Training in progress, step 1700, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5057c9842c32a69d89842ae1ea0f94292f62299087952cbb292a8939dab162b
+oid sha256:e62f7ec49e337899fe60ae17d255db8f70179b4e39b6c2c63d4369c4c9c02991
 size 1235573136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40095725fc0786a3c912798bc42b665ef77af7017cc5a4773c5369b9374cfaaf
+oid sha256:e7a9212260f8bf2a398b78af8f740ee3206cd998eb80d6106578b3826d7a7f64
 size 2471218763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:684e33945d5e9615d67982f907b4bd5b55d412c2b48b33613fdd4ef1c4d053c4
+oid sha256:730fa31435cb48457d9bff27c4dd280598a01503fe2e70600467d96a61b92ee0
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b3905bb99561ce66746740b1de5588d55bd3f6f12bc854dc34c827aebf5528
+oid sha256:d4e47d1d4f05a797c13ba0c0cf4a8d6bdae4ef929970ec2744f85af7b8f98bab
 size 1465

last-checkpoint/trainer_state.json

@@ -4,7 +4,7 @@
   "best_model_checkpoint": null,
   "epoch": 1.002,
   "eval_steps": 500,
-  "global_step": 1600,
+  "global_step": 1700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1128,6 +1128,76 @@
       "learning_rate": 0.00029098797595190375,
       "loss": 3103321489408.0,
       "step": 1600
+    },
+    {
+      "epoch": 1.0002,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002909278557114228,
+      "loss": 95.5510498046875,
+      "step": 1610
+    },
+    {
+      "epoch": 1.0004,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00029086773547094184,
+      "loss": 98.69436645507812,
+      "step": 1620
+    },
+    {
+      "epoch": 1.0006,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002908076152304609,
+      "loss": 99.0325439453125,
+      "step": 1630
+    },
+    {
+      "epoch": 1.0008,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00029074749498997994,
+      "loss": 97.31904296875,
+      "step": 1640
+    },
+    {
+      "epoch": 1.001,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000290687374749499,
+      "loss": 98.40114135742188,
+      "step": 1650
+    },
+    {
+      "epoch": 1.0012,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00029062725450901803,
+      "loss": 99.31021728515626,
+      "step": 1660
+    },
+    {
+      "epoch": 1.0014,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00029056713426853703,
+      "loss": 99.4878662109375,
+      "step": 1670
+    },
+    {
+      "epoch": 1.0016,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002905070140280561,
+      "loss": 99.3884521484375,
+      "step": 1680
+    },
+    {
+      "epoch": 1.0018,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002904468937875751,
+      "loss": 99.46731567382812,
+      "step": 1690
+    },
+    {
+      "epoch": 1.002,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00029038677354709417,
+      "loss": 99.4464599609375,
+      "step": 1700
     }
   ],
   "logging_steps": 10,
@@ -1147,7 +1217,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.66012131885056e+16,
+  "total_flos": 2.666982292581888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null