Training in progress, step 1200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12451cbc3f681c4d652adfbac061b94a617fe5288eadb9338e0c0116f1ab09a0
+oid sha256:afcab61d0f0cd6492620de0981d9e3af3b1d7bf197c5b9a30367af1e1384d769
 size 3237829088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2ac56c591f7d766084f7d7411df625b2b9385404ec3f7c675d4dea7dc7e6caf
+oid sha256:e4bf418fd1d2214f3b6dd2acb610220e68b528633af9c01c8a0638ef623a8e37
 size 2062272049

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dbfcd19dd04e87ea5a0a02be9024658d9d950751b047080030098d848f7be93
+oid sha256:63dea8701860badef7f13a7093d7c8f6df4c5eb7423d37c0b1df9d89c9a49eb9
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:504b7bc543b9e5f039f6559d07b099507a66c15c86836ff5981e4eee51792c02
+oid sha256:1b04ef7af3a89dd0eb8778c7ed7d28aeab310d9f53593d47cc2bdc9458a253ac
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb4a875674808f59301dfb232d0f66520f4ad75d8962141e97389a5c2ef15def
+oid sha256:76df728eeb65e9565f5601b8baa2ec9eb380c004fbfe2e79296e73893ec398b4
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2582866982350409,
+  "epoch": 0.34438226431338786,
   "eval_steps": 300,
-  "global_step": 900,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -638,6 +638,216 @@
       "learning_rate": 0.00017244452248319896,
       "loss": 0.8771,
       "step": 900
+    },
+    {
+      "epoch": 0.26115655043765246,
+      "grad_norm": 46.30351638793945,
+      "learning_rate": 0.00017180750950109504,
+      "loss": 0.788,
+      "step": 910
+    },
+    {
+      "epoch": 0.264026402640264,
+      "grad_norm": 6.262620449066162,
+      "learning_rate": 0.0001711644231338208,
+      "loss": 0.916,
+      "step": 920
+    },
+    {
+      "epoch": 0.2668962548428756,
+      "grad_norm": 7.936816215515137,
+      "learning_rate": 0.00017051531777277952,
+      "loss": 0.8425,
+      "step": 930
+    },
+    {
+      "epoch": 0.26976610704548715,
+      "grad_norm": 10.233474731445312,
+      "learning_rate": 0.00016986024831845296,
+      "loss": 0.9159,
+      "step": 940
+    },
+    {
+      "epoch": 0.27263595924809875,
+      "grad_norm": 13.751338958740234,
+      "learning_rate": 0.00016919927017575832,
+      "loss": 0.8484,
+      "step": 950
+    },
+    {
+      "epoch": 0.2755058114507103,
+      "grad_norm": 18.70934295654297,
+      "learning_rate": 0.00016853243924936173,
+      "loss": 0.8387,
+      "step": 960
+    },
+    {
+      "epoch": 0.27837566365332184,
+      "grad_norm": 6.2156853675842285,
+      "learning_rate": 0.0001678598119389502,
+      "loss": 0.9127,
+      "step": 970
+    },
+    {
+      "epoch": 0.28124551585593344,
+      "grad_norm": 10.486414909362793,
+      "learning_rate": 0.00016718144513446127,
+      "loss": 0.861,
+      "step": 980
+    },
+    {
+      "epoch": 0.284115368058545,
+      "grad_norm": 7.782724380493164,
+      "learning_rate": 0.00016649739621127146,
+      "loss": 0.8739,
+      "step": 990
+    },
+    {
+      "epoch": 0.2869852202611565,
+      "grad_norm": 30.388168334960938,
+      "learning_rate": 0.00016580772302534337,
+      "loss": 0.9009,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2898550724637681,
+      "grad_norm": 7.943617343902588,
+      "learning_rate": 0.0001651124839083324,
+      "loss": 0.8113,
+      "step": 1010
+    },
+    {
+      "epoch": 0.29272492466637967,
+      "grad_norm": 8.402076721191406,
+      "learning_rate": 0.00016441173766265315,
+      "loss": 0.8076,
+      "step": 1020
+    },
+    {
+      "epoch": 0.29559477686899127,
