Upload folder using huggingface_hub

README.md

@@ -1,6 +1,10 @@
 ---
 base_model: Salesforce/codet5-base
 library_name: peft
+tags:
+- base_model:adapter:Salesforce/codet5-base
+- lora
+- transformers
 ---
 
 # Model Card for Model ID
@@ -199,4 +203,5 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
+- PEFT 0.18.0
 - PEFT 0.12.0

adapter_config.json

@@ -1,8 +1,14 @@
 {
+  "alora_invocation_tokens": null,
   "alpha_pattern": {},
+  "arrow_config": null,
   "auto_mapping": null,
   "base_model_name_or_path": "Salesforce/codet5-base",
   "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,21 +17,27 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
+  "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
   "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o",
-    "v",
     "q",
-    "k"
+    "k",
+    "o",
+    "v"
   ],
+  "target_parameters": null,
   "task_type": "SEQ_2_SEQ_LM",
+  "trainable_token_indices": null,
   "use_dora": false,
+  "use_qalora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c922d4b9b4865f0895cf70990c49e7458cb3c5ac4e1b5b0b72a774b7514d4b
+oid sha256:640ecbfaac397ec3bfdcabb585e02a7c9d74cdca737214766274fbe3c6574c9f
 size 7117824

checkpoint-9213/README.md

@@ -1,6 +1,10 @@
 ---
 base_model: Salesforce/codet5-base
 library_name: peft
+tags:
+- base_model:adapter:Salesforce/codet5-base
+- lora
+- transformers
 ---
 
 # Model Card for Model ID
@@ -199,4 +203,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
-- PEFT 0.12.0
+- PEFT 0.18.0

checkpoint-9213/adapter_config.json

@@ -1,8 +1,14 @@
 {
+  "alora_invocation_tokens": null,
   "alpha_pattern": {},
+  "arrow_config": null,
   "auto_mapping": null,
   "base_model_name_or_path": "Salesforce/codet5-base",
   "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,21 +17,27 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
+  "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
   "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o",
-    "v",
     "q",
-    "k"
+    "k",
+    "o",
+    "v"
   ],
+  "target_parameters": null,
   "task_type": "SEQ_2_SEQ_LM",
+  "trainable_token_indices": null,
   "use_dora": false,
+  "use_qalora": false,
   "use_rslora": false
 }

checkpoint-9213/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c922d4b9b4865f0895cf70990c49e7458cb3c5ac4e1b5b0b72a774b7514d4b
+oid sha256:640ecbfaac397ec3bfdcabb585e02a7c9d74cdca737214766274fbe3c6574c9f
 size 7117824

checkpoint-9213/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8697ac1d3dba5f15118a269ae29435a8fbe2ace44928ccfb9668f1c1effd0a86
-size 14397434
+oid sha256:89b9a84a299ec73f6f694fa211f58c1a71f1ed383ff10ddd9bdde45563b5b823
+size 3912788

checkpoint-9213/tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 256,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 256
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "<pad>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

