Training in progress, step 40, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b50fab4df0857296b826fb533679d67b419acccbace03eded5bcde6b1019ad70
+oid sha256:ca649e14cea98c3cc44061ac56285aa5df5d776c782a04bdb4bedbecc0733771
 size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5236e7bb1e866cd6476e6e3665a868ca0c865cc4d75c0b8f33b968041717090
+oid sha256:cbe28617fceb4326d149bc2dffe3b42c8e87c0a1d3be8c4411e635fc5c164538
 size 255265850

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f0cd92d44290d6f6688c3ebd219b1a8e16a4fb3fc40ddaf684cb9273335ba6e
+oid sha256:8f7075b845fd2c310514c90a86f43f4a07f06ff68c6ffd9b017c704559836097
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a20a1acb52cc6e9c17e6c90786f46e7d0ce02edfc6be15f78dd6f0e42dd5db2
+oid sha256:a34eaafb81fc29861f92562a49db625bc4b7b8bc7deb6e0900ac3e1e04fdbdfe
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:671e391807b0ab9b289ecea768661c20458f82abb5fff2f5b02536860d7df3aa
+oid sha256:170259f6ec12ca458ff719ec610fe0ad1e4d444f8e1e1a9f502e530830402066
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:876b48ccbca60f6ef5833275c3979dd776f668d13202dfbd3055d06dd8704ebc
+oid sha256:003c71d0c6c30c0b2b1aab044884386c3f92f2c7e02b567413122f0724c87ec1
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84f22729b765b6841bd185712dd3ab8bf338866cd8396b5dce62f9950913691a
+oid sha256:02fba4d221acb6fea331334b3de1974a87e216e52fc96554556bafda3bca4247
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.3333333333333335,
+  "epoch": 6.666666666666667,
   "eval_steps": 20,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 284.095,
       "eval_steps_per_second": 2.271,
       "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.125,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 5.1824,
+      "step": 30
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 3.546875,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 5.0084,
+      "step": 40
+    },
+    {
+      "epoch": 6.666666666666667,
+      "eval_loss": 3.0989110469818115,
+      "eval_runtime": 5.3227,
+      "eval_samples_per_second": 282.0,
+      "eval_steps_per_second": 2.254,
+      "step": 40
     }
   ],
   "logging_steps": 10,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2598287978790912.0,
+  "total_flos": 5198666398695424.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null