Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b32571d072a7e9e58ec9df4d64d37de73b74df93891cbf7e0583d4df0b73a131
+oid sha256:7e0a9c71cd47c0e98e4df8a7e78f4b523fcd607377b8ca17db6e416015c3207f
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c7ccf4e08e09ae3c5b1c0681d904470cc25fc19ea1235c5e8961470a5e70349
+oid sha256:62ade698410c7671fb365897251dba414c6a38da64f7d2134b76611ae3967174
 size 25986148

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37869a54425cc950dac8e63e96f681db7fe42c26ab4cc02786464e2e696282b6
+oid sha256:3b21341e28491e7519aa247a7900dde9ffa5bc444ad819877747c1cba8a2f246
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d08f99970b931c4a23943a3b8e04e9c1c8914f8013b03146cd0e95b5d5847f
+oid sha256:69ae5e0ac083cbd6919e32143a287b06120b3d4d3cefddc87a84a5a2240ee75a
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0470aafc112e73e386f9c0796c9f7d47f712e4ec1725a9a8b0a60b35785a396a
+oid sha256:e59a7c6fcdbe021eb09a9b26ec2b45b55030c986399c9694fff97c95b645c400
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7773c4114e9a6400f44047ebbc36e6f819b09f52624f9b08749e5591a2949255
+oid sha256:2c01e7d96866ffb2310854fcb4f079a0cd8597ced3b2cd3eb4cea82a53748202
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b773dd0352daf5f6d7b7dbf00ce8796025d702b6c9d7b887e60406bd73ff69d
+oid sha256:789b5ac6a3d26da907edb51db958ba71233b76a160341b9ee57b430ce74531e6
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82f00a1ddd43d7cfda1c967aa1b3730028b00945a2e660902073d96e57b6ad89
+oid sha256:91edd18fb81e0ac338bab59cc220719cc869b33d86ada4ae9588d0548376122c
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a2eccd85b6a03f9cbe971d14978d89812e95a786f876dd323caf4ba3a9f4275
+oid sha256:2f3c1c4cc28dd44ba1817dffea22d63df2cc40ceac5849d28972cf3ae287c3d4
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a84d1bc751dc4bb97f124f2adf51847b23eeacb71aa0e4f3bf9c9a3061cddf
+oid sha256:2f4d82c554fbc426dbdfa4a4ba0d2eda37c9813afb5b4534eea5b76764acddac
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012415612632885854,
+  "epoch": 0.01862341894932878,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 90.03,
       "eval_steps_per_second": 11.266,
       "step": 10
+    },
+    {
+      "epoch": 0.01365717389617444,
+      "grad_norm": 0.31225091218948364,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.8059,
+      "step": 11
+    },
+    {
+      "epoch": 0.014898735159463024,
+      "grad_norm": 0.33488965034484863,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.7773,
+      "step": 12
+    },
+    {
+      "epoch": 0.01614029642275161,
+      "grad_norm": 1.0021756887435913,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.8657,
+      "step": 13
+    },
+    {
+      "epoch": 0.017381857686040194,
+      "grad_norm": 0.3065239489078522,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.748,
+      "step": 14
+    },
+    {
+      "epoch": 0.01862341894932878,
+      "grad_norm": 0.3766428828239441,
+      "learning_rate": 5e-05,
+      "loss": 0.8213,
+      "step": 15
+    },
+    {
+      "epoch": 0.01862341894932878,
+      "eval_loss": NaN,
+      "eval_runtime": 60.2571,
+      "eval_samples_per_second": 90.047,
+      "eval_steps_per_second": 11.268,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.293980070510592e+16,
+  "total_flos": 4.940970105765888e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null