Training in progress, step 50, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e219b25b7e3609e604ef05ade6d200dabd377e65247e60e3e2ff5ed1c7e25fe1
+oid sha256:2ee88c21b9bdff6d676565da3d78bc24646e37fec67cf8fdfc88ba63eaf89e49
 size 1738460416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb5c19a9e3e14de1d661eba59716d3a9e1a9a87a5be68b944fb729f292c5937b
+oid sha256:bb03d531654389e8b69bb5f8d65bf87f5aab7501a7e7cc0b22cb201d2abaa419
 size 3477327340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
+oid sha256:01f9a0f7843a37be87edd23f4e88aa93b38b95cc2c07503eeb1cf2e4632453a2
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac56030360eaf7d09a44b289120bcd685e39fa9a366361e9c512debf4fa01791
+oid sha256:f6ab4a60dabf5285d62294f6dabdfb5eda3b8675d8c862f026b8ef4fa5a2952a
 size 1465

last-checkpoint/trainer_state.json

@@ -11,112 +11,112 @@
   "log_history": [
     {
       "epoch": 0.025,
-      "grad_norm": 67.5,
-      "learning_rate": 0.0004,
-      "loss": 271.8493,
+      "grad_norm": 27.5,
+      "learning_rate": 4e-05,
+      "loss": 71.893,
       "step": 5
     },
     {
       "epoch": 0.05,
-      "grad_norm": 68.5,
-      "learning_rate": 0.0009000000000000001,
-      "loss": 208.6483,
+      "grad_norm": 11.5,
+      "learning_rate": 9e-05,
+      "loss": 62.6505,
       "step": 10
     },
     {
       "epoch": 0.05,
-      "eval_loss": 7.974327087402344,
-      "eval_runtime": 6.9602,
-      "eval_samples_per_second": 19.252,
-      "eval_steps_per_second": 1.006,
+      "eval_loss": 9.905916213989258,
+      "eval_runtime": 15.7082,
+      "eval_samples_per_second": 34.25,
+      "eval_steps_per_second": 2.292,
       "step": 10
     },
     {
       "epoch": 0.075,
-      "grad_norm": 114.5,
-      "learning_rate": 0.0009989068136093873,
-      "loss": 190.7281,
+      "grad_norm": 9.625,
+      "learning_rate": 9.989068136093873e-05,
+      "loss": 57.5435,
       "step": 15
     },
     {
       "epoch": 0.1,
-      "grad_norm": 26.25,
-      "learning_rate": 0.0009944739353007343,
-      "loss": 188.7951,
+      "grad_norm": 6.84375,
+      "learning_rate": 9.944739353007344e-05,
+      "loss": 53.1338,
       "step": 20
     },
     {
       "epoch": 0.1,
-      "eval_loss": 7.880503177642822,
-      "eval_runtime": 6.6198,
-      "eval_samples_per_second": 20.242,
-      "eval_steps_per_second": 1.057,
+      "eval_loss": 8.45786190032959,
+      "eval_runtime": 16.0113,
+      "eval_samples_per_second": 33.601,
+      "eval_steps_per_second": 2.248,
       "step": 20
     },
     {
       "epoch": 0.125,
-      "grad_norm": 23.75,
-      "learning_rate": 0.000986663298624003,
-      "loss": 186.3658,
+      "grad_norm": 4.8125,
+      "learning_rate": 9.86663298624003e-05,
+      "loss": 49.413,
       "step": 25
     },
     {
       "epoch": 0.15,
-      "grad_norm": 14.5,
-      "learning_rate": 0.0009755282581475768,
-      "loss": 185.2524,
+      "grad_norm": 4.96875,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 46.6506,
       "step": 30
     },
     {
       "epoch": 0.15,
-      "eval_loss": 7.70925760269165,
-      "eval_runtime": 6.8441,
-      "eval_samples_per_second": 19.579,
-      "eval_steps_per_second": 1.023,
+      "eval_loss": 7.606866836547852,
+      "eval_runtime": 16.4027,
+      "eval_samples_per_second": 32.799,
+      "eval_steps_per_second": 2.195,
       "step": 30
     },
     {
       "epoch": 0.175,
-      "grad_norm": 20.75,
-      "learning_rate": 0.0009611448774886924,
-      "loss": 182.743,
+      "grad_norm": 4.875,
+      "learning_rate": 9.611448774886924e-05,
+      "loss": 44.8354,
       "step": 35
     },
     {
       "epoch": 0.2,
-      "grad_norm": 146.0,
-      "learning_rate": 0.000943611409721806,
-      "loss": 181.0595,
+      "grad_norm": 3.625,
+      "learning_rate": 9.43611409721806e-05,
+      "loss": 43.8419,
       "step": 40
     },
     {
       "epoch": 0.2,
-      "eval_loss": 7.680881023406982,
-      "eval_runtime": 6.8778,
-      "eval_samples_per_second": 19.483,
-      "eval_steps_per_second": 1.018,
+      "eval_loss": 7.288437843322754,
+      "eval_runtime": 16.1342,
+      "eval_samples_per_second": 33.345,
+      "eval_steps_per_second": 2.231,
       "step": 40
     },
     {
       "epoch": 0.225,
-      "grad_norm": 14336.0,
-      "learning_rate": 0.0009230476262104677,
-      "loss": 183.6445,
+      "grad_norm": 5.0,
+      "learning_rate": 9.230476262104677e-05,
+      "loss": 43.2838,
       "step": 45
     },
     {
       "epoch": 0.25,
-      "grad_norm": 10176.0,
-      "learning_rate": 0.0008995939984474624,
-      "loss": 192.1855,
+      "grad_norm": 4.40625,
+      "learning_rate": 8.995939984474624e-05,
+      "loss": 42.7483,
       "step": 50
     },
     {
       "epoch": 0.25,
-      "eval_loss": 8.385082244873047,
-      "eval_runtime": 6.7705,
-      "eval_samples_per_second": 19.792,
-      "eval_steps_per_second": 1.034,
+      "eval_loss": 7.132974147796631,
+      "eval_runtime": 16.0666,
+      "eval_samples_per_second": 33.486,
+      "eval_steps_per_second": 2.241,
       "step": 50
     }
   ],
@@ -137,8 +137,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9622204484354048e+17,
-  "train_batch_size": 5,
+  "total_flos": 3.6791633313792e+16,
+  "train_batch_size": 15,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:855e4e426c5eafaf63f7a009322eb06b70910e4a4bee1286781bd91f0ef7fc5c
+oid sha256:7ee00a42c6101902398b3f09cb8e094a34fe74ca1ef85d5e6e740ab7c96f6947
 size 5841