Training in progress, step 60, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecf30145777b99e1483b3b8af8ca3c954b0bee05ef0cd517f6e62511cecc1737
+oid sha256:9f0661a72ba3b66e4cc9219a425dc921ded7fb63db1b28e737a02a8ac7fdf59c
 size 723674912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6361dd5e29307df7b873ae303523973ac614868fbd2cc1c02b982d5d15c248f8
+oid sha256:14923cfad5b25d998979f61b48520b8b8f6c1c8529883dfdb62b3f6c200c9927
 size 735625370

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9664d03c75ff248cdee237bc0f578d0ab4ef30cf459a48b947cc8ba96efcf94a
+oid sha256:19fc90eda86010024a75dd32530431e4c24bd0a1f6eff78d85286abbab03fba0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0fc8395b524cd5cac61206279bf13d167d68f260f6be7c6c7eca67cec66f27c
+oid sha256:566f4865681bbc83459877b33ce491582588f147022ba0534caf3300e631e63c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ca0fe34fb6c7827e42ed53ce617ab6af68578cc38e07c82ad0cc484dafb3017
+oid sha256:3338107951da02a423c8f8ac5237de9e0061e6b3d0456c6fc2efa3002cc8846d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f1cc5e77aed95b6e97dac8961ae1ecb44cecf9736fe10dadd3ddbb8b2eb1ac6
+oid sha256:fffd547e430c47ced000ae5492f6d5e18bd88a88193ec1ee24bfe6f6a4d8e35f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62b5eb3be65174d535b2988d2d3d904fb7ecffa959b2cce72a3b7b18e92c3e6a
+oid sha256:ceb70d09862bb859050a14662883ecf389a0e55aec23642f4305d8f0de2bee43
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 7.5,
   "eval_steps": 20,
-  "global_step": 40,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,28 @@
       "eval_samples_per_second": 309.785,
       "eval_steps_per_second": 3.509,
       "step": 40
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 0.138671875,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 2.1125,
+      "step": 50
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 0.126953125,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 2.0938,
+      "step": 60
+    },
+    {
+      "epoch": 7.5,
+      "eval_loss": 2.0711307525634766,
+      "eval_runtime": 5.3765,
+      "eval_samples_per_second": 279.177,
+      "eval_steps_per_second": 3.162,
+      "step": 60
     }
   ],
   "logging_steps": 10,
@@ -78,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4227753477865472e+16,
+  "total_flos": 2.134163021679821e+16,
   "train_batch_size": 23,
   "trial_name": null,
   "trial_params": null