checkpoint-9213/trainer_state.json

@@ -11,1329 +11,1329 @@
   "log_history": [
     {
       "epoch": 0.0162813415825464,
-      "grad_norm": 1.3991888761520386,
+      "grad_norm": 1.3473832607269287,
       "learning_rate": 4.973407142081841e-05,
-      "loss": 4.4039175415039065,
+      "loss": 4.392664489746093,
       "step": 50
     },
     {
       "epoch": 0.0325626831650928,
-      "grad_norm": 2.573707342147827,
+      "grad_norm": 1.8160868883132935,
       "learning_rate": 4.946271572777597e-05,
-      "loss": 3.261125183105469,
+      "loss": 3.211649169921875,
       "step": 100
     },
     {
       "epoch": 0.04884402474763921,
-      "grad_norm": 1.1588261127471924,
+      "grad_norm": 1.1382832527160645,
       "learning_rate": 4.919136003473353e-05,
-      "loss": 2.1376600646972657,
+      "loss": 2.1162736511230467,
       "step": 150
     },
     {
       "epoch": 0.0651253663301856,
-      "grad_norm": 1.4137802124023438,
+      "grad_norm": 1.3651690483093262,
       "learning_rate": 4.892000434169109e-05,
-      "loss": 1.8963032531738282,
+      "loss": 1.873338623046875,
       "step": 200
     },
     {
       "epoch": 0.08140670791273201,
-      "grad_norm": 1.9414198398590088,
+      "grad_norm": 1.7120460271835327,
       "learning_rate": 4.8648648648648654e-05,
-      "loss": 1.8314729309082032,
+      "loss": 1.8091192626953125,
       "step": 250
     },
     {
       "epoch": 0.09768804949527841,
-      "grad_norm": 1.4838837385177612,
+      "grad_norm": 1.4614651203155518,
       "learning_rate": 4.837729295560621e-05,
-      "loss": 1.7229083251953126,
+      "loss": 1.7023934936523437,
       "step": 300
     },
     {
       "epoch": 0.11396939107782482,
-      "grad_norm": 1.7064085006713867,
+      "grad_norm": 1.4845161437988281,
       "learning_rate": 4.810593726256377e-05,
-      "loss": 1.6793362426757812,
+      "loss": 1.6588560485839843,
       "step": 350
     },
     {
       "epoch": 0.1302507326603712,
-      "grad_norm": 1.4688920974731445,
+      "grad_norm": 1.4929733276367188,
       "learning_rate": 4.783458156952133e-05,
-      "loss": 1.598350067138672,
+      "loss": 1.5784068298339844,
       "step": 400
     },
     {
       "epoch": 0.14653207424291761,
-      "grad_norm": 1.336400032043457,
+      "grad_norm": 1.3720242977142334,
       "learning_rate": 4.756322587647889e-05,
-      "loss": 1.5864486694335938,
+      "loss": 1.5646693420410156,
       "step": 450
     },
     {
       "epoch": 0.16281341582546402,
-      "grad_norm": 1.780544638633728,
+      "grad_norm": 1.968331217765808,
       "learning_rate": 4.729187018343645e-05,
-      "loss": 1.4491355895996094,
+      "loss": 1.424574737548828,
       "step": 500
     },
     {
       "epoch": 0.17909475740801042,
-      "grad_norm": 1.9979498386383057,
+      "grad_norm": 1.8840748071670532,
       "learning_rate": 4.7020514490394014e-05,
-      "loss": 1.508986358642578,
+      "loss": 1.485799560546875,
       "step": 550
     },
     {
       "epoch": 0.19537609899055683,
-      "grad_norm": 2.582775115966797,
+      "grad_norm": 2.7317214012145996,
       "learning_rate": 4.674915879735157e-05,
-      "loss": 1.3531187438964845,
+      "loss": 1.3331263732910157,
       "step": 600
     },
     {
       "epoch": 0.21165744057310323,
-      "grad_norm": 1.9345420598983765,
+      "grad_norm": 1.773260474205017,
       "learning_rate": 4.647780310430913e-05,
-      "loss": 1.3679487609863281,
+      "loss": 1.3437060546875,
       "step": 650
     },
     {
       "epoch": 0.22793878215564964,
-      "grad_norm": 1.9719504117965698,
+      "grad_norm": 1.9822585582733154,
       "learning_rate": 4.620644741126669e-05,
-      "loss": 1.324554443359375,
+      "loss": 1.3029965209960936,
       "step": 700
     },
     {
       "epoch": 0.24422012373819602,
-      "grad_norm": 1.7349779605865479,
+      "grad_norm": 1.9712088108062744,
       "learning_rate": 4.593509171822425e-05,
-      "loss": 1.2080127716064453,
+      "loss": 1.1877630615234376,
       "step": 750
     },
     {
       "epoch": 0.2605014653207424,
-      "grad_norm": 2.53094482421875,
+      "grad_norm": 2.6370294094085693,
       "learning_rate": 4.566373602518181e-05,
-      "loss": 1.219000244140625,
+      "loss": 1.1992277526855468,
       "step": 800
     },
     {
       "epoch": 0.2767828069032888,
-      "grad_norm": 2.5429346561431885,
+      "grad_norm": 2.512601852416992,
       "learning_rate": 4.5392380332139374e-05,
-      "loss": 1.263201675415039,
+      "loss": 1.2441465759277344,
       "step": 850
     },
     {
       "epoch": 0.29306414848583523,
-      "grad_norm": 2.447312831878662,
+      "grad_norm": 2.6893482208251953,
       "learning_rate": 4.512102463909693e-05,
-      "loss": 1.1299581146240234,
+      "loss": 1.1057972717285156,
       "step": 900
     },
     {
       "epoch": 0.30934549006838163,
-      "grad_norm": 2.299469470977783,
+      "grad_norm": 2.995448589324951,
       "learning_rate": 4.484966894605449e-05,
-      "loss": 1.1863082122802735,
+      "loss": 1.1611495208740235,
       "step": 950
     },
     {
       "epoch": 0.32562683165092804,
-      "grad_norm": 2.7745773792266846,
+      "grad_norm": 2.9329564571380615,
       "learning_rate": 4.457831325301205e-05,
-      "loss": 1.1487353515625,
+      "loss": 1.1252006530761718,
       "step": 1000
     },
     {
       "epoch": 0.34190817323347444,
-      "grad_norm": 2.7474420070648193,
+      "grad_norm": 2.749084234237671,
       "learning_rate": 4.430695755996961e-05,
-      "loss": 1.1214525604248047,
+      "loss": 1.096492691040039,
       "step": 1050
     },
     {
       "epoch": 0.35818951481602085,
-      "grad_norm": 2.597487211227417,
+      "grad_norm": 2.9316182136535645,
       "learning_rate": 4.403560186692717e-05,
-      "loss": 1.0956230163574219,
+      "loss": 1.0722020721435548,
       "step": 1100
     },
     {
       "epoch": 0.37447085639856725,
-      "grad_norm": 2.393484354019165,
+      "grad_norm": 2.6080806255340576,
       "learning_rate": 4.3764246173884733e-05,
-      "loss": 1.0677281951904296,
+      "loss": 1.0462689971923829,
       "step": 1150
     },
     {
       "epoch": 0.39075219798111366,
-      "grad_norm": 2.6319406032562256,
+      "grad_norm": 2.7301759719848633,
       "learning_rate": 4.349289048084229e-05,
-      "loss": 1.0166962432861328,
+      "loss": 0.9948210144042968,
       "step": 1200
     },
     {
       "epoch": 0.40703353956366006,
-      "grad_norm": 2.9170615673065186,
+      "grad_norm": 3.1961374282836914,
       "learning_rate": 4.322153478779985e-05,
-      "loss": 0.9722758483886719,
+      "loss": 0.9516075897216797,
       "step": 1250
     },
     {
       "epoch": 0.42331488114620647,
-      "grad_norm": 3.030376672744751,
+      "grad_norm": 3.144866704940796,
       "learning_rate": 4.295017909475741e-05,
-      "loss": 0.9831496429443359,
+      "loss": 0.9630168914794922,
       "step": 1300
     },
     {
       "epoch": 0.4395962227287529,
-      "grad_norm": 1.9566906690597534,
+      "grad_norm": 2.025820255279541,
       "learning_rate": 4.267882340171497e-05,
-      "loss": 1.0231520080566405,
+      "loss": 0.9979273223876953,
       "step": 1350
     },
     {
       "epoch": 0.4558775643112993,
-      "grad_norm": 3.1707541942596436,
+      "grad_norm": 3.443812847137451,
       "learning_rate": 4.2407467708672534e-05,
