Upload folder using huggingface_hub

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f16612b3558a994f7f9fdb2eda772f0d7ee92b8ab65d308d952c16e2cf5882d6
+oid sha256:c9508f3e5ab410c13b37ce777d7f03968cd1ef912ad7468af91cddcd618845ed
 size 93378688

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e4753d8e967daf58be3c4586c14128aaf5cf8b18762c58bbde37b302042703
+oid sha256:fe0837d3b546e57addf74036233fb37d0d61eda99a01741c2eb7c08f60db9fc2
 size 187031330

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb920a55454edc05cad446eb986eb35a20c5c33567a5a093ac93baf95f6aec7c
+oid sha256:a18fdd216403847cd41e3eed155b254200482f615f1b6fea997a601e92ff90f0
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25ab4523fd7262af4b9e1ebf15a79d63c966e86fc99ff91e2840498756cca05b
+oid sha256:c17ddebb9f7da522ed1db7b26ff2dc5c2f0ec86d553faec156dfe4119486e13d
 size 1064

trainer_state.json

@@ -1,537 +1,177 @@
 {
-  "best_metric": 0.8183558583259583,
-  "best_model_checkpoint": "/content/Nasa_Mars_Model_Outputs/checkpoint-170",
-  "epoch": 0.1591451631237922,
+  "best_metric": 0.8372765183448792,
+  "best_model_checkpoint": "/content/Nasa_Mars_Model_Outputs/checkpoint-10",
+  "epoch": 0.05001705126747755,
   "eval_steps": 10,
-  "global_step": 350,
+  "global_step": 110,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.004547004660679777,
-      "grad_norm": 8.844450950622559,
+      "grad_norm": 8.836596488952637,
       "learning_rate": 2e-05,
-      "loss": 0.5029,
+      "loss": 0.6073,
       "step": 10
     },
     {
       "epoch": 0.004547004660679777,
-      "eval_loss": 0.852020800113678,
-      "eval_runtime": 20.6332,
-      "eval_samples_per_second": 2.423,
-      "eval_steps_per_second": 2.423,
+      "eval_loss": 0.8372765183448792,
+      "eval_runtime": 20.6797,
+      "eval_samples_per_second": 2.418,
+      "eval_steps_per_second": 2.418,
       "step": 10
     },
     {
       "epoch": 0.009094009321359554,
-      "grad_norm": 6.392278671264648,
+      "grad_norm": 9.525543212890625,
       "learning_rate": 4e-05,
-      "loss": 0.4208,
+      "loss": 0.5308,
       "step": 20
     },
     {
       "epoch": 0.009094009321359554,
-      "eval_loss": 0.8326458930969238,
-      "eval_runtime": 20.8468,
-      "eval_samples_per_second": 2.398,
-      "eval_steps_per_second": 2.398,
+      "eval_loss": 0.8388195037841797,
+      "eval_runtime": 20.8936,
+      "eval_samples_per_second": 2.393,
+      "eval_steps_per_second": 2.393,
       "step": 20
     },
     {
       "epoch": 0.013641013982039332,
-      "grad_norm": 5.979872703552246,
+      "grad_norm": 8.243130683898926,
       "learning_rate": 6e-05,
-      "loss": 0.3174,
+      "loss": 0.4263,
       "step": 30
     },
     {
       "epoch": 0.013641013982039332,
-      "eval_loss": 0.9364193677902222,
-      "eval_runtime": 20.7537,
-      "eval_samples_per_second": 2.409,
-      "eval_steps_per_second": 2.409,
+      "eval_loss": 0.9063456654548645,
+      "eval_runtime": 20.8341,
+      "eval_samples_per_second": 2.4,
+      "eval_steps_per_second": 2.4,
       "step": 30
     },
     {
       "epoch": 0.018188018642719107,
-      "grad_norm": 8.079290390014648,
+      "grad_norm": 5.157824993133545,
       "learning_rate": 8e-05,
-      "loss": 0.2436,
+      "loss": 0.3455,
       "step": 40
     },
     {
       "epoch": 0.018188018642719107,
-      "eval_loss": 0.9858406782150269,
-      "eval_runtime": 20.7434,
-      "eval_samples_per_second": 2.41,
-      "eval_steps_per_second": 2.41,
+      "eval_loss": 0.9459993839263916,
