Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d428b37c0fac2f592e6e5151e092e702731b786d18c56b43fae5827a3087e42e
+oid sha256:b32571d072a7e9e58ec9df4d64d37de73b74df93891cbf7e0583d4df0b73a131
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f18b3f29a7113f4142d740ee258044043cdf65ecf095059e415eabe43bf82c
+oid sha256:4c7ccf4e08e09ae3c5b1c0681d904470cc25fc19ea1235c5e8961470a5e70349
 size 25986148

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b13f321ff843d4cb3541fc386d712f93255b46e2bbf4dbd5f1ab87a177b71ea6
+oid sha256:37869a54425cc950dac8e63e96f681db7fe42c26ab4cc02786464e2e696282b6
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a831ef8834d938403e9c0f098e18c77fd0fb00d2276c5ed3a22cc30e8f04788c
+oid sha256:b4d08f99970b931c4a23943a3b8e04e9c1c8914f8013b03146cd0e95b5d5847f
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60303f6c9e58c93bee715177c84d63951f32109b70ca59c8412427592333ca4d
+oid sha256:0470aafc112e73e386f9c0796c9f7d47f712e4ec1725a9a8b0a60b35785a396a
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c69e67588f3f243d7af639fe894f60888578e0691482a5e2e4f12ce44f6fb52
+oid sha256:7773c4114e9a6400f44047ebbc36e6f819b09f52624f9b08749e5591a2949255
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fecf16e643a19e668fd3e5fc98a879d1e1a8a3cdef8d7c4d83a50e9678e5a6e9
+oid sha256:1b773dd0352daf5f6d7b7dbf00ce8796025d702b6c9d7b887e60406bd73ff69d
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:993d9833b97987ce359efb4d12d4ef2d67791a0fbce6a3077fa7bdd2c4c1b9f3
+oid sha256:82f00a1ddd43d7cfda1c967aa1b3730028b00945a2e660902073d96e57b6ad89
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1489062ce275ed397a63b84ee5391c411c4b0efa48081e8a84f6f2bb8b33a8a
+oid sha256:0a2eccd85b6a03f9cbe971d14978d89812e95a786f876dd323caf4ba3a9f4275
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf4bb2dc2a39117c20308ad1bdb17ab19e6132d8b3f96c4f3374a6c0e2560b51
+oid sha256:01a84d1bc751dc4bb97f124f2adf51847b23eeacb71aa0e4f3bf9c9a3061cddf
 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": 0.006207806316442927,
+  "epoch": 0.012415612632885854,
   "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": 90.356,
       "eval_steps_per_second": 11.307,
       "step": 5
+    },
+    {
+      "epoch": 0.007449367579731512,
+      "grad_norm": 0.3114588260650635,
+      "learning_rate": 6e-05,
+      "loss": 0.9081,
+      "step": 6
+    },
+    {
+      "epoch": 0.008690928843020097,
+      "grad_norm": 0.33595696091651917,
+      "learning_rate": 7e-05,
+      "loss": 0.8077,
+      "step": 7
+    },
+    {
+      "epoch": 0.009932490106308683,
+      "grad_norm": 0.32869091629981995,
+      "learning_rate": 8e-05,
+      "loss": 0.8406,
+      "step": 8
+    },
+    {
+      "epoch": 0.011174051369597269,
+      "grad_norm": 0.3324941396713257,
+      "learning_rate": 9e-05,
+      "loss": 0.896,
+      "step": 9
+    },
+    {
+      "epoch": 0.012415612632885854,
+      "grad_norm": 0.3595397472381592,
+      "learning_rate": 0.0001,
+      "loss": 0.7572,
+      "step": 10
+    },
+    {
+      "epoch": 0.012415612632885854,
+      "eval_loss": NaN,
+      "eval_runtime": 60.2689,
+      "eval_samples_per_second": 90.03,
+      "eval_steps_per_second": 11.266,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.646990035255296e+16,
+  "total_flos": 3.293980070510592e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null