-      "loss": 0.9151640319824219,
+      "loss": 0.8928343963623047,
       "step": 1400
     },
     {
       "epoch": 0.4721589058938456,
-      "grad_norm": 3.353412628173828,
+      "grad_norm": 3.585447311401367,
       "learning_rate": 4.213611201563009e-05,
-      "loss": 0.9734893035888672,
+      "loss": 0.9557633972167969,
       "step": 1450
     },
     {
       "epoch": 0.48844024747639203,
-      "grad_norm": 2.1188318729400635,
+      "grad_norm": 2.1626651287078857,
       "learning_rate": 4.186475632258765e-05,
-      "loss": 0.9237932586669921,
+      "loss": 0.9039353179931641,
       "step": 1500
     },
     {
       "epoch": 0.5047215890589385,
-      "grad_norm": 2.6821577548980713,
+      "grad_norm": 2.562255620956421,
       "learning_rate": 4.159340062954521e-05,
-      "loss": 0.8897212982177735,
+      "loss": 0.8657318115234375,
       "step": 1550
     },
     {
       "epoch": 0.5210029306414848,
-      "grad_norm": 2.135638475418091,
+      "grad_norm": 2.244072198867798,
       "learning_rate": 4.132204493650277e-05,
-      "loss": 0.9515829467773438,
+      "loss": 0.9271598815917969,
       "step": 1600
     },
     {
       "epoch": 0.5372842722240313,
-      "grad_norm": 2.822666645050049,
+      "grad_norm": 2.8100831508636475,
       "learning_rate": 4.105068924346033e-05,
-      "loss": 0.9121678161621094,
+      "loss": 0.8872251892089844,
       "step": 1650
     },
     {
       "epoch": 0.5535656138065776,
-      "grad_norm": 2.7274110317230225,
+      "grad_norm": 2.8497555255889893,
       "learning_rate": 4.0779333550417894e-05,
-      "loss": 0.9216725158691407,
+      "loss": 0.8983834838867187,
       "step": 1700
     },
     {
       "epoch": 0.5698469553891241,
-      "grad_norm": 2.2153918743133545,
+      "grad_norm": 2.229484796524048,
       "learning_rate": 4.050797785737545e-05,
-      "loss": 0.9212928009033203,
+      "loss": 0.9012404632568359,
       "step": 1750
     },
     {
       "epoch": 0.5861282969716705,
-      "grad_norm": 2.8363842964172363,
+      "grad_norm": 2.551394462585449,
       "learning_rate": 4.023662216433301e-05,
-      "loss": 0.8820828247070313,
+      "loss": 0.8586711883544922,
       "step": 1800
     },
     {
       "epoch": 0.6024096385542169,
-      "grad_norm": 3.7503888607025146,
+      "grad_norm": 3.706598997116089,
       "learning_rate": 3.996526647129057e-05,
-      "loss": 0.8915911865234375,
+      "loss": 0.8685987091064453,
       "step": 1850
     },
     {
       "epoch": 0.6186909801367633,
-      "grad_norm": 2.9024317264556885,
+      "grad_norm": 2.964557409286499,
       "learning_rate": 3.969391077824813e-05,
-      "loss": 0.8826235961914063,
+      "loss": 0.8568785095214844,
       "step": 1900
     },
     {
       "epoch": 0.6349723217193096,
-      "grad_norm": 2.6529974937438965,
+      "grad_norm": 2.809697151184082,
       "learning_rate": 3.942255508520569e-05,
-      "loss": 0.7980400085449219,
+      "loss": 0.7817304992675781,
       "step": 1950
     },
     {
       "epoch": 0.6512536633018561,
-      "grad_norm": 2.9299404621124268,
+      "grad_norm": 2.845287799835205,
       "learning_rate": 3.9151199392163254e-05,
-      "loss": 0.8449476623535156,
+      "loss": 0.8261214447021484,
       "step": 2000
     },
     {
       "epoch": 0.6675350048844024,
-      "grad_norm": 2.36393141746521,
+      "grad_norm": 2.3624467849731445,
       "learning_rate": 3.887984369912081e-05,
-      "loss": 0.8074803161621094,
+      "loss": 0.7863189697265625,
       "step": 2050
     },
     {
       "epoch": 0.6838163464669489,
-      "grad_norm": 3.3569858074188232,
+      "grad_norm": 3.5507824420928955,
       "learning_rate": 3.860848800607837e-05,
-      "loss": 0.7903826141357422,
+      "loss": 0.7708241271972657,
       "step": 2100
     },
     {
       "epoch": 0.7000976880494952,
-      "grad_norm": 2.7112410068511963,
+      "grad_norm": 2.853994131088257,
       "learning_rate": 3.833713231303593e-05,
-      "loss": 0.7987868499755859,
+      "loss": 0.7777981567382812,
       "step": 2150
     },
     {
       "epoch": 0.7163790296320417,
-      "grad_norm": 2.964090347290039,
+      "grad_norm": 3.099780321121216,
       "learning_rate": 3.806577661999349e-05,
-      "loss": 0.9639425659179688,
+      "loss": 0.9427651214599609,
       "step": 2200
     },
     {
       "epoch": 0.732660371214588,
-      "grad_norm": 2.48537015914917,
+      "grad_norm": 2.143392562866211,
       "learning_rate": 3.7794420926951055e-05,
-      "loss": 0.8240141296386718,
+      "loss": 0.8011217498779297,
       "step": 2250
     },
     {
       "epoch": 0.7489417127971345,
-      "grad_norm": 3.37619948387146,
+      "grad_norm": 3.4226908683776855,
       "learning_rate": 3.7523065233908613e-05,
-      "loss": 0.7668092346191406,
+      "loss": 0.7524455261230468,
       "step": 2300
     },
     {
       "epoch": 0.7652230543796809,
-      "grad_norm": 3.8201708793640137,
+      "grad_norm": 3.735076904296875,
       "learning_rate": 3.725170954086617e-05,
-      "loss": 0.8363259887695312,
+      "loss": 0.8192281341552734,
       "step": 2350
     },
     {
       "epoch": 0.7815043959622273,
-      "grad_norm": 2.115691900253296,
+      "grad_norm": 2.332482099533081,
       "learning_rate": 3.698035384782373e-05,
-      "loss": 0.6972411346435546,
+      "loss": 0.6744720458984375,
       "step": 2400
     },
     {
       "epoch": 0.7977857375447737,
-      "grad_norm": 3.023482322692871,
+      "grad_norm": 3.1311633586883545,
       "learning_rate": 3.670899815478129e-05,
-      "loss": 0.7648641967773437,
+      "loss": 0.7469883728027343,
       "step": 2450
     },
     {
       "epoch": 0.8140670791273201,
-      "grad_norm": 2.759094715118408,
+      "grad_norm": 2.872544050216675,
       "learning_rate": 3.643764246173885e-05,
-      "loss": 0.7846918487548828,
+      "loss": 0.7605148315429687,
       "step": 2500
     },
     {
       "epoch": 0.8303484207098665,
-      "grad_norm": 2.3906078338623047,
+      "grad_norm": 2.4674670696258545,
       "learning_rate": 3.6166286768696414e-05,
-      "loss": 0.7888090515136719,
+      "loss": 0.7708393096923828,
       "step": 2550
     },
     {
       "epoch": 0.8466297622924129,
-      "grad_norm": 2.275580644607544,
+      "grad_norm": 2.391380548477173,
       "learning_rate": 3.589493107565397e-05,
-      "loss": 0.751231689453125,
+      "loss": 0.7390218353271485,
       "step": 2600
     },
     {
       "epoch": 0.8629111038749593,
-      "grad_norm": 2.802598237991333,
+      "grad_norm": 2.9628641605377197,
       "learning_rate": 3.562357538261153e-05,
-      "loss": 0.6764369201660156,
+      "loss": 0.660747299194336,
       "step": 2650
     },
     {
       "epoch": 0.8791924454575057,
-      "grad_norm": 3.350801706314087,
+      "grad_norm": 3.0942180156707764,
       "learning_rate": 3.535221968956909e-05,
-      "loss": 0.7479486083984375,
+      "loss": 0.725975570678711,
       "step": 2700
     },
     {
       "epoch": 0.8954737870400521,
-      "grad_norm": 2.61865496635437,
+      "grad_norm": 2.7016773223876953,
       "learning_rate": 3.508086399652665e-05,
-      "loss": 0.7227684020996094,
+      "loss": 0.7020815277099609,
       "step": 2750
     },
     {
       "epoch": 0.9117551286225986,
-      "grad_norm": 2.1037511825561523,
+      "grad_norm": 4.184632778167725,
