Training in progress, step 100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9b20be4465fc9f2fdc45a6b03c5b94b7d02f5beb0c6ee41705041ee2fa42bb1
+oid sha256:66c490ccd97ff3a1c5be26a7a6caff2ab3d0f0f23f0ba25ff8645d1cc81be9dd
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89a4dd12c905f92cb01197f96241d3b525490721258224cc4c8522e1e53dc47
+oid sha256:5ebb2eae727fa1d60dd1ae5c5487d2139dfee54a62ac5572c925eef09f931879
 size 350603

last-checkpoint/trainer_state.json

@@ -11,160 +11,160 @@
   "log_history": [
     {
       "epoch": 0.025,
-      "grad_norm": 0.10900866985321045,
+      "grad_norm": 0.11061733961105347,
       "learning_rate": 1.6e-06,
-      "loss": 11.06564712524414,
+      "loss": 10.991944885253906,
       "step": 5
     },
     {
       "epoch": 0.05,
-      "grad_norm": 0.10152705758810043,
+      "grad_norm": 0.10693935304880142,
       "learning_rate": 3.6e-06,
-      "loss": 11.040735626220703,
+      "loss": 10.94852294921875,
       "step": 10
     },
     {
       "epoch": 0.075,
-      "grad_norm": 0.09875829517841339,
+      "grad_norm": 0.10685458779335022,
       "learning_rate": 3.995627254437549e-06,
-      "loss": 11.026320648193359,
+      "loss": 10.901692962646484,
       "step": 15
     },
     {
       "epoch": 0.1,
-      "grad_norm": 0.09957622736692429,
+      "grad_norm": 0.11649836599826813,
       "learning_rate": 3.9778957412029366e-06,
-      "loss": 11.012971496582031,
+      "loss": 10.860481262207031,
       "step": 20
     },
     {
       "epoch": 0.125,
-      "grad_norm": 0.1074257642030716,
+      "grad_norm": 0.13389746844768524,
       "learning_rate": 3.9466531944960116e-06,
-      "loss": 10.992045593261718,
+      "loss": 10.805369567871093,
       "step": 25
     },
     {
       "epoch": 0.15,
-      "grad_norm": 0.110373854637146,
+      "grad_norm": 0.14611287415027618,
       "learning_rate": 3.902113032590307e-06,
-      "loss": 10.97699432373047,
+      "loss": 10.771086883544921,
       "step": 30
     },
     {
       "epoch": 0.175,
-      "grad_norm": 0.11517436057329178,
+      "grad_norm": 0.1613965630531311,
       "learning_rate": 3.844579509954769e-06,
-      "loss": 10.947827911376953,
+      "loss": 10.723188781738282,
       "step": 35
     },
     {
       "epoch": 0.2,
-      "grad_norm": 0.1078442707657814,
+      "grad_norm": 0.15956223011016846,
       "learning_rate": 3.7744456388872234e-06,
-      "loss": 10.949494171142579,
+      "loss": 10.692904663085937,
       "step": 40
     },
     {
       "epoch": 0.225,
-      "grad_norm": 0.1252269148826599,
+      "grad_norm": 0.19351637363433838,
       "learning_rate": 3.6921905048418706e-06,
-      "loss": 10.916586303710938,
+      "loss": 10.633544921875,
       "step": 45
     },
     {
       "epoch": 0.25,
-      "grad_norm": 0.12218247354030609,
+      "grad_norm": 0.19844886660575867,
       "learning_rate": 3.598375993789849e-06,
-      "loss": 10.902359008789062,
+      "loss": 10.588146209716797,
       "step": 50
     },
     {
       "epoch": 0.25,
-      "eval_accuracy": 0.001978021978021978,
-      "eval_loss": 10.892147064208984,
-      "eval_runtime": 11.0414,
-      "eval_samples_per_second": 9.057,
-      "eval_steps_per_second": 1.54,
+      "eval_accuracy": 0.04886935286935287,
+      "eval_loss": 10.55318832397461,
+      "eval_runtime": 10.5347,
+      "eval_samples_per_second": 9.492,
+      "eval_steps_per_second": 1.614,
       "step": 50
     },
     {
       "epoch": 0.275,
-      "grad_norm": 0.12842494249343872,
+      "grad_norm": 0.22146697342395782,
       "learning_rate": 3.4936429539683075e-06,
-      "loss": 10.880451202392578,
+      "loss": 10.543079376220703,
       "step": 55
     },
     {
       "epoch": 0.3,
-      "grad_norm": 0.12605500221252441,
+      "grad_norm": 0.22231507301330566,
       "learning_rate": 3.3787068182371314e-06,
-      "loss": 10.865975952148437,
+      "loss": 10.494519805908203,
       "step": 60
     },
     {
       "epoch": 0.325,
-      "grad_norm": 0.12930333614349365,
+      "grad_norm": 0.2373388409614563,
       "learning_rate": 3.254352716947074e-06,
-      "loss": 10.846955871582031,
+      "loss": 10.443205261230469,
       "step": 65
     },
     {
       "epoch": 0.35,
-      "grad_norm": 0.1300428807735443,
+      "grad_norm": 0.24415704607963562,
       "learning_rate": 3.1214301147033453e-06,
-      "loss": 10.831236267089844,
+      "loss": 10.390926361083984,
       "step": 70
     },
     {
       "epoch": 0.375,
-      "grad_norm": 0.13403981924057007,
+      "grad_norm": 0.2557603716850281,
       "learning_rate": 2.9808470076610163e-06,
-      "loss": 10.815153503417969,
+      "loss": 10.339105987548828,
       "step": 75
     },
     {
       "epoch": 0.4,
-      "grad_norm": 0.1414586752653122,
+      "grad_norm": 0.2784874439239502,
       "learning_rate": 2.833563720990581e-06,
-      "loss": 10.798695373535157,
+      "loss": 10.287814331054687,
       "step": 80
     },
     {
       "epoch": 0.425,
-      "grad_norm": 0.1405540555715561,
+      "grad_norm": 0.28266823291778564,
       "learning_rate": 2.680586348883286e-06,
-      "loss": 10.79158706665039,
+      "loss": 10.275057983398437,
       "step": 85
     },
     {
       "epoch": 0.45,
-      "grad_norm": 0.15637332201004028,
+      "grad_norm": 0.31389370560646057,
       "learning_rate": 2.5229598819076393e-06,
-      "loss": 10.773637390136718,
+      "loss": 10.22107391357422,
       "step": 90
     },
     {
       "epoch": 0.475,
-      "grad_norm": 0.15481412410736084,
+      "grad_norm": 0.3142116963863373,
       "learning_rate": 2.36176106866422e-06,
-      "loss": 10.747270965576172,
+      "loss": 10.138157653808594,
       "step": 95
     },
     {
       "epoch": 0.5,
-      "grad_norm": 0.1801270991563797,
+      "grad_norm": 0.37546810507774353,
       "learning_rate": 2.198091060500926e-06,
-      "loss": 10.725272369384765,
+      "loss": 10.064350891113282,
       "step": 100
     },
     {
       "epoch": 0.5,
-      "eval_accuracy": 0.032405372405372404,
-      "eval_loss": 10.71803092956543,
-      "eval_runtime": 10.5701,
-      "eval_samples_per_second": 9.461,
-      "eval_steps_per_second": 1.608,
+      "eval_accuracy": 0.09671550671550672,
+      "eval_loss": 10.042438507080078,
+      "eval_runtime": 10.462,
+      "eval_samples_per_second": 9.558,
+      "eval_steps_per_second": 1.625,
       "step": 100
     }
   ],