Pushing complete fine-tuned model with all necessary files

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ebef7d5a7347009f334d030bc17a34a72c0a046597547a996fa3e252966e27
+oid sha256:f3f16fb1332d29600738b4376134403effff4be038f8b6bddb7948e9138d25e8
 size 93378688

checkpoint-25/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6d7b334eb490c2c309e20faf9e676ac140b812c2f25f174d784ba4737482e21
+oid sha256:c414724e6efbe25f59394136d833c6e589761346a36a2d9e3ddbe5b4eb9bc807
 size 93378688

checkpoint-25/generation_config.json

@@ -14,5 +14,5 @@
     32002
   ],
   "pad_token_id": 0,
-  "transformers_version": "4.48.0.dev0"
+  "transformers_version": "4.49.0.dev0"
 }

checkpoint-25/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c33271db3bb9fb15c420653e5e95f4ac97a7864bcb7a240b24143fe9ce831704
+oid sha256:62b39f752a8785b1af9a576a5a1e90728102a2e2ea1c05e6362d39529aa253f7
 size 48071944

checkpoint-25/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e9cf1e2b80a52e7a77a9580bf6adc6f13f28f3310ef491aeef3c52cc69312f2
+oid sha256:efc28ad80cea8f243bc60a65f57b083b27baee89443e3fcd78e3b1a5fd06f6a3
 size 14244

checkpoint-25/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd1ca147bfe22a3195c5bd942d2592aec616b2c4d98403ef43122a3fa147216c
+oid sha256:9c016ebe9cc98685d69c3b36179d5db608efbd4f844e87281ef2d749531cd8d2
 size 1064

checkpoint-25/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11841326228537596,
+  "epoch": 0.12195121951219512,
   "eval_steps": 10,
   "global_step": 25,
   "is_hyper_param_search": false,
@@ -9,54 +9,54 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.023682652457075192,
-      "grad_norm": 38.363624572753906,
-      "learning_rate": 9e-05,
-      "loss": 3.9738,
+      "epoch": 0.024390243902439025,
+      "grad_norm": 8.752623558044434,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 0.5615,
       "step": 5
     },
     {
-      "epoch": 0.047365304914150384,
-      "grad_norm": Infinity,
-      "learning_rate": 8.666666666666667e-05,
-      "loss": 3.5925,
+      "epoch": 0.04878048780487805,
+      "grad_norm": 11.641535758972168,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.8518,
       "step": 10
     },
     {
-      "epoch": 0.047365304914150384,
-      "eval_loss": 2.8427393436431885,
-      "eval_runtime": 244.1843,
-      "eval_samples_per_second": 2.756,
-      "eval_steps_per_second": 1.38,
+      "epoch": 0.04878048780487805,
+      "eval_loss": 1.3595986366271973,
+      "eval_runtime": 233.8268,
+      "eval_samples_per_second": 2.793,
+      "eval_steps_per_second": 1.398,
       "step": 10
     },
     {
-      "epoch": 0.07104795737122557,
-      "grad_norm": 12.08838939666748,
-      "learning_rate": 7.333333333333333e-05,
-      "loss": 2.7399,
+      "epoch": 0.07317073170731707,
+      "grad_norm": 10.912981033325195,
+      "learning_rate": 5e-05,
+      "loss": 0.8933,
       "step": 15
     },
     {
-      "epoch": 0.09473060982830077,
-      "grad_norm": 11.703186988830566,
-      "learning_rate": 5.666666666666667e-05,
-      "loss": 1.3988,
+      "epoch": 0.0975609756097561,
+      "grad_norm": 10.059850692749023,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.8969,
       "step": 20
     },
     {
-      "epoch": 0.09473060982830077,
-      "eval_loss": 1.3483482599258423,
-      "eval_runtime": 247.0633,
-      "eval_samples_per_second": 2.724,
-      "eval_steps_per_second": 1.364,
+      "epoch": 0.0975609756097561,
+      "eval_loss": 1.281290888786316,
+      "eval_runtime": 234.7195,
+      "eval_samples_per_second": 2.782,
+      "eval_steps_per_second": 1.393,
       "step": 20
     },
     {
-      "epoch": 0.11841326228537596,
-      "grad_norm": 21.7695369720459,
-      "learning_rate": 4e-05,
-      "loss": 1.3289,
+      "epoch": 0.12195121951219512,
+      "grad_norm": 9.400066375732422,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.8338,
       "step": 25
     }
   ],
@@ -77,7 +77,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2246384959161024.0,
+  "total_flos": 2183717354136384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

checkpoint-25/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc637676303d4f40e3a45fd2a9af293c99f68beb0db90cfaa8062315c931a25a
+oid sha256:4eed6c37f072298a1664e5513f470ad3c4130aa13a3822fa4fd447a25eec7a3f
 size 5304

checkpoint-30/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ebef7d5a7347009f334d030bc17a34a72c0a046597547a996fa3e252966e27
+oid sha256:f3f16fb1332d29600738b4376134403effff4be038f8b6bddb7948e9138d25e8
 size 93378688