       "learning_rate": 3.480950830348421e-05,
-      "loss": 0.738468017578125,
+      "loss": 0.7197840118408203,
       "step": 2800
     },
     {
       "epoch": 0.9280364702051449,
-      "grad_norm": 3.354844093322754,
+      "grad_norm": 3.345290422439575,
       "learning_rate": 3.4538152610441774e-05,
-      "loss": 0.7212671661376953,
+      "loss": 0.7012833404541016,
       "step": 2850
     },
     {
       "epoch": 0.9443178117876913,
-      "grad_norm": 3.2951793670654297,
+      "grad_norm": 3.3522071838378906,
       "learning_rate": 3.426679691739933e-05,
-      "loss": 0.7343311309814453,
+      "loss": 0.7069497680664063,
       "step": 2900
     },
     {
       "epoch": 0.9605991533702377,
-      "grad_norm": 2.4111647605895996,
+      "grad_norm": 2.183042049407959,
       "learning_rate": 3.399544122435689e-05,
-      "loss": 0.7199324798583985,
+      "loss": 0.6970455169677734,
       "step": 2950
     },
     {
       "epoch": 0.9768804949527841,
-      "grad_norm": 3.4211530685424805,
+      "grad_norm": 3.836655616760254,
       "learning_rate": 3.372408553131445e-05,
-      "loss": 0.6700502014160157,
+      "loss": 0.6455158996582031,
       "step": 3000
     },
     {
       "epoch": 0.9931618365353305,
-      "grad_norm": 3.150545120239258,
+      "grad_norm": 2.9731621742248535,
       "learning_rate": 3.345272983827201e-05,
-      "loss": 0.7762191009521484,
+      "loss": 0.7525621795654297,
       "step": 3050
     },
     {
       "epoch": 1.0,
-      "eval_bertscore_f1": 0.967131909063726,
-      "eval_bleu": 0.6360648795879948,
-      "eval_loss": 0.4895643889904022,
-      "eval_meteor": 0.7343290842184582,
-      "eval_rouge1": 0.8540844780031187,
-      "eval_rouge2": 0.7479710009166031,
-      "eval_runtime": 123.0031,
-      "eval_samples_per_second": 10.504,
-      "eval_steps_per_second": 1.317,
+      "eval_bertscore_f1": 0.9678319004297995,
+      "eval_bleu": 0.6471772455613484,
+      "eval_loss": 0.47463923692703247,
+      "eval_meteor": 0.7416422834916577,
+      "eval_rouge1": 0.855324288070084,
+      "eval_rouge2": 0.7532566990075111,
+      "eval_runtime": 127.1335,
+      "eval_samples_per_second": 10.163,
+      "eval_steps_per_second": 1.274,
       "step": 3071
     },
     {
       "epoch": 1.009443178117877,
-      "grad_norm": 3.3871090412139893,
+      "grad_norm": 3.100937604904175,
       "learning_rate": 3.318137414522957e-05,
-      "loss": 0.6021672821044922,
+      "loss": 0.5857192230224609,
       "step": 3100
     },
     {
       "epoch": 1.0257245197004232,
-      "grad_norm": 3.6125218868255615,
+      "grad_norm": 3.4073121547698975,
       "learning_rate": 3.291001845218713e-05,
-      "loss": 0.5918669891357422,
+      "loss": 0.5697959518432617,
       "step": 3150
     },
     {
       "epoch": 1.0420058612829697,
-      "grad_norm": 3.303037166595459,
+      "grad_norm": 3.4600396156311035,
       "learning_rate": 3.263866275914469e-05,
-      "loss": 0.6978528594970703,
+      "loss": 0.6803036499023437,
       "step": 3200
     },
     {
       "epoch": 1.0582872028655161,
-      "grad_norm": 4.224201202392578,
+      "grad_norm": 4.564633846282959,
       "learning_rate": 3.236730706610225e-05,
-      "loss": 0.6617731475830078,
+      "loss": 0.6410063934326172,
       "step": 3250
     },
     {
       "epoch": 1.0745685444480626,
-      "grad_norm": 3.4028713703155518,
+      "grad_norm": 3.4267613887786865,
       "learning_rate": 3.209595137305981e-05,
-      "loss": 0.6562766265869141,
+      "loss": 0.6364714813232422,
       "step": 3300
     },
     {
       "epoch": 1.0908498860306088,
-      "grad_norm": 3.408994436264038,
+      "grad_norm": 3.4027607440948486,
       "learning_rate": 3.182459568001737e-05,
-      "loss": 0.6277020263671875,
+      "loss": 0.6122965240478515,
       "step": 3350
     },
     {
       "epoch": 1.1071312276131553,
-      "grad_norm": 2.8505773544311523,
+      "grad_norm": 2.7794837951660156,
       "learning_rate": 3.155323998697493e-05,
-      "loss": 0.6104128646850586,
+      "loss": 0.5932202529907227,
       "step": 3400
     },
     {
       "epoch": 1.1234125691957018,
-      "grad_norm": 3.966662645339966,
+      "grad_norm": 3.5116841793060303,
       "learning_rate": 3.128188429393249e-05,
-      "loss": 0.6578683471679687,
+      "loss": 0.6330239868164063,
       "step": 3450
     },
     {
       "epoch": 1.1396939107782482,
-      "grad_norm": 3.1553022861480713,
+      "grad_norm": 2.800938129425049,
       "learning_rate": 3.1010528600890045e-05,
-      "loss": 0.6029189300537109,
+      "loss": 0.5926042938232422,
       "step": 3500
     },
     {
       "epoch": 1.1559752523607945,
-      "grad_norm": 2.4723594188690186,
+      "grad_norm": 2.6473214626312256,
       "learning_rate": 3.0739172907847604e-05,
-      "loss": 0.5845599365234375,
+      "loss": 0.5683625793457031,
       "step": 3550
     },
     {
       "epoch": 1.172256593943341,
-      "grad_norm": 3.4956090450286865,
+      "grad_norm": 3.2271904945373535,
       "learning_rate": 3.0467817214805167e-05,
-      "loss": 0.7056507110595703,
+      "loss": 0.6833554077148437,
       "step": 3600
     },
     {
       "epoch": 1.1885379355258874,
-      "grad_norm": 2.530539035797119,
+      "grad_norm": 3.032439947128296,
       "learning_rate": 3.0196461521762725e-05,
-      "loss": 0.6525007629394531,
+      "loss": 0.6369483947753907,
       "step": 3650
     },
     {
       "epoch": 1.2048192771084336,
-      "grad_norm": 3.184187173843384,
+      "grad_norm": 3.3694541454315186,
       "learning_rate": 2.992510582872029e-05,
-      "loss": 0.6267402267456055,
+      "loss": 0.6112889480590821,
       "step": 3700
     },
     {
       "epoch": 1.22110061869098,
-      "grad_norm": 2.8025341033935547,
+      "grad_norm": 2.811060905456543,
       "learning_rate": 2.965375013567785e-05,
-      "loss": 0.6082941436767578,
+      "loss": 0.5923568344116211,
       "step": 3750
     },
     {
       "epoch": 1.2373819602735265,
-      "grad_norm": 3.8412115573883057,
+      "grad_norm": 3.533724069595337,
       "learning_rate": 2.938239444263541e-05,
-      "loss": 0.6256865310668945,
+      "loss": 0.6127109909057618,
       "step": 3800
     },
     {
       "epoch": 1.253663301856073,
-      "grad_norm": 2.749920606613159,
+      "grad_norm": 3.5569841861724854,
       "learning_rate": 2.9111038749592967e-05,
-      "loss": 0.5645497512817382,
+      "loss": 0.554149169921875,
       "step": 3850
     },
     {
       "epoch": 1.2699446434386195,
-      "grad_norm": 3.3938541412353516,
+      "grad_norm": 3.246440887451172,
       "learning_rate": 2.8839683056550526e-05,
-      "loss": 0.6264593887329102,
+      "loss": 0.6123342514038086,
       "step": 3900
     },
     {
       "epoch": 1.2862259850211657,
-      "grad_norm": 3.3540456295013428,
+      "grad_norm": 3.752815008163452,
       "learning_rate": 2.8568327363508085e-05,
-      "loss": 0.6137894821166993,
+      "loss": 0.596214942932129,
       "step": 3950
     },
     {
       "epoch": 1.3025073266037122,
-      "grad_norm": 2.7908146381378174,
+      "grad_norm": 2.5075297355651855,
       "learning_rate": 2.829697167046565e-05,
-      "loss": 0.6254143142700195,
+      "loss": 0.6021640777587891,
       "step": 4000
     },
     {
       "epoch": 1.3187886681862586,
-      "grad_norm": 2.430589199066162,