+      "eval_runtime": 20.8498,
+      "eval_samples_per_second": 2.398,
+      "eval_steps_per_second": 2.398,
       "step": 40
     },
     {
       "epoch": 0.022735023303398886,
-      "grad_norm": 7.087987422943115,
+      "grad_norm": 9.51492977142334,
       "learning_rate": 0.0001,
-      "loss": 0.2069,
+      "loss": 0.317,
       "step": 50
     },
     {
       "epoch": 0.022735023303398886,
-      "eval_loss": 0.9912980794906616,
-      "eval_runtime": 20.7587,
-      "eval_samples_per_second": 2.409,
-      "eval_steps_per_second": 2.409,
+      "eval_loss": 0.9320575594902039,
+      "eval_runtime": 20.8158,
+      "eval_samples_per_second": 2.402,
+      "eval_steps_per_second": 2.402,
       "step": 50
     },
     {
       "epoch": 0.027282027964078664,
-      "grad_norm": 7.0141496658325195,
+      "grad_norm": 8.233291625976562,
       "learning_rate": 9.977000919963202e-05,
-      "loss": 0.2171,
+      "loss": 0.3006,
       "step": 60
     },
     {
       "epoch": 0.027282027964078664,
-      "eval_loss": 1.029310941696167,
-      "eval_runtime": 20.7996,
+      "eval_loss": 0.9950161576271057,
+      "eval_runtime": 20.7989,
       "eval_samples_per_second": 2.404,
       "eval_steps_per_second": 2.404,
       "step": 60
     },
     {
       "epoch": 0.03182903262475844,
-      "grad_norm": 7.3678998947143555,
+      "grad_norm": 11.2651948928833,
       "learning_rate": 9.954001839926403e-05,
-      "loss": 0.2756,
+      "loss": 0.3331,
       "step": 70
     },
     {
       "epoch": 0.03182903262475844,
-      "eval_loss": 0.9257596731185913,
-      "eval_runtime": 20.8032,
-      "eval_samples_per_second": 2.403,
-      "eval_steps_per_second": 2.403,
+      "eval_loss": 0.9437124729156494,
+      "eval_runtime": 20.8698,
+      "eval_samples_per_second": 2.396,
+      "eval_steps_per_second": 2.396,
       "step": 70
     },
     {
       "epoch": 0.036376037285438215,
-      "grad_norm": 8.662162780761719,
+      "grad_norm": 7.479197025299072,
       "learning_rate": 9.931002759889605e-05,
-      "loss": 0.3853,
+      "loss": 0.2957,
       "step": 80
     },
     {
       "epoch": 0.036376037285438215,
-      "eval_loss": 0.9099023342132568,
-      "eval_runtime": 20.8394,
-      "eval_samples_per_second": 2.399,
-      "eval_steps_per_second": 2.399,
+      "eval_loss": 0.9456791877746582,
+      "eval_runtime": 20.8644,
+      "eval_samples_per_second": 2.396,
+      "eval_steps_per_second": 2.396,
       "step": 80
     },
     {
       "epoch": 0.040923041946118,
-      "grad_norm": 8.646831512451172,
+      "grad_norm": 8.659111976623535,
       "learning_rate": 9.908003679852806e-05,
-      "loss": 0.4754,
+      "loss": 0.3325,
       "step": 90
     },
     {
       "epoch": 0.040923041946118,
-      "eval_loss": 0.8751680254936218,
-      "eval_runtime": 20.8501,
-      "eval_samples_per_second": 2.398,
-      "eval_steps_per_second": 2.398,
+      "eval_loss": 0.9326030015945435,
+      "eval_runtime": 20.8374,
+      "eval_samples_per_second": 2.4,
+      "eval_steps_per_second": 2.4,
       "step": 90
     },
     {
       "epoch": 0.04547004660679777,
-      "grad_norm": 5.3645501136779785,
+      "grad_norm": 4.722876071929932,
       "learning_rate": 9.885004599816008e-05,
-      "loss": 0.3919,
+      "loss": 0.2857,
       "step": 100
     },
     {
       "epoch": 0.04547004660679777,
-      "eval_loss": 0.8975805640220642,
-      "eval_runtime": 20.7625,
-      "eval_samples_per_second": 2.408,
