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:c1b2c7e01260fa2d76e74a450b8b2504c0cd038b513946673dcc793bf350a8b9
+oid sha256:df430b61030c98b01015cc1b8601ded09988276dbeed3e7add80122fe90410d5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28ef3294a582065127c0779372304455d587e1c5d7d390b662b394065b0872b0
+oid sha256:8972d5598b0c9562d231e92d89fabe426bbd149de3de4fa04fb0f783d6784a69
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eedb2a7e70cd3ddb5e4b069afa99ed1d476536fe99262e3af8da16dc7f01adbf
+oid sha256:3465f7c25c9aa7b7d0f0ef97318a58a46caf1594972ff0b6ab587309c9932dd4
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47e1693efd3253b65c059352e1453da814f21eb02ddf59e0d5b362c9c1691055
+oid sha256:9246be5539fbdfee7619655397cf993f2cfdd3b876b2e2fabfeeeb5329222011
 size 14512

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": 0.0045001968836136585,
+  "epoch": 0.006750295325420487,
   "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": 11.109,
       "eval_steps_per_second": 2.778,
       "step": 10
+    },
+    {
+      "epoch": 0.004950216571975024,
+      "grad_norm": 0.26608362793922424,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.6342,
+      "step": 11
+    },
+    {
+      "epoch": 0.00540023626033639,
+      "grad_norm": 0.22158242762088776,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.639,
+      "step": 12
+    },
+    {
+      "epoch": 0.005850255948697755,
+      "grad_norm": 0.23818451166152954,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.5802,
+      "step": 13
+    },
+    {
+      "epoch": 0.006300275637059122,
+      "grad_norm": 0.22042547166347504,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.5583,
+      "step": 14
+    },
+    {
+      "epoch": 0.006750295325420487,
+      "grad_norm": 0.19996048510074615,
+      "learning_rate": 5e-05,
+      "loss": 0.535,
+      "step": 15
+    },
+    {
+      "epoch": 0.006750295325420487,
+      "eval_loss": 0.610110342502594,
+      "eval_runtime": 1347.8184,
+      "eval_samples_per_second": 11.107,
+      "eval_steps_per_second": 2.777,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.3740393073934336e+17,
+  "total_flos": 3.5610589610901504e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null