+      "grad_norm": 2.307556629180908,
       "learning_rate": 2.802561597742321e-05,
-      "loss": 0.6473207092285156,
+      "loss": 0.628720359802246,
       "step": 4050
     },
     {
       "epoch": 1.3350700097688049,
-      "grad_norm": 3.0248193740844727,
+      "grad_norm": 3.7279775142669678,
       "learning_rate": 2.775426028438077e-05,
-      "loss": 0.6663880920410157,
+      "loss": 0.6525094604492188,
       "step": 4100
     },
     {
       "epoch": 1.3513513513513513,
-      "grad_norm": 2.987276077270508,
+      "grad_norm": 3.003065347671509,
       "learning_rate": 2.7482904591338327e-05,
-      "loss": 0.5809850692749023,
+      "loss": 0.5614350509643554,
       "step": 4150
     },
     {
       "epoch": 1.3676326929338978,
-      "grad_norm": 4.544067859649658,
+      "grad_norm": 3.551547050476074,
       "learning_rate": 2.7211548898295886e-05,
-      "loss": 0.5767688369750976,
+      "loss": 0.5608404922485352,
       "step": 4200
     },
     {
       "epoch": 1.3839140345164442,
-      "grad_norm": 2.878161907196045,
+      "grad_norm": 2.9098353385925293,
       "learning_rate": 2.694019320525345e-05,
-      "loss": 0.5451320266723633,
+      "loss": 0.5317767715454101,
       "step": 4250
     },
     {
       "epoch": 1.4001953760989905,
-      "grad_norm": 3.9910073280334473,
+      "grad_norm": 5.120357036590576,
       "learning_rate": 2.666883751221101e-05,
-      "loss": 0.6352932739257813,
+      "loss": 0.6232344818115234,
       "step": 4300
     },
     {
       "epoch": 1.416476717681537,
-      "grad_norm": 2.224102258682251,
+      "grad_norm": 2.4433658123016357,
       "learning_rate": 2.639748181916857e-05,
-      "loss": 0.5719359588623046,
+      "loss": 0.555752182006836,
       "step": 4350
     },
     {
       "epoch": 1.4327580592640834,
-      "grad_norm": 2.5918033123016357,
+      "grad_norm": 2.675360679626465,
       "learning_rate": 2.6126126126126128e-05,
-      "loss": 0.5936804962158203,
+      "loss": 0.5809175872802734,
       "step": 4400
     },
     {
       "epoch": 1.4490394008466296,
-      "grad_norm": 3.0837864875793457,
+      "grad_norm": 3.008749485015869,
       "learning_rate": 2.5854770433083687e-05,
-      "loss": 0.6499692535400391,
+      "loss": 0.6393648910522461,
       "step": 4450
     },
     {
       "epoch": 1.465320742429176,
-      "grad_norm": 4.25653600692749,
+      "grad_norm": 4.671627998352051,
       "learning_rate": 2.5583414740041246e-05,
-      "loss": 0.5930651092529297,
+      "loss": 0.5763546371459961,
       "step": 4500
     },
     {
       "epoch": 1.4816020840117226,
-      "grad_norm": 2.713430881500244,
+      "grad_norm": 2.942686080932617,
       "learning_rate": 2.5312059046998808e-05,
-      "loss": 0.5880680847167968,
+      "loss": 0.5711518478393555,
       "step": 4550
     },
     {
       "epoch": 1.497883425594269,
-      "grad_norm": 2.596726417541504,
+      "grad_norm": 2.2898240089416504,
       "learning_rate": 2.504070335395637e-05,
-      "loss": 0.609322280883789,
+      "loss": 0.5915301132202149,
       "step": 4600
     },
     {
       "epoch": 1.5141647671768155,
-      "grad_norm": 5.058499813079834,
+      "grad_norm": 5.238982677459717,
       "learning_rate": 2.476934766091393e-05,
-      "loss": 0.5476129531860352,
+      "loss": 0.5306437683105468,
       "step": 4650
     },
     {
       "epoch": 1.530446108759362,
-      "grad_norm": 2.4355289936065674,
+      "grad_norm": 2.6982979774475098,
       "learning_rate": 2.4497991967871488e-05,
-      "loss": 0.6133829498291016,
+      "loss": 0.5979887008666992,
       "step": 4700
     },
     {
       "epoch": 1.5467274503419082,
-      "grad_norm": 2.517214298248291,
+      "grad_norm": 5.090776443481445,
       "learning_rate": 2.4226636274829047e-05,
-      "loss": 0.6106953048706054,
+      "loss": 0.5904266357421875,
       "step": 4750
     },
     {
       "epoch": 1.5630087919244544,
-      "grad_norm": 2.7961008548736572,
+      "grad_norm": 2.6866397857666016,
       "learning_rate": 2.395528058178661e-05,
-      "loss": 0.6070757675170898,
+      "loss": 0.5932189178466797,
       "step": 4800
     },
     {
       "epoch": 1.5792901335070009,
-      "grad_norm": 3.7750861644744873,
+      "grad_norm": 3.7417988777160645,
       "learning_rate": 2.3683924888744168e-05,
-      "loss": 0.611992530822754,
+      "loss": 0.595960578918457,
       "step": 4850
     },
     {
       "epoch": 1.5955714750895473,
-      "grad_norm": 3.580327033996582,
+      "grad_norm": 3.4997494220733643,
       "learning_rate": 2.3412569195701726e-05,
-      "loss": 0.5429486083984375,
+      "loss": 0.5230794143676758,
       "step": 4900
     },
     {
       "epoch": 1.6118528166720938,
-      "grad_norm": 4.666822910308838,
+      "grad_norm": 4.909201145172119,
       "learning_rate": 2.3141213502659285e-05,
-      "loss": 0.49008914947509763,
+      "loss": 0.48100479125976564,
       "step": 4950
     },
     {
       "epoch": 1.6281341582546403,
-      "grad_norm": 3.0332093238830566,
+      "grad_norm": 2.8310112953186035,
       "learning_rate": 2.2869857809616847e-05,
-      "loss": 0.49931236267089846,
+      "loss": 0.4874506378173828,
       "step": 5000
     },
     {
       "epoch": 1.6444154998371867,
-      "grad_norm": 2.752690076828003,
+      "grad_norm": 2.82600736618042,
       "learning_rate": 2.2598502116574406e-05,
-      "loss": 0.5916973876953125,
+      "loss": 0.5806295776367187,
       "step": 5050
     },
     {
       "epoch": 1.660696841419733,
-      "grad_norm": 3.5713531970977783,
+      "grad_norm": 3.411588430404663,
       "learning_rate": 2.2327146423531965e-05,
-      "loss": 0.5342200469970703,
+      "loss": 0.517121810913086,
       "step": 5100
     },
     {
       "epoch": 1.6769781830022794,
-      "grad_norm": 2.947326898574829,
+      "grad_norm": 3.2024784088134766,
       "learning_rate": 2.2055790730489524e-05,
-      "loss": 0.48489521026611326,
+      "loss": 0.46841278076171877,
       "step": 5150
     },
     {
       "epoch": 1.6932595245848256,
-      "grad_norm": 3.4723641872406006,
+      "grad_norm": 3.798309803009033,
       "learning_rate": 2.1784435037447086e-05,
-      "loss": 0.5273918533325195,
+      "loss": 0.5157822418212891,
       "step": 5200
     },
     {
       "epoch": 1.709540866167372,
-      "grad_norm": 3.2168502807617188,
+      "grad_norm": 3.463024854660034,
       "learning_rate": 2.1513079344404645e-05,
-      "loss": 0.576658935546875,
+      "loss": 0.5623917007446289,
       "step": 5250
     },
     {
       "epoch": 1.7258222077499186,
-      "grad_norm": 3.858649492263794,
+      "grad_norm": 9.00114917755127,
       "learning_rate": 2.1241723651362204e-05,
-      "loss": 0.5316023254394531,
+      "loss": 0.5178924560546875,
       "step": 5300
     },
     {
       "epoch": 1.742103549332465,
-      "grad_norm": 2.8334648609161377,
+      "grad_norm": 3.134282350540161,
       "learning_rate": 2.0970367958319766e-05,
-      "loss": 0.5504447555541992,
+      "loss": 0.5335901641845703,
       "step": 5350
     },
     {
       "epoch": 1.7583848909150115,
-      "grad_norm": 4.290432453155518,
+      "grad_norm": 3.1152961254119873,
       "learning_rate": 2.0699012265277325e-05,
-      "loss": 0.47645130157470705,
+      "loss": 0.46617908477783204,
       "step": 5400
     },
     {
       "epoch": 1.774666232497558,
