Auto-save flat update: checkpoint-10000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:248fad6196016d5bb8fa97e7ca2cd99fdbc2e5115597a52bd0f7525d48177707
+oid sha256:b711109f0ad3f319d1bc6cd06062dae48744a3395a51ba0e6af33cece506c46c
 size 17315288

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e812adf6e44217b37bb95ea71945f039f7ed54815c7648506eacc625aec642b
+oid sha256:72fed1de07ba7856e90f74545259c787b689f6231e854dd0b9e5288e17c92f2c
 size 34640005

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa4c7a3f0413da0222033791fbd61f87fa01f48b28114defa805cbadbcde3d7c
+oid sha256:8a9f154b1359afdda4d3ed65870a0e8dc4d46259d77c6ba1858bc2095aee8d67
 size 1465

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.99,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 9900,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -13867,6 +13867,146 @@
       "learning_rate": 2.002002002002002e-06,
       "loss": 2.3372,
       "step": 9900
+    },
+    {
+      "epoch": 0.9905,
+      "grad_norm": 0.8105862140655518,
+      "learning_rate": 1.9019019019019022e-06,
+      "loss": 2.3333,
+      "step": 9905
+    },
+    {
+      "epoch": 0.991,
+      "grad_norm": 0.8059213757514954,
+      "learning_rate": 1.801801801801802e-06,
+      "loss": 2.3359,
+      "step": 9910
+    },
+    {
+      "epoch": 0.9915,
+      "grad_norm": 0.818318247795105,
+      "learning_rate": 1.7017017017017019e-06,
+      "loss": 2.3476,
+      "step": 9915
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 0.7882871031761169,
+      "learning_rate": 1.6016016016016016e-06,
+      "loss": 2.3351,
+      "step": 9920
+    },
+    {
+      "epoch": 0.9925,
+      "grad_norm": 0.817363440990448,
+      "learning_rate": 1.5015015015015015e-06,
+      "loss": 2.3523,
+      "step": 9925
+    },
+    {
+      "epoch": 0.993,
+      "grad_norm": 0.8170154094696045,
+      "learning_rate": 1.4014014014014014e-06,
+      "loss": 2.3567,
+      "step": 9930
+    },
+    {
+      "epoch": 0.9935,
+      "grad_norm": 0.8051609992980957,
+      "learning_rate": 1.3013013013013014e-06,
+      "loss": 2.3376,
+      "step": 9935
+    },
+    {
+      "epoch": 0.994,
+      "grad_norm": 0.8126572370529175,
+      "learning_rate": 1.2012012012012013e-06,
+      "loss": 2.3451,
+      "step": 9940
+    },
+    {
+      "epoch": 0.9945,
+      "grad_norm": 0.8231433629989624,
+      "learning_rate": 1.1011011011011012e-06,
+      "loss": 2.3174,
+      "step": 9945
+    },
+    {
+      "epoch": 0.995,
+      "grad_norm": 0.8126521110534668,
+      "learning_rate": 1.001001001001001e-06,
+      "loss": 2.3333,
+      "step": 9950
+    },
+    {
+      "epoch": 0.9955,
+      "grad_norm": 0.7962733507156372,
+      "learning_rate": 9.00900900900901e-07,
+      "loss": 2.3245,
+      "step": 9955
+    },
+    {
+      "epoch": 0.996,
+      "grad_norm": 0.8092034459114075,
+      "learning_rate": 8.008008008008008e-07,
+      "loss": 2.3472,
+      "step": 9960
+    },
+    {
+      "epoch": 0.9965,
+      "grad_norm": 0.8146346807479858,
+      "learning_rate": 7.007007007007007e-07,
+      "loss": 2.3337,
+      "step": 9965
+    },
+    {
+      "epoch": 0.997,
+      "grad_norm": 0.7841795086860657,
+      "learning_rate": 6.006006006006006e-07,
+      "loss": 2.3382,
+      "step": 9970
+    },
+    {
+      "epoch": 0.9975,
+      "grad_norm": 0.7981340885162354,
+      "learning_rate": 5.005005005005005e-07,
+      "loss": 2.3166,
+      "step": 9975
+    },
+    {
+      "epoch": 0.998,
+      "grad_norm": 0.8195034861564636,
+      "learning_rate": 4.004004004004004e-07,
+      "loss": 2.325,
+      "step": 9980
+    },
+    {
+      "epoch": 0.9985,
+      "grad_norm": 0.8242753148078918,
+      "learning_rate": 3.003003003003003e-07,
+      "loss": 2.3474,
+      "step": 9985
+    },
+    {
+      "epoch": 0.999,
+      "grad_norm": 0.9042975902557373,
+      "learning_rate": 2.002002002002002e-07,
+      "loss": 2.322,
+      "step": 9990
+    },
+    {
+      "epoch": 0.9995,
+      "grad_norm": 0.8336848020553589,
+      "learning_rate": 1.001001001001001e-07,
+      "loss": 2.3474,
+      "step": 9995
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8093213438987732,
+      "learning_rate": 0.0,
+      "loss": 2.3473,
+      "step": 10000
     }
   ],
   "logging_steps": 5,
@@ -13881,12 +14021,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8169853236019200.0,
+  "total_flos": 8252377006080000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null