Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73f8c1791b5ee7e58d663de47ee5fe8c35df4f1f6931e02c5c1c05ca2c095b6a
+oid sha256:e804d9311c8b6db40d3fb86cf3eaca1297d3d4f7332c4f8f051e0d9baa0c5dc1
 size 579824888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be87b0db9147168393b32986a7c8b1d815025dfeb0ce1175bbb3f22f44725ce1
+oid sha256:f1540ec263719b4b3cba968a2a351d9132483a93521620ed9c251f0803216f31
 size 1159794763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44dfb10fef84f1136d3eee8160822b0d721bb87ad12f498bd11540cf57bcb837
+oid sha256:7f6877654089e17195cec15c42052fefb64568bfec6cf56d9ddc6361105ecd2f
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eed2e2028bc81a04ee6b31f6b531dfb1c72a67f736dcd67eadafbd77d40b8d1c
+oid sha256:9008af82ea2c682c9b64de9d5bd271649247b8bd3c3761983a4def45d64125f2
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8,
+  "epoch": 1.0,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -192,6 +192,52 @@
       "eval_samples_per_second": 77.115,
       "eval_steps_per_second": 4.85,
       "step": 800
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 1.464524507522583,
+      "learning_rate": 7.586717784541531e-06,
+      "loss": 21.3955,
+      "step": 850
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.6547788381576538,
+      "learning_rate": 3.443464128710239e-06,
+      "loss": 21.3548,
+      "step": 900
+    },
+    {
+      "epoch": 0.9,
+      "eval_accuracy": 0.2200151717208807,
+      "eval_loss": 5.29579496383667,
+      "eval_runtime": 12.9348,
+      "eval_samples_per_second": 74.992,
+      "eval_steps_per_second": 4.716,
+      "step": 900
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 1.0555720329284668,
+      "learning_rate": 8.856374635655695e-07,
+      "loss": 21.3268,
+      "step": 950
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.3585398197174072,
+      "learning_rate": 3.4150841404789745e-10,
+      "loss": 21.3675,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.22028451011683436,
+      "eval_loss": 5.292044639587402,
+      "eval_runtime": 13.1086,
+      "eval_samples_per_second": 73.997,
+      "eval_steps_per_second": 4.653,
+      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -206,12 +252,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.338013309206528e+17,
+  "total_flos": 1.67251663650816e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null