-      "grad_norm": 3.450201988220215,
+      "grad_norm": 3.5342652797698975,
       "learning_rate": 2.0427656572234887e-05,
-      "loss": 0.49983680725097657,
+      "loss": 0.48794960021972655,
       "step": 5450
     },
     {
       "epoch": 1.7909475740801042,
-      "grad_norm": 3.0057594776153564,
+      "grad_norm": 2.6719322204589844,
       "learning_rate": 2.0156300879192446e-05,
-      "loss": 0.5014204025268555,
+      "loss": 0.48549480438232423,
       "step": 5500
     },
     {
       "epoch": 1.8072289156626506,
-      "grad_norm": 2.4749011993408203,
+      "grad_norm": 2.8136425018310547,
       "learning_rate": 1.9884945186150005e-05,
-      "loss": 0.5224055862426757,
+      "loss": 0.504596939086914,
       "step": 5550
     },
     {
       "epoch": 1.8235102572451969,
-      "grad_norm": 3.564490556716919,
+      "grad_norm": 2.985659599304199,
       "learning_rate": 1.9613589493107567e-05,
-      "loss": 0.4841350555419922,
+      "loss": 0.46674480438232424,
       "step": 5600
     },
     {
       "epoch": 1.8397915988277433,
-      "grad_norm": 4.468665599822998,
+      "grad_norm": 4.119204521179199,
       "learning_rate": 1.9342233800065126e-05,
-      "loss": 0.49803077697753906,
+      "loss": 0.4856386566162109,
       "step": 5650
     },
     {
       "epoch": 1.8560729404102898,
-      "grad_norm": 2.853323221206665,
+      "grad_norm": 3.0939385890960693,
       "learning_rate": 1.9070878107022685e-05,
-      "loss": 0.5557261276245117,
+      "loss": 0.5406102752685547,
       "step": 5700
     },
     {
       "epoch": 1.8723542819928363,
-      "grad_norm": 2.240102767944336,
+      "grad_norm": 2.096914052963257,
       "learning_rate": 1.8799522413980247e-05,
-      "loss": 0.5035658645629882,
+      "loss": 0.49306621551513674,
       "step": 5750
     },
     {
       "epoch": 1.8886356235753827,
-      "grad_norm": 4.524099349975586,
+      "grad_norm": 4.529496669769287,
       "learning_rate": 1.8528166720937806e-05,
-      "loss": 0.4709853363037109,
+      "loss": 0.4564324188232422,
       "step": 5800
     },
     {
       "epoch": 1.904916965157929,
-      "grad_norm": 3.5889639854431152,
+      "grad_norm": 3.7081360816955566,
       "learning_rate": 1.8256811027895364e-05,
-      "loss": 0.5654364395141601,
+      "loss": 0.5462873458862305,
       "step": 5850
     },
     {
       "epoch": 1.9211983067404754,
-      "grad_norm": 4.631803512573242,
+      "grad_norm": 4.159782886505127,
       "learning_rate": 1.7985455334852927e-05,
-      "loss": 0.4828892517089844,
+      "loss": 0.47431507110595705,
       "step": 5900
     },
     {
       "epoch": 1.9374796483230217,
-      "grad_norm": 3.324930191040039,
+      "grad_norm": 3.467459201812744,
       "learning_rate": 1.7714099641810485e-05,
-      "loss": 0.5719730377197265,
+      "loss": 0.5584798049926758,
       "step": 5950
     },
     {
       "epoch": 1.9537609899055681,
-      "grad_norm": 4.518911838531494,
+      "grad_norm": 4.213109970092773,
       "learning_rate": 1.7442743948768044e-05,
-      "loss": 0.4871857833862305,
+      "loss": 0.47076557159423826,
       "step": 6000
     },
     {
       "epoch": 1.9700423314881146,
-      "grad_norm": 4.349981307983398,
+      "grad_norm": 4.383584022521973,
       "learning_rate": 1.7171388255725606e-05,
-      "loss": 0.5515385437011718,
+      "loss": 0.5349767303466797,
       "step": 6050
     },
     {
       "epoch": 1.986323673070661,
-      "grad_norm": 3.0791079998016357,
+      "grad_norm": 3.1514296531677246,
       "learning_rate": 1.6900032562683165e-05,
-      "loss": 0.5213652801513672,
+      "loss": 0.5139558792114258,
       "step": 6100
     },
     {
       "epoch": 2.0,
-      "eval_bertscore_f1": 0.9760125298802698,
-      "eval_bleu": 0.7369094701809736,
-      "eval_loss": 0.36441001296043396,
-      "eval_meteor": 0.8127092299374118,
-      "eval_rouge1": 0.8875418149898048,
-      "eval_rouge2": 0.8077254196229909,
-      "eval_runtime": 132.4191,
-      "eval_samples_per_second": 9.757,
-      "eval_steps_per_second": 1.223,
+      "eval_bertscore_f1": 0.9762323709095225,
+      "eval_bleu": 0.7430723352502658,
+      "eval_loss": 0.3539265990257263,
+      "eval_meteor": 0.8151086573537881,
+      "eval_rouge1": 0.8885716440737175,
+      "eval_rouge2": 0.8125576905491395,
+      "eval_runtime": 137.3289,
+      "eval_samples_per_second": 9.408,
+      "eval_steps_per_second": 1.18,
       "step": 6142
     },
     {
       "epoch": 2.0026050146532075,
-      "grad_norm": 1.9988925457000732,
+      "grad_norm": 2.005295991897583,
       "learning_rate": 1.6628676869640724e-05,
-      "loss": 0.4895309066772461,
+      "loss": 0.4775341796875,
       "step": 6150
     },
     {
       "epoch": 2.018886356235754,
-      "grad_norm": 3.848978042602539,
+      "grad_norm": 3.9823381900787354,
       "learning_rate": 1.6357321176598286e-05,
-      "loss": 0.5836200714111328,
+      "loss": 0.5708214950561523,
       "step": 6200
     },
     {
       "epoch": 2.0351676978183004,
-      "grad_norm": 3.77553129196167,
+      "grad_norm": 3.592066764831543,
       "learning_rate": 1.6085965483555845e-05,
-      "loss": 0.5029875564575196,
+      "loss": 0.494837646484375,
       "step": 6250
     },
     {
       "epoch": 2.0514490394008464,
-      "grad_norm": 3.317784070968628,
+      "grad_norm": 3.034447193145752,
       "learning_rate": 1.5814609790513404e-05,
-      "loss": 0.4987943649291992,
+      "loss": 0.48195556640625,
       "step": 6300
     },
     {
       "epoch": 2.067730380983393,
-      "grad_norm": 6.215928554534912,
+      "grad_norm": 3.7622528076171875,
       "learning_rate": 1.5543254097470966e-05,
-      "loss": 0.4729055404663086,
+      "loss": 0.46555606842041014,
       "step": 6350
     },
     {
       "epoch": 2.0840117225659394,
-      "grad_norm": 4.411025524139404,
+      "grad_norm": 4.787505626678467,
       "learning_rate": 1.5271898404428525e-05,
-      "loss": 0.47504291534423826,
+      "loss": 0.4631903076171875,
       "step": 6400
     },
     {
       "epoch": 2.100293064148486,
-      "grad_norm": 3.878382444381714,
+      "grad_norm": 4.470603942871094,
       "learning_rate": 1.5000542711386087e-05,
-      "loss": 0.5043264389038086,
+      "loss": 0.4912979888916016,
       "step": 6450
     },
     {
       "epoch": 2.1165744057310323,
-      "grad_norm": 3.332885980606079,
+      "grad_norm": 2.7138943672180176,
       "learning_rate": 1.4729187018343646e-05,
-      "loss": 0.5287798309326172,
+      "loss": 0.5140954208374023,
       "step": 6500
     },
     {
       "epoch": 2.1328557473135787,
-      "grad_norm": 5.045743942260742,
+      "grad_norm": 4.439281463623047,
       "learning_rate": 1.4457831325301205e-05,
-      "loss": 0.5503104782104492,
+      "loss": 0.5343180465698242,
       "step": 6550
     },
     {
       "epoch": 2.149137088896125,
-      "grad_norm": 4.425091743469238,
+      "grad_norm": 3.9600956439971924,
       "learning_rate": 1.4186475632258767e-05,
-      "loss": 0.5537314224243164,
+      "loss": 0.5393027114868164,
       "step": 6600
     },
     {
       "epoch": 2.165418430478671,
-      "grad_norm": 4.250468730926514,
+      "grad_norm": 5.374337673187256,
       "learning_rate": 1.3915119939216326e-05,
-      "loss": 0.4960391235351562,
+      "loss": 0.4814667892456055,
       "step": 6650
     },
     {
