Training in progress, step 890, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffa025eef66bca258a2c708a31c66bb49b5202ba33b130daf5de077761934229
+oid sha256:3981e030b93d87183bf27dee61297bc699920b1d1063e2a14a6d844ffe232f8b
 size 34214640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e709cb101cfd8d2dd59ad22fd294f05828ac74f45d4df2ab19d3003e533d2b7
+oid sha256:f9bbf306e4b6a97f05c3a91de8c636a98b058cb119c3bdee85b0cb98f796a16d
 size 34779282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b037e5462f43b98863a52a70d9f69f81f9004d95e58dd3cc99f3d31398dfddf
+oid sha256:491f63818c64ff6648de457327747921b2babcb32039fca8bf9c3307b28a7558
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:257f76464e0d9243a61928311900fe542b5678e71f0478f88ff81e44cf6e3237
+oid sha256:ffddba77a8223104775eb3a1c056a7d75edc6bf860f477efa9250d5724119c2a
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64d146221a9f59ee3b78ccdc66adddb4900a155cb4ae8103f470cd7f08945a00
+oid sha256:bd946489a63144cac84a6b6a74fc737d9b6756458719a76e2f70310c4ca7f8f9
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e711701998d560976276f5eb7abd4d8a1b7eda77f2ca19fa9b083af4b4513e38
+oid sha256:7b9d2ba99876c3fefd1687e4c0947b9787ec544cab12a64bdb6814ccefbfbfd3
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9de3d917a87f8cb2c303bfbdb68d659ac5d78b440b0a9b3f99298c272d4c77e6
+oid sha256:bc2121f36b82fd0af2305e5cdccd3b5d0ed7e9605006dca6684c3e6d513aeddb
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ea47ff99682637e8d78f3d6ea5166c5ef0c28701ccde7be14f382923f62868e
+oid sha256:95bd7e70c78cf607370cf86fe76ce57495142b48bf65473af517bedfd74dc36d
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33abddde94c43cab804538893438ae725c4c7fd8020079e009890e9435b1cdb5
+oid sha256:78dee00f79cb684b52a789dfffc13b50359ff9b6a646306b391a800ef6536778
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ad36dd84f6ec0f0585e1b305ef3a581ba463bfbc2fcc37cec9828adc24449c9
+oid sha256:1b8b731c550646d4b266437a563c6210a81eba271f5c46c3dc0af7053d7c4bd3
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b67e699223ef06988912f76428500b4db8666c11753105f4263488a2b94e4057
+oid sha256:20e46998e3e088e3aec913e9faf45e0989d546f2ea882278b706c60253407ebc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.438202247191011,
+  "epoch": 10.0,
   "eval_steps": 20,
-  "global_step": 840,
+  "global_step": 890,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -939,6 +939,57 @@
       "eval_samples_per_second": 1042.336,
       "eval_steps_per_second": 6.94,
       "step": 840
+    },
+    {
+      "epoch": 9.55056179775281,
+      "grad_norm": 1.0234375,
+      "learning_rate": 1.055836141905553e-06,
+      "loss": 5.8358,
+      "step": 850
+    },
+    {
+      "epoch": 9.662921348314606,
+      "grad_norm": 0.58203125,
+      "learning_rate": 5.943661777680354e-07,
+      "loss": 5.8508,
+      "step": 860
+    },
+    {
+      "epoch": 9.662921348314606,
+      "eval_loss": 6.0900702476501465,
+      "eval_runtime": 1.4106,
+      "eval_samples_per_second": 1064.779,
+      "eval_steps_per_second": 7.089,
+      "step": 860
+    },
+    {
+      "epoch": 9.775280898876405,
+      "grad_norm": 1.328125,
+      "learning_rate": 2.643083299427751e-07,
+      "loss": 5.8201,
+      "step": 870
+    },
+    {
+      "epoch": 9.887640449438202,
+      "grad_norm": 0.6875,
+      "learning_rate": 6.609892782699633e-08,
+      "loss": 5.8517,
+      "step": 880
+    },
+    {
+      "epoch": 9.887640449438202,
+      "eval_loss": 6.0848469734191895,
+      "eval_runtime": 1.5852,
+      "eval_samples_per_second": 947.512,
+      "eval_steps_per_second": 6.308,
+      "step": 880
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.8203125,
+      "learning_rate": 0.0,
+      "loss": 5.7949,
+      "step": 890
     }
   ],
   "logging_steps": 10,
@@ -953,12 +1004,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.4175123888144384e+16,
+  "total_flos": 1.5024257713045504e+16,
   "train_batch_size": 19,
   "trial_name": null,
   "trial_params": null