Training in progress, step 17000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:175884cade4e067c9fa3009c5873e488ef4e170548016dcad81294d3815c5e3d
+oid sha256:688c3b1d28f6b863bee92004557adc364c4b2e5ee4097d484ed3aaba40d50c14
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e366c1ad2c23dec12c48d6136cf496f7476337ed3fe80251ddb60c2daadec8e
+oid sha256:9a993357ca1b551b4a094ee2409999ca1a4657c3428fde811fa9954bc1b8b645
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f95e1dd2cd7704ca98aa1bf80c979e7e594652b8372e360c80de457ba4b96d7
+oid sha256:b8fa477eb7529f96adee96884288f62ffdf70dbb1416c416ce42fdc1eba5e518
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edb1f065dac584748e029b7253ed918a3ede6790f2209ff8eedc0176fafb2e83
+oid sha256:57233dc32b29f0dc0010f99ddb975758e3cef5e747558908f115a1d09e80f707
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1,
+  "epoch": 1.1333333333333333,
   "eval_steps": 500,
-  "global_step": 16500,
+  "global_step": 17000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1170,6 +1170,41 @@
       "learning_rate": 1.2668444444444446e-05,
       "loss": 0.0544,
       "step": 16500
+    },
+    {
+      "epoch": 1.1066666666666667,
+      "grad_norm": 0.17457172274589539,
+      "learning_rate": 1.2624444444444446e-05,
+      "loss": 0.0587,
+      "step": 16600
+    },
+    {
+      "epoch": 1.1133333333333333,
+      "grad_norm": 0.1655428558588028,
+      "learning_rate": 1.2580000000000002e-05,
+      "loss": 0.0553,
+      "step": 16700
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.23929822444915771,
+      "learning_rate": 1.2535555555555557e-05,
+      "loss": 0.0595,
+      "step": 16800
+    },
+    {
+      "epoch": 1.1266666666666667,
+      "grad_norm": 0.1591082215309143,
+      "learning_rate": 1.2491111111111112e-05,
+      "loss": 0.0589,
+      "step": 16900
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.14291773736476898,
+      "learning_rate": 1.2446666666666667e-05,
+      "loss": 0.058,
+      "step": 17000
     }
   ],
   "logging_steps": 100,
@@ -1189,7 +1224,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.019122077696e+16,
+  "total_flos": 4.140913655808e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null