Training in progress, step 100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66c490ccd97ff3a1c5be26a7a6caff2ab3d0f0f23f0ba25ff8645d1cc81be9dd
+oid sha256:f9e0d930706cfcb392491da03f8a50820f032ca5714fc8d8cf3a436cc2b448c3
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ebb2eae727fa1d60dd1ae5c5487d2139dfee54a62ac5572c925eef09f931879
+oid sha256:a7861d452becbacd4ed7de2869406ad518e79c266cc3e0868a27bae3770d6e23
 size 350603

last-checkpoint/trainer_state.json

@@ -11,160 +11,160 @@
   "log_history": [
     {
       "epoch": 0.025,
-      "grad_norm": 0.11061733961105347,
+      "grad_norm": 0.17093215882778168,
       "learning_rate": 1.6e-06,
-      "loss": 10.991944885253906,
+      "loss": 10.88990478515625,
       "step": 5
     },
     {
       "epoch": 0.05,
-      "grad_norm": 0.10693935304880142,
+      "grad_norm": 0.2938487231731415,
       "learning_rate": 3.6e-06,
-      "loss": 10.94852294921875,
+      "loss": 10.514610290527344,
       "step": 10
     },
     {
       "epoch": 0.075,
-      "grad_norm": 0.10685458779335022,
+      "grad_norm": 0.37134891748428345,
       "learning_rate": 3.995627254437549e-06,
-      "loss": 10.901692962646484,
+      "loss": 10.039398193359375,
       "step": 15
     },
     {
       "epoch": 0.1,
-      "grad_norm": 0.11649836599826813,
+      "grad_norm": 0.2268853634595871,
       "learning_rate": 3.9778957412029366e-06,
-      "loss": 10.860481262207031,
+      "loss": 9.626433563232421,
       "step": 20
     },
     {
       "epoch": 0.125,
-      "grad_norm": 0.13389746844768524,
+      "grad_norm": 0.2303772270679474,
       "learning_rate": 3.9466531944960116e-06,
-      "loss": 10.805369567871093,
+      "loss": 9.306468963623047,
       "step": 25
     },
     {
       "epoch": 0.15,
-      "grad_norm": 0.14611287415027618,
+      "grad_norm": 0.20847690105438232,
       "learning_rate": 3.902113032590307e-06,
-      "loss": 10.771086883544921,
+      "loss": 9.164946746826171,
       "step": 30
     },
     {
       "epoch": 0.175,
-      "grad_norm": 0.1613965630531311,
+      "grad_norm": 0.18881037831306458,
       "learning_rate": 3.844579509954769e-06,
-      "loss": 10.723188781738282,
+      "loss": 9.01562728881836,
       "step": 35
     },
     {
       "epoch": 0.2,
-      "grad_norm": 0.15956223011016846,
+      "grad_norm": 0.14287346601486206,
       "learning_rate": 3.7744456388872234e-06,
-      "loss": 10.692904663085937,
+      "loss": 8.989354705810547,
       "step": 40
     },
     {
       "epoch": 0.225,
-      "grad_norm": 0.19351637363433838,
+      "grad_norm": 0.16693444550037384,
       "learning_rate": 3.6921905048418706e-06,
-      "loss": 10.633544921875,
+      "loss": 8.803133392333985,
       "step": 45
     },
     {
       "epoch": 0.25,
-      "grad_norm": 0.19844886660575867,
+      "grad_norm": 0.12351641803979874,
       "learning_rate": 3.598375993789849e-06,
-      "loss": 10.588146209716797,
+      "loss": 8.753093719482422,
       "step": 50
     },
     {
       "epoch": 0.25,
-      "eval_accuracy": 0.04886935286935287,
-      "eval_loss": 10.55318832397461,
-      "eval_runtime": 10.5347,
-      "eval_samples_per_second": 9.492,
-      "eval_steps_per_second": 1.614,
+      "eval_accuracy": 0.10913064713064713,
+      "eval_loss": 8.707348823547363,
+      "eval_runtime": 10.3624,
+      "eval_samples_per_second": 9.65,
+      "eval_steps_per_second": 1.641,
       "step": 50
     },
     {
       "epoch": 0.275,
-      "grad_norm": 0.22146697342395782,
+      "grad_norm": 0.11024487018585205,
       "learning_rate": 3.4936429539683075e-06,
-      "loss": 10.543079376220703,
+      "loss": 8.706148529052735,
       "step": 55
     },
     {
       "epoch": 0.3,
-      "grad_norm": 0.22231507301330566,
+      "grad_norm": 0.11397001892328262,
       "learning_rate": 3.3787068182371314e-06,
-      "loss": 10.494519805908203,
+      "loss": 8.635591125488281,
       "step": 60
     },
     {
       "epoch": 0.325,
-      "grad_norm": 0.2373388409614563,
+      "grad_norm": 0.11307007819414139,
       "learning_rate": 3.254352716947074e-06,
-      "loss": 10.443205261230469,
+      "loss": 8.56150131225586,
       "step": 65
     },
     {
       "epoch": 0.35,
-      "grad_norm": 0.24415704607963562,
+      "grad_norm": 0.11745881289243698,
       "learning_rate": 3.1214301147033453e-06,
-      "loss": 10.390926361083984,
+      "loss": 8.52124252319336,
       "step": 70
     },
     {
       "epoch": 0.375,
-      "grad_norm": 0.2557603716850281,
+      "grad_norm": 0.10288426280021667,
       "learning_rate": 2.9808470076610163e-06,
-      "loss": 10.339105987548828,
+      "loss": 8.491536712646484,
       "step": 75
     },
     {
       "epoch": 0.4,
-      "grad_norm": 0.2784874439239502,
+      "grad_norm": 0.11181551218032837,
       "learning_rate": 2.833563720990581e-06,
-      "loss": 10.287814331054687,
+      "loss": 8.444434356689452,
       "step": 80
     },
     {
       "epoch": 0.425,
-      "grad_norm": 0.28266823291778564,
+      "grad_norm": 0.10100872069597244,
       "learning_rate": 2.680586348883286e-06,
-      "loss": 10.275057983398437,
+      "loss": 8.523983764648438,
       "step": 85
     },
     {
       "epoch": 0.45,
-      "grad_norm": 0.31389370560646057,
+      "grad_norm": 0.09801367670297623,
       "learning_rate": 2.5229598819076393e-06,
-      "loss": 10.22107391357422,
+      "loss": 8.447149658203125,
       "step": 90
     },
     {
       "epoch": 0.475,
-      "grad_norm": 0.3142116963863373,
+      "grad_norm": 0.09665904939174652,
       "learning_rate": 2.36176106866422e-06,
-      "loss": 10.138157653808594,
+      "loss": 8.304853820800782,
       "step": 95
     },
     {
       "epoch": 0.5,
-      "grad_norm": 0.37546810507774353,
+      "grad_norm": 0.08705192059278488,
       "learning_rate": 2.198091060500926e-06,
-      "loss": 10.064350891113282,
+      "loss": 8.243639373779297,
       "step": 100
     },
     {
       "epoch": 0.5,
-      "eval_accuracy": 0.09671550671550672,
-      "eval_loss": 10.042438507080078,
-      "eval_runtime": 10.462,
-      "eval_samples_per_second": 9.558,
-      "eval_steps_per_second": 1.625,
+      "eval_accuracy": 0.11717704517704518,
+      "eval_loss": 8.261603355407715,
+      "eval_runtime": 10.4554,
+      "eval_samples_per_second": 9.564,
+      "eval_steps_per_second": 1.626,
       "step": 100
     }
   ],