Training in progress, step 1320, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76da35fcd2eceb4682b02e4d6f4efd1f654fac0b25429d515156667dd817308a
+oid sha256:11643bfec0b8066f81435dfab9d6924d7eb3edeeac2270017d461eea734a9479
 size 2433024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f660c44323f7dc691c0421faf42c40cc765dca5c21d11bff643a623b003967a0
+oid sha256:fdf2381d631ef4eb0f2ec3ba77196b6c928d7cc0993c1395a01f1054cc6eb637
 size 2498406

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b3ba644702b51ab6ceb3cfb78b0712e10c56d7a898133b9cf775673605d71a6
+oid sha256:20d70fad263b22723fec206cf46c7be2eacd2f78f087c3d0bdf030ac5240ae13
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a575d13944792443c2e0faf6af7562460ac52c5628f17b918747a2fad55be01
+oid sha256:ec3fcb4be00d780df479f9dac4126d0348e75ff289a5063a7ed0574b57fbc9eb
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3378545ae3c0bb849e88bd71db9a81f0556e610f7a1d6ea4af902425e910afa6
+oid sha256:ec5b78147ecf7eb0aa33d5383c0a50cc39cc808ebc0f0a52f2c385de2c5c0c79
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3581eff136704b2f763bfac1cfe6d4ca215660e05f32de8938f8c598bdd09e1
+oid sha256:def24f9a4a2da9e3ecf86804e9ee3edba51a08304bdf5081e4331fade20eec8a
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4710f39f928214c6084305a96ed4d69309abcb477c5fe9ea3b79644e92349f58
+oid sha256:d542d427bf2bb6ef4b7b489b3ff8728a8d7a7269befb6dac998921cfec4fa2fe
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17f2040b06510c4ed4dae6986e8f9b63891a60d4b9fa2e8045fc74b430abf05b
+oid sha256:23a2b76363f40a9152be338f15b92fe9aea0c0d9d18bae8b15de98ba4365477a
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f0418024306b84efbd06ecb22274609094ccd51161118b224af78a4c9aa3c2e
+oid sha256:e1ca7fe9106d3f63890388b3012f13801b1f0ccf1ae72d0176ee3cc810f72b56
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d46bb0bbf258912802dbc17d20db208430fc3ab3a923169293e1cbe07fb7ae7
+oid sha256:71951a6bb2a69638cdc2957f124934a2a5d71b1ae3bd32982c92819f8437c8ba
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25cf578d94ac1a7be20caf3c6bf3d856ece0554beb81a56caa6f17d994e34988
+oid sha256:f2e3675f249d7d0e817b058a9658660c0c52e027175e9ede4bed994c9c640c8b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.514792899408284,
+  "epoch": 1.5621301775147929,
   "eval_steps": 20,
-  "global_step": 1280,
+  "global_step": 1320,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1423,6 +1423,50 @@
       "eval_samples_per_second": 394.774,
       "eval_steps_per_second": 24.706,
       "step": 1280
+    },
+    {
+      "epoch": 1.5266272189349113,
+      "grad_norm": 0.46484375,
+      "learning_rate": 0.00010297580629631325,
+      "loss": 10.4277,
+      "step": 1290
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00010165339447663587,
+      "loss": 10.4369,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "eval_loss": 10.48730182647705,
+      "eval_runtime": 3.8109,
+      "eval_samples_per_second": 394.136,
+      "eval_steps_per_second": 24.666,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5502958579881656,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00010033069336079952,
+      "loss": 10.4141,
+      "step": 1310
+    },
+    {
+      "epoch": 1.5621301775147929,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.900793438320037e-05,
+      "loss": 10.4642,
+      "step": 1320
+    },
+    {
+      "epoch": 1.5621301775147929,
+      "eval_loss": 10.487874031066895,
+      "eval_runtime": 3.5355,
+      "eval_samples_per_second": 424.833,
+      "eval_steps_per_second": 26.587,
+      "step": 1320
     }
   ],
   "logging_steps": 10,
@@ -1442,7 +1486,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 501547991040.0,
+  "total_flos": 517262671872.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null