps_per_second": 2.784,
+      "eval_loss": 1.8316441774368286,
+      "eval_runtime": 56.2573,
+      "eval_samples_per_second": 177.755,
+      "eval_steps_per_second": 2.791,
       "step": 471
     },
     {
       "epoch": 3.18,
-      "grad_norm": 272919.25,
+      "grad_norm": 270056.0,
       "learning_rate": 4.076433121019109e-06,
-      "loss": 1.9779,
+      "loss": 1.8572,
       "step": 500
     },
     {
       "epoch": 4.0,
-      "eval_loss": 1.933491587638855,
-      "eval_runtime": 56.2041,
-      "eval_samples_per_second": 177.923,
-      "eval_steps_per_second": 2.793,
+      "eval_loss": 1.8257514238357544,
+      "eval_runtime": 56.1934,
+      "eval_samples_per_second": 177.957,
+      "eval_steps_per_second": 2.794,
       "step": 628
     }
   ],

checkpoint-628/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7f5e90c7805641bc892f9f4320eca12b2c8f20b081b2afe84a46e2610a9d64d
+oid sha256:b9e6c9dcf12487c2d88138c370883e2f459a3d4aa9dcd2df9d77cc3b163b525a
 size 4539