checkpoint-30/generation_config.json

@@ -14,5 +14,5 @@
     32002
   ],
   "pad_token_id": 0,
-  "transformers_version": "4.48.0.dev0"
+  "transformers_version": "4.49.0.dev0"
 }

checkpoint-30/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e246e143a47a3be4c37648d013008ce5b18ceaccabdfa487e854f6a2668ced1
+oid sha256:e93c12b54990119a04354f6bbc24075b3c635809ff27f85b65441ec577efddff
 size 48071944

checkpoint-30/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b98cbc14b559a2c3eabfc23b1ceaf69d5c3ce0cefe144a24e4fcfe9f6f18a81b
+oid sha256:04248c42bbebc8c793e7835eb43553821faa507ba4b4f25d2dcfb0d342fe243e
 size 14244

checkpoint-30/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9241253195e2761992c7c0b60b7dd0fd1941182b7ded242213ead4f9c0f8c82
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

checkpoint-30/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14209591474245115,
+  "epoch": 0.14634146341463414,
   "eval_steps": 10,
   "global_step": 30,
   "is_hyper_param_search": false,
@@ -9,69 +9,69 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.023682652457075192,
-      "grad_norm": 38.363624572753906,
-      "learning_rate": 9e-05,
-      "loss": 3.9738,
+      "epoch": 0.024390243902439025,
+      "grad_norm": 8.752623558044434,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 0.5615,
       "step": 5
     },
     {
-      "epoch": 0.047365304914150384,
-      "grad_norm": Infinity,
-      "learning_rate": 8.666666666666667e-05,
-      "loss": 3.5925,
+      "epoch": 0.04878048780487805,
+      "grad_norm": 11.641535758972168,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.8518,
       "step": 10
     },
     {
-      "epoch": 0.047365304914150384,
-      "eval_loss": 2.8427393436431885,
-      "eval_runtime": 244.1843,
-      "eval_samples_per_second": 2.756,
-      "eval_steps_per_second": 1.38,
+      "epoch": 0.04878048780487805,
+      "eval_loss": 1.3595986366271973,
+      "eval_runtime": 233.8268,
+      "eval_samples_per_second": 2.793,
+      "eval_steps_per_second": 1.398,
       "step": 10
     },
     {
-      "epoch": 0.07104795737122557,
-      "grad_norm": 12.08838939666748,
-      "learning_rate": 7.333333333333333e-05,
-      "loss": 2.7399,
+      "epoch": 0.07317073170731707,
+      "grad_norm": 10.912981033325195,
+      "learning_rate": 5e-05,
+      "loss": 0.8933,
       "step": 15
     },
     {
-      "epoch": 0.09473060982830077,
-      "grad_norm": 11.703186988830566,
-      "learning_rate": 5.666666666666667e-05,
-      "loss": 1.3988,
+      "epoch": 0.0975609756097561,
+      "grad_norm": 10.059850692749023,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.8969,
       "step": 20
     },
     {
-      "epoch": 0.09473060982830077,
-      "eval_loss": 1.3483482599258423,
-      "eval_runtime": 247.0633,
-      "eval_samples_per_second": 2.724,
-      "eval_steps_per_second": 1.364,
+      "epoch": 0.0975609756097561,
+      "eval_loss": 1.281290888786316,
+      "eval_runtime": 234.7195,
+      "eval_samples_per_second": 2.782,
+      "eval_steps_per_second": 1.393,
       "step": 20
     },
     {
-      "epoch": 0.11841326228537596,
-      "grad_norm": 21.7695369720459,
-      "learning_rate": 4e-05,
-      "loss": 1.3289,
+      "epoch": 0.12195121951219512,
+      "grad_norm": 9.400066375732422,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.8338,
       "step": 25
     },
     {
-      "epoch": 0.14209591474245115,
-      "grad_norm": 10.536179542541504,
-      "learning_rate": 2.3333333333333336e-05,
-      "loss": 1.2495,
+      "epoch": 0.14634146341463414,
+      "grad_norm": 8.542190551757812,
+      "learning_rate": 0.0,
+      "loss": 0.7171,
       "step": 30
     },
     {
-      "epoch": 0.14209591474245115,
-      "eval_loss": 1.2752900123596191,
-      "eval_runtime": 247.8091,
-      "eval_samples_per_second": 2.716,
-      "eval_steps_per_second": 1.36,
+      "epoch": 0.14634146341463414,
+      "eval_loss": 1.2695448398590088,
+      "eval_runtime": 234.1517,
+      "eval_samples_per_second": 2.789,
+      "eval_steps_per_second": 1.397,
       "step": 30
     }
   ],
@@ -92,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2689832869002048.0,
+  "total_flos": 2620003251974592.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

checkpoint-30/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc637676303d4f40e3a45fd2a9af293c99f68beb0db90cfaa8062315c931a25a
+oid sha256:4eed6c37f072298a1664e5513f470ad3c4130aa13a3822fa4fd447a25eec7a3f
 size 5304

generation_config.json

@@ -14,5 +14,5 @@
     32002
   ],
   "pad_token_id": 0,
-  "transformers_version": "4.48.0.dev0"
+  "transformers_version": "4.49.0.dev0"
 }