Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af67a3337a04c7bef942f80acbe65becffb010ba36cb846e7ec18ff623f4bdc9
+oid sha256:ca6b069f65aa61429387188b368c55cdc14261221c22bea5b90acd29ed3f1d40
 size 37134420

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:559d97a40cec88700264340343a511cc241180f89b4514f2077b695270f50215
+oid sha256:ad70bae417fea217f6030e746ac1a46c6b1f642874878654cb2b0a9313d3c2cb
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3d8554f2cfccaf61db3f417541e33487c63c5f1bfa1b7686c5c397b8d691caf
+oid sha256:7ed97e4effc8cc706427ccc73b0048401e6016e71f210e07c43ef20b1160a27d
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25613140c123dbec3f0ce999ad818e0d16433627c5b926b6464e5a6405ade16b
+oid sha256:f01dd1ef3dff59a46ab95cae98f72234ae45e0225057ea2382d1d6a0cf11647a
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d193e9f160c5756ff976597c4def00e99d69cde71253028ec108359c465b35c3
+oid sha256:9e241b2a00c7d1568e69b70492eede367aea70326bde0c8d4c6df4e686d4eff8
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17f08f8de0eb229073858604faa79039086a8cab47004b3a8ec08f96e0f08a92
+oid sha256:4dbba45eec4e431103e03115cf1abb0fbb9ba54a601065a6e91d6025886821eb
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d45deb139a5d427118ef264384f77e8ba69e516923a3c0ca8022e52473cccdff
+oid sha256:5cbe4132bcc02cbe35ae58586fa18777ccc4a6874318646a1956c9364ae8dfd8
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2b48dbfe36432110952ff45c4c87b7a4ee1b924b114ad1f13f9006ad13eb377
+oid sha256:c35e8ce36b6d9a33913a1b929a57f56cf5e18239f6a5bdb3300b0e44b01678c5
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7ea18677afa47e7ce9aac22a4882deee9f49fdf4380e62c44997c7ee70e963e
+oid sha256:d57b44cb0f4c1d4f6fb310f448131297bb8aa17e47d1d8d82299f9cac85e7810
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0711743772241993,
+  "epoch": 0.1423487544483986,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 37.633,
       "eval_steps_per_second": 4.764,
       "step": 5
+    },
+    {
+      "epoch": 0.08540925266903915,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 2033.0361,
+      "step": 6
+    },
+    {
+      "epoch": 0.099644128113879,
+      "grad_norm": NaN,
+      "learning_rate": 7e-05,
+      "loss": 366.2248,
+      "step": 7
+    },
+    {
+      "epoch": 0.11387900355871886,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 588.2904,
+      "step": 8
+    },
+    {
+      "epoch": 0.12811387900355872,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 2884.811,
+      "step": 9
+    },
+    {
+      "epoch": 0.1423487544483986,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 441.9196,
+      "step": 10
+    },
+    {
+      "epoch": 0.1423487544483986,
+      "eval_loss": NaN,
+      "eval_runtime": 12.6367,
+      "eval_samples_per_second": 37.51,
+      "eval_steps_per_second": 4.748,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.561882493812736e+16,
+  "total_flos": 5.123764987625472e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null