Training in progress, step 13000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35af312258ec2ecc580cd7ccdb601acf0843f55378f8ced88aa3b6791062f0ec
+oid sha256:890ad2873a2bbd9defa42e9be53c396630c1fa479c804ecbcda9c1bef5c9a5b7
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc0410b7f00647d202243d6032612ef86b9b1ad740cc13589fc9a20d6719723c
+oid sha256:7df779224de4aac7dbc2c481b18f226ef75df55b33434fd2a24aaa00199ae182
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f42d5f8190e167df10f51b86e202ce65c6f8b2e34f31e34e57377eb8f3a2ccc
+oid sha256:392a7eb84bc6c0f11073a38c2f0980cc2fcea2ab711f0ee9d31a3b2c47437b70
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72aa0a4db9a1d4fcb9226563e6d35e410e13273eff2f98d7fe41149f20f9d2f4
+oid sha256:f8f863bfc80aea1aeb546487ead9ef6092bc37fe14387401d70bc8b324d152f2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8333333333333334,
+  "epoch": 0.8666666666666667,
   "eval_steps": 500,
-  "global_step": 12500,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -882,6 +882,41 @@
       "learning_rate": 1.4445777777777779e-05,
       "loss": 0.0666,
       "step": 12500
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.12742094695568085,
+      "learning_rate": 1.4401333333333334e-05,
+      "loss": 0.0641,
+      "step": 12600
+    },
+    {
+      "epoch": 0.8466666666666667,
+      "grad_norm": 0.12476657330989838,
+      "learning_rate": 1.4356888888888889e-05,
+      "loss": 0.0708,
+      "step": 12700
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.18345853686332703,
+      "learning_rate": 1.4312444444444446e-05,
+      "loss": 0.0666,
+      "step": 12800
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.24870257079601288,
+      "learning_rate": 1.4268000000000001e-05,
+      "loss": 0.0643,
+      "step": 12900
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.41013413667678833,
+      "learning_rate": 1.4223555555555557e-05,
+      "loss": 0.0723,
+      "step": 13000
     }
   ],
   "logging_steps": 100,
@@ -901,7 +936,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.0447894528e+16,
+  "total_flos": 3.166581030912e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null