       "epoch": 2.1816997720612177,
-      "grad_norm": 2.38873028755188,
+      "grad_norm": 2.706310987472534,
       "learning_rate": 1.3643764246173885e-05,
-      "loss": 0.4847539520263672,
+      "loss": 0.4734183883666992,
       "step": 6700
     },
     {
       "epoch": 2.197981113643764,
-      "grad_norm": 3.1205639839172363,
+      "grad_norm": 3.1908249855041504,
       "learning_rate": 1.3372408553131447e-05,
-      "loss": 0.530453872680664,
+      "loss": 0.5154135131835937,
       "step": 6750
     },
     {
       "epoch": 2.2142624552263106,
-      "grad_norm": 3.130052089691162,
+      "grad_norm": 3.3044145107269287,
       "learning_rate": 1.3101052860089006e-05,
-      "loss": 0.4768033981323242,
+      "loss": 0.4694767761230469,
       "step": 6800
     },
     {
       "epoch": 2.230543796808857,
-      "grad_norm": 2.549163341522217,
+      "grad_norm": 2.6275320053100586,
       "learning_rate": 1.2829697167046565e-05,
-      "loss": 0.5177365493774414,
+      "loss": 0.5074032974243164,
       "step": 6850
     },
     {
       "epoch": 2.2468251383914035,
-      "grad_norm": 3.2036118507385254,
+      "grad_norm": 3.4295599460601807,
       "learning_rate": 1.2558341474004127e-05,
-      "loss": 0.48484851837158205,
+      "loss": 0.47720569610595703,
       "step": 6900
     },
     {
       "epoch": 2.26310647997395,
-      "grad_norm": 3.249213695526123,
+      "grad_norm": 3.5452775955200195,
       "learning_rate": 1.2286985780961686e-05,
-      "loss": 0.5264522933959961,
+      "loss": 0.5167514038085937,
       "step": 6950
     },
     {
       "epoch": 2.2793878215564964,
-      "grad_norm": 3.0506670475006104,
+      "grad_norm": 3.8189544677734375,
       "learning_rate": 1.2015630087919246e-05,
-      "loss": 0.5557387161254883,
+      "loss": 0.5443729400634766,
       "step": 7000
     },
     {
       "epoch": 2.295669163139043,
-      "grad_norm": 4.090348243713379,
+      "grad_norm": 3.834667682647705,
       "learning_rate": 1.1744274394876805e-05,
-      "loss": 0.44691120147705077,
+      "loss": 0.43803905487060546,
       "step": 7050
     },
     {
       "epoch": 2.311950504721589,
-      "grad_norm": 4.048130512237549,
+      "grad_norm": 3.922828435897827,
       "learning_rate": 1.1472918701834365e-05,
-      "loss": 0.47702239990234374,
+      "loss": 0.465465202331543,
       "step": 7100
     },
     {
       "epoch": 2.3282318463041354,
-      "grad_norm": 4.8760528564453125,
+      "grad_norm": 3.319157838821411,
       "learning_rate": 1.1201563008791926e-05,
-      "loss": 0.5293217468261718,
+      "loss": 0.5172126388549805,
       "step": 7150
     },
     {
       "epoch": 2.344513187886682,
-      "grad_norm": 1.611255407333374,
+      "grad_norm": 1.2773399353027344,
       "learning_rate": 1.0930207315749485e-05,
-      "loss": 0.5165376281738281,
+      "loss": 0.5022563552856445,
       "step": 7200
     },
     {
       "epoch": 2.3607945294692283,
-      "grad_norm": 3.9336297512054443,
+      "grad_norm": 3.884661912918091,
       "learning_rate": 1.0658851622707045e-05,
-      "loss": 0.5475522232055664,
+      "loss": 0.5398352813720703,
       "step": 7250
     },
     {
       "epoch": 2.3770758710517748,
-      "grad_norm": 3.2688589096069336,
+      "grad_norm": 3.0721209049224854,
       "learning_rate": 1.0387495929664604e-05,
-      "loss": 0.4639253616333008,
+      "loss": 0.4502225875854492,
       "step": 7300
     },
     {
       "epoch": 2.393357212634321,
-      "grad_norm": 2.2077689170837402,
+      "grad_norm": 2.1282992362976074,
       "learning_rate": 1.0116140236622165e-05,
-      "loss": 0.49176544189453125,
+      "loss": 0.4745651626586914,
       "step": 7350
     },
     {
       "epoch": 2.4096385542168672,
-      "grad_norm": 3.6767163276672363,
+      "grad_norm": 4.129814147949219,
       "learning_rate": 9.844784543579723e-06,
-      "loss": 0.46481277465820314,
+      "loss": 0.4516494369506836,
       "step": 7400
     },
     {
       "epoch": 2.4259198957994137,
-      "grad_norm": 2.3092267513275146,
+      "grad_norm": 2.759620428085327,
       "learning_rate": 9.573428850537284e-06,
-      "loss": 0.4961623382568359,
+      "loss": 0.4808626174926758,
       "step": 7450
     },
     {
       "epoch": 2.44220123738196,
-      "grad_norm": 2.597843885421753,
+      "grad_norm": 2.358985424041748,
       "learning_rate": 9.302073157494844e-06,
-      "loss": 0.48158348083496094,
+      "loss": 0.46834888458251955,
       "step": 7500
     },
     {
       "epoch": 2.4584825789645066,
-      "grad_norm": 3.8426899909973145,
+      "grad_norm": 4.089727401733398,
       "learning_rate": 9.030717464452403e-06,
-      "loss": 0.5378573989868164,
+      "loss": 0.5258768844604492,
       "step": 7550
     },
     {
       "epoch": 2.474763920547053,
-      "grad_norm": 3.84844970703125,
+      "grad_norm": 4.14641809463501,
       "learning_rate": 8.759361771409964e-06,
-      "loss": 0.44852672576904296,
+      "loss": 0.43479076385498044,
       "step": 7600
     },
     {
       "epoch": 2.4910452621295995,
-      "grad_norm": 1.7561177015304565,
+      "grad_norm": 2.1294007301330566,
       "learning_rate": 8.488006078367524e-06,
-      "loss": 0.47510692596435544,
+      "loss": 0.4723660659790039,
       "step": 7650
     },
     {
       "epoch": 2.507326603712146,
-      "grad_norm": 3.857144355773926,
+      "grad_norm": 3.301629066467285,
       "learning_rate": 8.216650385325085e-06,
-      "loss": 0.40881168365478515,
+      "loss": 0.39770748138427736,
       "step": 7700
     },
     {
       "epoch": 2.5236079452946925,
-      "grad_norm": 3.1903669834136963,
+      "grad_norm": 2.9783337116241455,
       "learning_rate": 7.945294692282644e-06,
-      "loss": 0.47881248474121096,
+      "loss": 0.46555194854736326,
       "step": 7750
     },
     {
       "epoch": 2.539889286877239,
-      "grad_norm": 5.834493637084961,
+      "grad_norm": 4.9203619956970215,
       "learning_rate": 7.673938999240204e-06,
-      "loss": 0.4648504638671875,
+      "loss": 0.4547107696533203,
       "step": 7800
     },
     {
       "epoch": 2.556170628459785,
-      "grad_norm": 4.4403252601623535,
+      "grad_norm": 4.045784950256348,
       "learning_rate": 7.402583306197765e-06,
-      "loss": 0.45219791412353516,
+      "loss": 0.43739501953125,
       "step": 7850
     },
     {
       "epoch": 2.5724519700423314,
-      "grad_norm": 3.979234457015991,
+      "grad_norm": 3.234687566757202,
       "learning_rate": 7.1312276131553235e-06,
-      "loss": 0.4795208358764648,
+      "loss": 0.467929573059082,
       "step": 7900
     },
     {
       "epoch": 2.588733311624878,
-      "grad_norm": 7.058864593505859,
+      "grad_norm": 3.6721928119659424,
       "learning_rate": 6.859871920112884e-06,
-      "loss": 0.47828922271728513,
+      "loss": 0.4593897247314453,
       "step": 7950
     },
     {
       "epoch": 2.6050146532074243,
-      "grad_norm": 2.258791923522949,
+      "grad_norm": 2.296928644180298,
       "learning_rate": 6.5885162270704446e-06,
-      "loss": 0.47586013793945314,
+      "loss": 0.46631996154785155,
       "step": 8000
     },
     {
       "epoch": 2.6212959947899708,
-      "grad_norm": 3.1901180744171143,
+      "grad_norm": 3.3836448192596436,
       "learning_rate": 6.317160534028005e-06,
-      "loss": 0.42454421997070313,
+      "loss": 0.4127694702148437,