-      "eval_steps_per_second": 2.408,
+      "eval_loss": 0.9288083910942078,
+      "eval_runtime": 20.844,
+      "eval_samples_per_second": 2.399,
+      "eval_steps_per_second": 2.399,
       "step": 100
     },
     {
       "epoch": 0.05001705126747755,
-      "grad_norm": 7.332831859588623,
+      "grad_norm": 6.449366569519043,
       "learning_rate": 9.86200551977921e-05,
-      "loss": 0.5172,
+      "loss": 0.3643,
       "step": 110
     },
     {
       "epoch": 0.05001705126747755,
-      "eval_loss": 0.8908578753471375,
-      "eval_runtime": 20.8039,
-      "eval_samples_per_second": 2.403,
-      "eval_steps_per_second": 2.403,
-      "step": 110
-    },
-    {
-      "epoch": 0.05456405592815733,
-      "grad_norm": 5.561324119567871,
-      "learning_rate": 9.83900643974241e-05,
-      "loss": 0.4599,
-      "step": 120
-    },
-    {
-      "epoch": 0.05456405592815733,
-      "eval_loss": 0.8581109046936035,
-      "eval_runtime": 20.8113,
-      "eval_samples_per_second": 2.403,
-      "eval_steps_per_second": 2.403,
-      "step": 120
-    },
-    {
-      "epoch": 0.059111060588837104,
-      "grad_norm": 7.407668113708496,
-      "learning_rate": 9.816007359705612e-05,
-      "loss": 0.5029,
-      "step": 130
-    },
-    {
-      "epoch": 0.059111060588837104,
-      "eval_loss": 0.8726012706756592,
-      "eval_runtime": 20.8342,
+      "eval_loss": 0.9256532192230225,
+      "eval_runtime": 20.8316,
       "eval_samples_per_second": 2.4,
       "eval_steps_per_second": 2.4,
-      "step": 130
-    },
-    {
-      "epoch": 0.06365806524951688,
-      "grad_norm": 5.486892223358154,
-      "learning_rate": 9.793008279668814e-05,
-      "loss": 0.4758,
-      "step": 140
-    },
-    {
-      "epoch": 0.06365806524951688,
-      "eval_loss": 0.8502522110939026,
-      "eval_runtime": 20.7835,
-      "eval_samples_per_second": 2.406,
-      "eval_steps_per_second": 2.406,
-      "step": 140
-    },
-    {
-      "epoch": 0.06820506991019666,
-      "grad_norm": 7.221977710723877,
-      "learning_rate": 9.770009199632015e-05,
-      "loss": 0.6792,
-      "step": 150
-    },
-    {
-      "epoch": 0.06820506991019666,
-      "eval_loss": 0.827602207660675,
-      "eval_runtime": 20.7446,
-      "eval_samples_per_second": 2.41,
-      "eval_steps_per_second": 2.41,
-      "step": 150
-    },
-    {
-      "epoch": 0.07275207457087643,
-      "grad_norm": 5.567179203033447,
-      "learning_rate": 9.747010119595217e-05,
-      "loss": 0.6319,
-      "step": 160
-    },
-    {
-      "epoch": 0.07275207457087643,
-      "eval_loss": 0.8225394487380981,
-      "eval_runtime": 20.7953,
-      "eval_samples_per_second": 2.404,
-      "eval_steps_per_second": 2.404,
-      "step": 160
-    },
-    {
-      "epoch": 0.07729907923155621,
-      "grad_norm": 6.063055992126465,
-      "learning_rate": 9.724011039558418e-05,
-      "loss": 0.7255,
-      "step": 170
-    },
-    {
-      "epoch": 0.07729907923155621,
-      "eval_loss": 0.8183558583259583,
-      "eval_runtime": 20.804,
-      "eval_samples_per_second": 2.403,
-      "eval_steps_per_second": 2.403,
-      "step": 170
-    },
-    {
-      "epoch": 0.081846083892236,
-      "grad_norm": 8.263747215270996,
-      "learning_rate": 9.70101195952162e-05,
-      "loss": 0.6679,
-      "step": 180
-    },
-    {
-      "epoch": 0.081846083892236,
-      "eval_loss": 0.8275816440582275,
-      "eval_runtime": 20.8116,
-      "eval_samples_per_second": 2.403,
-      "eval_steps_per_second": 2.403,
-      "step": 180