+      "grad_norm": 7.3927764892578125,
+      "learning_rate": 0.00016370554355650584,
+      "loss": 0.8263,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2984646290716028,
+      "grad_norm": 8.749371528625488,
+      "learning_rate": 0.0001629939613188638,
+      "loss": 0.8673,
+      "step": 1040
+    },
+    {
+      "epoch": 0.30133448127421436,
+      "grad_norm": 4.924167156219482,
+      "learning_rate": 0.0001622770511344213,
+      "loss": 0.869,
+      "step": 1050
+    },
+    {
+      "epoch": 0.30420433347682596,
+      "grad_norm": 34.14529037475586,
+      "learning_rate": 0.00016155487363850342,
+      "loss": 0.9202,
+      "step": 1060
+    },
+    {
+      "epoch": 0.3070741856794375,
+      "grad_norm": 13.217582702636719,
+      "learning_rate": 0.00016082748991193757,
+      "loss": 0.8409,
+      "step": 1070
+    },
+    {
+      "epoch": 0.30994403788204905,
+      "grad_norm": 19.251298904418945,
+      "learning_rate": 0.00016009496147588735,
+      "loss": 0.8624,
+      "step": 1080
+    },
+    {
+      "epoch": 0.31281389008466065,
+      "grad_norm": 52.710453033447266,
+      "learning_rate": 0.00015935735028664908,
+      "loss": 0.8695,
+      "step": 1090
+    },
+    {
+      "epoch": 0.3156837422872722,
+      "grad_norm": 15.96419906616211,
+      "learning_rate": 0.00015861471873041184,
+      "loss": 0.8773,
+      "step": 1100
+    },
+    {
+      "epoch": 0.3185535944898838,
+      "grad_norm": 7.947400093078613,
+      "learning_rate": 0.0001578671296179806,
+      "loss": 0.8387,
+      "step": 1110
+    },
+    {
+      "epoch": 0.32142344669249534,
+      "grad_norm": 13.167436599731445,
+      "learning_rate": 0.00015711464617946402,
+      "loss": 0.8582,
+      "step": 1120
+    },
+    {
+      "epoch": 0.3242932988951069,
+      "grad_norm": 11.579595565795898,
+      "learning_rate": 0.00015635733205892653,
+      "loss": 0.8615,
+      "step": 1130
+    },
+    {
+      "epoch": 0.3271631510977185,
+      "grad_norm": 4.840546131134033,
+      "learning_rate": 0.00015559525130900523,
+      "loss": 0.822,
+      "step": 1140
+    },
+    {
+      "epoch": 0.33003300330033003,
+      "grad_norm": 8.159014701843262,
+      "learning_rate": 0.0001548284683854925,
+      "loss": 0.8512,
+      "step": 1150
+    },
+    {
+      "epoch": 0.3329028555029416,
+      "grad_norm": 33.13652038574219,
+      "learning_rate": 0.00015405704814188442,
+      "loss": 0.8686,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3357727077055532,
+      "grad_norm": 5.398830890655518,
+      "learning_rate": 0.00015328105582389557,
+      "loss": 0.8685,
+      "step": 1170
+    },
+    {
+      "epoch": 0.3386425599081647,
+      "grad_norm": 23.8563289642334,
+      "learning_rate": 0.00015250055706394057,
+      "loss": 0.8617,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3415124121107763,
+      "grad_norm": 5.886293411254883,
+      "learning_rate": 0.00015171561787558297,
+      "loss": 0.8559,
+      "step": 1190
+    },
+    {
+      "epoch": 0.34438226431338786,
+      "grad_norm": 7.887658596038818,
+      "learning_rate": 0.000150926304647952,
+      "loss": 0.8811,
+      "step": 1200
     }
   ],
   "logging_steps": 10,
@@ -657,7 +867,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.6826944897024e+19,
+  "total_flos": 4.9102593196032e+19,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91ccf64bfb489d98f1d53ff4b75bafff9ef6970cd7568bffdd38c9685c6b4b38
+oid sha256:c826a3ab5235a63f61a75099a41de538ae2f6fe824df40b96ea1279de029afd1
 size 6033