       "step": 8050
     },
     {
       "epoch": 2.6375773363725172,
-      "grad_norm": 5.115426540374756,
+      "grad_norm": 3.1450395584106445,
       "learning_rate": 6.045804840985564e-06,
-      "loss": 0.478512077331543,
+      "loss": 0.4709606170654297,
       "step": 8100
     },
     {
       "epoch": 2.6538586779550632,
-      "grad_norm": 2.2929582595825195,
+      "grad_norm": 2.056903600692749,
       "learning_rate": 5.774449147943124e-06,
-      "loss": 0.5165943527221679,
+      "loss": 0.5080145263671875,
       "step": 8150
     },
     {
       "epoch": 2.6701400195376097,
-      "grad_norm": 4.737906455993652,
+      "grad_norm": 4.611896514892578,
       "learning_rate": 5.503093454900684e-06,
-      "loss": 0.5091237640380859,
+      "loss": 0.5028559875488281,
       "step": 8200
     },
     {
       "epoch": 2.686421361120156,
-      "grad_norm": 2.8958566188812256,
+      "grad_norm": 2.8389217853546143,
       "learning_rate": 5.231737761858245e-06,
-      "loss": 0.5252229690551757,
+      "loss": 0.5155687713623047,
       "step": 8250
     },
     {
       "epoch": 2.7027027027027026,
-      "grad_norm": 3.7006046772003174,
+      "grad_norm": 3.570791721343994,
       "learning_rate": 4.960382068815804e-06,
-      "loss": 0.4727284240722656,
+      "loss": 0.46154869079589844,
       "step": 8300
     },
     {
       "epoch": 2.718984044285249,
-      "grad_norm": 4.118995189666748,
+      "grad_norm": 3.8014798164367676,
       "learning_rate": 4.689026375773364e-06,
-      "loss": 0.5148253631591797,
+      "loss": 0.5015551376342774,
       "step": 8350
     },
     {
       "epoch": 2.7352653858677956,
-      "grad_norm": 2.285799980163574,
+      "grad_norm": 2.136251926422119,
       "learning_rate": 4.417670682730924e-06,
-      "loss": 0.47666587829589846,
+      "loss": 0.4702875900268555,
       "step": 8400
     },
     {
       "epoch": 2.751546727450342,
-      "grad_norm": 5.824726104736328,
+      "grad_norm": 5.566357612609863,
       "learning_rate": 4.146314989688484e-06,
-      "loss": 0.3846194839477539,
+      "loss": 0.3770464324951172,
       "step": 8450
     },
     {
       "epoch": 2.7678280690328885,
-      "grad_norm": 3.3558638095855713,
+      "grad_norm": 5.836922645568848,
       "learning_rate": 3.874959296646044e-06,
-      "loss": 0.47148590087890624,
+      "loss": 0.4574332809448242,
       "step": 8500
     },
     {
       "epoch": 2.784109410615435,
-      "grad_norm": 5.155383110046387,
+      "grad_norm": 16.352832794189453,
       "learning_rate": 3.603603603603604e-06,
-      "loss": 0.49628185272216796,
+      "loss": 0.48586685180664063,
       "step": 8550
     },
     {
       "epoch": 2.800390752197981,
-      "grad_norm": 2.7732632160186768,
+      "grad_norm": 3.018529176712036,
       "learning_rate": 3.3322479105611635e-06,
-      "loss": 0.4713264465332031,
+      "loss": 0.4619815063476562,
       "step": 8600
     },
     {
       "epoch": 2.8166720937805274,
-      "grad_norm": 4.7110066413879395,
+      "grad_norm": 5.671543598175049,
       "learning_rate": 3.0608922175187236e-06,
-      "loss": 0.46566177368164063,
+      "loss": 0.45566730499267577,
       "step": 8650
     },
     {
       "epoch": 2.832953435363074,
-      "grad_norm": 3.182767868041992,
+      "grad_norm": 3.141303062438965,
       "learning_rate": 2.7895365244762837e-06,
-      "loss": 0.4322200775146484,
+      "loss": 0.423536491394043,
       "step": 8700
     },
     {
       "epoch": 2.8492347769456203,
-      "grad_norm": 2.3082404136657715,
+      "grad_norm": 2.619455337524414,
       "learning_rate": 2.5181808314338434e-06,
-      "loss": 0.45952880859375,
+      "loss": 0.4463621520996094,
       "step": 8750
     },
     {
       "epoch": 2.865516118528167,
-      "grad_norm": 3.0804383754730225,
+      "grad_norm": 3.0434818267822266,
       "learning_rate": 2.2468251383914035e-06,
-      "loss": 0.5015320205688476,
+      "loss": 0.4879434967041016,
       "step": 8800
     },
     {
       "epoch": 2.8817974601107132,
-      "grad_norm": 2.3712687492370605,
+      "grad_norm": 2.338992118835449,
       "learning_rate": 1.9754694453489636e-06,
-      "loss": 0.46776729583740234,
+      "loss": 0.4577774429321289,
       "step": 8850
     },
     {
       "epoch": 2.8980788016932593,
-      "grad_norm": 3.109934091567993,
+      "grad_norm": 3.1424238681793213,
       "learning_rate": 1.7041137523065235e-06,
-      "loss": 0.4564864349365234,
+      "loss": 0.4456531524658203,
       "step": 8900
     },
     {
       "epoch": 2.9143601432758057,
-      "grad_norm": 5.136889934539795,
+      "grad_norm": 4.704187870025635,
       "learning_rate": 1.4327580592640834e-06,
-      "loss": 0.4858356857299805,
+      "loss": 0.4674592590332031,
       "step": 8950
     },
     {
       "epoch": 2.930641484858352,
-      "grad_norm": 5.105923175811768,
+      "grad_norm": 5.090559959411621,
       "learning_rate": 1.1614023662216434e-06,
-      "loss": 0.44804500579833983,
+      "loss": 0.43730361938476564,
       "step": 9000
     },
     {
       "epoch": 2.9469228264408986,
-      "grad_norm": 2.8601877689361572,
+      "grad_norm": 2.395810604095459,
       "learning_rate": 8.900466731792033e-07,
-      "loss": 0.42105804443359374,
+      "loss": 0.4117137908935547,
       "step": 9050
     },
     {
       "epoch": 2.963204168023445,
-      "grad_norm": 2.99465012550354,
+      "grad_norm": 2.933120012283325,
       "learning_rate": 6.186909801367633e-07,
-      "loss": 0.39937313079833986,
+      "loss": 0.38719585418701175,
       "step": 9100
     },
     {
       "epoch": 2.9794855096059916,
-      "grad_norm": 1.473414421081543,
+      "grad_norm": 1.5927964448928833,
       "learning_rate": 3.4733528709432325e-07,
-      "loss": 0.43089988708496096,
+      "loss": 0.42159496307373046,
       "step": 9150
     },
     {
       "epoch": 2.995766851188538,
-      "grad_norm": 3.2104876041412354,
+      "grad_norm": 4.6336774826049805,
       "learning_rate": 7.597959405188321e-08,
-      "loss": 0.48259429931640624,
+      "loss": 0.4757699966430664,
       "step": 9200
     },
     {
       "epoch": 3.0,
-      "eval_bertscore_f1": 0.9784284891912443,
-      "eval_bleu": 0.7639446756702927,
-      "eval_loss": 0.33530932664871216,
-      "eval_meteor": 0.8315404974609083,
-      "eval_rouge1": 0.8979837043455776,
-      "eval_rouge2": 0.8245087404389784,
-      "eval_runtime": 131.767,
-      "eval_samples_per_second": 9.805,
-      "eval_steps_per_second": 1.229,
+      "eval_bertscore_f1": 0.9787175891107819,
+      "eval_bleu": 0.7693596969484261,
+      "eval_loss": 0.32842469215393066,
+      "eval_meteor": 0.8357277347287969,
+      "eval_rouge1": 0.8992664738649058,
+      "eval_rouge2": 0.828427573552017,
+      "eval_runtime": 129.1375,
+      "eval_samples_per_second": 10.005,
+      "eval_steps_per_second": 1.254,
       "step": 9213
     }
   ],

checkpoint-9213/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21e7988a724f50ab4d65854a8bd4de7b4eceb713886a6a05ceeaeae7fb11b713
+oid sha256:8945bcdf4317e2f7559f3b2665cbaf54f85caa090c8d212b42fe7b6b9307fa8e
 size 4920

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 256,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 256
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "<pad>"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,