-    },
-    {
-      "epoch": 0.08639308855291576,
-      "grad_norm": 8.163738250732422,
-      "learning_rate": 9.678012879484822e-05,
-      "loss": 0.6618,
-      "step": 190
-    },
-    {
-      "epoch": 0.08639308855291576,
-      "eval_loss": 0.8254545331001282,
-      "eval_runtime": 20.8251,
-      "eval_samples_per_second": 2.401,
-      "eval_steps_per_second": 2.401,
-      "step": 190
-    },
-    {
-      "epoch": 0.09094009321359554,
-      "grad_norm": 10.39909839630127,
-      "learning_rate": 9.655013799448022e-05,
-      "loss": 0.7477,
-      "step": 200
-    },
-    {
-      "epoch": 0.09094009321359554,
-      "eval_loss": 0.8232752084732056,
-      "eval_runtime": 20.7836,
-      "eval_samples_per_second": 2.406,
-      "eval_steps_per_second": 2.406,
-      "step": 200
-    },
-    {
-      "epoch": 0.09548709787427533,
-      "grad_norm": 5.135624885559082,
-      "learning_rate": 9.632014719411224e-05,
-      "loss": 0.6157,
-      "step": 210
-    },
-    {
-      "epoch": 0.09548709787427533,
-      "eval_loss": 0.8450194597244263,
-      "eval_runtime": 20.7915,
-      "eval_samples_per_second": 2.405,
-      "eval_steps_per_second": 2.405,
-      "step": 210
-    },
-    {
-      "epoch": 0.1000341025349551,
-      "grad_norm": 5.748319149017334,
-      "learning_rate": 9.609015639374425e-05,
-      "loss": 0.6228,
-      "step": 220
-    },
-    {
-      "epoch": 0.1000341025349551,
-      "eval_loss": 0.8414835333824158,
-      "eval_runtime": 20.8517,
-      "eval_samples_per_second": 2.398,
-      "eval_steps_per_second": 2.398,
-      "step": 220
-    },
-    {
-      "epoch": 0.10458110719563488,
-      "grad_norm": 6.394444942474365,
-      "learning_rate": 9.586016559337627e-05,
-      "loss": 0.846,
-      "step": 230
-    },
-    {
-      "epoch": 0.10458110719563488,
-      "eval_loss": 0.8268595933914185,
-      "eval_runtime": 20.7853,
-      "eval_samples_per_second": 2.406,
-      "eval_steps_per_second": 2.406,
-      "step": 230
-    },
-    {
-      "epoch": 0.10912811185631466,
-      "grad_norm": 5.815967082977295,
-      "learning_rate": 9.563017479300829e-05,
-      "loss": 0.7647,
-      "step": 240
-    },
-    {
-      "epoch": 0.10912811185631466,
-      "eval_loss": 0.8257486820220947,
-      "eval_runtime": 20.7865,
-      "eval_samples_per_second": 2.405,
-      "eval_steps_per_second": 2.405,
-      "step": 240
-    },
-    {
-      "epoch": 0.11367511651699443,
-      "grad_norm": 7.9722161293029785,
-      "learning_rate": 9.54001839926403e-05,
-      "loss": 0.6884,
-      "step": 250
-    },
-    {
-      "epoch": 0.11367511651699443,
-      "eval_loss": 0.8330263495445251,
-      "eval_runtime": 20.7919,
-      "eval_samples_per_second": 2.405,
-      "eval_steps_per_second": 2.405,
-      "step": 250
-    },
-    {
-      "epoch": 0.11822212117767421,
-      "grad_norm": 6.1814799308776855,
-      "learning_rate": 9.517019319227232e-05,
-      "loss": 0.7325,
-      "step": 260
-    },
-    {
-      "epoch": 0.11822212117767421,
-      "eval_loss": 0.8296122550964355,
-      "eval_runtime": 20.7856,
-      "eval_samples_per_second": 2.406,
-      "eval_steps_per_second": 2.406,
-      "step": 260
-    },
-    {
-      "epoch": 0.12276912583835399,
-      "grad_norm": 14.889198303222656,
-      "learning_rate": 9.494020239190432e-05,
-      "loss": 0.6521,
-      "step": 270
-    },
-    {
-      "epoch": 0.12276912583835399,
-      "eval_loss": 0.8349407911300659,
-      "eval_runtime": 20.7358,
