Training in progress, step 16500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75a86cd786a5d3a1e1f2adcb3f9a3150ccda047965e61deb6383da469625f4c5
+oid sha256:175884cade4e067c9fa3009c5873e488ef4e170548016dcad81294d3815c5e3d
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d52a7d049b044518630bdac24825b9c5aace7c2129b9296a1f4f71f920000ff
+oid sha256:4e366c1ad2c23dec12c48d6136cf496f7476337ed3fe80251ddb60c2daadec8e
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c907d42c9636b923c5bcc4fd78594e76582ee7e7c3af9d3ccfeae6b74654c31c
+oid sha256:3f95e1dd2cd7704ca98aa1bf80c979e7e594652b8372e360c80de457ba4b96d7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cf6ca81cadd867bd2c8ff23d5105fee09afef52498d5c300dfd5de226b319d5
+oid sha256:edb1f065dac584748e029b7253ed918a3ede6790f2209ff8eedc0176fafb2e83
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0666666666666667,
+  "epoch": 1.1,
   "eval_steps": 500,
-  "global_step": 16000,
+  "global_step": 16500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1135,6 +1135,41 @@
       "learning_rate": 1.2890666666666667e-05,
       "loss": 0.061,
       "step": 16000
+    },
+    {
+      "epoch": 1.0733333333333333,
+      "grad_norm": 0.16027814149856567,
+      "learning_rate": 1.2846222222222224e-05,
+      "loss": 0.0559,
+      "step": 16100
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.21083027124404907,
+      "learning_rate": 1.2801777777777779e-05,
+      "loss": 0.0576,
+      "step": 16200
+    },
+    {
+      "epoch": 1.0866666666666667,
+      "grad_norm": 0.13497234880924225,
+      "learning_rate": 1.2757333333333334e-05,
+      "loss": 0.0599,
+      "step": 16300
+    },
+    {
+      "epoch": 1.0933333333333333,
+      "grad_norm": 0.28260791301727295,
+      "learning_rate": 1.2712888888888891e-05,
+      "loss": 0.0585,
+      "step": 16400
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.1817014068365097,
+      "learning_rate": 1.2668444444444446e-05,
+      "loss": 0.0544,
+      "step": 16500
     }
   ],
   "logging_steps": 100,
@@ -1154,7 +1189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.897330499584e+16,
+  "total_flos": 4.019122077696e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null