Training in progress, step 80, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f0661a72ba3b66e4cc9219a425dc921ded7fb63db1b28e737a02a8ac7fdf59c
+oid sha256:ca5ae10db168677b2a3c9eebebb9f8c7f9b9d67457d37ffa9c3acda730924ede
 size 723674912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14923cfad5b25d998979f61b48520b8b8f6c1c8529883dfdb62b3f6c200c9927
+oid sha256:1fce942f56022b1c968835cb5703df1ddb7bb2d9c6269c456723dbdb59672d7c
 size 735625370

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19fc90eda86010024a75dd32530431e4c24bd0a1f6eff78d85286abbab03fba0
+oid sha256:e8e86174b3eb32925060e9953680fbcda12f487778e2fa23373bff16bb360a64
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:566f4865681bbc83459877b33ce491582588f147022ba0534caf3300e631e63c
+oid sha256:96e7dd869a6e1b32bc9520ed4dad315337bd74e7bba1905b1527b70f353d1ff6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3338107951da02a423c8f8ac5237de9e0061e6b3d0456c6fc2efa3002cc8846d
+oid sha256:9cdef07c8fb03613426123802d3ee28840d50c7dc4d30cb68fc9cabc31660adb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fffd547e430c47ced000ae5492f6d5e18bd88a88193ec1ee24bfe6f6a4d8e35f
+oid sha256:24cc5299af352f51d11766db1f1a250378308cfbc684430ac64ca9d7b85e55c6
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceb70d09862bb859050a14662883ecf389a0e55aec23642f4305d8f0de2bee43
+oid sha256:a7c81ebb017017feee3c6c3f2477294c6f8e1ba38c8568a1c58d53f7e2c4e60d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.5,
+  "epoch": 10.0,
   "eval_steps": 20,
-  "global_step": 60,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -81,6 +81,28 @@
       "eval_samples_per_second": 279.177,
       "eval_steps_per_second": 3.162,
       "step": 60
+    },
+    {
+      "epoch": 8.75,
+      "grad_norm": 0.138671875,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 2.0638,
+      "step": 70
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.140625,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 2.0632,
+      "step": 80
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 2.067866325378418,
+      "eval_runtime": 4.9082,
+      "eval_samples_per_second": 305.813,
+      "eval_steps_per_second": 3.464,
+      "step": 80
     }
   ],
   "logging_steps": 10,
@@ -100,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.134163021679821e+16,
+  "total_flos": 2.8455506955730944e+16,
   "train_batch_size": 23,
   "trial_name": null,
   "trial_params": null