-      "eval_samples_per_second": 2.411,
-      "eval_steps_per_second": 2.411,
-      "step": 270
-    },
-    {
-      "epoch": 0.12731613049903376,
-      "grad_norm": 9.311092376708984,
-      "learning_rate": 9.471021159153634e-05,
-      "loss": 0.6413,
-      "step": 280
-    },
-    {
-      "epoch": 0.12731613049903376,
-      "eval_loss": 0.8341807723045349,
-      "eval_runtime": 20.7945,
-      "eval_samples_per_second": 2.404,
-      "eval_steps_per_second": 2.404,
-      "step": 280
-    },
-    {
-      "epoch": 0.13186313515971354,
-      "grad_norm": 2.8647501468658447,
-      "learning_rate": 9.448022079116836e-05,
-      "loss": 0.6104,
-      "step": 290
-    },
-    {
-      "epoch": 0.13186313515971354,
-      "eval_loss": 0.8275405764579773,
-      "eval_runtime": 20.7773,
-      "eval_samples_per_second": 2.406,
-      "eval_steps_per_second": 2.406,
-      "step": 290
-    },
-    {
-      "epoch": 0.13641013982039332,
-      "grad_norm": 6.136713027954102,
-      "learning_rate": 9.425022999080037e-05,
-      "loss": 0.5325,
-      "step": 300
-    },
-    {
-      "epoch": 0.13641013982039332,
-      "eval_loss": 0.8468616008758545,
-      "eval_runtime": 20.7933,
-      "eval_samples_per_second": 2.405,
-      "eval_steps_per_second": 2.405,
-      "step": 300
-    },
-    {
-      "epoch": 0.1409571444810731,
-      "grad_norm": 9.0726900100708,
-      "learning_rate": 9.402023919043239e-05,
-      "loss": 0.6315,
-      "step": 310
-    },
-    {
-      "epoch": 0.1409571444810731,
-      "eval_loss": 0.8461413383483887,
-      "eval_runtime": 20.7716,
-      "eval_samples_per_second": 2.407,
-      "eval_steps_per_second": 2.407,
-      "step": 310
-    },
-    {
-      "epoch": 0.14550414914175286,
-      "grad_norm": 7.699874401092529,
-      "learning_rate": 9.379024839006441e-05,
-      "loss": 0.6473,
-      "step": 320
-    },
-    {
-      "epoch": 0.14550414914175286,
-      "eval_loss": 0.8356756567955017,
-      "eval_runtime": 20.7971,
-      "eval_samples_per_second": 2.404,
-      "eval_steps_per_second": 2.404,
-      "step": 320
-    },
-    {
-      "epoch": 0.15005115380243264,
-      "grad_norm": 7.28955602645874,
-      "learning_rate": 9.356025758969642e-05,
-      "loss": 0.5936,
-      "step": 330
-    },
-    {
-      "epoch": 0.15005115380243264,
-      "eval_loss": 0.8357100486755371,
-      "eval_runtime": 20.7802,
-      "eval_samples_per_second": 2.406,
-      "eval_steps_per_second": 2.406,
-      "step": 330
-    },
-    {
-      "epoch": 0.15459815846311242,
-      "grad_norm": 4.673826217651367,
-      "learning_rate": 9.333026678932844e-05,
-      "loss": 0.5555,
-      "step": 340
-    },
-    {
-      "epoch": 0.15459815846311242,
-      "eval_loss": 0.8365601897239685,
-      "eval_runtime": 20.7353,
-      "eval_samples_per_second": 2.411,
-      "eval_steps_per_second": 2.411,
-      "step": 340
-    },
-    {
-      "epoch": 0.1591451631237922,
-      "grad_norm": 5.104877948760986,
-      "learning_rate": 9.310027598896044e-05,
-      "loss": 0.5903,
-      "step": 350
-    },
-    {
-      "epoch": 0.1591451631237922,
-      "eval_loss": 0.8396795392036438,
-      "eval_runtime": 20.7413,
-      "eval_samples_per_second": 2.411,
-      "eval_steps_per_second": 2.411,
-      "step": 350
+      "step": 110
     }
   ],
   "logging_steps": 10,
@@ -551,7 +191,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.854748142605779e+16,
+  "total_flos": 9148674554486016.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null